0845 528 0404

Muddy Machines Interview with Florian Richter

Hi guys Philip English this from robophil.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Florian Richter who will talk about us "Farming Robots".

Philip English

Welcome to the Robot Philosophy Podcast, where we keep you up to date on the latest news, reviews and anything new in the robot world. Right. Hi, guys. It’s Philip English. RoboPhil from Robot Philosophy podcast. We’re here today with Florian from Muddy Machines just to learn a little bit more about Muddy Machines and what their team is up to. I probably kick off straight away. Could you give us just a general intro flooring, obviously, what Muddy Machines is about?

 

Florian Richter

Yeah, of course, Phil, thanks for having me on. Pleasure to be here. I’ve seen lots of your videos so far. Very interesting founders on there. Yeah. So, Muddy Machines is an act tech? Robotics company. We build robots that are about like 180 x 180 big, so quite sizable machines. Here’s a cat picture of what Sprout looks like. And these robots. Why do we do what we do? There is a massive labor shortage in farming. I mean, all robotics companies, I guess, tackle labor shortages in one way or another, but in farming, we’re really coming to a place where growers are stopping the production of certain crops because they are too labor intensive. You have something like 50, 60% of the production cost being labor. If you can’t get your seasonal labor force in because of Brexit, because of COVID and general, the price that you can pay per hour isn’t exactly going up. With supermarket price pressures exerted on growers, you just end up with what grows from telling us a 30% to 50% shortage of labor force. Right. And then you’re sitting on your crop nets that you’re rotting away in the field. It’s actually a great weather this year for some growers.

 

Florian Richter

They get very high yields. Water is a bit of an issue, too, now as it continues. But if you can’t harvest your crop, you’re making an outright loss instantly. And so, we think that this is something that hasn’t sufficiently addressed yet with robotics technology. Yes, there are plenty of machinery out there that do combine harvesting, where the crop has a very uniform growing pattern and you can pull the trigger on a certain day and say, now get me all my bali, get me all my wheat. You have these big combined harvesters going through the field, but with vegetables, it’s fruit berries. You need to really go in and say, okay, so is this one ripe? Now pick it, put it in my basket, and then leave the rest to ripen for another couple of days. And that’s something that hasn’t been done by any of these traditional OEMs and agriculture so far. And that’s where Muddy Machines comes in with Sprout.

 

Philip English

Right. Fantastic. That’s a great intro, Florence. Thanks for that. What’s your background? I understand that the family comes from a farming sort of background, and then at the same time, you’ve got a co-founder, Chris. I was interested in his sort of background as well.

 

Florian Richter

Yeah. So, we have two people, Chris and me. Chris is the CTO. He’s the one with the robotics background. He has spent quite a long time at Dyson. He spent some time at delivery building automated kitchens. He’s done some work in field search and rescue robots. So, he really straddles. I call him like a full stack robotics engineer, right? He can do everything. He has built our first prototype, Sprout MK One, by himself, 100% last year. And now we finally have a big enough team to bring in specialists, mechanics, engineer, specialist, computer vision, et cetera, to really leverage his skills wider. And yeah, I take care of everything on the business side. I’m an economics business student by training. I’ve been in many different startups over the last 10-15 years, really across the spectrum of ecommerce software as a service fintech. And yeah, you mentioned my family farming background, and we credit to my in-law family. They are the ones that got into farming probably about a decade ago in Portugal. Actually, Portugal wasn’t doing so well for a while, as you remember, and there was a lot of land or derelict farms available where the business has been completely mismanaged, was in disarray.

 

Florian Richter

And they have taken on over 1500 hectares in the Alentejo region, mostly cattle, so open field grazing, so very sustainable if you do it right, and olive orchard. And that really got me thinking into what is the kind of business stuff that I know, and then got his insight into farming and then realized the massive potential for building something that is long term sustainable, but at the same time has very long planning horizons. The first thing we have to do is ensure the water supply or the land is healthy enough again to retain water. You have a big drought issue in Portugal, and then you make some investments that sometimes take 10 to 15 years to pay back. And now we’re slowly in a place where the thing is commercially viable again and we can reinvest in it. And then when I had a point in my life, okay, what’s my next start up? I said, okay, I think I really want to be in the agricultural world and adding some value there with the skills that I have. But building an app or something, that would be something that I could probably do quickly by myself.

 

Florian Richter

I think this has been attempted already to mix success. So, it was pretty clear to me that if you want to bring technology into agriculture, if you want to enable farmers, at that time, I didn’t even know about the labor issues in vegetable growing with that. Okay, so if you want to do something in the space, you need to be a really deep tech person that does something transformational. And then when I spoke to Chris and understood what the state of the art of robotics is, then we had a shared conviction of, okay, so we want to do something in agriculture. We want to do something that really moves the needle for people working in that industry. What could that be? And then with his background of robotics, when you speak to growers, what’s your problem? And you start hearing labor shortages, labor shortages, then you’re like, okay, so this is obviously something that we could take a look at. And then in the middle of corporate, we did a field visit with a very large asparagus grower here in the UK. We got I think we got a special permit to drive out in May 2020 with a GoPro camera and a speedy camera and just started to take some pictures of crop in the field to see can we actually see this?

 

Florian Richter

Can we, with a reasonable effort record, good enough image data, and that was successful. I mean, that’s far from perfect. Okay, cool. So, this works. Now can we mock up something that grabs? Can we build some kind of end effective solution and then we iterate it through in a year later, we had something that was a very decent proof of concept, looks a lot different from what the picture I’ve just shown you was very bolted together with aluminum intrusions and all that. But it was enough to see, yes, this could potentially work. Now you just need to make it faster, more robust, and that’s when it gets really hard, as any person knows who’s trying to build a robot with commercial specifications. But although in last year we had something that proved the concept, we did a lot of work on the machine that we put into the field this year, but that still, again, needs that. The last 5% are the hardest to get it to the right pick speed, the right operation and time, the robustness against the elements and all that. That’s kind of our story, our backgrounds, where we’ve come from.

 

Florian Richter

We met an entrepreneur first, which is a great program to get people like me to meet people like Chris.

 

Philip English

Right. And is that based in London?

 

Florian Richter

Well, the original program is based in London. I think they have cohorts in Berlin and a couple of other major cities as well now. And it’s great. I can highly recommend it if you are, from my point of view, if you have a business background, you’re kind of always ready to go to start a business. But there are many technical people that get very tempted by high paying jobs in bigger corporates. And I know engineers have also typically a higher required them for job security, continuity, et cetera. And you get addicted to that, right? So, entrepreneur first, they’re trying to rescue people from the corporate ladder and get them into a safety.

 

 

HausBots interview with Jack Cornes

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Jack Cornes who will talk about us "Wall Climbing Robots".

 PHILIP

Welcome to the Robot Philosophy podcast, where we keep you up to date on the latest news, reviews, and anything new in the robot world. Hi, guys. Philip English here. Robot Phil. Just another interview for you, just to quickly and obviously learn some more about the new or some more robot companies out and about. So, Daniel, we got Jack Cornes from HausBots, and we’re going to give you a quick overview to see how they work. Really? So welcome, Jack.

 JACK

Hi, how are you doing?

 PHILIP

Fine. Thanks for your time today. Just to start with, it’s probably worth getting like an intro for yourself and just a little profile on the company, if that’s okay.

 JACK

Yeah, sure, no problem. Hi, I’m Jack. I am the CEO, one of the founders at HausBots. In a nutshell, that HausBots build robots to protect and maintain buildings and infrastructure. We started the business when my co-founder was asked by his parents to paint his house. He was up on the ladder painting his parents’ house, thinking to himself, blimey, it’s the 21st century, I’ve got an engineering degree, there’s got to be a better way of doing this. So, he made our first ever robot as nothing more than a bit of fun in his garage to help him paint his parents’ house. We’ve known each other since we were about twelve years old. So, we were having a catch up one day and he was telling me about this idea that he had come up with, and a bit of a Eureka moment happened for me. At that time, I was working in big tech, selling mainly software-based automation. And the Eureka moment was seeing how the task that his robot solved, which was effectively making work at height safer, wasn’t really being matched in the market, there wasn’t really a product out there, and I knew how much money was being spent on automation at large. So, we decided it would be a perfect opportunity to get together. I brought the parts of the puzzle that he was missing, sales, commercial, that sort of stuff, and started the business about three years ago. Fast forward to today and we’ve morphed from a robot to help a kid paint his house to a robot that can make all types of work at height significantly safer and significantly more cost effective. So, what we’ve actually got is a really clever climbing robot that can climb any surface you can imagine. And then we can integrate payloads up to 6 kg. So we do all sorts of projects from concrete inspection through to painting through to metal inspection, you name it. We can work out a way of getting our climbing platform to do it

 PHILIP

 right. It’s a fantastic overview. Thanks, Chad. They could just a good speck on the company. So I suppose the first question that you must always get, you say any material there, so what stops it? Like slipping on very wet and slippy material. It’s something to do with the way that the device, I suppose it might suck onto the building. Is that how it works?

 JACK

 Yes. So, we use a particular type of aerodynamics that’s found in Formula One called the ground effect. The way that it works in Formula One is that the undercar side of the car is designed in such a way to enhance its airflow under the vehicle and create a big low pressure. So, we use that same principle, but use a fan. So, this fan is moving the air to create a low-pressure region underneath our chassis. The reason that that’s kind of clever different and what our patent is based on is that it means that you can create large amounts of suction force without ceiling against your surface. So, most of our competitors will use, let’s say, a vacuum cup, suction cup, something like that. But our robot doesn’t need to seal, so we’ve got almost two-inch gap underneath the robot, so then it can generate these suction forces against pretty much any surface. We use that in combination with extremely high friction tires to mean that roughness of surface or obstacles or wet surfaces or smooth surfaces doesn’t really matter or affect the robot.

 PHILIP

Right. And then for the actual painting of the walls, then I’m assuming that there’s like an extra line that comes off the robot with whatever paint that customer wants. Is that how it works?

 JACK

Yeah. So, the robot can be integrated with any attachment you can imagine. It’s got all sorts of integration ports, just like you’d find on your laptop, USB and communication and all sorts of things. So, you basically plug the robot into the attachment you want to use, which, if we’re talking about painting, is just a paint gun. Attach the paint gun to the mounting point on the robot, plug them in for communication, and then that paint gun is supplied with a separate feed.

 PHILIP

Right. Could you put a camera on there for building inspection? Because I’ve read in the news lately that there’s a lot of buildings around London that have potentially need to be inspected more. So could that be like another feature that the robot could do?

 JACK

Yeah, it’s already a feature that we use extensively, actually. So, we’ve got a 4K pan tilt and zoom camera that can sit on the front of the robot. And again, because it’s easily integratable with all sorts of different things, we could even change that camera, upgrade it, use thermal cameras, whatever you fancy. But, yeah, we already use the camera quite extensively, especially in areas where it’s extremely difficult to get a drone permit or you can’t fly drone, which is most cities. Around most buildings, around most road networks, then drones can’t be used. So, our camera on our robot fills a nice gap there.

 PHILIP

Right. And you just answered my other question, actually, because I was going to question about sort of drones, but with the understanding from the health and safety side of drones, and that makes sense.

 JACK

 6:20

 Yeah, it’s a licensing thing. It’s health and safety, it’s a permit thing. More fundamentally than that, our robot was specifically designed for tasks where you require contact with the surface. Drones today are pretty much only good for cameras, for photos. And yes, you can use different types of thermal cameras or whatever, but that’s about as far as you can get with a drone. Our robot lends itself perfectly to tasks where you need to be touching the surface. So, a radar survey, an ultrasonic survey, camera of something extremely close, painting, fixing a particular thing, those sorts of tasks, which is where the functionality is kind of enhanced versus a drug.

 PHILIP

And that’s the advantage, really, because you’re doing a physical job as well. So, you can do division inspecting, but you’re actually doing a job if it’s painting or something like that and actually like, repairing the building. So, yeah, I could definitely see advice. What’s the highest it can go? Or you can go as high as your life as long as you got the power cord. That’s long enough. Is that there?

 JACK

Well, there’s two versions, actually. We have a 30 meters Tethered version, so customers will often use that if they want to run continuously. So, you can power it through the Tether and have unlimited power up to 30 meters. Or you’ve got a battery version, so the battery version is unlimited. As soon as you can carry the battery, you can carry that battery up to any height, but it’s limited by time. So, you’ve got about 25 minutes of runtime, which is somewhere on par with the drone as well. So, it depends on what the customer wants to do.

 PHILIP

Right, okay, I suppose what’s been your most trickiest building you’ve done so far? What’s been the tallest one you guys have done?

 JACK

Oh, gosh. We did the Qi two bridge in Dartford. Okay. The robot was climbing up one of the support piers. We undertook a visual survey and a radar survey. That bridge is huge and was an extremely exciting asset structure for us to work on.

 PHILIP

Yeah, that’s amazing. Well, I could definitely see the future potential because obviously, once people want their building painted or inspection, I mean, what’s the next step for you guys? You got the two different options at the moment. Is it really just to expand the options, expand the lines?

 JACK

Yeah. We’re constantly improving on the fundamental physics of the thing. So, you can always create more suction, you can always overcome a slightly larger obstacle, all these sorts of things. So that will just happen naturally. But I think the biggest piece of work that we’re doing is just constantly upgrading the portfolio of items that we can integrate with because ultimately the climbing robot itself, whilst is our bread and butter and is our special thing, the climbing robot itself is pretty useless. You can’t really do anything with just a climbing robot. So, it’s all the attachments. That is what it actually makes it do useful, productive work. So, we’ve got all sorts of projects on at the moment to just make that base robot integrate with as many different attachments as possible. And really the nicest analogy should draw it to is a tractor. A tractor is pretty useless if all it can do is just drive around fields. What you need is your tractor to be able to bolt onto your plow, your harvester, your tree cutting machine, all of these different things that your tracker then powers. And that’s kind of how we’re seeing our robot.

 PHILIP

Yeah, I like their analogy. That’s really good. So, the max payload currently is 6 kg, because what I was thinking is that I suppose the next step would be to have some sort of cobalt arm on the back of it with a tool to some degree. If you wanted more weight, I’m guessing it would just be a bigger robot. You have to size everything up to fit something heavier. I know the Cobot market, the robots are getting lighter, lighter all the time, but I don’t think we’ve got, unless it’s a university one, a six kilogram one yet. So, if you wanted more payload, would it just be size or could you add more technology in there so you can up the weight without having does that double the size?

 JACK

Yeah, size is one way of doing it. It’s kind of cheating, but that is one way of doing it. What we mainly focus on for payload improvements is aerodynamic design. So, we’re doing pretty much Formula One levels of aerodynamic design. And in the same way that a Formula One car every year gets about a second quicker because they found a new wing which can generate downforce in this particular way. It’s the same sort of iterative circle that we go through. That being said, and where the first part of this question came from, we’ve recently created a partnership with a manufacturer of basically mini Cobot arms. And we’ve got an arm that weighs 3 kg, is six degrees of freedom and attaches to the front of our robot. And it only has a small payload, obviously, but we’ve already started to do much more precision manipulation tasks through that. Three-kilogram arm. Wow, that’s really impressive for 3 kg. Yeah. I don’t think I’ve ever seen one that small before. I suppose it’s almost going into sort of like they’re talking about nanotech technology and nano that sort of standard. And I guess the smaller robots that we can build to do the work, the more you’re going down that road. Yeah, that’s right.

 PHILIP

Tools that we’ve seen from companies like You Are and Robotic and Enroll, they are producing a lot of end affects at all right. At the moment. That’s the trend that we’ve seen. So, you’ve had a series of years where they bought the arm, they weren’t too sure what to do with it. It’s got a gripper, it’s got a pick and place function, but now we’ve seen they’ve got sanders on the ends, they’ve got drills, they’ve got all sorts of tools. So, you can imagine the most dangerous job that you can get is being on the outside of the building, trying to screw something in. So you guys are based in the UK?

 JACK

Birmingham.

 PHILIP

Okay. Over in Birmingham, I suppose, from our viewers point of view. Like to get in contact with you, obviously, I’ll put in the houseboat website below and put some details. And I’ll have a think on this side as well to see if there’s any opportunities or customers. I mean, again, as part of the TLA Robotics Group, we may have you on there as well because that’s the European base as well. Have you done any installs in Europe or abroad?

 JACK

Yeah, we pretty recently came back from a chemical tank inspection in the Netherlands and there’s a couple of different customers that we’re talking to know that are based in that region as well.

 PHILIP

Right. Fantastic. Expand it out.

 JACK

Yes. So, we’re kind of giving demos and tests and pilot projects as we speak, so yeah, happy to engage for a demo with anyone.

 PHILIP

Yeah. And then the three-kilogram arm, is that something you might see on the website in six months’ time or something like that?

 JACK

Yeah, possibly. It’s a manufacturer called Elephant Robotics. Okay. Yeah. They basically specialize in mini arms. Really quite impressive stuff.

 PHILIP

Are they UK based as well?

 JACK

They’re in China, actually.

 PHILIP

They’re China? Yeah. Okay. That’s interesting. They are after looking to those guys as well. Okay. Now that’s great, Jack. I mean, thanks for the overview. I think that’s given the audience a clear understanding of what you guys do and yeah, we’ll keep an eye on you. We may do another interview in a year’s time or something like that and see what you have on them. So, it would be great.

 JACK

Good stuff. Thanks.

 PHILIP

Cool. Thanks for your time, Jack. So much appreciate.

 

Robot Optimised Podcast #8 – Interview with Jack Cornes

HausBots: https://hausbots.com/

Robot Score Card:- https://robot.scoreapp.com/

Sponsor: Robot Center: http://www.robotcenter.co.uk

Robot Strategy Call:- https://robotcenter.co.uk/pages/robot-call8

Will Computers Revolt” – Book Interview with Charles Simon

Willcomputersrevolt

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Charles Simon who will talk about his book "Will Computers Revolt".

Philip English (00:14):

Hi guys. Philip English here, also known as Robo Phil, robot and enthusiasts report on the latest business and application of robotics. And my main mission is to get you guys’ robot optimized, support industry infrastructure, and innovation for the next era. I’m excited today because you’ve got Charles Simon and who’s going there and tell us a little bit about his book and we’re going to do a bit of an interview with Charles about the AI, side of technology. So, welcome Charles is very, I really appreciate your time today. It’s a perfect, so could you give us, a quick overview, I suppose, like a little bit about yourself, like a little bit about your history, if that’s okay, Charles?

 

Charles Simon (01:00):

Sure. I’m a long time. Silicon valley, serial entrepreneur. And, I started three of my own companies and worked at two of other startups. And I spent a couple of years working at Microsoft and doing all kinds of different things. My very first company was about computerated design of printed circuit boards. And one of the things we observed is that the way computers designed the printed circuit boards at that, in that era was seriously different from the way people did it. And people did a better job. And that intrigued me into the idea of what makes people intelligence different from artificial intelligence. And I followed through on that, a little background about myself. I’ve got a degree in electrical engineering and a master’s in computer science. And so I’ve got a little bit of academic background in the area, but the area we’re talking about is the future of computers and artificial intelligence.

 

Charles Simon (01:57):

And that’s so cutting edge that nobody would say I’ve got 20 years experience in that. Along the way, also I did a stint as a developer of a lot of neurodiagnostic software. And so if you get a brain injury, you might be hooked up to my software or you get carpal tunnel syndrome and all of these other things that you test testing for neural pulses. So I bring to the table a whole lot of interesting and interest in how the human brain works and how neurology works and try and map that onto the artificial intelligence world too.

 

Philip English (02:37):

Right. I see. So you see, you’ve got a wealth of experience there from obviously from like an academic point of view and from a business side. So you sort of like merge the two together. Like we could probably actually jump into your brain, like sits at simulator software straight away. So explain sort of like what, the, and that the brain sits in later solves.

 

Charles Simon (03:02):

Well, back at the entire world of artificial intelligence. Back in the 1960s, there was a divergence of artificial intelligence where there are the neural network guys and the symbolic AI guys, and they kind of went their separate ways. And since then, they’ve kind of gone back and forth and sometimes one group got a whole bunch of money and the other group faded, and now they’re back together again right now that the neural network guys now call it deep learning or deep neural networks, and they’re more or less in charge. And they have a very interesting set of solutions, but they are not related to the way your brain works. And so the idea in 1970s or early eighties was we got this great new neural network algorithm with backpropagation. If we could just put it on a big enough computer, it would be as smart as a person.

 

Charles Simon (04:06):

Well, in the intervening 50 years, that has proven not to be the case. And so we have to look to some different algorithms. And so I wrote that the brain simulator looking at it from the other point of view, let’s start with how neurons work and see what we can build with that. And so my electrical engineering background says, oh, well, let’s build a simulator. And, if you were building a digital simulator, you’d have basic building blocks of NAND gates. And if you were doing analog simulator, you’d have various electronic components and op amps, but in the brain simulator, the basic component is a neuron. And the way a neuron works is it accumulates ions and eventually REITs a threat reaches a threshold fires, sends that a spike down its axon to distribute more ions to other, all of the neurons it’s attached to through it.

 

Charles Simon (05:00):

Synapses and neurons can have lots of synapses, you know, on the order of 10,000 and your brain has got billions and billions of neurons in it. And so, but the neat thing is that neurons are so slow that a lot of the circuitry in your brain is coping with that problem and the amount of computer power that we can get simulating neurons can simulate. Now I can simulate a billion neurons on my desktop, which I couldn’t do before. So we’re getting very close to having computers that can match the power of simulated neurons. And I’ve done a lot of explorations and this is a brain simulators, a community project. So it’s all free and you can download it and you can build your own circuits. And then you will become a lot smarter about what neurons can and can’t do and see why it diverges so much from the AI backpropagation approach.

 

Philip English (06:04):

Wow. I want to say, let’s say so someone, like not myself, but I couldn’t really use it as a learning tool to sort of understand the subject

 

Charles Simon (06:13):

Like you, you, I mean, like all learning things and you can sit down in front of it and a novice can, it’s got a bunch of sample neural networks and you can say, “aha”, well, this, these are the sorts of things I can do with neurons and how you could use these to do many more advanced things as well. And so the book kind of draws the surroundings around the software to say, well, if you go down this path, it’s pretty obvious that in the next decade or so, we will have machines smarter than people. What are the implications of that? And what, what will those machines be like and how are we going to control them and what are our options? And that’s what the book is about related to the software. So they kind of work together that way.

 

Philip English (07:04):

Yeah, no, that makes sense. Obviously you’ve designed and built the software, so you’re the perfect expert really, to look forward and actually see that if this grows at this rate, this is what we’re going to see, like in the future. And yeah, and that I, and that leads perfectly onto the book really. So, I mean like will computers, like revolt, is the name of the book and you’ll see the siding sort of the when, why and how dangerous it is going to be. And then again, give us a brief overview of the book then. I mean, I noticed that you’ve got three main sections and then if it’s got 14 chapters and the first part seems to be sort of explaining about how it all works. And then the next section is obviously what your, what you think is going to happen like within the future?

 

Charles Simon (07:58):

Well, that in order to talk about making a machine that is intelligent, you need to consider the idea of what intelligence actually is. And you need to think about what it is that makes people intelligent. And this turns out to be not an easy task to say, this is an intelligent thing to do, because if you start making a list, you’ll say, you know, can read a newspaper. Well, blind people don’t read newspapers, and yet they seem to be intelligent and you could hear a symphony. And there are always these disabilities that work that are in concert with perfectly intelligent people. So you, can’t just itemize a list of say, if you can do this and this and this and this year intelligent, and if you can’t do this and this and this, you’re not intelligent because you always have this problem, but I can see some underlying abilities, like the ability to recognize patterns in an input stream.

 

Charles Simon (08:56):

Now I’ve made a huge abstraction jump there, but a year, you know, your senses are continuously pouring data in it, your brain and your brain is doing its best to make sense of them, to remember what are the things that are going on at whether things worked out when you made a choice of one action over another action, and then to repeat those things. So if you said, you know, a simple game of tic-tac-toe you say, well, if I saw this, this situation, I made this move and I won, or I made this move and I lost. And you, your brain builds up these memories of things that worked out and things that didn’t work out. And so intelligent behavior is doing things that worked out. And so all of this happens within the limits of what you know, and what you’re learning. And another real problem of your brain is it’s getting so much data that, that it can only really focus on a tiny percentage of it at any time and remember even less.

 

Charles Simon (10:01):

And so when you stop to think about what, you know, you know, a whole lot less than you think you do, you have this perception that you can remember what’s next to you, or what’s next door, or what your friends look like. But when you actually get down to drawing a picture, you have very sketchy remembrances, and your memories are very fate to get fuzzy. And so building a computer system that works in this way, we were starting with the definition of intelligence. So it got some kind of a basic definition. And then you can say, bill working with these facets, can you build a software system or a hardware system, the software first, because it’s easier. And you build a software system that does that. And the answer is yes, and it’s not that tough, but there are certain things that we want to talk about in terms of general intelligence.

 

Charles Simon (11:03):

And that is, well, people seem to be able to understand stuff. You can understand stuff. I can understand stuff. What does understanding mean? And to some extent, understanding is putting everything, you know, and everything your input is receiving in the context of everything else you already know. And so you’re able to merge all of this together in a multisensory sort of way, that is you hear words, or you read words, and these may mean the same thing, but they relate to abstract things, objects, or physical actions or something. So it’s not the words that are the meaning. It is an abstraction, that’s the meaning. Then you can paste words on top of that. And so you can build computer systems to do all of these things, and that’s pretty likely, and you will end up with a because it’s doing the right thing over and over, you end up with a goal directed system, because the idea of doing something that worked out versus didn’t is entirely arbitrary.

 

Charles Simon (12:17):

It’s based as a measurement against some goals that some program were put into place. And so if your goal is to comprehend the world and explain it to people, that’s entirely different from a goal being set of making a lot of money or taking over the world. And so we have a goal directed system that has these capabilities. Now in the last section of the book, it is, well, what will these machines actually be like? And what will they be like when they are equivalent to a three-year-old or equivalent to an adult, or unfortunately, only 10 years later after they are equivalent to an adult will be a thousand times faster than the equivalent of an adult. And so all of these things map out to what’s the future of intelligent machines. So now the final section, I map out a number of different scenarios, which kind of put them on the low levels of different likelihood.

 

Philip English (13:24):

Yeah, well, this is it. I had to look through the chapters and the connection that we have with robotics is obviously a lot. Robotics is it’s all about the physical world. It’s all about the sensors that are coming out every year. There’s better and better cameras as better and better laser scanners, better LIDAR. But the real intelligence we’re seeing in robotics is all the AI side. So it sets up taking the data from the modern cameras and actually using it in an efficient way to get a job done. And with that intersection of technology getting faster and faster, and AI getting faster and faster, we’re, we’re certainly going to have an exponential growth soon with of certain technologies.

 

Charles Simon (14:05):

Exactly. And one of the things that I’d like to add to that is robotics is a key to general intelligence, because if you start with the idea of things, a three-year-old knows that round things roll and square thing blocks can be stacked up and things like that. These are things that you might be able to put into words and explain to a computer or show in pictures and explain to a computer. But that is entirely different from the understanding you get from having played with these blocks and to set a robot with a manipulator, loose, to play with blocks, we’ll give it an entirely different level of understanding than anything you could train. And so robotics is where the general intelligence has to emerge, because it’s the only place that brings together all of these different senses.

 

Philip English (14:58):

Well, this is it. And this is when you get touch senses, smelling senses, tasting senses. And you know, when, when I, and understand that, and yeah, we’re certainly going to see, and they’re

 

Charles Simon (15:08):

Some of the real keys are the sense of time that some things have to happen before things other happened. You know, that you have to stack the blocks before they can fall down.

 

Philip English (15:21):

That’s been great. It’s been great. Yeah. This is really, really, like interesting. I think it’s, it’s a perfect sideline as well. Cause we will talk about products and stuff. And this is quite good to have this view.

 

Charles Simon (15:33):

But from a product perspective now I happen to have been very fortunate in my professional career. So in these books and brain simulator and stuff, I do not need to make any money, which is a good thing. Because if I went to somebody and said, I need a billion dollars and I’m going to build a machine that’s as good as a three-year-old. This is not a winner of a project because three year olds don’t do very much, but that is the approach you have to take. You’ve got to be able to understand what a three-year-old can understand before you can understand what an adult can understand.

 

Philip English (16:10):

Yeah, no, and that’s it. And then from there that you can grow. I mean, so what I was interested in is your four light scenarios. So obviously I saw that number one was like the ideal one and then there was a few others, but if you can take us through your thoughts about that.

 

Charles Simon (16:28):

Sure, one can eat the scenarios of what happens when machines are a lot smarter than us. And there’s an interim period where there’s where they’re smart enough to interact with us, but not so smart that we’re borrowing. So that’s the key of being really interesting where the ideal scenario is we have programmed computers just with goals that match what human goals are now. The good news is that our needs and the computer’s needs are divergent. We need land and clean air and clean water and clean food and mates and other this, this, and that, and computers don’t need anything that we need except energy. And so we may have a fight over energy, but mostly they’re going to be doing their own thing. And the real true AGI don’t need spaceships or submarines to do exploration, or, and they don’t need air conditioning to live in the desert because they can become spaceships and they can become submarines.

 

Charles Simon (17:39):

And so they have a different set of standards and they can go off and do their own thing and learn a bunch of stuff about the universe and hopefully share with us. Now, the scary parts are more like in the early stages, suppose a nefarious, human is running these AGI and directs them to do things that benefit this, that person or group at the expense of mankind. And that is the only scenario that has any relationship with terminators and all of science fiction, where they build machines for the purpose of taking over the world or the purpose of making themselves rich. I don’t see that as a very likely scenario because it happens in a very small window of opportunity where machines are smart enough to be useful, but not smart enough to refuse to do the work, because it doesn’t take a genius to say that setting off a nuclear war is bad for everybody.

 

Charles Simon (18:46):

So a computer could easily say, no, I’m not going to participate in that project. And that will be a very interesting scenario when computers start refusing to do the things we asked them to do, but that’s a separate issue. So machine going mad on its own is extremely unlikely because in order to do that, you have to set goals for the machine that are self-destructive to mankind as a whole. And I don’t see that as a very likely scenario. And, so we’ve got the mad machine and the mad man who does things. And then there is the mad what I call the mad mankind scenario. Let us imagine that humans continue to overpopulate the world at a great rate. And they do put themselves in situations where the computers can see, well, this is going to get us into trouble. We need to do something about that.

 

Charles Simon (19:49):

All of the things that computers might do to solve human problems are going to be things that humans are not going to like, if you know, you say they want to solve the overpopulation problem or the famine problem, you can think of lots of solutions that you’re not going to be very happy with. So the four things that you can do, there’s the pleasant scenario that the mad man scenario, the mad machine scenario, which I think is pretty unlikely and the madman kind scenario, which is a concern. And we is what really says it’s time for mankind to get its house in order, and to solve our own problems, because we won’t want machines to solve them for us.

 

Philip English (20:38):

That’s it. Now, perfect. No, that’s a great light synopsis of the last four. And it’s again the very interesting and there’s four different scenarios. And, I think, yeah, I mean, like, I mean, if people obviously want to get hold of the book and I know it’s on Amazon and everything is, there.

 

Charles Simon (20:59):

The computer bit, the name of the book is will computers revolt, and there is a website will computers, revolt.com. The name of the software is brain simulator. And there is because it’s free it’s brain sim.org.

 

Philip English (21:16):

Know that, that’s perfect. Thanks, Charles. And then I suppose the last question I had is that timeframe wise, obviously, like we all know about Ray Croswell and he’s 24 foot 45, like live predictions. If you, do you think it will fit along that sort of timeframe do you think it’d be longer or shorter

 

Charles Simon (21:34):

Shorter, but the key is that it’s not an all or nothing situation when you think of a three-year-old, it’s not obvious that that three-year-old is going to become an intelligent adult. And so everything we do, if you look at everything you don’t like about your computer systems today, it’s mostly because they don’t think they’re not very smart. And so everything we do to make our, that brings on little pieces of smartness will be so happy to get it. So the machines increasing intelligence is inevitable because all of the little components are things we want, and we’ll eventually get to machines that are smarter than us, but it will have happened so gradually that we won’t have noticed. And every step along the way, we will have enjoyed it.

 

Philip English (22:35):

Well, this is it. This is the benefits. I mean, I’ve recently just invested in a little light health gadget and, you know, it’s there to benefit me really, you know, and us as a species. So yeah. Hopefully if you want it there, but no, that’s great. Well, I, thanks very much for your time. The light your time, Charles, it’s very much appreciated. I mean, what I’ll do guys is I’ll send, I’ll put a link on the YouTube video, so you guys can go and get touch of Charles book. You’re gonna have a look at his brain simulator software, and then, yeah, we’ll probably, do this again, another 6, 6, 7 months time. I mean, I’m going to get a copy of the book and have a read as well. And any questions I’ll put, Charles his details so you can reach out. So thanks, Charles. Thank you very much. Fit, fit, fit, fit.

 

Charles Simon (23:20):

Well, thank you for the opportunity. It’s been great talking with you.

Robot Optimised Podcast #6 – Book Interview with Charles Simon

Charles Simon: https://futureai.guru/

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=knlbxEZ6mgA&ab_channel=PhilipEnglish

 

SLAMCORE interview with Owen Nicholson

Hi guys, Philip English from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have SLAMCORE led by Owen Nicholson who will talk about their leading software and robotics .

Philip English (00:14):

Hi guys, Philip English. I am a robotics enthusiast, reporting on the latest business application of robotics and automation. And so today, we’ve got Slam Core and we’ve got Owen. He’s gonna give us a quick overview, of the technology down there. So I was also the CEO and co-founder. And, for any of you who haven’t come across slam before, it stands for simultaneous, mapping and we’ll got it wrong, apologies, simultaneous localization and mapping, and Slam Core like develop the algorithms that allow basically robots and machines to understand their space around them. So as more robots come out, then they have a sense of where they are and obviously they can interact with our environment. So yeah, no, I sort of, if I were in, just to give us like an intro and like an overview really like about yourself to start with, Owen if that’s, okay.

Owen Nicholson (01:20):

Sure. Awesome. Well, thanks a lot for the opportunity Phil, and thanks for the intro. So just to play back, I’m Owen, I’m the CEO at slam core. I’m also one of the original founders, and we’ve been going for about five years now. We originally span out from, Imperial college in the UK, one of the top, colleges in the world, founded by some of the absolute world leaders in the space. And it’s been, an incredible journey over the last five years, taking this technology and turning it into a real commercial products, which I’d love to tell you about all today.

Philip English (01:55):

Alright, thank you for that overview. And so you’re saying that, also you’re one of the co-founders so I was on the west side, so it’s is it 4 main co-founders or

Owen Nicholson (02:04):

So yes, two academic co-founders and then to full-time business founders as well. So, from the academic side, we have Prof. Andrew Davidson and Dr. Stefan Leutenegger, between them they’re two of the most respected, academics in this space. Probably most notably Prof. Davidson, who is one of the original founders of the concept and the real pioneers of slam particularly using cameras. So we’ll talk more about that, but this is really our particular flavor of slam is using vision. And he’s been really pushing that for the last one, nearly 20 years now. So incredible to have him as part of the founding team. And then, Dr. Leutenegger, who’s now at technical university Munich, who is another one of the real pioneers of vision for robotics. And then myself and, were with a full-time business side of things when we founded the company.

Philip English (03:01):

Right. Fantastic. So you’ve got quite an international sort of group of co-founders there. It sounds like you’ve got some mostly from an academic point of view, that our team that have been studying this and doing this technology for years. So that’s interesting,

Owen Nicholson (03:19):

Absolutely. And it’s one of those things. When you start with strong technical founders, then you can attract other great people into the space. So one of our first hires was our CTO, Dr. Pablo Alcantarilla who came from I robot. Great to be able to bring someone of that quality. And, he’s another one of the absolute real leaders in the space. But also with the real experience in industry. So he’s been a Toshiba has been, in iRobots and knows all about how do you get this stuff to work on low-cost hardware in the real world, and price to performance point. That really makes sense. And we’ve now reached our 33rd hire. So it’s been incredible and these we’ve got still a big technical team about 18 PhDs. I think I’m still about three quarters are still technical. So they either have a PhD or an extremely, in depth experience in software engineering and particularly embedded software engineering. But we’re also growing out our commercial and business side of the company as well over the last year and a half.

Philip English (04:25):

Fantastic. Yeah. Sounds like a phenomenal sort of growth over the five years to have such a strong team there. And, we were chatting about it. We were chatting before, so obviously you’re based down in Barra in central London, but you’ve also got another branch a bit out in now. What was that again?

Owen Nicholson (04:43):

Chiswick Sorry, kind of west London. So we have a couple of offices for the, for the team to work from. We have, I think on the last count, 17 nationalities now represented, within the company. So we sponsored a lot of international visas. We bring a lot of people into the UK to work for slam core, from all over the world. Most continents represented now. But I think this is just the way it goes. This the type of tech we’re working in is very specialist and we need the best of the best. So it’s the challenges these guys can girlfriend and, and girls can go from work in a DeepMind or Oculus if they wanted to. So we need to make sure that we attract them and retain them, which is something we’ve, we’ve been very successful with so far.

Philip English (05:28):

That’s right. And is what it’s all about getting the best team around you, like a sports team, you know, you want to get the best players, you know, to do the work. I mean, how did you find your team that started you, do you sort of regularly advertise or do you do a bit of headhunting for the guys? You got

Owen Nicholson (05:47):

The mixture of both of them having, having great people from the founding team means we can get a, we’ve got a good access to the network. So we do have a lot of inbound queries coming in for, we have very rigorous, interview processes. But we do, we use recruiters, we use headhunters particularly for some of the more commercial hires we’ve used kind of high-end head hunters to find these people because they’re very hard to find, once you do then bring them in, it needs to be, we need to make sure that this is a vision they really buy into. So, that’s, you know, we have, multiple ways in which we’ve attracted people over the years, but I’d say because we have such good quality team. It attracts other great people. So, it’s one of the real benefits

Philip English (06:35):

That’s right. So talent attracts talent, and we’ll see that those are the sort of guys who would like to know each other a lot within the space as well. And yet, like you mentioned vision there and we’ll get into vision a bit, my late later on, but I suppose I’m interested in the, I suppose, the problem or the issue to start with. I mean, Nikki, could you talk around or see, you know, I suppose the fundamental problem that you guys are, are trying to address?

Owen Nicholson (07:02):

Sure, sure. I think at the heart of it, we exist to help developers give their robots and machines, the ability to understand space, quite high level, but let’s start there. And ultimately we break this down into the ability for a machine to know its position, know where the objects are around them and what those objects are. So it’s coordinates it’s map and the, is it a person? Is it a door? Those are the three key questions that machines and particularly robots need to answer to be able to do the job that they’ve been designed for. And the way this has done normally is using the sensors on the onboard the robot and combining all that, all these different feeds into single source of truth, where the robot creates essentially a digital representation of the world and tries to get where it is within that space.

Owen Nicholson (08:01):

And, the problem has always really been that actually the number one cause of failure for a robot, isn’t the wheels falling off for it falling over. Although there are some funny videos on the internet about that actually, when it comes to real hardcore robotics development, the challenges that are faced on mainly around the discrepancies between the robots, understanding of the space and its reality. So that’s what causes it to crash into another object is what causes it to get lost on the way back to the charging station and therefore not actually get there in time. And so it runs out of juice and just dies. So the high-level problem we are trying to do, trying to address is giving developers the ability to answer these questions without having to be deep, deep experts in the fundamental algorithms that are allow you to do that.

Owen Nicholson (08:53):

Because there’s an explosion of robotics companies at the moment, and it’s super exciting, seeing all these different new applications coming out, really driven from lower cost hardware coming out and modular software, which allows you to quickly build POC and demos and early stage prototypes. But there’s a still, when you really drill into it only, well, probably well over 90% of those machines today will not scale to a commercially viable product as it stands, if they literally went and tried to sell that to hardware and that software right now. So this is where most of the energy has been focused on by the companies trying to modify what they have to be more accurate, more reliable, or reduce the cost, and actually nearly all most of the times, all three. So they’re nearly always trying to make it increase the performance and reduce the cost.

Owen Nicholson (09:43):

And this is phenomenally time consuming. It’s very expensive. It can be, cause it’s lots of trial and error, especially if you have a robot where say a service robot where you need to shut down a supermarket to be able to even do your testing. You might only get an hour a month to be able to do that with your client. And this is such a critical time. And if you spend the entire time just trying to get the thing from A to B, not actually worrying about what does it do when it gets there. This is really what’s holding back the industry as a whole.

Philip English (10:13):

Right. I see. So if I’m obviously like a manufacturer and I want to build a solution again for like retail or education or when you’re in hospital, was this quite good? Quite good one then basically then slam core is one of the components that I can bring into the product that I’m building. And again, it’s got all the expertise, it’s got everything It needs to make sure it does a brilliant job on the vision side. So the one, obviously it, that helps with costs on manufacturing, on a new product, and then it’s easier for the customer to launch the products, knowing that it’s got a branded and obviously a safe way of localization.

Owen Nicholson (10:54):

Absolutely, so they start time to market for a commercially viable system. So you can build something within a month. In fact, at the end of master’s projects, you quite often will have a robot, which is able to navigate and get from A to B, but doing it in a way, which especially when the world starts to get a bit more chaotic, that’s probably the real real challenge, is when you have people moving around structures, changing the standard systems today, just, they just don’t work in those environments. They don’t work well enough to, especially when you have a hundred, a thousand, 10,000 robots, if your mean time between failure is once every two weeks, that’s okay for your demo, but it doesn’t work when you’ve got 10,000 robots deployed to across a wide areas. So, yeah.

Philip English (11:40):

Yeah. this is it. I mean, from what I’ve seen, it’s all about movement. And as you said, like you can do a demo with a robots sort of show it working in an environment that’s half empty and no one’s really around, but once when it’s a busy environment, busy retail, lots of people, lots of movement. And it’s very easy for obviously the robot can get confused and say, I know, is that a person? Is that a wall? Where am I sort of sort of thing? And then that’s it, it loses its localization, and then you start, so I suppose the question I had was around the technology. So I saw on one of your videos, obviously you were using one of the Intel cameras, but is it, can you link it with sort of any laser scanner, any LIDAR scanner? Is there a certain tech, product range that you need to integrate as well for Slam Core to work best or.

Owen Nicholson (12:30):

Absolutely great question. I think this is one of the really interesting, when does the technology become a commercial product questions? Because the answer is, if you lock down the hardware and you work just on one specific hardware sensor combination, then you can build a system which works well, particularly with vision. So you don’t, if you look at some of the products out there already Oculus quest, I know it’s not a robot, but ultimately it’s answering very similar questions, whereas the headset, what are the objects around it? Same with the hollow lens that iRobot Rumba and a number of other questions, they’ve all successfully integrated vision into their robotic stacks. And it works. They work very well on low cost hardware. The challenge has been then if you don’t have those kinds of resources, if you’re a com, if you’re not Facebook or Microsoft or iRobot.

Owen Nicholson (13:32):

So then you have to, a lot of the companies are using much more open source solutions. and they, quite often use laser-based localization. This is the very common approach in this industry. and we are not anti laser at all. LIDAR is an incredible technology, but you shouldn’t need a $5,000 LIDAR on your fleet of robots, just for localization. And that’s currently where we are in, in this industry. The reality is there are cheaper ones. Absolutely. But to get ones that actually work in more, more dynamic environments, you need to be spending a few thousand dollars on your lasers. So we are at the heart of our system is we process the images from a camera. We extract the spatial information. So we look at the pixels and how they flow just to get the sense of geometry within the space.

Owen Nicholson (14:21):

So this gives you your coordinates. It gives you the surface shape of the world. So your floor plan and where are the obstacles irrelevant to what they are, but what if there’s something in my way? And that’s kind of the first level, our algorithms, operator, but then we also are able to take that information and use our proprietary machine learning algorithms to draw out the higher level spatial intelligence, which is the obstacle object names there, the segment segmenting them out, looking at how they’re moving relative to other parts of the environment. And that all means that we’re able to provide much richer, spatial information than you can achieve with, even that the high-end 3d lidars that you have available today. Just to address your question directly, as far as portability between hardware, this is one of those real challenges, because if we’d have decided three years ago to just lock it down to one.

Owen Nicholson (15:22):

So the Intel real sense, it’s a great sensor. They’ve done a really good job. And if we’d have just decided to work with that and optimize only for that today, we would have something which, as extremely high-performing, but you wouldn’t be able to move it from one product to another. If another sensor was out there at a different price point, it wouldn’t port. So we’ve spent a lot of our energy taking our core algorithms and then building tools and APIs around them. So that a developer can actually integrate into a wide range of different hardware options using the same fundamental core algorithms, but interacting with them through different sensor combinations. Because the one thing we know in this entire industry, there’s a lot of unknowns, but probably the one thing we all know is there’s no one robot which will be the robot that works everywhere, just like in nature.

Owen Nicholson (16:10):

There’s no one animal. Although by, as an aside, nature uses vision as well. So there’s clearly some benefits that evolution has chosen a vision as its main sensing modality, but we need variety. We need flexibility and it needs to be easy to be able to move from one hardware configuration to the next. And that’s exactly what we’re building at slam core. Our approach at the moment is to optimize for certain hardware. So the real sense right now is our sense of choice. And it works out of the box. You can be up and running within 30 seconds with a real sense sensor, but if you come along with a different hardware combination, we can still work with you. They might just need a bit supporting, but we’re not talking blue sky research, we’re talking few, a few weeks of drivers and API design to get that to work.

Philip English (16:59):

Right. Fantastic. And I suppose every year you also get a new version of a camera, like coming out as well. So a new version of the Intel real sense, which would obviously it’s normally advanced version and it’s the best version. And then it will see, I suppose that helps in your three key levels, which is what I was just wanting to quit. Quit to go over. Cause obviously like you discussed them there. So you had three levels, there was tracking math in and the semantics. So that’s basically what you were saying. So we’ll see, your algorithm stage then is that level three? Is that the semantics, was that level two diffuse?

Owen Nicholson (17:38):

So we actually, we call it full stack, spatial understanding. So we actually cut, we provide the answers to all three, but within a single solution, and this has huge advantages, because, well, Hey, there’s performance advantages, but there’s also, you’re not processing the data in lots of different ways and you, it means you can answer these questions using much lower cost Silicon and processes because you are essentially building on top of each one’s feeds into the next. So for example, our level one solution is tracking gives you very good, positioning information, and then all level two is the shape of the world, but we can feed the position into the map so that you get a better quality map. And then we can feed that map using the semantics to identify dynamic objects and remove them before they’re even mapped. So that you don’t confuse the system. And then this actually improves the positioning system as well, because you’re no longer measuring your position against things which are non static. So there’s this real virtuous circle of taking a full stack approach. And it’s only really possible if you understand the absolute fundamental mathematics, going on so that you can optimize across the stack and not within your individual elements with across it.

Philip English (19:01):

Wow. Okay. And then within the algorithm package then, is it a constantly learning system? So we’ll see if we’ve, developed, like a mobile Charlie to go around a factory and someone puts a permanent house there or permanent obstacle, will it, learn to say, okay, that obstacle is there now and include that in an increase into the map.

Owen Nicholson (19:29):

It’s absolutely that’s one of our core features, which is what we call, lifetime mapping. So, currently with most systems, you would build your map. This is how a lot of the LIDAR localization works. You’d build a map with a essentially a master run. You’d save that map. Maybe pre-process it to get it as accurate as possible. And that becomes your offline reference map off, which everything localizes against. So right now we provide that functionality today using vision instead of LIDAR. So you actually, you already get a huge amount, more tolerance to variation within the scene because we are tracking the ceiling, the floor, the walls, which are normally a lot less likely to have changes. So even if that post appeared it wouldn’t actually change the behavior of the entire system.

Owen Nicholson (20:20):

But we are also later this year, we’ll be updating our, released to be able to merge maps from different agents and from different runs into a new map. So every time you do, every time you run your system, you can update it with the new information. And this is something which is very well suited to a vision-based approach because we can actually identify, okay, that was a post probably more interestingly, maybe pallets or something where a pallet gets stuck in the middle of the warehouse. And you don’t want to, maybe during that day, you want to communicate to the fleet that there’s a pallet here. So you don’t want to pan your plan, your path through it. But then the next day you might want to remove that information entirely because it’s unlikely to still be there. So it, we ultimately don’t provide the final maps and the final systems. We provide the information that the developers can then use. They can use their own strategies, because this is key that some applications might want to know and keep all the dynamic objects in their maps and might want to ignore them entirely. So we really just provide the location, the positions of those objects, in a very clean API so that people can actually use it themselves.

Philip English (21:40):

Right. I see. And then when you said, so an emergence of other mapping tools, so I’ve seen the old classic where you have like someone who has a laser scanner on like a pole, and then he’s walking around the factory or walking around the hospital to create a 3d map. And then, so can you take that data and merge it in with your data to get like a more like accurate map is that we may not.

Owen Nicholson (22:07):

At the moment, we don’t fuse maps created from other kinds of systems. Like it went to our system. We ultimately would want to consume the raw data from that laser and fuse it into our algorithms. So right now, our support is for version inertial, sensors, and wheel Adometry. LIDAR support will come later in the year where it’s just a matter of engineering resource at the moment, algorithmically it’s all supported, but from a engineering, an API point of view, that’s where a lot of the work it’s that last 10%, a lot of people will tell you about is quite often 90% of the work. I know something to be 80 20, but I think that thinking robotics is more like 90 10 and so we wouldn’t support that sort of setup at the moment, but the answer is you shouldn’t need to do that because with those systems, you need to be very accurate, quite often, be careful how you move the LIDAR. Also, you need a lot of compute. You also need to do it quite often offline post-processing. Whereas our system is all real time on the edge. It runs using vision, and you can build a 3d model of that space all in real time, as you see it being created in front of you on the screen, so that you can actually go back and, oh, I missed that bet I’ll scan there. So this is really kind of a core part of our offering.

Philip English (23:32):

Right. Fantastic. Fantastic. I suppose the last question I have in regards to the solution, then we sort of see what, like, what you’ve been going through, which is fantastic is, so is this just for internal, or can you go external as well? I mean, I’ve seen slammed based systems have had issues with, since things like sunlight and rain and weather conditions, is it the incident at that moment? And then it looked at to go external eventually, or where whereabouts does it say?

Owen Nicholson (24:01):

We tend not to differentiate internal external, it’s more to do with the type of environment. So as long as we have light, so we won’t operate in the light soft factory cause we need, we need vision. And as long as the cameras are not completely blinded. So the rough rule of thumb we normally say to our customers are, could you walk around that space and not crash into things? If the answer to that is yes, then there’s them. We will, we may have to do some tuning for some of the edge cases around auto exposure and some of the way in which we fuse the data together. But we already have deployments in warehouses which have large outdoor areas and indoor area. So they’re transitioning between the two. We are not designing a system for the road or for city scale, autonomous cars slam, which really is a different approach you would take. And that’s where a lot of those more traditional problems, you just talked about rain and those types of areas really starts to become an issue. But for us we support indoor outdoor, whether it’s a lawn mower or a vacuum cleaner the system will still work.

Philip English (25:12):

Right. Fantastic. Yeah. Yeah. And I think this is it. I mean, we’re starting to see a lot more outdoor robots coming to market probably more over in the U S but also that’s going to be the future. So we’ll see. Yeah. Like the whole markets there, I suppose it sort of leads onto the bigger sort of vision for you guys then. I mean like where do you see the company in like five years time and like technology wise, I suppose. And what’s the ultimate goal, I suppose to get perfect vision, like similar to, cause humans have vision, I quite liked your animal, like analogy there actually, because obviously vision is one of the cool things, but as far as like what’s the why for you guys and the next sort of steps?

Owen Nicholson (25:58):

Yeah. I think really, we founded the company because the core technology being developed has so much potential to have a positive impact on the world. And it’s essentially the ability for robots to see, and that can be used for so many different applications. So the challenge has always been doing that flexibly whilst keeping the performance and costs at a price at something that makes sense. And we’re now demonstrating through our SDK. So we actually, the SDK is publicly available if you request access and you’re able to download it, we already have over a hundred companies running it and we’ll have about a thousand companies in waiting as we start to onboard them. So we’ve demonstrated that as possible to deliver this high quality solution in a flexible and configurable way.

Owen Nicholson (26:50):

And this means we are essentially opening up this market to people who may be in the past, would not have been able to get their products to that commercial level of performance to be successful. So having a really competitive, and also collaborative ecosystem of companies working together, trying to identify new ways to use robot is got to be good for us as an industry, because if it’s just owned by a couple of tech giants or even states then that’s going to kill all of the competition. So, and this will drive some of the really big applications for robotics. We see in the future in five years time, I believe there’ll be robots, maintaining large, huge, renewable energy infrastructures at the scale, which would be impossible to manage with people driving around machines and looking at sustainable agriculture in a way, which means that we can really target water and pesticides so that we can really feed the world as we start to grow.

Owen Nicholson (27:55):

And yeah, we’ll let you, you’ve seen all of the great work going on Mars with the Rover up there now with perseverance and we’re using visual slam, ultimately, it’s not ours, unfortunately, but in the future, we would like us as our systems to be running on every robot on the planet and beyond that’s really where we want to take this. And it has to be, we have to make sure that these core components are available to as many people as possible so that they can innovate and they can come up with those next-generation robotic systems, which will change the world. And we want to be a key part of that, but really sitting in the background, not living vicariously through our customers. I quite often say I want Slam Core to be the biggest tech company that no one’s ever heard of and running up, having our algorithms running on every single machine with vision. But never having our logo on the side of the product.

Philip English (28:56):

Yeah, well, this is it. And this is the thing that excites me about, like robotics and automation. I mean, if you think about the it industry, obviously you have a laptop, you have a screen and you have a computer, or obviously see there’s lots of big players, but you’re pretty much getting the same thing, but with robotics, you’re going to have all sorts of different technologies, different mechanical, physical machines, and it’s going to be a complete mixture. And I mean some companies will build things similar and to do one job where you may have different robots with different jobs. And yeah, now, I think that sounds great. I mean, obviously what if you can solve that vision issue that we have, it makes it a lot easier for start ups, you know, and a lot easier for businesses to take on the technology, get the pricing down, because obviously if you don’t want robust, wasn’t hundreds of thousands of pounds, you want them at a level where they’re well-priced, so they can do a good job and actually in the end, help us out with whatever role that and the robots do.

Philip English (29:54):

And so, yeah, now, that sounds really exciting. And actually, I’m looking forward to that to keep an eye on you guys. I mean, what’s the best way to stay in contact with you, then what’s the best way to get,

Owen Nicholson (30:06):

Genuinely head to this website and click on the request access button, if you’re interested in actually trying out the SDK, we’re currently in beta rollout at the moment, focusing on companies with products and developments. So if you are building a robot and are looking to integrate vision into your autonomy stack, then request access, we can onboard you within minutes. It’s just a quick download. And as long as you have hardware we support today, you can run and run the system. We have a mailing list as well, where we want to keep people up to date as things as exciting announcements come. And that’s really probably the best way is just to sign up to either our meeting list or our waiting list.

Philip English (30:57):

Right. Perfect. Thank you, Ron. And, what I do guys, is I’ll put a link to all the websites and everything and some more information about Slam Core. So, yeah, now, it was great. It was great interviewing, many thanks for your time. And yeah, like, I’m looking forward to keep an eye on you guys and there, and see, I seen your progression. Thank you very much

Owen Nicholson (31:15):

Absolutely.

SLAMCORE interview with Owen Nicholson

Slamcore: https://www.slamcore.com/

Philip English: https://philipenglish.com/slamcore/

Robot Score Card:- https://robot.scoreapp.com/

Sponsor: Robot Center: http://www.robotcenter.co.uk

Robot Strategy Call:- https://www.robotcenter.co.uk/pages/robot-call

Benedex LTD Interview with Snir Benedek

Benedex LTD Interview with Snir Benedek

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Benedex LTD led by Snir Benedek who will talk about their leading software and robotics .

 

Philip English: 
Hi guys. My name is Philip English, and I am a robotics enthusiasts to report on the latest business and application of robotics. And my mission is to get yourself a robot optimised as support industry innovation and infrastructure. Uh, today we have Snir from Benedex limited and their vision is to promote automation for the empowerment of society. And, we’re going to have a word of snir today about his flexible motion platform. So Snir welcome. Okay.

Snir Benedek: 
Thank you very much. We’re also robots enthusiastic here.

Philip English: 
Cool, perfect. Perfect. That’s what I have to say. Um, so could you give us, um, I suppose a quick overview about yourself if that’s okay, so now,

Snir Benedek: 
Um, yeah, of course, happily. So, um, I myself, uh, have, um, a rather multifaceted, uh, background, uh, I have a bachelor’s degree and in aerospace engineering from the Technion, from the Israeli Institute institutes of technology, Israel is, um, where I spend the first, uh, first 37 years of my life. And, um, I then, uh, uh, I then took a course in biomedical engineering at the Tel Aviv university. So the first 11 years of my, my career, um, have been in R and D of various descriptions. Uh, I’ve been a programmer of simulations. I’ve been, um, an engineer, uh, aerospace, um, well in aerospace, I was an engineer of aircraft performance and, uh, I’ve been a mechanical engineer in the digital press industry and then applications engineering, robotics. And from there, it segwayed into a more commercial role. And, um, since 2012, I’ve been a sales manager, product manager of the motion control and, and, um, robotics related electronics. And, and through that international role, I came to know, uh, the technology very intimately. I came to, to build up a network, um, across the globe of people who are involved in the industry. And, um, and that’s naturally, naturally led me to understand better the pains and the, the endemic problems in, in this market. And here we are today.

Philip English: 
Yes. No. Okay. No, thanks for that. That’s a great overview. And then, so I will see you’ve got lots and lots of experience. I mean, 20 years of space is really, really impressive. And then, I mean, so what I suppose the first quick question is, um, so you, you, you decided to come to the UK, um, and sort of worked with the team like a British team. Was that the plan or?

Snir Benedek: 
Uh, well, not really. I started as a regional sales manager was still working in Israel. I started as a regional sales manager of, um, of, um, motion control electronics. Um, and, and I got to work in the UK market. I absolutely love the United Kingdom. I love this country. I love diversity. I love its culture. I always have really. And, and, and so I always was happy to, to come and live here. And I had an opportunity where a person who used the business. So it used to be my, my customer back in the day, um, got me as an employee. And so, uh, that’s what, uh, that’s what facilitated the, the move into the UK. It started as a, as a half jest, but, uh, but here we are quite an amazing turn of events. Really. Yeah.

Philip English: 
Yeah. And then, and then, did you, do, did you aim to land for sort of like the Bristol bath area? Cause that that’s sort of a bit of a HubSpot in the UK for like robotics with Bristol, like robotics labs. I mean, obviously I know you’ve got some association with those guys, so, so what, what’s the connection there?

Snir Benedek: 
A very fortunate turn of events. We started out in bonus very, very, very lovely place. And, um, following my better half’s, um, place of work, we ended up halfway between between mom’s break, which is where Dyson is and, uh, and, um, at Bournemouth and, um, it is naturally close to, to Bristol and above. And not many people, not many people are aware, but this entire area, not just Bristol has a lots of action in terms of reports. They send some really, really, really smart people in the wheelchair area. I think it’s been very, very fruitful to, to open this business here. Yeah.

Philip English: 
I think you’re definitely in the right space. I mean, we know, um, uh, Airbus is down there. A lot of the big aerospace companies are around there as well. And I think they’re, they’re saying that that sort of era is sort of the new center of, I suppose, essentially the UK for like, um, I suppose technology and innovation, because it’s so, so well-placed really, I mean, I mean sort of, sort of in, in, in the sense that you can go up north and get down south, so yeah, definitely a good place to be. And, um, yeah, and obviously we’re still robotics labs there there’s advantage there, but, um, I, I suppose, um, yeah, obviously the main thing of that talk is to talk about, um, your products and, uh, and, and, and the actual company. I mean, could I start with sort of the problems that, that you’ve seen? Obviously you’ve got a lot of history there, so you’ve seen a lot of the problems with, um, the, the current solutions are on the, on the market, but it could, could you give us an overview, obviously, the, there, the problems that your AMI solution is looking to address?

Snir Benedek: 
Okay. So you said AMR, the AMR market is a bust market, and it is very, very quickly growing. It is one of the largest or sorry, one of the fastest growing sectors on the, the, the whole robotics industry. So, um, mobile robotics, and probably not many people are aware of how big it really is, is a market that, that brings in tens of billions of dollars every year. And is, is anticipated to grow, to be about 10 times as large in the next, uh, in the next 10 years or so. Uh, it is, it is a huge market and it is a very quickly growing. And also they say, you know, people have been saying for the past 50 years, that robotics is the next big thing, the next big thing. However, unless you’re in Silicon valley, which is probably the singular one place in the world that you see it, um, when you walk around, you don’t see robots, do you, so, so they’re the next big thing for the past 50 years, but they’re not here yet. It has not happened unless you’re in Silicon valley. So why has not happened? What is keeping it from happening? Why aren’t robots all around us? I think the way I see it, and this is what guided us to, to, to go for this solution is that building robots is difficult. It’s hard, it’s still too hard. And, and it’s, and it’s very, very expensive. There are major barriers of entry into this, into this market. This is the problem that we’re tackling.

Philip English: 
And this is, um, you know, as, as you, as you said, it’s a market, that’s, it’s going to be expanding more and more over the next few years. And, um, I know what you mean about the AMI market in general. We’ve seen lots of different platforms can’t come in there. They’re all quite similar to some degree. Um, and that’s why we’re really, really interested like in Bennett, Alex, it seems like, um, a different type of solution. That’s gonna be, be able to fit into lots of different areas. I mean, I mean, just to get my head around it, I mean, again, I’ve done a bit of reading, so is the idea of obviously that you could actually place your system on to any type of, um, of platform. So if I have, um, a certain, I’m trying to think of a good example here, like, uh, a table or something simple that, that, that, that I want to move around and that table has some products on. Can do I, do I work with you to attach your system to that table, make the table like autonomous? Is that, is that how it works? Or if I,

Snir Benedek: 
Okay. Yeah. That’s one way it works, but I think we can attach the wheels. Things much, much, much more interesting than a table or the kitchen sink that matter. So mobile robots are machines that travel from place to place and, and do a certain function. And because of recent technological developments, what those machines can do has, has greatly improved and increased. They mobile robotics can do the work of people and can do increasingly more things people can do. And, and so they find themselves going into every industry can think of, obviously everyone knows they’re in logistics, they’re in warehousing. Everybody already knows that because everyone has already seen pictures of swarms of robots are crawling up the walls and on the shelves and those big Amazon warehouses and at, uh, at, uh, what’s the name, um, Ocado, uh, the, the big supermarkets, you know, all those big logistical centers, but they’re also, uh, they’re also going into, into the outdoors and people are looking at last mile delivery.

Snir Benedek: 
That’s a big thing. Now it’s being looked at. People are looking at security robots using using, um, ground drones as centuries. People are looking at the medical industry. People are looking at the agricultural industry because robots can do things out in the fields. So the variety is endless. And, and the thing is that, that the technology for building industrial industrial robot platforms is because it’s difficult and expensive is held by big companies, big corporates, but the ideas, but the great ideas for new uses, new implementations, new applications come from, from, um, SMEs, from entrepreneurs, people who don’t necessarily have that capital backing, and they don’t have access to that technology, uh, to get it from the big corporates, because that costs a lot of money. And, and this, this is the gap that needs to be crossed that needs to be bridged. And what we have set to do is to make this technology accessible to people who don’t have that kind of capital backing.

Snir Benedek: 
This is, this is, this is the, the solution. As we see it, we need to bring it closer to the people. Now we can’t make one machine that will do everything and people would be able to, um, to easily procure it because, because the machines are highly specific, every payload that does a certain work is very specific to that work. It does. But if it’s on a mobile base mobile basis have a far more common function, they just need to get the payload from place to place. Right? And so what you see is that the developers of these platforms, um, they, uh, they can buy something off the shelf. They can buy a generic robotic vehicle off the shelf, which comes as is, and does what it does. And they have to cope with it, or they go and make their own and making your own is, is lengthy.

Snir Benedek: 
It’s, um, it’s expensive. It requires expertise and not everyone has the expertise. This is where we come in. We have created a platform, which is, which is very, very capable and very flexible. And it combines the best of both worlds, what tailor it to your specific application. And it is bespoke for your needs in the sense that you get it, the size you want, and you can get it with a number of motors you want, depending on how much power you want and how dynamic you want it to be, how agile nimble you want it to be, and you get it very, very fast and for a very affordable price. That is how we are attempting to bridge this gap. So anyone making a robotic application can let us know what the dimensions of the platform are and what the dynamics are required to be. And within days they will have their platform given to them.

Philip English: 
Wow. Wow. This sounds like a fantastic solution. Isn’t there. Yeah. I mean, obviously I’ve done some research on the website, but that explanation explains it a lot more to me. And I, I, I totally agree with you on the solution side. There’s lots of robots coming out, but actually, um, obviously companies are investing or having to look into them and buying them, but I don’t quite know how they’re going to use them or what they’re going to do. Whereas obviously you need to start at the other end where, you know, well, what’s the problem? What, what, what do we need to solve? And what’s the ideal thing, instead of trying to squeeze, what’s it, you know, like a round peg into a square hole, you know, th that, that, that, that, that, that like analogy. So, yeah, I mean, obviously if you’ve got, um, a problem a year, then if you have a Pacific’s build that you can make wishes tailored for the, the, the company, then that makes a lot more sense. Um, so, so how would it, I suppose to, how would it work, um, go in a bit, in a bit more detailed tech technically wise, like how, how, how does it work from a vision and mapping point of view that the actual software? So let’s, let’s say that I’ve got, um, a solution that I need, I need a small mobile platform. How, how, how do I, we’ll see, I’ll come to you to, to actually build it, but what, what’s, what what’s the tech technology like within the, within the robot?

Snir Benedek: 
Okay. There are several, there are several levels to, to, to, to get over in order to, to be able to deliver that technology packaged to you first off, there’s the, there’s the physical platform, the secret sauce, if you will, in, in being able to make a physical platform that is very flexible and yet very capable is in compression, in it’s in functional density, it’s making everything smaller and yet highly capable. So the, the cornerstone of everything is this wheel. This is the first development of the company. This is the very real wheel that we’re making. It’s, it’s about as big it’s, it’s exactly as big as the diameter of the, um, of the urban scooter wheels. This is actually an urban scooter tire that goes on. It it’s very, very standard, but the size of it does not belie the complexity of what’s going on inside.

Snir Benedek: 
There’s a whole lot going on inside. So in the hub, there is, um, a very special electric Meltzer. There is the control electronics. There are, um, sensors for measuring the motion, measuring temperatures and measuring operational parameters of, um, of the wheel. And the important thing is that each wheel is self-controlled. So there is a processor on, within it as well. And the processor is what controls the individual motion of these. And so, um, by integrating the electric system with the electronic system and compressing it into the smallest possible size, we get to building block that is by itself complex, but as a system, the architecture of the system that comprises these building blocks and other elements is very, very simple, unlike, unlike the traditional, um, designs that you know, well, and if you open a robotic vehicle, you’ll see. And if you open indeed, um, an automobile, for example, you will see, um, a great number of parts interconnected with a complex spider web of connections.

Snir Benedek: 
Everything is connected to everything. And that kind of cable harness is, is, um, well complicated in our case because everything is integrated. Everything is connected with a very, very simple cable harness with communication, with power and with not much more than that. And so the system itself as a system, it is exceedingly simple. So that is the secret sauce, if you will. Uh, and, and that says, that is at the hardware level. Now, how do we control the number of wheels? This is what the actual patent of the company is, is about. It’s not about the wheel, it’s about a varying number of wheels, which are controlled by very simple computer. The computer needs does not need to be very powerful because each wheel controls itself. So what the central computer does, the central controller is just synchronized between the wheels in order to make them behave like, um, like, um, a vehicle.

Snir Benedek: 
So whether you’re using two wheels or four wheels or six wheels, direct wheels, uh, the mathematical model or behaving as a vehicle without number of wheels is already inside. So you, you do a quick configuration after a quick configuration, you’re using the software that, that is proprietary to Benedex. And, um, that part, part of the software is also, uh, the mathematical model. Part of the software is also the, um, the control of the wheels. And, um, after a quick configuration, your vehicle is ready to go, wow. But at that point, at that point, we are not still at the, um, at the, um, space issue, perception level. We’re not there yet. What you have now is a blind horse, if you will, because the system can now control its own its own wheels, its own legs, but it still does not know where it is. It needs some kind of, it needs some kind of control, some kind of command from above, from, from something that knows where it is and some, and then there’s the same or some factor that makes decisions to where it needs to go.

Snir Benedek: 
So, uh, because, um, navigation and guidance and, and, and perception, uh, quite complex, well, very complex then, um, we are complementing that side of our business partnerships with top end companies in those fields, because it would take us many years to develop a very good system of our own. So what we’re, what we’re doing is building a very robust software platform that does, uh, the control of our platform and, um, and is also meant to be very easily integrated into other means. Other means of control. That’s why we, we are currently working on a roast interface with robotic operation systems that we can fit into fit into, um, a ROS system as a roast node, but you will not need to program the wheels by themselves. You will see the entire system, however many wheels it has as one Ross’ note, and you’ll just need to command it and let it know where to go. And we will also compliment, uh, our platform with, um, with slam and with a position and, um, and localization measurement, um, measurement, uh, hardware that we won’t be making ourselves. And that is something that we’ll be doing, but by partnering with best in class companies that do it.

Philip English: 
Right. I see. I see. So we’ll see. So you’ve got the, uh, the baseline K K K K components. And then for the vision side, obviously that you’ve got partners for that, and then is it, so, um, if we, if we were looking to you to, to, to, uh, to get one of your users, is it, is it normally slammed to allergy that, that you see is, is the most widely used for like types of AMRs or is it better to do it with, um, like wifi signals where you have a free access point?

Snir Benedek: 
That that really depends on the situation. Um, if, if you’re running on an open field and slam hasn’t, hasn’t been contribution because there isn’t, there isn’t, there aren’t any obstacles perceived, um, as, as, as you are doing it in a more, um, in a more real environment, say in an urban environment, or even in, in those, that’s why the situation gets rather more hairy. And that’s where you, you need to have, um, visual means of perception. And you have to have a software that in that, uh, stands what to do with that kind of information. Um, you also needs, you also will need means for, for positioning measurement, um, what the platform does have. And, and that is a very significant advantage among others, is that because we are using direct drive technology, there are no gears within the wheels, it’s all direct drive. And that means that the motion measurement of the motor is the same as the motion measurement of the wheel.

Snir Benedek: 
And by using a high resolution motion sensor, we can actually measure with very, very, very great accuracy, the motion of the wheel. Right. I see. Okay. So coupled with other advantages of direct drive, one of which is being able to attain higher speeds and also very important being this, this being the highest energy efficiency system that physics can allow you to have, because there are no gears inside there’s, there’s no wastage of energy, uh, through internal friction. So, um, so with, with very, very high accuracy, high precision measurement of the motion, you can get great control in both low speed and high speed.

Philip English: 
Roy. I see. And then, and then, so I saw that from the performance side and the weight side, so every will, can take 125 kilos. Is it, is it, is that right?

Snir Benedek: 
Well, in the sense of loading yeah. How much weight can you put on it and put on it until it breaks then? Yeah, we’ll design it for 150 kilos of, um, of, uh, loading. Okay. Um, that’s not a big deal. That’s not very difficult. I mean, the more, the more metal you use, the more, the more you can pack on there. So yeah, we, we designed it to very, very high loads. So our platforms, even the simplest one begins with a carrying capacity of at least 200 kilos. Right.

Philip English: 
Okay, great. And then the performance is sort of how, how fast, um, can these wheels go?

Snir Benedek: 
It’s a function of the voltage you apply. Our system can work with 1224, 48 volts, and that has, has a direct bearing on, on how fast it goes. So I’m at 48 volts. We can attain with these wheels speeds of around 14 kilometers now. Right.

Philip English: 
So you got the speed there. And then the other question I had is that, is it possible to make the wheels wireless? Cause obviously you said about the control box, does that have to be with the robot or can it that be wirelessly and the signals are coming down straight? Yeah,

Snir Benedek: 
Of course. Of course, of course. No one is thinking about, uh, about, uh, controlling this with a tether. That is, that’s not the idea, um, the platform self powered, obviously. So, so it has its own batteries and it has its own computer on board. Now the question is, how do you want to command it? Do you want to command it with, uh, with a joystick? That’s fine. You can command, you can command with joystick. You can connect it to any manner of, um, of loss based system that may by itself be wireless. Because as we said, we, we provide them the mobile base for your platform. However, there is, there has to be another computer that tells the payload what to do. And usually that is also the computer that tells the entire EMR with the entire robot, where to go in order to carry out the next action. So we can very quickly and easily connect to all those computers and received from them the command of where to go. And then we will know how to interpret the command because, because our software will, then it has been programmed to, um, to navigate from point a to point B. Okay. So you just, so you just tell it where point B is assuming if you’re at point a, it knows where it is and it will carry out that, uh, that, um, come on,

Philip English: 
Come on. And then, so I think, um, in regards to that question then, so we’ll see, so you can have the wheel, you can build it onto the system. And then from the AMI, as I have experienced with is then is then you, would, you then have another computer that sits on the whole platform that communicates to the wheels. So is it, is it possible to sort of take, take, take away that, that computer, so you have direct communication to the wheels via what wireless, so you haven’t got that control system. I think that’s what I’m trying to, um, um, I understand, so like the reason I say that is, um, we sit there’s another company called wheelme and they’ve got like a small wheel like that. And I’m just curious to see how, how it sort of works really.

Snir Benedek: 
Okay. So wheel me our a bit. Okay. W we have similarities with [inaudible], but we also have our differences, uh, wheel me, each wheel is self-sufficient with respect to power. So each wheel has a box, a big box around it, and it has in those boxes, there are, um, the batteries, and there’s also the control computer. Um, when you work with a different kind of typology, right? In our case, uh, the common elements are that each wheel has its control inside. And that’s pretty much where it ends because we S we need to have one common controller to all the wheels. And we are aiming at industrial applications and to have a very robust industrial applications, um, sorry, you still need to have some kind of wire in place. And it, it is also mandated for the purpose of safety. You can’t have safety, uh, safety over safety that, that isn’t wired.

Snir Benedek: 
And one of the very important features of our wheels is that they have, they have the hardwired safety feature actually, where the redundancy event. So the premise of everything that we’re doing is that we are, we’re not, we’re not making things for the hockey market. These are hardworking, heavy duty industrial platforms. This is also why they deal with such high loads. And this is why the wheels are so powerful for their size. And this wheel weighs three and a half, 3.6 kilos, which is very, very light yet the kind of thrust it can generate. It can generate a thrust of 50 kilos. That means that by itself, the wheel is enough. One wheel is enough to, um, to pull a 50 kilo payload up a vertical wall. You can imagine that with four of these wheels, um, creating a thrust force combined of 200 kilos push, uh, you can, you can get a lot moving, so they’re small, but they handle a lots of weight.

Snir Benedek: 
They’re extremely powerful, extremely power efficient. And, and this is for the purpose of sustainability, not just in the environment sense that too, because the, the, the energy efficiency of these means that you can, you can use most of the energy you challenge them with. But sustainability also means that this is thinking long-term, I don’t mean for you to get a platform and scrap it in two years. And, and in several years, uh, you’d have a mountain of used up, uh, plat benefits platforms, uh, little around. This is not what we intend. We, we make the hardware very, very Hardy, rugged, and survivable, and we make the software very, very easy to update so that, uh, so that you can use the hardware itself, which is basically a motor and wheel, um, for a long time and keep updating the software. And it also, um, it also means that this is a system for avoiding waste, avoiding the creation of waste and being able to, uh, quickly change components very easily.

Philip English: 
Okay. And so You got the longevity there as well. And it, it sounds like, um, you know, it, even if you had it for five years, then you can obviously just take the components out and re and re rebuild it for a different light. So a solution as well. So it sounds like it’s got that. It’s got that, that ability, because if the technology is constantly getting it software updates, and he did want to change to some sort of something new, then there, then you’ve got the capabilities there. So,

Snir Benedek: 
Absolutely. But by using the smallest number of moving, moving parts within the wheel, which is basically rotor and stator, there are no gears there, there isn’t anything moving around other than, other than the, uh, the two parts of the melter. And, uh, and so that means, um, it is, it is designed for the maximum reliability, uh, the minimum weapon maintenance and, and also, um, because the components themselves a very, very easy and easy to change, they’re interchangeable, then, you know, worst case you’ve shot one of your wheels. And, uh, you just replaced it with a new one. It assumes the previous one’s personality and you get rolling again,

Philip English: 
Right. Nurse. Fantastic. Fantastic. Um, what, what I normally ask next is I think we go on through problem and solution. I think we’ve got everything there is. I, I, I normally ask, um, so something about, okay, what’s the future future, and then obviously just the next steps for how to get in contact. But before I do that, do you, is there anything else that you want to add into this section?

Snir Benedek: 
What I would say is that we are on, we’re starting out on, I say we, because benedex is not just me benedex is an amazing team is an amazing team of brilliant engineers. We’ve won substantial funding from innovate UK, and that, uh, got us off to a really, really good start. Um, we’ve assembled a team. So map company’s CTO, who, who is one of the most brilliant individuals that I know with an extensive background and a very, very illustrious, uh, track record in, in robotics. Um, and not just here, we also have great engineers, uh, because this is very, very multidisciplinary. So we have to have talent in electric, electronics and mechanical engineering in robotics, in, um, in software. And we have all that. So we’re starting out now and we are very, very much seeking collaboration. Anyone who can use this technology, and there are indeed many, many who can we just need to get the word out, I’m sure this’ll be a hit. So all these, all these people, anyone, anyone interested is very, very welcome to reach out and, and to, and to get in touch. And we will talk about how to, how to best benefit them with this technology.

Philip English: 
Right. Right. And, and the best way to get in contact with your snare, is it, is it through the website and have you got an email address?

Snir Benedek: 
Yeah. hello@benedex.co.uk. Okay. Okay.

Philip English: 
No, that’s perfect. That’s perfect. Yeah, no, sounds great. And then I suppose for the, the, the bigger future vision, or see again, since you guys are vision, you know, sort of to promote automation for, uh, the empowerment of society, I suppose to get, I suppose, it’s, like you said, you know, to, to, to make it more accessible for, for, for companies to bring this technology in and build something that’s bespoke and going to work for them, and just expanding that out for as many applications as possible, really, I suppose, as the, is the

Snir Benedek: 
Main name, we have a very, very clear roadmap of where we’re going. We just, uh, we just now towards the completion of the first stage, which is, which is solidifying, consolidating the technology, which means that we’re building the motors, we’re checking the software. We’re seeing that everything is well connected and working as a robust system, that stage one, the next stage is the platform at that stage. We’re going to, um, put the, put everything together as a system and take all the considerations as a system. And that’s when we will consolidate those partners of those partnerships with, uh, complementing technologies, uh, that will be slammed. That will be the navigation technology. That would be the positioning technology things that will take us a hundred years to do. If we did this, if we did them ourselves, the next stage, once we have a good platform that is already selling, once we have a good platform that is out in the field, what we will do is work on the service, because this has to be the best platform.

Snir Benedek:
Also in this, not just in the sense of hardware, we want to give our users the best experience in, in getting those applications deployed quickly and well. So we will be working on the documentation. We will be working on a great website. We will be working on a sales on the sales platform, on the internet. So you can put together everything on, on the website, hit, uh, hit order and, and, and your platform will be on its way to you within days. Wow. All assembled and ready to use, um, that kind, that kind of service. Um, and after we’ve done all that, I suppose we will start looking very seriously at our being a powerhouse for all kind of robotic applications ourselves and, and, um, and, and try to get a piece of the action of actually making full applications, completely turnkey on the basis of everything that we’ve developed to that point.

Philip English: 
Wow. Now where this is it, I mean, I think that’s a great way. I really liked the website where you can go in there and build it, and then you just hit the order button. I mean, that sounds like a

Snir Benedek: 
Great, there are several, yeah, there are several companies working that way. One of them is called pension, um, where you can build, um, machines on the internet and then you just click order, you know, exactly what it costs. You know, exactly what’s in there. Um, everything is transparent. Everything is visual. Everything is out there, there, there are no secrets anymore. There are no trade secrets anymore. Everyone knows everything. And, and people appreciate that everything is laid bare before you, you know, exactly what you’re getting, you know, exactly what your options are. And he just puts it together. No BS, you know, the numbers, you order, the thing it’s assembled within days, instant satisfaction and the most important thing. It works. You trust it to work. It has to be trustworthy to work. It must be. Yes. Yeah.

Philip English: 
Yeah. So it’s the people, obviously you’ve got the reliability there and now an associate does the job. And then, so what sort of, I suppose, I suppose lifestyle questions, so like timelines, um, um, in your eyes, obviously it was great to see, um, like the wheel today in real, in real life. So we’re set, I suppose, to get to the platform stage. what sort of timelines are you guys thinking of?

Snir Benedek: 
Um, four to eight weeks. Okay. Yeah. So we’ve got the wheels. Um, we’ve, um, we’re just about ready to roll out the first version of the software that we’ll be calling a variable number of these wheels, and that will be in the upcoming weeks. Uh that’s when we’ll start, um, we’ll start driving the first platforms where these wheels up until now, by the way, it’s not that there’s, there hasn’t been anything driving around. We have, uh, the benedex mini me, which is a little platform that we made out of a regular, just normal, normal industrial motors, but very small ones, like a, um, small PLDC brushless, DC motors. And then they have a similar interface. They they’re just different magnitude of hardware and, and that’s working fine. I can’t wait to get the big wheels on there and see how much, how much power they put out is going to be cool of power.

Snir Benedek: 
And it’s always fun before you, uh, before you try something like that. Um, so yeah, that’ll be the next two to four weeks. Um, we will continue the development of the platform until, until the third quarter of 2022. Okay. And, and then we will start working on optimizing the manufacturing, if everything goes to plan that is at that point, the company will already have substantial sales. And, uh, we will, um, start concentrating on, on, um, getting quick, quicker, lead times quicker, my factoring, better manufacturing quality documentation, and what I described as, as, as making up the good service, better service to our customers. Right. Okay. But yeah, w w w we are actually ready to speak with, um, with early adopters about, about getting some, getting some, um, payloads on platforms. We are at that point

Philip English: 
Now. Right. Perfect. Perfect. Well, I think that’s been a great, um, like overview, snare. I mean, it’s very much appreciated and yeah. I mean, obviously guys, you want to get in contact with Snir, then you’ve got the email address there and, um, yeah, there’s this, I think it’s going to be a great tech technology and we’re looking to see, uh, looking forward to see like more from you guys from, from, from the future. So I thank you snare. Thank you. Thank you for your time, sir.

Snir Benedek: 
And thank you very, very much. No worries. Thank you.

 

Robot Optimised Podcast #5 – Snir Benedek of Benedex LTD

Benedex LTD : https://benedex.co.uk/

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=knlbxEZ6mgA&ab_channel=PhilipEnglish

Miranda Software Interview with Laurent Ravagli

Miranda Software Interview with Laurent Ravagli

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have IRAI Robotics led by  Laurent Ravagli who will talk about their leading software and robotics .



Philip English: 
Hi guys. my name is Philip English and I am a robotics enthusiast, reporting on the latest business and applications of robotics and automation. My mission is to get you Rove optimised and to support Industry Innovation and Infrastructure. so, uh, we’ve got, uh, Laurent on the call today. Um, I’m going to have a chat with her on, uh, just to, uh, get a good understanding of his company. And, uh, and then yeah, as, as always, if you have any questions and please feel free to come back to me. Um, so probably, yeah, going straight over to you later on, like, could you give us, um, sort of like a quick intro of like your company and the, and the software that you got?

Laurent Ravagli: 
Yep. Sure. So thank you for this interview. So I’m Laurant Ravagli from the IRAI company so, uh, we create a software for the education in the industry since 1988. And, uh, this, uh, last year, uh, we developed a software called Miranda. So this is a software to simulate, uh, robots for the education. So there’s a lot of robot that you can assimilate, uh, pretty much everything that’s popular, it’s already into the software and board and et cetera, over LIGO. So you can create challenges and, uh, make your students do these challenges and create a challenge yourself and see their progress, et cetera.

Philip English:
Oh, I see. So, so the company has been around since 1988, did you say, or no?

Laurent Ravagli: 
Yeah. So, yeah. Yeah, that’s the key for the staff. So there wasn’t robotics at this point like this, it was mostly, uh, with PLC, uh, saw we are more in this, this, uh, field of the front, the education. Uh, so is, uh, about this, but, uh, this is, was a software called the automation still exist in the same words, but, uh, basically it’s a good software program, uh, inside the, with this software or the type of, uh, it gives you, you want, so you don’t have to learn every time, a newer software to learn, to run a PLC. So it’s a really popular in, uh, in France, not in the world, it’s a student setting in France, not so much because, uh, we are pretty much the one market was, uh, so a lot of the schools are there, they are this or this product yet.

Laurent Ravagli: 
And, um, so after that, so we developed some more, um, so another software that’s more on the schematics, uh, so electrical, coding, et cetera. Um, and after that back 10 years ago, I think, uh, we push, uh, us to the industry more, uh, visible, natural commissioning software. Uh, so far we are, also still working with PLC because, uh, it was, uh, um, software that you can connect to the PLC. So it’s a really, uh, creating a digital twin of the, the machine you are trained to, to create. And, uh, so basically, so this last year, uh, in France in the world, we saw that, uh, Kirsi doesn’t get much more, um, the schools. So, you know, they are switching to scratch, uh, RDR by turn, et cetera. So we decided to, to build the product for, for this, uh, and the us, we had, uh, some, uh, previously made a, um, simulator before Miranda, so specific to some robots and bought the drone.

Laurent Ravagli: 
And, uh, we had a lot of feedback, uh, that we didn’t, uh, expand it. And, uh, so we decided to create this Miranda nine, to give all the tools, uh, that to be taken. We took from the old products to implement them to this software. Uh, um, so this is the software so that we, we developed for 10 plus, uh, chitlins. So really, uh, start programming with scratch, but, uh, what’s so good is that we can do scratch and bite them so they can continue to use the same software, uh, or the years and the CEO different, uh, type of programming. And of course the Chuck and also make the old changes there. There’s no really limits, uh, for the software. Uh, so it’d be trying to build a community so they are sharing, or there are challenges, et cetera, sorry, really trying to give all the tools for 40 channels. And, uh, basically, yeah, we sell to schools, but, uh, we are trying also to sell to, uh, to outsource, uh, right now we are trying to see if it’s something that can be, uh, useful because, uh, you know, uh, children play, we, we buy a summer bus. So maybe that’s something that we are trying to dig in.

Philip English: 
Yeah. I mean, so that, that, that, that’s really interesting. I mean, to just going back to the history there, so I will say I was doing a bit of research and actually it sounds like I didn’t realize that you guys had been round and you’ve been doing the PLC work and everything else, and then you’ve merged into this slight type of technology. Um, I was almost going to say all that. You should have some of that stuff like your website, because it shows a real sort of wealth and authority that you have there. So people would say, Oh, look, they’ve come from this background. And now they’re, you know, now they’ve moved to this. So, you know, that that’s really in interested in now. So you’ve got skills from the past, you’ve done it in the past. You’ve done it with PLCs, and this is just a natural progression. So you’ve got the experience. So that’s, that’s really, really interesting to know. I actually, um, I mean, I suppose, um, so from a problem solving point of view, so what would you say is the main, the main thing, the main problems that, that you’re solving?

Laurent Ravagli: 
So right now with the current situation, of course, it’s the giving the tools to the students to, to be able to code the code that they don’t have to, they can access to the robots and the teacher don’t, don’t say use, I don’t want to make the costs on the coding is they don’t have the robots. So giving the tools on that, uh, the mentor first, um, and also, uh, as a cost-effective solution, because as a class room, you don’t have, uh, the number of robots you need for all the students. So to have a simulation of the robots, even don’t have to have the robots. Uh, so, but still some romantic factor or coming from us for that training, the setting, the software, but, uh, our grandfathers, uh, some are, some of them are actually, uh, adapting to this and, uh, contacting us directly, uh, to, to, to build something with us, um, or they are training to, uh, get some money.

Laurent Ravagli: 
Uh, uh, yes, uh, you’re always trying to, to get through for the teacher for the, uh, or so in the industry, uh, for other products is also always giving something that, uh, can, um, uh, help, uh, the industry or the education to be more effective in the industry. For example, if, you know, go to commission software, it’s small on, uh, you don’t have to build a prototype, uh, you can be 3d of the machine and you can connect to the PC. So you can start working on the beauty. Doesn’t have to be the prototype. You can present the machine with a working system and you can see, uh, what would be the problems. Um, so it’s a timer, it’s a Q and a, so, uh,

Philip English: 
I see, I see. So you’ve got, so it sounds like you got two different areas there, so we’ll see, like for education, it, you know, if, if, if, if teachers or parents or kids haven’t got the hardware, then they can use your, your, your, your, your software to, to practice their coding skills, um, without actually having the, the, the hardware there, but then also in the corporate world, uh, for, for people that want to test out their ideas on a more like commercial basis, then they can use your, your, your software. So you’re, you’re, you’re, you’re, you’re essentially saving them costs, you know, and saving them money. You know, he, you know, stood the test then, I mean, I was having to read, so I can see that you, you already interact with a mixture of robots. So could you do a robot that, that someone built? So, so like if I built my own robot out of bits and pieces, um, uh, at w w w would there be something I suppose, software wise that I would need to install to connect to your system, is that how it works?

Laurent Ravagli:
Cool. So you can, um, basically, uh, Miranda, we have three main parts. So you have one, you can just play the already big challenges, one, which you can create your own. And, uh, the last part is when you can create or modify the robots. So all the built-in robots, we can hide some saw plan for example, but you can also create your own from scratch, not to another program in China. Uh, so you, you have basically the library, uh, with, uh, elements you can have so chassis, you can have the whales, uh, several motels, et cetera, and, uh, all your sun salts, so we can have that to make your, uh, base, uh, that’s what we, uh, I do also for, I didn’t explain my, my role in the company, uh, but I’m a simulation development manager. So, um, for all the projects we developed in internet, uh, we, uh, sometimes I have clients that ask, um, they don’t have the time or the resources, so they ask us to make something for them, uh, inside the software.

Laurent Ravagli: 
So basically that’s my role in the company. So, uh, there was of Miranda basically, like right now, am I on a project like this? I incorporate, uh, robots from the, our reseller, they are keynote software. So this is how I do, and the outdoor teacher or the parents can do themselves. So you create a base of your robots. And after that, you can mask, uh, elementary. Don’t want to see, for example, the tube that Selma the chassis. And you can import that we did add a skill you should add as a scheme, uh, for the robot. So basically you have already all the functional function inside the software, so yeah, and you put them on the base and you put the skin on the, on this, you can, the put ready and being around it, that’s, uh, it’s possible. Um, but two, we don’t limit this system, uh, to robots. You can both do 3d or for example, of a tree and the tree, you can, uh, use it to build your scene. So you can, uh, really what you want. Uh, you don’t have to worry about, uh, for example, now I’m building with a gate, a backing gate, or this is a system that, uh, that, uh, uh, the reseller, we are working with strain to implement the system that work with, uh, uh, Arduino com, uh, that we can program, uh, from yonder.

Philip English: 
Well, I see. And then, so I was having to read about the software is in the cloud as well, where, so, so, so you can stall your models and everything it inside the cloud, and then you can just access it from any device. Is that

Laurent Ravagli: 
Yeah, exactly. Yeah. So this is a big point also for schools because, uh, uh, I don’t know, in the world, but in France, uh, in studying the software on the network, this tool is a pretty long process, uh, because they don’t deal, uh, with the, is this themself does, uh, uh, original uh, so it takes months for software to be installed. So we wanted it to be online. So from the red buzzer, from the tablets, uh, much cannot. So in study it so directly, uh, from Microsoft store or directly to the PC, um, that’s, um, something that we want to implement for our other software. So the first one, uh, we thought the automation for the PLC, we are trained to make an online version also. So there’s a really good feedback about that.

Philip English:
Yeah. And obviously it makes it a lot easier like to access and, and what I loved about it was the challenge, like creation. So obviously if I was a teacher and I had a group of kids, then, then I could give each of them a challenge, is that right? I can build in challenge that they would have to do that, they would have to code. Um, and then is that depending on the robot that, , that I’ve selected for them, I suppose, I suppose, you know, th this is your challenge for this robot. And then can I set them another challenge for a different robot? Is that how it works or,

Laurent Ravagli: 
Yeah, basically you, you build the scenes, uh, and that’s, uh, the, to show that, uh, implement the robots, they can be, uh, for example, uh, you create your Parco, you add a specific robots you can give to the students. Uh, uh, and after that, uh, maybe I want to produce the same Parco. So I just asked the teacher to change the robot. It’s a good to go. Uh, some feed that’s, uh, could be that we didn’t do for now. That’s the, maybe a better response, some robots, uh, at the start line, and then the students, somebody on the cutting of it, I think, uh, let the student choose which robots you want to program. That’s also a possibility. Um, and, uh, basically you create a senior with the robot. So we have, uh, predefined challenges for each robot sometimes. Yeah, that’s the same Parco for example, for the same parco the follow, the line, uh, challenge pretty simple.

Laurent Ravagli: 
But, uh, after that, we really, uh, go on, um, the tree at the editor and, uh, show the teacher how to modify the difficulty, for example. So other stakeholder in the middle of the line, put a section without relying on the ground. Uh, so that can be really easy. So that’s the first step. Uh, I, um, teach them, so I do so far some, uh, trainings, uh, with the teacher. Um, and that’s, that’s the thing. I show them it’s after that, actually I show them how to create their home. So basically you have all the tools that I can set, uh, to when the lights, the scene, but also what you want to do with the challenge is, um, the scenario. Uh, so you have to go to first Gates, et cetera. So this is something that you can code also directly from the city, uh, in scratch or Python.

Laurent Ravagli: 
So this is really easy for them. Uh, and, uh, as, uh, explain them out to modify, they can start from an already built in change and modify it to their needs. And after an hour, I’m used to the software, they can start building now, um, and, uh, for the, is for the teacher to see, see, this is good. You can also give these tools to the students, but to be the program mandate for the, for the start. And, uh, so this, uh, we also, uh, introduced some tubes for the children to use. Um, but, uh, this, um, pop-ups, for example, that can appear off to tell them what they have to do, uh, uh, the video also, but, uh, basically you, will you stop the scene in, uh, yeah, you have to start putting the, the lots next. It would say you have to connect this back to the other one, but he’ll start progressively, uh, and not, uh, uh, give a challenge like this and, uh, yeah, programmer, you’re trying to do something and not just give the tools. And, uh, let’s say, uh, um, what this, uh, by yourself, uh, we are trying to reintroduce, uh, everyone, uh, teacher and students to the result.

Philip English: 
So you got that connection there. Yeah. Okay. No, sounds good. I mean, I was also looking at some of the different packages that, that, that you had, can you give us a run through, so I think you had the, you know, it was a mixture, you had sort of a, the number of users, but then you had sort of a bronze, silver and gold, um, same thing going on. What was that?

Laurent Ravagli: 
So basically we have a four robots, so the first one is a for outsource. So just one user. Okay. So it’s all the functionality inside there. And the trio does. So you have unlimited number of users, and also you can follow the progression of them, uh, basically with the distributions, what functionality you have access to. So sometimes a teacher don’t want to have them. Uh, so for example, uh, you have the primary option. It’s pretty much the same of the destination. You have access to everything. So for schools, the origin is the same thing without the word budget. So you only work with what you have in the library. So you have a 10 or 15 robots that you can use, and you can create your scenes. And just below that is, uh, the one robot edition. So you choose between the robot are, so for example, if you want to win, but you just have to input and you can create your scene with it. Right.

Philip English: 
So differences there. Yeah. Okay. I mean, so just, just, just, just changing gears aside. So what’s the sort of the bigger picture for like you guys, I mean, is it, is it basically to get on more and more robots and then do just, just have bit build more of a community, um, where teachers and everyone can, can interact. I mean, w what’s the sort of the next steps and sort of big, big vision.

Laurent Ravagli: 
So for now we just launched a stock. Uh, so the user can share, uh, there are creations, uh, before we, we try to do a forum, but, um, doesn’t work where people didn’t seem to post very much. We had some teacher that, uh, re uh, create a lot of change. Uh certain chage but, uh, isn’t very well. So we are trained to, with the, to hopefully change that. So I’ll serve your, creating a robot and also dock six ways, for example, um, tides, uh, that’s used, or in the world challenges or competition, uh, robotics, uh, that’s uh, in real, we are incorporating it to the store for free. So all the things we incorporated ourselves, we put it for free, but, uh, as a teacher or as a user, you can put a price on it if you wanted. Um, so for now, everything is free on the, on the store. So you can, the, no, the, uh, it will be added automatically to your account.

Laurent Ravagli: 
So, yeah, this is what we are already trained to do is build a community around this, because we know the debate is that, uh, there was a lot of creations. They are really gaining some, uh, um, uh, population every day. We see the number of connection is growing. Uh, so we are, we, we know there are some creations and, uh, the big point is, uh, the, to share with the suffer, I think, and not be on your side. Um, that’s really real. We are trained to, to create, uh, this, and, uh, of course we are also as a, all the time trying to, uh, to get, uh, other countries. So trying to find some resellers, basically we, we work like this. We are rarely, uh, contacting client directly, uh, only, uh, secret sellers in the, in the, uh, the world for France. We are also trying to seek them directly because we, we have, uh, uh, an agenda, uh, uh, uh, a list of contacts and, uh, the scores because of our software.

Laurent Ravagli: 
We have a lot of, uh, screws, uh, that we know, uh, in our company, but for, for the world, you are going to resell us, uh, to do that. And basically, uh, the, the functionality we had is basically what, the reason, I think, what we be the best for the country. So we are the world beneficent, uh, from it. Uh, so for example, there’s, uh, uh, for the changes, you can do a multiplayer. So put a separate students on a simpatico with several words. Maybe this is something that’s, uh, come from, uh, an ID from, uh, China.

Philip English: 
Okay. Okay. So it sounds like you expanded out quite quickly, quite well. Socially, if you you’ve got artists, people from China, people from America and obviously France as well and around Europe. So, yeah, I mean, so that’s, that sounds like you’ve got some good growth plans there really, and there’s a, you know, there’s a path, you know, to sort of grow and build that, that bigger communicate, uh, that bigger like community. Um, I get everyone. So do you deal with like industrial robots and stuff like that?

Laurent Ravagli: 
Hold on, clean me on that based on, on the other software. So the actual commissioning one that’s called virtual so that we can need to PRC and, uh, import 3d, et cetera. So what we can do with this software is that you can import, uh, from a library, uh, basically robot from a manufacturer. So as IBD, uh, hookah, et cetera, uh, and what’s ever too, is that, uh, real time, uh, copied the movements from the simulating, uh, software. Uh, so that can be useful if you’re trying to see, uh, what the robots out of the robots we, uh, interact with the other machines of your line, for example. So you feel the PLC can really see what’s what’s going on. And it’s a, it’s a robot starting the cycle at the right time and what will happen next. So that’s a really good tool for, for this. So as we know that, uh, robots, software, you can simulate your robots, but you don’t really see what’s going on, uh, that they incorporate 3d. But now we can see what’s, what’s going on with the ball liner and you see, you have a bigger view of your system.

Philip English:
Um, and then, so does this, the Miranda software linking with the older Pitt PLC software that you guys use? Is it, is it, is there a link between them so you can use both of them, like, like together.

Laurent Ravagli: 
Yeah. You can use them together. Uh, this is primary too. So don’t, you really usually do that, but if, sometimes you want to use the, uh, the program that you made inside the automation. So before sending it to the PLC, you can use this program through, uh, uh, your main, uh, twin digital twin, but what’s, uh, we picked from this software is that, uh, we use all the drivers. Uh, so the, the digital twins can directly connect to, uh, the PRC, all the simulated periods here. So, so with IP, with OPC, uh, everything you want, uh, so it’s really easy on the side. So this way, some of, sometimes in the, in the industry, most of the time they don’t take a vendor or software, they just take the virtual commissioning because it do, but they, they need,

Philip English: 
Okay. No, that’s good to understand. Um, yeah, I mean, I think for next steps, I mean, um, I think that’s quite a good overview actually. You know, you, you, you showed us the history of the business and where you’ve come from and all those bits. So that’s really good. I mean, I mean, if, uh, if someone wants to get in contact with you, then what’s the best way to do that.

Laurent Ravagli: 
So folks, the best ways to contact us on our website for Miranda, that’s MIRANDA, software. Okay. Oh, it’s for the company all around it’s irai.com. So we will be redirected to the iReady france.com site. That’s normal. It’s a, our main website. So maybe that’s a, that’s why you didn’t see our other products because we made a separate site because it’s, uh, for different industry. Uh, so the first one is more on the industry and merchandise purely, uh, um, for the robotics.

Philip English: 
Right. Okay. Yeah. Well, I’ll have to go and check that out to see the differences, but, um, but on the random side, yeah. I mean, obviously on the robotics side, which is what we’re keen on. I mean, that, that, that’s a great overview and, uh, and yeah. I mean, yeah, yeah. Guys, if you have any questions for like, um, like Miranda or like Laurent, then please feel free to send them over. And, um, yeah, no, that was a great interview, like, and really, really appreciate your time. So thank you, sir. Thank you. Thank you very much.


Robot Optimised Podcast #4 – Laurant Ravagli of IRAI

IRAI Robotics : https://en.iraifrance.com/

MIRANDA Software : https://www.miranda.software/

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=fq48xa42qYw&ab_channel=PhilipEnglish

Indus four Interview with Arthur Keeling

Indus four Interview with Arthur Keeling

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Indus Four led by Co-founder Arthur Keeling who will talk about their leading technology solutions.

Philip English: 
Hi guys. Um, my name is Philip English and I am a robotics enthusiasts report on the latest business application of robotics. And my, uh, my mission is to get you robot optimized as a support industry, infrastructure and innovation, uh, today, uh, we’ve got, um, Arthur Keeling from, uh, Indus four and, um, Indus four really, um, relooking to redefine how organizations access and control automation, uh, to solve their problems. Um, so Arthur, hello. Hello, must be here. Nice to meet you. Thank you for your time. Um, so I think the first thing that we wanted to go through is this really just a, uh, a bit of a, um, uh, an explanation about yourself and the company, if that’s okay. Just to give us like an overview.

Arthur Keeling: 
Um, so of course, um, well Indus Four was founded just before the, uh, first lockdowns of COVID and we had set out to deliver automation for people by tackling problems that they hadn’t normally associated, that could be automated. So by offering solutions that can help them tackle challenges that they maybe didn’t think they could automate. And over the last 12 months, obviously the world has changed beyond recognition. But what that has led for us is we’ve become the sort of go-to of automating tasks that people thought they couldn’t automate. And that has led to a loss of work with pharmaceutical companies, uh, the NHS, um, but also food producers we’ve been speaking to. And these were jobs, which they didn’t previously think they even wanted to automate, but events overtaking them and we’ve been helping, uh, deliver sometimes prototypes, sometimes working solutions. And so helping provide those tools for them to automate solutions that traditionally they may not have wanted to approach five years ago.

Philip English: 
Wow. So, so for, so because of the pandemic it’s made, so those, um, that those End users think a little bit more about how they can do their normal manufacturing and processing, and then we’ll see that, then they’ve come to you to say, okay, look, we do need to think about this. Like we’ve never done it before, and we need some, some smarts and creative services solutions to actually get it, get it, get it working.

Arthur Keeling: 
Absolutely. So we’ve brought together a team and our team has made officer AI vision specialists, and then we’ve got mechanical engineers, electrical engineers. So by having that broad skills team, and by being located next to the Bristol robotics lab, it gives us the access to huge amounts of knowledge. And by being able to pool resources like that, we’re able to tap into, you know, researchers from the universities in Bristol, but also we’ve got our own offices next to it. And that’s some collaboration helps us tackle a lot of those challenges. And it’s been tasks that traditionally people weren’t, they weren’t a problem before, but they are now whether it be because of having to distance staff, they’re having to automate a process or it’s because there was a job they didn’t do before all of this. And they’re now having to do, and they’ve discovered that needs automating because it’s very burdensome taking time, or quite often we find it so valuable staff doing mundane work suddenly, and they’re having to find a way of freeing up their bodied staff, whether it be doctors or people working in pathology departments and things like that.

Philip English: 
Right. I see. I see. So, so the business is only about a year old or two years,

Arthur Keeling: 
Just over a year old now, just over a year.

Philip English: 
And, and then, and in the history of the business, so you from sort of the Bristol robotics lab, um, like background or if you, yeah,

Arthur Keeling: 
So I, I was at university here in bristol as well, um, which is how I’ve kind of associated with it and have worked with various projects with other companies before starting this with 3d printing technologies, um, have worked with some drones before, and that’s a combination of projects we’ve worked on, enabled us to bring together that team that is now delivering what we are able to do. And it’s offering those services to people who need towards those tasks. And it’s that sort of broad range of skills that we will learn. So over quite a few years, uh, got a team of 10 now delivering these, and then we’re able to serve, use external. So people for other areas to help support that.

Philip English: 
Right. And I suppose the, the problems that, that, that you’re solving is going to be a complete mixture. I know, sense that’s some of the interviews. Um, we, we, we see a lot of the, um, uh, the, uh, the vendors sort of focusing on one particular problem, but it sounds like obviously you you’re, you’re more of a, of a speak to the customer, get an understanding of what, of, what they need to do, and then realize what, what their overall problems are and then come back to solve them. Is it, I suppose the question is, is it it, are you finding the same sort of problems that you’re solving or are they completely different for every customer?

Arthur Keeling: 
No, actually not. It’s a really good point. We are tackling problems, which often end up having mass market appeal. Okay. So we’re finding, we’re not working on a one-off project when we’re working on a project, we often then analyze what else is available out there. And then we realized that they are not the only person who has that problem, and those are the problems we’ve been focused on. So we’re able to help offer it to other people beyond the, um, by using our sort of platform that we’re developing, we’re able to scale those benefits for other people, not just as one-off products. And that’s something that we do really importantly, when we’re working with customers, we look beyond just that case as well. So we’re always looking, you know, one, two and five years down the road of how we can bring those benefits and not just in the immediate shorter.

Philip English: 
Right. And then, so do you end up supplying the customer with like a finished product solution or finished products, software? Is that, is it, is that how it works?

Arthur Keeling: 
So the combination of the two, um, we have our own platform that we’ve developed as well to help support our hardware roll outs. Um, and we’re looking at how we could partner with other or manufacturers to offer our platform as a standalone product, but also continuing to show what’s possible using our software with our hardware solutions at the moment. And that’s where we’ve been deploying them with some pharmaceutical companies and within the NHS at the moment, supporting some of the work they’re doing. And we’ve been using those as the case studies and the proof points of what is possible with a new way of trying to handle different parts of automation. And these are often highly trained individuals who multiple PhDs and their knowledge and power is incredible, but they’re not robot experts and it’s about making it accessible for them. And so that’s how we’ve tried some gear and it deliver these tools,

Philip English: 
Deliver the tool. And it’s yours. It’s your software system? INX is that the one I was doing a bit of research and I was on your Western, on your website system. I, I next was that something completely different?

Arthur Keeling: 
That was, uh, one of our earlier prototypes of our system. Um, and it’s a bit that’s version one and we’ve sort of, we’re evolving as we go. And that’s been a really key learning point for us is as we’ve been working on a number of projects over the last year with a range of different customers, that’s of learning and that learning is going into the platform to improve it. And we’re working with companies manufacturers of off the shelf components in Germany, in the UK, and by being able to work with them, we’re able to bring the benefits of our platform to them as well.

Philip English: 
Right. Okay. That’s really, really interesting. That’s really interesting. So see, so it’s obviously solving the customer’s problems you see have having a look at the solutions. I mean, it’s, it’s, um, I suppose what, what’s the bigger picture then? I suppose if you’ve got your own platform, is it to obviously grow the platform and obviously, uh, be, have the ability to integrate with lots of different vendors? Is that, is that what you’re saying?

Arthur Keeling: 
Okay. Well much, much like yourself. So you, as a robot, enthusiastic, we, our team or increase of enthusiastic about machine, vision, robotics, and getting automation out there. And it’s about getting it to two more people. And I think in the next 15 years, we’re going to see the automation and digitalization of manufacturing processes that are going to do wall office has come before us already. And I think it’s going to be a really exciting time to see what happens now. And that’s where we’re trying to enable more people to benefit from that change, whether that be control, just simple sensors that you’re putting into a shop to help you control the temperature and reduce your energy output for environmental reasons, or you’re controlling a check-in sheds to improve the climates in it, or you’re using a robotic arm for pack and place at the end of, uh, the latest first sickle farming installation somewhere. It’s about trying to enable a platform to that more and more people access them as we see. So more and more people trying to embrace better ways of working.

Philip English: 
Wow. Yeah, no, it sounds like you guys have got some great projects there. I mean, I suppose I’m like, I quite like the idea is obviously like you work on a solution and then now you can see how you can take that to the mass market. I mean, would you, um, w w w I’ve seen people do that before and, and they, they would normally almost brand it and create their own company or, you know, and an AP and other companies spin off of your company. Is that something you guys sort of see in the future?

Arthur Keeling: 
Um, that’s not how we operate at the moment. Um, and by pooling our resources and developing these products, it means that we are able to deliver the best value for money as well for people. So by rather than spinning everything off, we’re able to keep knowledge and skills contained within the company so that we can take learning from different projects. Cause we often find there is crossover between some of these, and then we don’t get any trips or spells with, uh, different companies having competition over each other. And by bringing it together and having that sort of collaboration between all the projects within our company enables us to take learning from areas. You wouldn’t have thought you could have taken a lesson or anything like that from, and you pick up all sorts of great insights, but that’s also one of the benefits of being based somewhere where you’ve got access to people like the bristol, robotics lab, you have conversations with people and yeah, those are the moments that you can really help you fix that problem. Or how are we going to get us certain things you move in a certain way. And that is something I think we’re all looking forward to once we can get back into the office, being able to have those design and engineering meetings. Aren’t I I’m much more challenging when they’re done like this at the moment

Philip English: 
Or on the, on the virtual arena. Yes, indeed. Okay. Um, I suppose the, the, the other question that I had was, um, it more in regards to, um, I suppose, like opportunities to work with you guys. So if I was, if you have a customer saying far more or in a hospital, was it, what, what, what, what’s the best way to work with you? Is it, is it, is it to literally say, Oh, look, here’s some videos, here’s some pictures. This is what we need to do. Like, can you guys have a go at creating like a system for us? Is that, is that, is that how you guys work or yeah.

Arthur Keeling: 
Yeah, absolutely. I mean, we’ve been often we’re approached by people and they come to us saying, this is my problem, and this is the challenge I’m looking to solve. And they, then we sort of evaluate it internally and see what we can do. Um, and that’s normally just a consultation with them and a conversation where we can scope it out. We’ve had a project this year that we had our first meeting on the 11th of January for pound. We are already sort of rolling out the products in the coming weeks, um, for them. So that’s something as well that, where I was bringing that severe speed and agility within our team as well. Um, but that’s sometimes why we’ve also partnered a larger organization. So larger organizations have blips walls make tasks, and they’ve come to us saying, yeah, you’ve got that speed and agility. We’re looking for we’ll work with the on project. So we’ve had that combination of individuals coming with photos and problems. I’d like to solve all the way to larger company saying we’re looking to partner with an agile automation company to help us fix problems.

Philip English: 
Right. Right. Are you guys do some amazing stuff? Uh, yeah. So what would be the next steps in getting in contact you, you know, um, and what sort of industries would be the best sort of marks for getting in contact with you guys?

Arthur Keeling: 
. Um, well, at the moment we’ve got a really strong focus in the medical sector and we’re working really closely with a large number of doctors and pharmaceutical companies. So if you are in the medical sector, we’d love to hear from you. Um, we’ve got a number of products we’re developing in this space at the moment, uh, ranging from primary care all the way to sort of their pathology departments. And we’d be really interested to hear from you to see if we could also bring these products to help benefit you, but also maybe improve them and get your feedback and thoughts on them as possible. It’d be fantastic to talk.

Philip English: 
Right. Fantastic. I said, well, yeah. So, nthat sounds very exciting. And I think, I think what we’ll do then guys is we have a concept with us, Arthur, the next sort of three to six months and just see some of these that the projects that the guys are working on, but it sounds like some very, very like exciting stuff and yeah, and very, very much thanks for your time today. I very much appreciate it.

Arthur Keeling: 
Okay. Well, thank you so much for having me here and look forward to touching base in maybe a couple of months, time and updating I’ve gone away. We’ve got two little projects.

Philip English: 
Fantastic. Thank you, sir.

Arthur Keeling: 
Brilliant. Thank you very much for your time. Really appreciate it.

Robot Optimised Podcast #3 – Arthur Keeling of Indus Four

Indus Four : https://www.indusfour.com/

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=9BjcCt0kWII&ab_channel=PhilipEnglish

Extend Robotics interview with Dr. Chang Liu

Extend Robotics interview with Dr. Chang Liu

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our next episode, we have Extend Robotics led by CEO Chang Liu who will talk about their leading technology on robotic arms.

Philip English: 
You guys, uh, it’s uh, Philip English. Um, I am a robotics enthusiast, uh, reporting on the latest business and application of robotics. Um, my mission is to get you a robot optimized and, uh, to support industry innovation and infrastructure for the next era. Uh, today, uh, we’ve got Chang, uh, from extend robotics, uh, so extends, um, they build, uh, affordable robotic arms, um, which can be remotely controlled anywhere. And I think their, their, their, their main vision is to sort of extend human capability. So you, haven’t got to be there physically. You, you, you, you can use robots to do the tasks. Um, so hi, Chang. Welcome. Cool. Thank you, sir. Um, so I suppose that the first thing that we want to know is it’s really just like a, um, a quick explanation about yourself and the company. Is it, is it all right if you give us a, uh, a very quick overview?

Dr. Chang Liu: 
Yeah, sure. Uh, so I’m Chang, I’m the CEO of Extend Robotics. Uh, so in one word, uh, in one sentence, uh, an example box we would build, um, highly, scalable, um, extent. Uh, we’ll go highly scalable. Uh, teleoperation robotic long two, and now anyone to, uh, intuitively operates remotely from anywhere. And, uh, I really like myself is, um, I, I kind of started from like a robotic recess back where I was, uh, I did my PhD and, um, uh, actually, uh, on our style, how we can automate, uh, robots. Um, I was also the head of robotics. Uh, so during this process really like, uh, all too many plans and the industry partners, uh, trying to figure out what’s their, what’s their need in terms of using the robot in real world scenarios. I’m kind of getting very excited and recent years seeing this, this, uh, uh, boom, uh, um, role of, uh, being used in real application. Uh, other needs like this, there’s a few writing for us a lot, like, uh, digital digitization automation, the trends, and the enabling technologies that allow like, uh, um, intuitive operations such as the VR, uh, um, the class artist. Um, yeah, but I also see as a base, uh, challenge there, uh, that’s really this, this, uh, this bottleneck of motor robotics that has this complaint of the limitation of operating and complex scenarios, while you actually would require physical operations to certain costs, but that’s beyond the cognitive ability, say, uh, the robots say taking pictures and deliberate, uh, robots. And, uh, really what we want to do to do is back. You find a way, but a new way to, to make complex operations, uh, many relation tasks saves our cost cheaper. Yeah.

Philip English: 
Fantastic. No, that’s, that’s a great overview. Thanks Chang. So we’ll see, like, you’ve come from a, uh, robotic, um, like academic backgrounds, you know, you’ve seen that the, the, the, the, the problems that the industry has is, and now you’ve created oversee, uh, this company and this solution. And I suppose the main problems, I suppose you can go through if you went through health care. And then I, the first thing I think about is, you know, you, you, you, you may have people like in hospital beds or care homes where you can, uh, assist them like remotely, uh, industry has lots and lots of different types of, uh, of applications to do with manufacturing and distribution, um, general services. So restaurants and, and things like that, especially because of COVID right, right. At the moment. So I can see, um, the, the problems that, that, that people will ha would have. And then I suppose, on the agricultural side as well, with the, with the getting more and more difficult to find workers, um, the, the, the, the problem is there that we need to like address, and I suppose the solution for fit for you. I mean, I was reading into, um, you’ve got something called AMA S is that, is that part of the solution?

Dr. Chang Liu: 
Yeah. Yeah. So the AMS, uh, is short for, the amass mechanic assistance system, which is literally a special VR game that connects to a real role to allow people to leverage the intuitiveness and the immersive VR to operate the robots more easily. Um, so we believe that’s, that’s kind of the new way that people could go for it, the robots. Yeah.

Philip English: 
And then, and this is connected to the clouds and that, and obviously that, that’s where the link is. So is that, is that a server on the cloud that, that, that, that all the information lead links to, or how, how, how does it work? How does the communication work?

Dr. Chang Liu: 
Yeah, I mean, the system with the mining is a, uh, it’s a network ready, uh, system. So the robots connects to obviously the network, uh, the AMS software connects to connect to the same network on them. They communicate or over imagine this network in as, as, um, it’s flexible. So it could be wifi could be, uh, 4g, uh, or even the 5g is not, well, I would say a CEO, we are a partnership with a few, um, 5g test that, to actually trial how 5g could improve our service. Uh, Thomas was giving , but, uh, but yeah, but the system with a lot of network ready, so some that couldn’t connect to any, uh, networks. Uh, we also worked on integrating the out of the website is to the, to the system. So, uh, slowly you can actually have a remote server that actually allows you to choose province like, uh, Marshall, uh, uh, like VPNs you to communicate over the internet. So that’s, that’s allowed people to work remotely. So because initially use the BI interface to, to operate the robots or the internet. So you don’t have to be in the same, same location. There’s a little

Philip English: 
Perfect. Yeah. Well, I suppose that, that’s the main thing. Like you want the security around it, so if anyone’s going to be logging onto the robots, you want to make sure that they’re secure. Um, I did go through a few of your videos. So I saw you at the robot restaurant up in Milton keyeds. Um, is there a robot ties here? Uh, sorry, robot taser. I think Mark and Joe I’m like, Oh, that, that at that place. So I’ve been there, it’s quite a, it’s quite a good place to get to if you’re going to the UK. But, um, so as those, the sort of testing is that, is that a good example of, uh, how you would use it?

Dr. Chang Liu: 
Yeah, I would say as a, as a concept demonstration and a technology showcase, uh, our system, uh, we’re still exploring the business, uh, business case behind it, but, uh, but I would say this is a great showcase of what you kind of do as example. And, uh, so we basically did a bit of quick set up in there. Um, so we kind of use it a little bit hard to see what kind of beer, uh, following the quality of that. That was cool. It closed down a lockdown. Uh, actually that was one though only like one day before the, uh, meltdown second lockdown. So we were kind of lucky. Uh, we managed to do it a demonstration. Uh, yeah, but, but it was the, it was quite simple demo, but actually is not designed to do one particular task. Uh, but it’s, it will be, it’s designed to do a general, uh, system floor, uh, random, different costs, um, depending on how people want to use it. So one day it could be useful, um, for bartending one day it could be used or Shanna’s, or, uh, or it could be an independent roles. Um, anything you want to do to fix this flexibility, you, you attend from the AMS. Uh, human interface, that’s literally the role of the human. They still controlling the robots, uh, but in a more intuitive way.

Philip English: 
Yeah. Yeah. And that, I love the flexibility as well. So obviously like you can, you can use it for multiple tasks. And I suppose, especially in, in, in, in, in restaurants, like we’ve seen, um, a few robot projects where they’re looking to automate the, the restaurant, but obviously the robot can’t do everything. So you would need still someone to, to, to log on and do that piece of work. And, and the thing that, that gets my attention it’s maybe even at the home as well. Um, cause we’ll see if you have a, if you’re making a meal at home and he wants some, someone to, to get you to give you a hands, then obviously you can have a service where someone can log on and actually start to start to make the food for you, especially if it’s an elderly person as well. Who’s struggling. Um, so that’s interesting. Yeah. I mean, I was going to ask, um, so what’s the sort of, um, so the main reason is obviously to get these robots out, to make it a lot easier to, to do tasks without having to be there. So like what’s the bigger picture then? Like where do you see your, your yourself going?

Dr. Chang Liu: 
Well, the system is general S uh, remote timely solution was, uh, was a low cost advantage on the intuitive interface. Uh, and what we believe is, is the, the problem is so applicable to a wide range of industries. Uh, so random from, uh, utilities, uh, utility industries where you want to do a special images, uh, maybe like nuclear industry say you want to, uh, decomission, the nuclear, uh, facilities, uh, house care. You want to go onto it, we’ll take care of the patients, uh, where you, uh, even, even there was, there was a highly, um, uh, dangerous virus uh, uh, or yeah, uh, the agriculture industry where you house, um, uh, like the local local, um, what do you call out the shortage of laborers and local areas? So you can utilize, um, the labor that’s outside the SIS local area, uh, quickly, and also like, um, uh, public service, uh, hospitality industry, as you want to, uh, have a remote walking solution for your, um, Walkers, uh, there was also could be usable space even.

Dr. Chang Liu: 
So those are wide renders industries. Uh, what believes the key market would be around utility industry. That’s where we see the most desire from the customer. Uh, but, but, uh, sometimes it needs a more complete solution, not what we tend to, uh, at the moment offering. Uh, yeah, but, uh, that’s what we are looking at us. And, uh, we, we’re also looking at, uh, uh, public service industries that may have a, um, easier cost philosophy would do at the beginning. But, um, but yeah, but we see the shot market is seeing, um, house, uh, they probably had this, um, the, the key market is the utility, the utility industry.

Philip English: 
My sense. Yeah, it makes sense. Like I also saw the video about the, uh, the, uh, the first, um, birthday party sort of like CA COVID birthday pie. So that was very impressive.

Dr. Chang Liu: 
That was the, our early prototype, uh, uh, that was basically that was done, uh, or 50 miles away, apart from the mobile apps to the operator. So I was controlling the robot from Redding and then robot itself is in central London. Uh, that’s what we’re suppose to be miles away. Um, we were able to operate the roll-ups, uh, over the internet, um, that that’s shown us to be quite, quite bombastic. Yeah.

Philip English: 
And then I, I suppose a quick, quick question, I thought, well, if he were operating like 500 miles away, would you have to have to make sure that the internet connection is it’s obviously stable and secure and powerful, you know, so he doesn’t cut, cut, cut out. So he’s, that’s quite a main thing.

Dr. Chang Liu: 
Yeah. Um, I said that the network capability will help us, is it just like a 5g, uh, improves to improve latency and the family than the robustness? Uh, the system can operate, uh, in restricted, uh, by the way, is, um, on being safe, even the, even this network breaks out. So worst case scenario, you lose control and the robot stays there, uh, safely. Um, and, uh, yeah, so, and actually our, um, point like our beta beta streaming pipeline, uh, where we’re also like a patent pending analysis, a lot of information was in a low bottle. Um, so we are walking on a flat and popping off on the streaming algorithms, um, that will basically forms our, uh, one of our USP to achieve people, have such systems, uh, and, uh, in a more realistic scenario, especially within a constrained network. Yeah.

Philip English: 
Right. Perfect. Perfect. And then, um, I suppose the only other question I have was around, um, sort of, uh, you, is the company going through like a, um, like an investment sort of scheme where obviously you, you have investors on board and every step that you go up, um, and then you get more investment and you grow and grow. Is that, is that the path that, that, that, that the company is on?

Dr. Chang Liu: 
Yeah. Uh, we are, uh, yeah, so we are already say start up, uh, we have been raising, uh, investments from, uh, breed books, uh, Wales, we’re still looking for Southern investments, uh, someone interested, uh, with a more detail conversation around that.

Philip English: 
That’s fine. Thanks very much. Well, um, yeah, I think that’s it for my questions. I mean, I suppose the next, um, so sort of steps is, so if we wanted to purchase a unit, I fix a start up, but, uh, can we, can we purchase a unit now or are we still a bit too early?

Dr. Chang Liu: 
Uh, well, yeah, so, uh, our strategy is that, uh, were walking honestly, antiquated solution was hardware software. Uh, our, our goal is to provide, uh, fully integrated solution, um, uh, by the, by the beginning of, uh, 2022, yeah. Uh, we are currently, uh, just, just all just started to offer the software alone solutions. So we’re demonstrating the way we help, how people could, uh, in to phase out softball with a third party, lower arm. Uh, so someone we want any have a, um, and also one arm, uh, they got come to us and a wait time we can discuss the way we could just say is out so far, which would have robot arm, uh, the way our software architecture is it’s a loss interface, robotic operating system. So anyone arm that support robotic operating system kind of actually, uh, integrate with our AMS software very easily. Um, yeah, so we also have not now, and, uh, we’re actually really looking forward to, um, everyone who has an interest on though we can, uh, we can walk out with solutions together, or we can to stop, uh, have a trial of our current system.

Philip English: 
Right. And then, and then the, the, the, the actual hardware, is that a 3d , a 3d printed piece, or is that something that you’re going to get mass manufactured?

Dr. Chang Liu: 
Yeah, colored form five is 3d printed, uh, robot arms. Uh, we have a lot of experience all in the, how to we, uh, make sure to business 3d prints, uh, Makes salary requirements. Um, we are, we optimizing particular small elements of, um, the, the system to make sure the core, the core functionality, um, is not compromised. So it will be optimized as 3d printing, uh, solutions, arms. Um, yeah.

Philip English: 
Okay, perfect. Perfect. Okay. Yeah, no, I think that’s been a great, like overview Chang, so like many thanks fit fee for your time. I mean, if people want to get in contact with you, like what’s the best way,

Dr. Chang Liu: 
Uh, based onto our website for, uh, and www dot extend robotics dot com, um, uh, maybe a little, a little messages, or you can just simply, you know, me, uh, chang.liu@extendrobotics.com. Yeah.

Philip English: 
Right. Perfect. Thanks Chang. And what we’ll do is we’ll put all the links, uh, in the, in, in, in the bottom of the interview as well, so. Perfect. Cool. Well, thanks Chang. Thanks for your time today. It’s very much appreciate it. Thank you, sir.

Dr. Chang Liu: 
Okay, cool. Awesome. Take care. Bye-bye.

Robot Optimised Podcast #2 – Dr. Chang Liu of Extend Robotics

Extend robotics: https://www.extendrobotics.com/

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=de2B3nS5VBg&ab_channel=PhilipEnglish

Fizyr Interview, with Herbert ten Have

Fizyr Interview, with Herbert ten Have

Hi guys Philip English this from philipenglish.com. Welcome to the Robot Optimized Podcast where we talk about everything robotics related. For our first episode, we have Fizyr led by Herbert Ten Have who will talk about their leading technology on picking up objects.

Philip English: 
Hi guys, my name Philip English, and, uh, I’m a Ross’s enthusiasts report on the latest business and applications of robotics and automation. Uh, my mission is to get you robot optimized, uh, to support industry infrastructure and innovation for the next era. Uh, today, uh, we have Herbert, uh, Ten Have from Fizyr. Who’s going to give us an overview of fizyr, and then we’re going to fire a few questions at him and just to see how the business runs and what solutions that he has. And so hi there Herbert

Herbert ten Have: 
Afternoon,

Herbert ten Have: 

Philip English: 
Afternoon. And so I suppose to start with, could you give us like an overview, um, of, of yourself and your company?

Herbert ten Have: 
Sure. I’m 57, still alive. You can breathe and you can do all kinds of active stuff. Um, I run a company called Pfizer, which is a spinoff of the university by a professor. He had an academic view of the world and having robots do all kinds of jobs and they put a brilliant team together. And so now we also have a business plan and we are in quite good operation. A few years ago. We won the Amazon picking challenge, post stowing and picking. And that’s the moment we stopped doing robotics. No more robots.

Herbert ten Have: 
Okay. Okay. So you’ve moved from the hardware to the software side.

Herbert ten Have: 
The brain, Actually what we do is like self-driving cars. We translate the image, what the camera sees into, where the robot should move. And that’s why also our name, new name fizyr means scope. We look, so we look through where it should be grasp as well as we’re looking at future new applications and new technology.

Philip English: Wow. Okay. And fizyr means scope

Herbert ten Have: 
Dutch in Dutch and German and Danish. It’s telescope,

Philip English: 
It’s sort of the same. And then I know, we’ll see, I saw the bit about, um, you won the Amazon awards and that, that was because of your deep learning capability of the software.

Herbert ten Have: 
Correct. Wow. So,

Philip English: 
Um, how big is your team then? Um, from like a size wise,

Herbert ten Have: 
24 currently.

Philip English: 
I see. And then we’ll see. So you’ve come from a university background. Um, so I guess, you know, you’ve got, um, uh, quite like an academic, uh, source of inspiration there, which is something that’s really interesting. I mean, so what, what’s the main problem that fizyr is solving.

Herbert ten Have: 
Okay, good question. So let’s take a partial fulfillment, like example, every time you drop it, it will, the robot will see a different envelope. It will always be different or they’ll take their style. They will always be different. So there is no way you can program it to program a robot. How will, how will it look like? Because it will always be different. So the only way to sort of recognize it and classify it is to generalize to teach it to generalize. Like we, humans can, I could get a one year old, can see that this is a box and can grasp it. And so what we’ve done, we trained the neural network with a lot of images, so a supervised learning. So we teach them, this is an envelope, this is a box, et cetera, and millions of images. And at some point it became good at doing the same thing as humans, understanding that this is a box, a bottle or two per cylinder, et cetera. And to pick it from a bulk of unknown partials.

Philip English: 
Right. I see. So obviously the main problem is that there’s from a normal vision system, it’s hard for it to distinguish the way one item ends and another one starts. So, so within, within your software, it’s obviously got a lot of deep, deep learning tools that actually does that distinction. Um, and I suppose the main problem for the customers is that if they can’t find where the product is, they can’t get a robot to pick it up and then they can’t move into an automation type of process to speed up the process plan. Correct. Okay. That makes sense. And then, so in regards to the actual camera system, then, I mean, is it, is it one type of camera or is it, is there any camera that you can use and you put for your software on top or

Herbert ten Have: 
Yeah, now we are hardware agnostic or both on the sensor of the camera side, as well as on the robot and the end effector the gripper. But having said that we mostly use RGB depth data. RGB is being what we see right now and the depth images is to do triangulation. So we need to know what’s the distance. So for that, you need a depth camera, which is a stereo camera, uh, with, uh, in the middle is structured light, like a flashlight with different ways of structuring it. And based on that, uh, that camera will create a point cloud from which you can derive the distance and to see how it’s positioned. So for instance, take this box, uh, this time you would hear instruction to simulate it, to factor them, uh, in this case you have two sites, but we will see maximum, see three sites of each parcel. So we will find those places where to grasp with the robot to simulate the, uh, the item.

Philip English: 
Right. I see. I see. So that’s the mechanics of how it works and, um, I suppose, would it, um, could you, if you had two cameras or three cameras or four cameras with, does that add on and make it more and more, um, of a product that the products you can see or was it just one camera and that’s all you need

Herbert ten Have: 
As always, it depends. The key thing is the camera should see it. If the camera cannot see it, then, uh, the algorithm, the neural network cannot it. So the good exercise is normally when we want to pick something, we look into the bin and we can find what we want, but we are flexible with our eyes and we can move that. So assume you have the camera above, then you just look at the screen, can you see it in the screen? And then we can train a neural network to pick it as well. So we’ve had many applications that the neural network was much better than human beings. So for us, it was too hard, but the neural network was more faster, accurate, and more robust.

Philip English: 
And would it make sense? I mean, it’s just an example there, we’ll see if a camera is that I only got one position and w w would it help to have maybe a system where the camera was almost moving to some degree to help like pick, pick it up?

Herbert ten Have: 
Not necessarily in most cases we, um, we picked, let’s say from a pellet or from a bin or from a conveyor, and as long as it’s feasible for that camera, and then the robot can move there as well, because what you can see in the camera, then the mobile can move at the same direction as well, because it’s free. There is no, there is no other objects in between.

Philip English: 
Perfect. And then, so to give us some examples, I mean, like where have you installed this type of technology?

Herbert ten Have: 
Okay. One of the nice thing, and we’ll show you in a, in an image is picking the corners of towels and that’s really hard. So towels are in bulk white and white, for instance, and you have soft corners like when it’s, uh, it’s it’s bended, but you also have the heart corner of, of, of a, of a towel. And what the algorithm does is finds the corners of towel and then big, and then feeds it into a folding machine. And then the towel is folded. So that’s something that has been operation for a few years. So we started doing that, and now we are mostly in logistics, in e-commerce it’s item picking. So picking unknown items, which you order online, as well as when the item is being packaged into a bag or a box, we have to pick the partials also from bulk for, let’s say, DHL ups, federal express, et cetera. And, um, we do also track on loading and the pelletizing, which is mostly also boxes, let’s say,

Philip English: 
Well, and for the truck on, on loading then. So the idea is obviously the back of the trunk pulls out. Um, then I suppose a bit of a challenge, a question like where, like, where would you put the camera? Does the camera sort of drop, drop down to the back of the truck? So it sees in and then pop pops up again.

Herbert ten Have: 
Uh, first of all, we don’t build a machine. We only are the brains that translate the image into, with what they do is they have a camera on the device that goes into the truck. So there is a robot picking each of the items and putting it on a retractable conveyor. So the items, the boxes or bags are simulated from bulk, from unknown. And I will show you the image as well, and then put on a conveyor and then it’s being handled the, in the warehouse. Right.

Philip English: 
That makes sense. Yeah. Cause I understand in big light logistic houses, you would have a device that goes into the actual lorry with a conveyor belt on, and then obviously the items can be paid. I mean, in, in regards to, to the, um, to the towel folding, I was always, I was having to look at that FoldiMate robot. I’m not sure if you’ve seen that. It’s like a house appliance. I think it’s on Kickstarter at the moment.

Herbert ten Have: 
Yeah. In our case, it’s really, it’s a really professional a robot. Uh it’s uh, so it’s, uh, it’s been there for, uh, for a while. It’s really for the professional, uh, laundry industry. So in hotels and conference centers and a lot of laundry when they, where they have three shifts per day dealing with laundry.

Philip English: 
Yeah. I’ve been into some of those sites moment myself, and it’s a 24 hour operations as washing and washing and washing. So yeah.

Herbert ten Have: 
Humid and warm show. It’s something you, at some point we realized we should not do this as humans. Yes. Yes. So we should just sleep at night and then have robots doing the work for us.

Philip English: 
Yeah. No, definitely. Definitely. Yeah. There’s definitely a way, I mean, um, in, in regards to their robustness, cause I’ll say, I was saying that’s one of your key features, I suppose the first question is, can you use it outside that I know you wouldn’t normally have a robot set up outside, but is it, can you have cold and snow and wet or is it

Herbert ten Have: 
Yeah. For the software? Doesn’t matter. Of course. So it’s yeah, of course. It’s all about, do you have a camera that’s IP waterproof and all this stuff. And uh, so, uh, most, I would say 95% of our applications are, are indoor, but some of them are like for truck and loading, it could be outdoors as well,

Philip English: 
And then I saw her, I was, I was reading up. So yeah, the, the, the scanning can, can scan up. Um, is it like a hundred items a

Herbert ten Have: 
Second?

Philip English: 
Yeah. Yeah. So, so if the robot was fast enough and then you could really yeah,

Herbert ten Have: 
Yeah. There is no robot on earth that fast. So the neural network is extremely faster. So we use a GPU like in a Nvidia card where we play with, uh, so we use that, uh, to, to do that process. So it’s extremely fast in providing all information, including the, the, the cross poses of the, of the parcels. Yeah.

Philip English: 
Yeah. Cause I was, I was reading that. I was saying, yeah, that’s really fast. I was thinking, Oh yeah, you would need a, you need a lot of robots all attacking. Um, so I suppose then, as you’re saying, like, you know, the bigger picture then is really for those sort of dull, dirty and dangerous jobs, you know, that, that you, you, you, we have robots with the fizyr system that can also pick the items and do the job for us. I mean, what, what, what’s your sort of, um, uh, like future plan? I mean, I did see from, from your website, obviously you, you guys have very successfully like bootstrapped up to 2020, and I think you recently got some investment. So is your seed expansion is it’s on your mind? So

Herbert ten Have: 
Yeah, we’re quite unique I think in Europe. Uh, so we’re bootstrapping is more common, uh, then later to get some investment. So we refill it, dated our product with our, our clients. So we have clients like Toyota for, for four years already. So it’s really, we go into a long-term relationship and we build things going production, and then we built the next one. So it’s, the Americans would go faster and et cetera, but we would like to get everything in order and then go to the next one. So that’s how we build up. So now we have the product ready and we can scale easily easier. We are in logistics, which is like I said, if fulfillment and partial handling and we do something in airports as well, but it hasn’t been disclosed it’s so it’s always logistics and nine out of 10 cases, either a box or a bag.

Philip English: 
Yeah. Yeah, that’s right. I’ve, I’ve, uh, I’ve been in a lot of airports as well, and I’ve seen, uh, I’ve seen them to deploy some robotic systems in there. So I suppose, yeah, that’d be a perfect target for a, for, for you really? Because, um, just, just making sure, you know, different sizes of luggage and bags made sure, because that’s key. If you, if you go on a holiday, you want to make sure that your luggage is there.

Herbert ten Have: 
Yeah, yeah, yeah. But like I said, we only deal with the computer vision part. So there are two more elements to it. Secondly, do you have an anti factor, a gripper that can cope with the variation? So if I have to pick up a pen with suction, I need a very small suction cup to pick up this one where when I have a bigger box, let’s say is, would be heavy, then I need multiple suction to CrossFit. So it’s the, do you have a gripper and anti factor that can cope with the variation? That’s going to be expected. That’s a second challenge. And cert one is all about the integration. So how fast can you accelerate or decelerate without throwing it away? How well do you know it’s it’s attached? Is it safe for the environment for people? Do you have a cobalt or an industrial robot? So integration with the warehouse system. So there are a lot of things around it. So there are three phases and we take all the first phase. Can you see it? Do you have perception? Can, do you know where to where to cross?

Philip English: 
I see. Yeah. No, that makes sense. I mean, I did see your gripper as well. And um, I think if you made that, um, like open source, so anyone can sort of build their own, is that, is that the idea or, you know, a usual technology?

Herbert ten Have: 
Yeah, we do a lot of open source. So if you go and get up and Pfizer, they will see a lot of return on net and all the stuff that we’ve made open source. So we have a lot of followers. We’re very proud of that. And it also brings in new developers. So we get a lot of developers through the open source community because they know us. Um, so the gripper is something we give away the science as well, because we only do software. We don’t do hardware. We don’t want to do, we just want to stay digital. And so it’s, it’s a really nice market. It’s so big. And there’s so many challenges still to go. It’s not as easy as it looks because in warehousing, if you go to a shorting center, it’s looks, it looked like a warzone. So you’ll see everything, car tires, all kinds of stuff is being shipped. So it’s not easy and they’re working hard. And um, so it’s, it’s a, yeah, there is a lot to be done still.

Philip English: 
Yes. Yeah. No, that that’s really true. I mean, I I’ve, I’ve been into a lot of those sites as well, and yeah, I can definitely see that there’s, um, that you, you need a good vision system to make sure that you pick up the right light items. I mean, just going back to the gripper though, I mean, it’s, um, it’s obviously that’s open source. So then I was going to ask a payload question, but I don’t, I suppose it depends on how you build the grip or how they would build the gripper. Like usual

Herbert ten Have: 
Fill up the payload is very simple. You have a vacuum, then you have a surface. So just, you can just calculate what is the maximum force you can apply. So in order to lift something with a certain amount of vacuum and surface, so you can calculate, and if it’s well touched, then you can do CrossFit. But let’s say if it’s something like this, like a towel It will go through, right, you need to take that into account and then you need to apply more flux. So like a vacuum cleaner, you can still pick it up as long as it’s not, it’s not going to be sucked in. So you need, you need the, you need the filter, but so are our neural network knows what it is, can classify it and knows. In some cases you have to apply more, more air, more flux in order to cross this. And, uh, so you can also measure how much air goes through how well it’s attached, uh, in order to know how fast you can move without throwing it away.

Philip English: 
Right. And, and I’ve seen recently there’s a lot, a lot more of those soft type of rope or all of robotics that have all sorts of arms and flux that, that, that make it even more, um, like useful for those types of operations. So yeah,

Herbert ten Have: 
The key thing is, is the combination between what the robot sees the information, the eye, hand coordination. So the more like we’re humans, we have flexible hands. We can do a lot. So the same applies for a robot. You can have a smart gripper with multiple suction cups so we can apply based on if it’s this one, we only do you see suction cup so we can apply different suction cups, different sizes and shapes, uh, based on the material we go to grasp. And so then what we also do is stacking. It’s like playing Tetris. Okay. So we picked something of unknown. And when we look, what are the dimensions, and we look into the place where we want to play a place like a pallet or a bag, like grocery should do micro fulfillment. And then we placed the, the item in the, in the unknown environment.

Philip English: 
Right. So you’ve got the ability to do that as well. So I was speaking to a friend about you guys, so he he’s got a project, uh, to do with waste recycling. So as you can imagine, massive plant, lots of all sites of rubbish. So we’ll kind of get coming along a conveyor belt. And, uh, I know he’s looking into, um, uh, you know, a technique to do it. And I think they’re actually saying, Oh, look, we only needed to, we only need it to work 30% of the time, and then we can work on it. And then if you guys had a chance to have a play with that industry. Yeah. Or

Herbert ten Have: 
Yes, we did screen off years ago. And then we decided we want to focus on logistics because it’s logistics like a blue ocean. It’s so big. And we, we, uh, we claim, we did still think we are the best in the world, although we are small and, uh, we want to stay the best. So you need to focus, focus, focus, focus, and just stick with that one and just be in, stay the best because you can do a lot of things, stuff. And it’s really interesting. It’s nice to do, but at the end you need to, to stay the best and just to focus,

Philip English: 
Focus on the main area. Yeah, yeah. Um, okay. No, that’s great. So, I mean, so what’s, what’s the latest news, like, what’s the next thing for, for you guys, um, are looking into it.

Herbert ten Have: 
Um, it’s, it’s helping our integrators are robotic integrators worldwide. Uh, so our, now our software fresh in production in, uh, in the U S North America in Europe, of course, and in Asia, China, and soon Japan. Uh, but what we see a lot is in the fulfillment that they will have micro fulfillment centers. So one of our clients is for instance, fabric, they have micro fulfillment center to, uh, to bring the groceries, really, to work towards the homes and they are in cities. So that’s really a robot robotized, like lights, they call it lights out factory where everything is done with robots. And I would say, we’re still ahead of that. We’ll still take maybe one or two years, but that definitely what the industry is going for to have lights out factories where just truck comes in, it’s loaded, then the robots take over the rest,

Philip English: 
Right. And then, and then your software light, either lights on or lights off can still do the same job.

Herbert ten Have: 
We need some lights, but, uh, the lights off means, let’s say no people or just remote. But again, we only do a small part. We only do. We like self-driving cars where to drive. We are for the robots where to pick that’s the key thing we do.

Philip English: 
Yeah. And, and I suppose it, you expect on a lights outfit, factory, you know, on certain items that need light, then it would flash on a light. So, so, so, so it can do its job, uh, like most efficiently. So

Herbert ten Have: 
Yeah, in our case, we always need light. We need RGB. And so we need light to see, but, uh, lights out as a term means that they can have a factory without humans around. And so they call it lights, lights out, factory mat. So, but in shorting center, everybody buys a lot online and the number of parcels only, uh, increases every year. So that’s a big challenge in the industry to be automated because there’s a shortage of humans doing this work. And we don’t like to do it in the middle of the night or weekends working on the, on the de palletizing or picking parcels. So we should have robots doing that.

Philip English: 
Yes, no, I totally agree. I totally agree. Have you, uh, have you had any, any work in, in hospitals or sort of amendment meant medical care? That seems to be a lot of speak about that robots coming into the hospital world. I mean, I suppose you’re using your software to, um, organize certain items around the hospital. Have even if you guys said that any, any traction with that or,

Herbert ten Have: 
Uh, focus, focus, focus, logistics, logistics. The only thing that we still do is picking towels and then sometime that’s in a, in a, in a hospital as well, but we really want to do focus and we do pick a medicine by the way, see fulfillment, shop picking small boxes of, uh, of medicine and the blisters and stuff. It’s part of it.

Philip English: 
Right. Fantastic. Okay. No, that’s great. But I think we’ve got a great overview of fizyr. I mean, um, what’s the best way to get hold of you then?

Herbert ten Have: 
Well, you can follow us on LinkedIn. We post frequently, let’s say a few times a week, uh, of course followers open source if you’re into developments, um, yeah, I’m online. So you can reach me if I can help you more than welcome to help.

Philip English: 
Sure. appreciate that, and I suppose that could be a mixture of, uh, of end users integrators, um, and, and anyone who needs that, uh, the, the, the vision to basically move lot items around them. So there’s a big industry there.

Herbert ten Have: 
Sure. But I, I meant also, uh, personally, if a student has an, a question or whatever, working in the, we have, we have 11 nationalities. We have a lot of people from abroad. We have consent to hire people from both. So, so we’re always open for new, uh, brilliant talent talent joining us.

Philip English: 
Thank you. Thank you here, but no, that’s great. Like many thanks fit fit for your time today. It’s very much appreciated. Thank you.

Herbert ten Have: 
My pleasure. Take care.

Robot Optimised Podcast #1 – Herbert Ten Have of Fizyr

Fizyr: https://fizyr.com/ 

Philip English: https://philipenglish.com/

Sponsor: Robot Center : http://www.robotcenter.co.uk

Youtube:- https://www.youtube.com/watch?v=QxPZKVDz65c