In this episode, we discuss research coming out of George Mason University where the RobotiXX lab has been training robots to drive more like humans

Podcast: Robot That Drives Better Than The Average American

This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/2b4595aa-c087-4a18-9ed9-6c05655462a7?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>Picture this: You’re out for a drive and in a hurry to reach your destination.At first, the road is clear and dry. You’ve got great traction and things are going smoothly.&nbsp;But then the road turns to gravel, with twists and turns along the way. You know your vehicle well, and have navigated such terrain before.And so, instinctually, you slow the vehicle to navigate the more challenging conditions. By doing so, you avoid slipping on the gravel. Your experience with driving, and in detecting the conditions, has saved you from a potential mishap. Yes, you slowed down a bit. But you’ll speed up again when the conditions improve. The same scenario could apply to driving on grass, ice – or even just a hairpin corner on a dry paved road.For human beings, especially those with years of driving experience, such adjustments are second-nature. We have learned from experience, and we know the limitations of our vehicles. We see and instantly recognize potentially hazardous conditions – and we react.But what about if you’re a robot? Particularly, a robot that wants to reach a destination at the maximum safe speed?That’s the crux of fascinating research taking place at <a href="https://www.gmu.edu/" target="_blank">George Mason University</a>: Building robots that are taught – and can subsequently teach themselves – how to adapt to changing terrain to ensure stable travel at the maximum safe speed.It’s very cool research, with really positive implications.Below: You don’t want this happening on a critical mission…<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEyNTk4MjUwMzM0LVBpY3R1cmUyLnBuZy53ZWJwIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 328px;" class="fr-fic fr-dib" alt="research platforms"> <h3 id="isPasted">“XX”</h3>Those are the initials of Dr. Xuesu Xiao, an Assistant Professor at George Mason University. He holds a PhD in Computer Science, and runs a lab that plays off his initials, called the <a href="https://cs.gmu.edu/~xiao/RobotiXX/lab.html" target="_blank">RobotiXX Lab</a>. Here’s a snippet of the description from his website:“At RobotiXX lab, researchers (XX-Men) and robots (XX-Bots) perform robotics research at the intersection of motion planning and machine learning with a specific focus on robustly deployable field robotics. Our research goal is to develop highly capable and intelligent mobile robots that are robustly deployable in the real world with minimal human supervision.”We spoke with Dr. Xiao about this work.It turns out he’s particularly interested in making robots that are particularly useful to First Responders, and carrying out those dull, dirty and dangerous tasks. Speed in such situations can be critical, but comes with its own set of challenges. A robot that makes too sharp a turn at speed on a high friction surface can easily roll over – effectively becoming useless in its task. Plus, there are the difficulties previously flagged with other terrains.This area of “motion planning” fascinates Dr. Xiao. Specifically, how to take robots beyond traditional motion planning and enable them to identify and adapt to changing conditions. And that involves machine vision and machine learning.“Most motion planners used in existing robots are classical methods,” he says. “What we want to do is embed machine learning techniques to make those classical motion planners more intelligent. That means I want the robots to not only plan their own motion, but also learn from their own past experiences.”In other words, he and his students have been focussing on pushing robots to develop capabilities that surpass the instructions and algorithms a roboticist might traditionally program.“So they’re not just executing what has been programmed by their designers, right? I want them to &nbsp;improve on their own, utilising all the different sources of information they can get while working in the field.”&nbsp;<h3>The Platform</h3>The RobotiXX Lab has chosen the <a href="https://indrorobotics.ca/hunter-se/" target="_blank">Hunter SE</a> as its core platform for this work. That platform was supplied by InDro Robotics, and modified with the <a href="https://indrorobotics.ca/commander/" target="_blank" rel="noopener noreferrer"></a><a href="https://indrorobotics.ca/commander/" target="_blank" rel="noopener noreferrer">InDro Commander module</a>. That module enables communication over 5G (and 4G) networks, enabling high speed data throughput. It comes complete with multiple USB slots and the Robot Operating System (ROS) library onboard, enabling the easy addition (or removal) of multiple sensors and other modifications. It also has a remote dashboard for controlling missions, plotting waypoints, etc.Dr. Xiao was interested in this platform for a specific reason.“The main reason is because it’s high speed, with a top speed of 4.8m per second. For a one-fifth/one-sixth scale vehicle that is a very, very high speed. And we want to study what will happen when you are executing a turn, for example, while driving very quickly.”As noted previously, people with driving experience instinctively get it. They know how to react.“Humans have a pretty good grasp on what terrain means,” he says. “Rocky terrain means things will get bumpy, grass can impede a motion, and if you’re driving on a high-friction surface you can’t turn sharply at speed. We understand these phenomenon. The problem is, robots don’t.”So how can we teach robots to be more human in their ability to navigate and adjust to such terrains – and to learn from their mistakes?As you’ll see in the diagram below, it gets *very* technical. But we’ll do our best to explain.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEyNTk4NDM4NTk4LUdlb3JnZS1NYXNvbi1qcGcud2VicCIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 100%px;" class="fr-fic fr-dib"><h3 id="isPasted">The Approach</h3>The basics here are pretty clear, says Dr. Xiao.“We want to teach the robots to know the consequences of taking some aggressive maneuvers at different speeds on different terrains.&nbsp;If you drive very quickly while the friction between your tires and the ground is high, taking a very sharp turn will actually cause the vehicle to roll over – and there’s no way the robot by itself will be able to recover from it, right?&nbsp;So the whole idea of the paper is trying to enable robots to understand all these consequences; to make them ‘competence aware.'”<a href="https://cs.gmu.edu/~xiao/papers/cahsor.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">The paper</a> Dr. Xiao is referring to has been submitted for scientific publication. It’s pretty meaty, and is intended for engineers/roboticists. It’s authored by Dr. Xiao and researchers Anuj Pokhrel, Mohammad Nazeri, and Aniket Datar. It’s entitled: CAHSOR: Competence-Aware High-Speed Off-Road Ground Navigation in SE(3).That SE(3) term is used to describe&nbsp;how objects can move and rotate in 3D space. Technically, it stands for Special Euclidean group in three dimensions. It refers to keeping track of an object in 3D space – including position and orientation.We’ll get to more of the paper in a minute, but we asked Dr. Xiao to give us some help understanding what the team did to achieve these results. Was it just coding? Or were there some hardware adjustments as well?Turns out, there were both. Yes, there was plenty of complex coding. There was also the addition of an RTK GPS unit so that the robot’s position in space could be measured as accurately as possible. Because the team soon discovered that intense vibration over rough surfaces could loosen components, threadlock was used to keep things tightly in place.But, as you might have guessed, machine vision and machine learning are a big part of this whole process. The robot needs to identify the terrain in order to know how to react.We asked Dr. Xiao if an external data library was used and imported for the project. The answer? “No.”“There’s no dataset out there that includes&nbsp;all these different basic catastrophic consequences when you’re doing aggressive maneuvers.&nbsp;So all the data we used to train the robot and to train our machine learning algorithms were all collected by ourselves.”&nbsp;<h3>Slips, Slides and Rollovers</h3>As part of the training process, the Hunter SE was driven over all manner of demanding terrain.“We actually bumped it through very large rocks many times and also slid it all over the place,” he says. “We actually rolled the vehicle over entirely many times. This was all very important for us to collect some data so that it learns to not do that in the future, right?”And while the cameras and machine vision were instrumental in determining what terrain was coming up, the role of the robot’s Inertial Measurement Unit was also key.“It’s actually multi-modal perception, and vision is just part of it. So we are looking at the terrain using camera images and we are also using our IMU. Those inertial measurement unit readings sense the acceleration and the angular velocities of the robot so that it can better respond,” he says.“Because ultimately it’s not only about the visual appearance of the terrain, it is also about how you drive on it, how you feel it.”&nbsp;<h3>The Results</h3>Well, they’re impressive.The full details are outlined in <a href="https://cs.gmu.edu/~xiao/papers/cahsor.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">this paper</a>, but here’s the headline: Regardless of whether the robot was operating autonomously heading to defined waypoints, or whether a human was controlling it, there was a significant reduction in incidents (slips, slides, rollovers etc.) with only a small reduction in overall speed.Specifically, “CAHSOR (Competence-Aware High-Speed Off-Road Ground Navigation)&nbsp;can efficiently reduce vehicle instability by 62% while only compromising 8.6% average speed with the help of TRON (visual and inertial Terrain Representation for Off-road Navigation).”That’s a tremendous reduction in instability – meaning the likelihood that these robots will reach their destination without incident is greatly improved. Think of the implications for a First Responder application, where without this system a critical vehicle rushing to a scene carrying medical supplies – or even simply for situational awareness – might roll over and be rendered useless. The slight reduction in speed is a small price to pay for greatly enhancing the odds of an incident-free mission.“Without using our method, a robot will just blindly go very aggressively over every single terrain – while risking rolling over, bumps and vibrations on rocks, maybe even sliding and rolling off a cliff.”What’s more, these robots continue to learn with each and every mission. They can also share data with each other, so that the experience of one machine can be shared with many. Dr. Xiao also says the learnings from this project, which began in January of 2023, can also be applied to marine and even aerial robots.For the moment, though, the emphasis has been fully on the ground. And there can be no question this research has profound and positive implications for First Responders (and others) using robots in mission-critical situations.Below: The Hunter SE gets put through its paces. (All images courtesy of Dr. Xiao.)<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEyNTk4NTAwNzQ4LWh1bnRlcjItanBnLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib"><h3 id="isPasted">InDro's Take</h3>We’re tremendously impressed with the work being carried out by Dr. Xiao and his team at George Mason University. We’re also honoured to have played a small role in supplying the Hunter SE, InDro Commander, as well as occasional support as the project progressed.“The use of robotics by First Responders is growing rapidly,” says InDro Robotics CEO Philip Reece. “Improving their ability to reach destinations safely on mission-critical deployments is extremely important work – and the data results are truly impressive.“We are hopeful the work of Dr. Xiao and his team are adopted in future beyond research and into real-world applications. There’s clearly a need for this solution.”If your institution or R&amp;D facility is interested in learning more about InDro’s stable of robots (and there are many), please reach out to us <a href="https://indrorobotics.ca/connectwithanexpert/" target="_blank">here</a>.

Empowering Robots with Adaptive Terrain Navigation

George Mason University Researchers Enable Robots to Intelligently Navigate Challenging Terrain

It’s been some time since we’ve had an update on&nbsp;<a href="https://www.realliferobotics.com/" target="_blank">Real Life Robotics</a>, an Ontario-based firm gaining traction with its BUBS last-mile delivery platform.A lot has happened over the past year, with all of it appearing to point toward a solid trajectory.“We started off 2024 with a bang – with a really exciting story that has to potential to significantly change the current trajectory of Canadian small and medium businesses from coast to coast,” says CEO and Founder Cameron Waite.The story? Real Life Robotics (RLR) was one of eight Canadian startups selected by the&nbsp;<a href="https://www.cfin-rcia.ca/media/news-releases/foodtechnext-jan" target="_blank">Canadian Food Innovation Network</a> to receive funding through its&nbsp;<a href="https://www.cfin-rcia.ca/funding/foodtech-next" target="_blank">FoodTech Next</a> program. FoodTech Next offers funding for early-stage Canadian technology firms who seek to be part of – or sell to – the wider food industry. Through this program, RLR will receive nearly $250,000 to test its solution in real-world environments and validate the return on investment for the food sector.&nbsp;In the current economic landscape, Canadian businesses grapple with increased customer demands for last-mile delivery and reduced profitability. Currently, most rely on third-party companies like Skip The Dishes, DoorDash and Uber Eats, which charge 20-35 per cent commissions on each order.Automation is poised to play a critical role in helping businesses efficiently and sustainably move products from Point A to B (and even C, D, E…).“The overarching goal of FoodTech Next is to accelerate the commercialization of Canadian innovation by generating first demonstration opportunities,” says its website.The announcement made the news, including <a href="https://www.cbc.ca/listen/live-radio/1-92/clip/16042550" target="_blank">this CBC interview</a> with Waite.Below: Founder/CEO Cameron Waite making a pitch for the FoodTech Next program…<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA5OTIzNzIzMDY0LTIwMjQwMjE0LUNGSU4tRm9vZFRlY2gtMjAyNC0xNTAtc2NhbGVkLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib"><h3 id="isPasted">THE PLATFORM</h3>When the RLR team carries out demonstrations across the country, it brings along BUBS – one of several solutions Real Life Robotics has available to customise and deploy. Out of the box, BUBS has a large cargo bay (50 kg) suitable for transporting everything from bottled water to medical supplies to prepared meals.BUBS can be remotely tele-operated over 5G networks with near-zero latency, or carry out deliveries autonomously. It can work indoors or out and has an IP protection that makes it impervious to inclement weather (with the exception of, say, a hurricane or tornado). It has excellent obstacle avoidance and a number of other features intended for safe operation near people. It’s also perceived as “friendly” – which is important as these devices are introduced in public spaces.BUBS can also be customised, pending client needs.“We’re a cargo and last-mile delivery robotics platform,” says Waite. “But clients inevitably and always have some sort of unique requirement to their business in order to fully adopt and scale automation. There’s no reason BUBS can’t be bigger or smaller, or a different shape or colour – or have its cargo bay modified to carry something unique or unusual that requires modification.”And the business model? Well, it’s not just about selling a single robot. It’s about that first robot proving its worth to the client in economic terms.“It’s nice to say: ‘I have a robot,'” says Waite. “But our goal is really to have a robot or automation solution that has a positive business impact so that you want to scale and buy more of them. Otherwise, you buy just one.”&nbsp;<h3>MORE OPTIONS EN ROUTE</h3>It’s not just BUBS. Real Life Robotics, says Waite, has another solution it’s about to unveil: A quadruped delivery robot. Having four legs instead of wheels means deliveries are not limited by stairs or rough terrain. And, in a world where businesses increasingly want their space or inventory scanned, this robot is capable of carrying out those tasks as it goes about its delivery work.While food delivery in public spaces is clearly the focus of Real Life Robotics (and is tied to the federal grant), Waite emphasises that BUBS can be put to use in far wider use-cases.“Right now our focus is the local delivery side of the food industry,” says Waite. “But beyond that, it could also be products – like hats at a hockey game or bottled water&nbsp;at a. convention centre. It all really comes down to increasing the margins for our clients while ensuring a high-quality memorable delivery experience for the customer.”Below: BUBS, making things easier…<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA5OTIzODc2NTk4LUN1c3RvbWVyLWxvYWRzLUJVQlMtanBnLndlYnAgY29weS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib"> <h3 id="isPasted">NEW TEAM AND FUNDING ROUND</h3>Though we’ve been focusing on the robots, you can’t build a business without a team. And there, Waite says Real Life Robotics has been fortunate in attracting some A-level talent who share his vision.The company has acquired <a href="https://uwaterloo.ca/scholar/bjdehart" target="_blank">Brandon J. DeHart</a> as Chief Technical Officer. DeHart is the head of the University of Waterloo’s <a href="https://uwaterloo.ca/robohub/" target="_blank">RoboHub</a>, the epicentre of all things robotic at the university. (Waterloo’s Engineering department, according to the RoboHub website, “has the largest and most active robotics and automation research group in Canada, supporting Canada’s largest robotics and automation cluster.”)So DeHart comes with impeccable credentials, and has the expertise to both modify products and engineer completely new solutions for RLR. He has both a PhD and a Masters degree.“In terms of a robotics pedigree, this guy is top of the tops,” says Waite. “So we’re really, really excited about having him on board as CTO and I’m really excited to see what we can build together.”You can read more about DeHart in this <a href="https://www.realliferobotics.com/news/supercharging-the-real-life-robotics-team" target="_blank">RLR blog post</a>. And you can look at him, in the photo below…<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1709924018119-Brandon-J-DeHart-RLR-jpg.webp" style="width: 100%px;" class="fr-fic fr-dib"><h3 id="isPasted">NEW CFO, HEAD OF GROWTH</h3>Real Life Robotics has also attracted a new Chief Financial Officer, as well as a Head of Growth.The CFO is Ian Watson. Based in the UK, Watson spent 25 years with <a href="https://www.pwc.com/ca/en/" target="_blank">Price Waterhouse Cooper</a> before venturing into the startup space. He has owned and managed several startups, and is a Canadian Chartered Accountant. Watson holds a Master’s degree in Business (McMaster University) and a BA in Economics (Wilfrid Laurier University).“He’s deeply experienced in the financial and accounting worlds, plus he knows startups and how to help businesses grow strategically,” says Waite.Sharif Virani is the new Head of Growth – and appears to be a great fit. Before joining RLR, Virani held a similar position with&nbsp;<a href="https://tinymile.ai/" target="_blank">Tiny Mile</a>, which deploys small pink robots for food delivery. The company is currently operating in Miami – and had previously been running its operation in Toronto. If you ever saw one of those little robots on the news or social media, odds are Virani was behind that.“He’s a serial entrepreneur in the restaurant industry space – so he understands that market really well,” says Waite.And those are just three of the recent additions to the RLR team. A total of 10 people are now part of the company, with several on the sales and operations side. Together, they bring a total of 53 years of direct experience in the robotics industry.&nbsp;<h3>FUNDING ROUND</h3>As Real Life Robotics prepares for its next phase of growth, the company is currently in a Series A raise round.“The traction we’ve received – from the partnerships we’ve been developing, the grants we’ve been winning, and the client revenue we’re now generating – tells a really strong story to the investment community,” says Waite.Below: a 360° video tour of the University of Waterloo’s RoboHub. Be sure to scroll around to see the big picture…<iframe width="640" height="360" src="https://www.youtube.com/embed/O_7KSGdVLoc??si=GRuboC_a2bKF_SND&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&amp;lt;span class="fr-mk" style="display: none;"&amp;gt;&amp;amp;nbsp;&amp;lt;/span&amp;gt;</iframe><h3 id="isPasted">WAIT A MINUTE</h3>Cameron Waite talks a good game. But how do we safely introduce robots onto public roadways? Though Toronto now has a pilot project underway to evaluate such delivery robots, it’s not like they’re going to be embraced tomorrow.So how can Waite be so optimistic, when public acceptance (and even permission from municipalities) is not guaranteed?The answer, he says, has been in ground work and relationship building. RLR is also part of multiple stakeholder organisations that have been actively engaging on precisely this issue. The company is part of the following groups:<ul><li><a href="https://www.urbanroboticsfoundation.org/" target="_blank">Urban Robotics Foundation</a></li><li><a href="https://www.roboticscouncil.ca/" target="_blank">Canadian Robotics Council</a></li><li>Founding member of the&nbsp;<a href="https://uwaterloo.ca/robohub/professional-partnership-program" target="_blank">RoboHub Professional Partnership Program</a></li><li>Founding member the Toronto Autonomous Mobility Working Group</li></ul>That last one? Its members are <a href="https://gatik.ai/" target="_blank">Gatik</a>,&nbsp;<a href="https://www.tesla.com/" target="_blank">Tesla</a>,&nbsp;<a href="https://www.uber.com/ca/en/" target="_blank">Uber</a> and&nbsp;<a href="https://www.realliferobotics.com/" target="_blank">Real Life Robotics</a>.Lobbying groups are one thing. But getting the automated rubber to meet the road is another. Here, Waite reveals that RLR is ahead of the game: It has permission from five municipalities across the country to operate and test its vehicles in public spaces.“That’s really what this government grant is targeted toward: Exploring the validity of robots in public environments,” says Waite.&nbsp;<h3>MAJOR PARTNERSHIPS</h3>Waite also says RLR has some significant partners onboard, including “an incredibly large restaurant space company.”“This partner not only gives us some amazing insight and data that we can utilise to ensure that this technology truly has ROI and business value to that industry. They also give us some scale and scope as we grow.”But why not name names?“The reason is simply that we’re moving a little bit faster than their marketing team can handle.”Waite promises some significant announcements on this front soon, and deployment of RLR robots in the streets in the near future. Again, Waite won’t reveal details but pledges that the use-case is “really cool” and will grab headlines.“By the summer, for sure, Real Life Robotics robots will be in the field – and there will be a huge story around it.”He adds that RLR has Indro Robotics as an engineering partner, and access to&nbsp;<a href="https://indrorobotics.ca/indro-forge-prepped-for-next-phase-expansion/" target="_blank">InDro Forge</a>, a rapid fabrication and prototyping facility based in Ottawa. These two partnerships, he says, speed custom fabrication for clients, in addition to builds of entirely new robots.Below: BUBS on the street…doing good work<iframe width="640" height="360" src="https://www.youtube.com/embed/kCwf5IxBOQE??si=K4hr3BrPVpKTftsV&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&amp;lt;span class="fr-mk" style="display: none;"&amp;gt;&amp;amp;nbsp;&amp;lt;/span&amp;gt;</iframe><h3 id="isPasted">INDRO’S TAKE</h3>We’ve been watching Real Life Robotics with interest over the past year and we’re pleased to see the terrific progress that’s been made.“Robotics and automation can make things much easier for many businesses, but municipal permissions for more than a one-off demo have traditionally been tricky in this space,” says InDro Robotics CEO Philip Reece.“That’s starting to shift, but you can’t have public adoption and acceptance until these devices are actually in the field. And they can’t be put in the field without the vision and cooperation of municipalities. We’re pleased to see that Real Life Robotics has made gains in this area, and congratulate them on winning that important grant. We look forward to seeing RLR robots in the streets – somewhere – this summer.”For more information on RLR, including an investor deck, contact Cameron Waite&nbsp;<a href="Mailto:cameron@realliferobotics.com">here</a>.

New Team, Research Grant and Partners

Real Life Robotics Expands

There’s a new robot in town. Actually, there are two of them.They’re small but mighty. In fact, numerous universities and robotics labs already use their predecessor for high-level research. That original robot, the AgileX LIMO, was a game-changer when it came to an affordable and flexible platform. Boston University currently has a fleet of LIMOs running custom algorithms and simulations related to how real-world autonomous vehicles will interact in the Smart Cities of the future. (It’s really cool research, and you can read all about it <a href="https://indrorobotics.ca/boston-university-uses-agilex-limo-for-research/" target="_blank">here</a>.)That first LIMO was truly a ground-breaker – and remains an excellent R&amp;D research platform. But now, AgileX has taken things further. Two new versions of LIMO offer advanced hardware, software, runtime – and capabilities.Below: The original LIMO that started it all…<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5MzAzMjcwNzgyLUxJTU8gb24gcm9jay5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><h3 id="isPasted">Main Features</h3>Before we get into the significant changes incorporated into the new models, it's worth looking at some of the strong features common to all members of the LIMO family. For starters, each LIMO has four steering modes: Omnidirectional steering, tracked steering, Ackerman and four-wheel differential.All LIMOs are equipped with obstacle detection. Multiple onboard sensors can pick up on the size, distance and location of obstacles, allowing the robot to navigate its environment without conflict. The newer LIMO models have significant enhancements here, which we'll explore in a moment.Despite their relatively small size – so small an untrained eye might potentially mistake them for a toy – the LIMOs feature a robust, all-metal build and powerful motor. They also feature powerful onboard EDGE computing suitable to pretty much any R&amp;D requirements.&nbsp;<h3>Who Uses the LIMO robot?</h3>There are really two main categories of users, with the first being those in the educational field."This is a great tool for anyone looking to learn ROS, because they can do all of the advanced concepts – obstacle detection, SLAM, teleoperation, to name a few," explains Luke Corbeth, Head of InDro's R&amp;D Sales Division."And we make that really simple through our improved documentation. We’ve basically built a course around it, so it can be used for teaching students."The other main group of users, of course, are on the research side of things."It’s almost always used in labs for multi-agent systems or multiple robot projects. Because it’s multi-modal, when you're doing a multi-agent system it can be homogenous or heterogeneous, meaning you use different steering in different robots simultaneously."Dimensions of all versions of LIMO are identical, as seen below.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5MzA0NjE2MTM4LUxJTU8gVGVjaCBTcGVjcyBmb3IgV2V2b2x2ZXIgUG9zdC5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><h3 id="isPasted">Meet the New LIMOs</h3>The original LIMO is still a great robot – and is currently in use by many universities. But AgileX didn't rest on its laurels. In response to the availability of new technologies – along with a wish-list from existing clients – the company has taken things further with its new LIMO PRO and the LIMO ROS2."Obviously as research in autonomy advances, so do the computational requirements," explains Corbeth. "So it’s very important as a robotics manufacturer to stay ahead of the curve so that the hardware meets up with the current research requirements of the day."To that end, the new versions feature upgrades on computational power, sensors and run-time."The big difference is in compute – we're moving from the Jetson Xavier to the Jetson Orin Nano on the LIMO PRO and the INTEL NUC on the LIMO ROS2. Both of these are actually massive upgrades."The Orin Nano is a very powerful EDGE computer. That power translates into more stable multi-sensor data fusion and speed with SLAM (Simultaneous Localization and Mapping) processing.Speaking of SLAM, the LIMO PRO and LIMO ROS2 come with a new LiDAR unit. While the original LIMO used the very capable EAI X2L unit, the new versions come with the EAI T-mini Pro."Plus, the battery in the new unit goes from an hour of run-time to 2-1/2 hours – with a standby of four hours," adds Corbeth.&nbsp;<h3>SOFTWARE</h3>Not surprisingly, the two new versions also feature some software upgrades. The LIMO PRO and ROS2 versions come with Ubuntu 20.04 (the original LIMO runs version 18.04). In terms of ROS (Robot Operating System) libraries, the first generation LIMO is outfitted with ROS1 Melodic. The LIMO PRO features both ROS1 Noetic and ROS2 Foxy. The LIMO ROS2 has ROS2 Humble onboard.Already have some of the first-generation LIMOs in your lab? No problem."The new models can co-exist with the original LIMO," says Corbeth. "And if the computing demands are higher than previous applications, it makes sense of have a blend of models."The graphic below outlines the feature sets of the three models:<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5MzA2MzQ4ODk4LUxJTU8gQ29tcGFyaXNvbiBDaGFydC5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><h3 id="isPasted">INDRO'S TAKE</h3>InDro Robotics has a lot of clients who have put the original LIMO to use in labs and educational institutes across North America. Boston University has a very large fleet of LIMOs deployed – hard at work on multiple research projects related to Smart Cities and autonomous vehicles. They've proven to be a robust, cost-effective tool for high-level research.And now, with the fresh release of LIMO PRO and LIMO ROS2, there are two more affordable options."This is a significant development for anyone looking to expand their current fleet of LIMOS, as well as those who have been waiting in the wings for an upgrade," says Corbeth. "These are incredibly powerful and versatile robots/research tools, with the added bonus that the entire line is very affordable."If you're interested in learning more, InDro Robotics is the exclusive distributor of AgileX in Canada, as well as a distributor for all of North America. We have built excellent documentation and manuals to assist users ranging from beginning to expert – and all of that added value and support comes with every purchase made through InDro.For more information from a robot expert, contact Luke Corbeth <a href="https://indrorobotics.ca/connectwithanexpert/" target="_blank">here.</a>

Bringing Advanced Abilities to Research and Development

LIMO Pro Robot and LIMO ROS2

Exploring Cutting-Edge Research with the LIMO Robot

Boston University Uses LIMO Robot For Research

In this episode, we discuss the fascinating world of bioinspired robotics. Discover how researchers have created versatile robots inspired by nature's flight, rolling, and walking abilities.

Podcast: Mighty Morphing All Terrain Robots Made By Nature

This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1672821999265000&usg=AOvVaw3lLKdHdEN0YvCEsaHI7hx9" href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/b6d8f955-457e-488d-a053-4a6409fafab0?dark=false" class="fr-draggable" data-gtm-yt-inspected-7="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>The new robot, dubbed M4 (for Multi-Modal Mobility Morphobot) can roll on four wheels, turn its wheels into rotors and fly, stand on two wheels like a meerkat to peer over obstacles, &quot;walk&quot; by using its wheels like feet, use two rotors to help it roll up steep slopes on two wheels, tumble, and more.A robot with such a broad set of capabilities would have applications ranging from the transport of injured people to a hospital to the exploration of other planets, says Mory Gharib (PhD &#39;83), the Hans W. Liepmann Professor of Aeronautics and Bioinspired Engineering and director of Caltech&#39;s <a href="http://cast.caltech.edu/" target="_blank">Center for Autonomous Systems and Technologies</a> (CAST), where the robot was developed.<iframe width="640" height="360" src="https://www.youtube.com/embed/J91jTI2-k_U?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true" data-gtm-yt-inspected-7="true" id="966413990" title="M4 Drives and Flies Around Caltech's Campus">&nbsp;</iframe>M4 is the brainchild of Gharib and Alireza Ramezani, assistant professor of electrical and computer engineering at Northeastern University. The team supporting M4&#39;s technical aspects consisted of Eric Sihite, a postdoctoral scholar research associate in aerospace at Caltech; Reza Nemovi, a design engineer at CAST; and Arash Kalantari from JPL, which Caltech manages for NASA. A paper announcing the new robot was published in Nature Communications on June 27.&quot;Our aim was to push the boundaries of robot locomotion by designing a system that showcases extraordinary mobility capabilities with a wide range of distinct locomotion modes. The M4 project successfully achieved these objectives,&quot; says Ramezani, corresponding author of the Nature Communications paper.The robot&#39;s flexibility of motion, coupled with artificial intelligence, allows it to choose what form of locomotion will be most effective based on the terrain ahead of it. Picture the M4 exploring an unfamiliar environment: it might start by rolling along on four wheels, which is its most energy-efficient mode. Upon reaching an obstacle like a boulder, it could stand on two wheels to peer over it for a clearer picture of the ground ahead. Then, if it saw a ravine or another feature that a wheeled robot could not traverse, it could reconfigure its wheels into rotors, fly over the ravine to the other side, and resume rolling along.&quot;When encountering unknown environments, only robots that have the ability to repurpose their multi-modal components aided by artificial intelligence can succeed,&quot; says Gharib, co-author of the Nature Communications paper.One of the key features of M4 is its ability to repurpose its appendages to wheels, legs, or thrusters. When M4 needs to stand up on two wheels, two of its four wheels fold up and their inset propellors spin upwards, providing balance for the robot. When M4 needs to fly, all four wheels fold up, and the propellors lift the robot off the ground.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1688030564956-M4-Fly.max-500x500.gif" style="width: 766px;" class="fr-fic fr-dib">The M4 robot takes flight with four rotors located within its tilting wheels. Credit: Caltech&nbsp;Joints on the wheel assemblies allow M4 to execute a walking motion. In M4&#39;s current iteration, the walking motion is mostly proof of concept. However, with anticipated advances, future M4 generations could possess the ability to effectively walk across broken terrain that a wheeled robot would struggle with.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1688030589455-M4-Stand.max-500x500.gif" style="width: 766px;" class="fr-fic fr-dib">The M4 robot transforms from driving mode to walking mode. Credit: Caltech&nbsp;The design of M4 was heavily influenced by nature: Gharib and his colleagues were inspired by how chukar birds (a type of partridge) use the flapping of their wings to give them leverage while running up steep inclines, for example, and how sea lions use their flippers for different types of locomotion on sea and land. Although such examples of appendage repurposing from the animal kingdom have been previously reported by biologists, the concepts they illustrate are just now being explored in the engineering domain.M4 has been equipped with autonomous capabilities and can make decisions for itself about how best to navigate through a complex environment. The robot has also been tested outdoors and has navigated the terrain of Caltech&#39;s campus.The Nature Communications paper is titled &quot;Multi-Modal Mobility Morphobot (M4), A Platform to Inspect Appendage Repurposing for Locomotion Plasticity Enhancement.&quot; This research was funded by JPL and the National Science Foundation.

A newly created real-life Transformer is capable of reconfiguring its body to achieve eight distinct types of motion and can autonomously assess the environment it faces to choose the most effective combination of motions to maneuver.

New Bioinspired Robot Flies, Rolls, Walks, and More

A sun-drenched Mediterranean country, Greece is an ideal site for climate-friendly solar energy generation. Heavy private sector investment in solar power backed by government incentives mean that today, Greece ranks fifth in the world for installed photovoltaic capacity per capita. By 2022, large Greek solar farms provided more than 4GW of generation capacity.&nbsp;But the abundant sunlight that makes solar power so attractive in Greece has an unwanted side-effect for the operators of solar farms: it makes the grass and other vegetation around and under the panels grow fast. Left unchecked, grass growth can shade the panels, and restrict the access of maintenance staff.&nbsp;Traditionally, facilities maintenance contractors would cut the grass three or four times a year. But this is an expensive service that requires careful management: a solar farm contains crucial equipment such as cabling that is easily damaged by a manually operated mower.&nbsp;Automation is a far better approach: cheaper and more reliable, autonomous mowing can be safely performed day and night, so that the robot mower can be kept continually in use.&nbsp;While many products today serve the agricultural robot market, the particular requirements of solar farms call for a special solution. This is what Athens-based technology manufacturer <a href="https://www.iknowhow.com/" rel="noopener noreferrer" target="_blank">iKnowHow</a> developed for <a href="https://www.enelgreenpower.com/" rel="noopener noreferrer" target="_blank">Enel Green Power&reg;</a>, the world&#39;s largest private renewable energy operator with a total capacity of more than 59 GW and a generation mix that includes wind, solar, geothermal, and hydroelectric power, as well as energy storage facilities. Enel Green Power is at the forefront of integrating innovative technologies into renewable energy plantsAnd iKnowHow&rsquo;s robotic mower, called Aristos, relies on an Xsens <a href="https://www.movella.com/products/sensor-modules/xsens-mti-680g-rtk-gnss-ins" rel="noopener noreferrer" target="_blank">MTi-680G RTK GNSS/INS</a> sensor module from Movella to keep it on track, even when the satellite positioning signal is temporarily unavailable.&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg0NzM5MDM5MTkwLWVuZWxncmVlbnBvd2VyLXJlc2l6ZWQuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib">The Aristos robot mower, showing the RTK-capable GNSS antenna at the rear. The Xsens MTi-680G sensor is mounted underneath the upper green panel.&nbsp;Keeping strictly to the pathEnel&rsquo;s requirement for the Aristos autonomous mobile robot included a maximum size and weight: the mower needs to be low enough to cut underneath solar panels as well as between them, and light enough to be transported from one site to another by small van. It also needed to be 100% autonomous, both for mowing and charging its battery.&nbsp; &nbsp;The cutting deck is a standard mower blade configuration. The principal challenge for the robot designers was in localization, navigation and object avoidance. Aristos follows a pre-set route, mapped out by the solar farm operator, to minimize operating time and battery power consumption. The robot&rsquo;s systems have to locate and orientate the mower so that it follows its route accurately, and so avoids contact with the panels or the solar farm&rsquo;s infrastructure.&nbsp;Apart from the mower itself, the iKnowHow system&rsquo;s other main element is a static charging station at each solar farm: this houses a battery charger and an RTK transmitter beacon for the robot&rsquo;s enhanced GNSS satellite positioning system. &nbsp;With a clear GNSS signal and receiving RTK corrections, Aristos can navigate its route to within &plusmn;5cm accuracy. When cutting underneath the panels, however, multipath effects degrade the satellite signal, so it relies on a combination of wheel odometry and magnetic heading signals to maintain accurate positioning until satellite reception is recovered.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg0NzM5MDczODM0LWVuZWxncmVlbnBvd2VyIDMgcmVzaXplZC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib">The Aristos robot mower operates as well under solar panels as between themAll-in-one sensor provides combined positioning signalAt the heart of this autonomous navigation system is the <a href="https://www.movella.com/products/sensor-modules/xsens-mti-680g-rtk-gnss-ins" rel="noopener noreferrer" target="_blank">Xsens MTi-680G</a> all-in-one positioning and motion sensor from Movella. Michalis Logothetis, Lead Robotics Engineer at iKnowHow, says that it chose this sensor because it combined high performance, robust construction and easy integration. The MTi-680G integrated GNSS/IMU solution includes an RTK-capable GNSS receiver alongside its 3D accelerometer, 3D gyroscope and magnetometer, all in one 56.5 &times; 40.9 &times; 36.75mm package.&nbsp;Michalis Logothetis says: &lsquo;The Xsens sensor fusion firmware combines and synchronizes all these signals, producing easy-to-use digital position, attitude and heading outputs that keep Aristos on track under the panels as well as in the open air.&rsquo;&nbsp;Autonomous operation of the mower is not just about maintaining an accurate absolute position at all times. Aristos works in a dynamic environment in which unmapped, random obstacles such as a or equipment left behind by maintenance technicians can obstruct its path. The MTi-680G helps the robot deal with obstacles that could upset its progress. The sensor continually measures pan/tilt as well as heading: Aristos stops automatically when tilt exceeds a safety threshold and reports back via 4G to its control center. An onboard RGB camera enables a remote operator to monitor the scene when an alert is raised.&nbsp;The rugged <a href="https://www.movella.com/products/sensor-modules/xsens-mti-680g-rtk-gnss-ins" rel="noopener noreferrer" target="_blank">MTi-680G</a> is well suited to use in these dynamic outdoor conditions. It is housed in an IP68-rated aluminium enclosure, and handles the shock and vibration inherent in mowing operations on rough ground.&nbsp;Michalis Logothetis comments that the MTi-680G quickly proved its value in a prototype design reviewed enthusiastically by Enel. He says: &lsquo;We are delighted with the operation of the <a href="https://www.movella.com/products/sensor-modules" rel="noopener noreferrer" target="_blank">Xsens MTi sensor</a>. Aristos passed its field trials with flying colors, and after iKnowHow started production in 2023, it is now supplying units to Enel for use on solar farms all around the world.&rsquo;&nbsp;

Centimeter-accurate Xsens MTi-680G pilots autonomous mower around large solar panel installations

When Angela Loh &rsquo;23 was 10 years old, she and her family moved to Shanghai from Michigan. She was immediately struck by how much more pollution she saw in Shanghai.&ldquo;When I stepped outside my home, the skies were grey and I could smell the stench of <a href="https://www.health.ny.gov/environmental/indoors/air/pmq_a.htm" target="_blank">PM2.5 particles</a> hanging in the air. I would walk on certain local streets and see litter everywhere,&rdquo; she says. She noticed that most residents seemed complacent. &ldquo;Nobody seemed to care.&rdquo;But Loh did care, deeply, about environmental sustainability.As a freshman, Loh and Alan Hsiao &rsquo;21 founded <a href="https://cornellnexus.teleporthq.app/" target="_blank">Cornell Nexus</a>, a group of students from diverse colleges and majors who are designing and building an autonomous robot that will remove microplastics from the sand on beaches. The team hopes to have a working land-based prototype built by spring 2023, when they will turn their attention to creating a submersible robot that will remove microplastics from sea water.&ldquo;We are a team of individuals who want to step outside the boundaries of university competitions to make a difference on our planet,&rdquo; Loh says.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1670761221613-1206_micro1_0.jpg" style="width: 766px;" class="fr-fic fr-dib">Angela Loh &rsquo;23 wires a component of the autonomous robot prototype.&nbsp;Microplastics, tiny bits of plastic the size of a sesame seed or smaller, are proliferating and pose a significant risk to ecosystems and to human and animal health. &ldquo;There are 50 trillion pieces of microplastics embedded in our sand, our marine life, our oceans and even in our drinking water,&rdquo; Loh says. A <a href="https://www.nationalgeographic.com/science/article/microplastics-in-virtually-every-crevice-on-earth" target="_blank">recent survey</a> of the sea floor in the Mediterranean west of Italy found 1.9 million microplastics in one square meter. &ldquo;This is just one layer of sand in a single square meter of the Mediterranean,&rdquo; she says. &ldquo;Imagine how much microplastic has accumulated in all of our bodies, our water and our land.&rdquo;Beach cleaning operations focus on removing the waste we can see, such as plastic water bottles and trash, often using gas-powered tractors that bury microplastics beneath the top layer of sand. In contrast, the Cornell Nexus robot will use renewable solar energy to collect and remove microplastic waste. &ldquo;We believe that Nexus&rsquo; focus on autonomy and microplastics will revolutionize the technology for waste removal from beaches and bodies of water,&rdquo; Loh says.<h2>Planting the seed</h2>Loh recalls making hand-drawn posters promoting recycling and distributing them to her neighbors when she was in elementary school. Moving to Shanghai &ndash; a city she loves &ndash; was a wake-up call. &ldquo;I realized what big issues plastics, and pollution and waste in general, are on our planet,&rdquo; she says, &ldquo;and I really wanted to do something about them.&rdquo;In the summer after graduating from high school, Loh read a biography of Elon Musk and the founding of Tesla. &ldquo;Reading this allowed me to realize the boundless possibilities there are in the field of engineering,&rdquo; she says. Loh spent the next few months binge-reading biographies about inventors, entrepreneurs and engineers, from Steve Jobs to Leonardo da Vinci and Nike founder Phil Knight. She realized that engineering would be her springboard for creating change.After perusing the College of Engineering website, Loh switched her major from environmental science to electrical and computer engineering and computer science. &ldquo;Reading about the <a href="https://www.engineering.cornell.edu/students/undergraduate-students/special-programs/project-teams" target="_blank">engineering project teams</a> before I arrived at Cornell planted a seed in my brain that maybe one day it wouldn&rsquo;t be impossible to start my own,&rdquo; Loh says.Alan Hsiao was a junior and one of the first people Loh met as a freshman at Cornell. &ldquo;When we first started Nexus, I didn&rsquo;t know anything &ndash; not even basic knowledge about programming or wiring circuit boards &ndash; let alone building an entire vehicle that was going to traverse beaches and charge itself,&rdquo; Loh says. &ldquo;Alan would spend hours and hours mentoring me and teaching me concepts that I hadn&rsquo;t even heard of. &hellip; Through his kindness, wisdom and compassion, he has definitely left his impact on me, our Nexus team, the Cornell campus and our planet.&rdquo;<h2>Unleashing creativity, with help from alumni</h2>Nexus team members are now building a prototype with a multilayered filtering system to catch a range of different sizes of microplastics. When full, the robot will return to its docking station to offload the collected plastics and recharge.&ldquo;Creating our robot requires knowledge about concepts and implementation mechanisms that are usually taught in graduate-level courses,&rdquo; Loh says. Team members conduct their own in-depth research and seek out faculty who can guide their work. <a href="https://www.engineering.cornell.edu/about/branding-microsite/independent-thinkers/faculty-stories/joe-skovira" target="_blank">Joseph Skovira</a>, Ph.D. &rsquo;90, senior lecturer in the School of Electrical and Computer Engineering and the group&rsquo;s faculty adviser, is helping them refine their product.<a href="https://www.linkedin.com/in/whelangreg/" target="_blank">Greg Whelan &rsquo;83</a> of <a href="http://greywale.com/" target="_blank">Greywale Advisors</a> and part of the <a href="https://www.northeastern.edu/vmn/" target="_blank">McCarthy&rsquo;s Venture Mentoring Network</a> has been helping them navigate business outreach and fundraising.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1670761265270-1206_micro2_0.jpg" style="width: 766px;" class="fr-fic fr-dib">Alan Hsiao &rsquo;21 solders a component of the autonomous robot prototype.&nbsp;To ensure they have funding to purchase specialized hardware and software components, Nexus members have been developing relationships with companies that might sponsor the project once they have a prototype. In spring 2021, Nexus won first prize in the <a href="https://www.engineering.cornell.edu/students/undergraduate-students/entrepreneurial-options-undergrad-students/innovation-competition" target="_blank">Cornell Engineering Innovation Competition</a>. The <a href="https://www.engineering.cornell.edu/news/celebrating-new-product-concepts-and-prototypes-2020-engineering-innovation-competition" target="_blank">Yunni and Maxine Pao Social Innovation Award</a>, funded by Carolyn Wang &rsquo;00 and Jeff Pao &rsquo;00, allowed them to buy better wheels, a more robust material for the robot&rsquo;s frame, filtration nets and more accurate sensors.<h2>Doing the greatest good</h2>Nexus is testing and refining their prototype in the 2022-2023 academic year, using a sand bed to test the robot&rsquo;s moving, digging and filtering mechanisms. Then they will place their robot at several beaches, including some recommended by alumni from the Cornell Peter and Stephanie Nolan School of Hotel Administration.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1670761294974-1206_micro3_0.jpg" style="width: 766px;" class="fr-fic fr-dib">This rendering illustrates what the Cornell Nexus robot will look like when completed.&nbsp;Once the land-based robot is completed, the team hopes to launch their robot into the water, where the vast majority of microplastics are. &ldquo;Our vision is to expand our technology to address the heart of the microplastics problem, which is underwater,&rdquo; Loh says. &ldquo;Very few commercial robots are tackling this issue, on a macro and micro scale.&rdquo;There are multiple design possibilities for a seafaring robot, including a water-based recharging and waste removal station, which could be more efficient than returning the robot to land.The Nexus team plans to make their design freely available to the public. &ldquo;This includes all of our software code, mechanical CAD files, electrical circuit board designs, and so forth,&rdquo; Loh says. &ldquo;Our goal is to make an impact and do our part to save our planet.&rdquo;

Cornell Nexus, a group of students from several colleges and majors, are designing and building an autonomous robot that will remove microplastics from the sand on beaches. Jason Koski/Cornell University

Beach cleaning operations focus on removing the waste we can see, such as plastic water bottles and trash, often using gas-powered tractors that bury microplastics beneath the top layer of sand. In contrast, the Cornell Nexus robot will use renewable solar energy to collect and remove microplastic waste.

Students design robot to collect microplastics from beaches

Yasuhide “Yasu” Yokoi is the cofounder of design and technology firm Final Aim Inc., which works with laboratories, startups, and multinational companies to transform ideas into tangible solutions. There, he and his team use Ultimaker 3D printers to better enable rapid design iterations during the prototyping phase.<section>One of the company’s latest projects is the OSTAW Camello, an autonomous package delivery robot.<h2>Revolutionizing package delivery</h2>The Camello was designed to address issues in the delivery logistics chain in Singapore, which causes high shipment costs and operational complexities. Due to low loads and long waiting periods in loading and unloading bays, package deliveries are often inefficient – a fact exacerbated by high delivery volumes and tight delivery deadlines.To tackle this challenge, Final Aim collaborated with a Singaporean robotics start-up OTSAW Digital PTE LTD, with the Camello being the final product.<iframe src="https://www.youtube.com/embed/ZLfuav7Goc8?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 789px; height: 441px;"></iframe>The Camello is user friendly, featuring an ergonomic cargo space and sleek design – optimal for Singapore’s urban environment. Plans are currently underway for it to be used by various industrial key players, delivery companies, and retailers throughout Singapore, creating an improved ecosystem that provides smooth and efficient delivery to customers, while increasing profit margins for those businesses that use it.<h2>The birth of the Camello</h2>As with any product, several phases were involved in Camello’s design, with the Ultimaker S3, Ultimaker Cura, and CAD software acting as Yasu’s and Final Aim’s greatest companions throughout the process.First came the robot’s concept development and evaluation. From the initiation to ideation, he used both hand-drawn design sketches and CAD software.<div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351339935-ezgif-4-ff30c01cc212.jpg" style="width: 788px;" class="fr-fic fr-dib">Industrial designer Yasuhide Yokoi with the Ultimaker S3 and Camello prototypes&nbsp;</div>Once he developed the idea, Yasu began the process of presenting it to the higher-level management, frontline members, and end-users. This divergent approach allowed Yasu to gain as much feedback as possible, which he could then use to refine, improve, and further flesh out his concept.&nbsp;<div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351389427-ezgif-4-074c26f97a5a.jpg" style="width: 788px;" class="fr-fic fr-dib">Early sketches of design ideas&nbsp;</div><div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351426664-ezgif-4-9f90c2806768.jpg" style="width: 788px;" class="fr-fic fr-dib">A CAD design iteration, which can be 3D printed&nbsp;</div>Next came the prototyping phase. As Yasu now had numerous potential ideas, he needed to rapidly actualize them – often on tight deadlines. Luckily, this was a task that 3D printing was able to easily handle. Compared to other common prototyping methods such as sculpting or carving from Styrofoam, chemical wood, or industrial clay, 3D printing is much more efficient – freeing up time for Yasu to work on other design tasks.“More than just cost-cutting, 3D printing has added value to my process,” Yasu said.<div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351476615-ezgif-4-89136559e3a3.jpg" style="width: 788px;" class="fr-fic fr-dib">3D printed iterations of the robot, ready to be tested and compared&nbsp;</div><h2 id="isPasted">Finalizing an intuitive design</h2>Yasu was also responsible for ensuring that the Camello’s final design was of excellent quality. As his works often incorporate organically curved surfaces and silhouettes, which are often difficult to implement, he needed to create numerous iterations. 3D printing technology utilizes the contour layers of printouts to analyze the curvature of surfaces – essentially an equivalent to the zebra mapping that CAD software performs. “The Ultimaker S3’s double extrusion feature has [also] been essential to my everyday design applications,” Yasu said. “Together with Breakaway and PVA material, my printing experience has become exponentially more efficient. I am deeply satisfied with the resulting quality as it leaves behind no support structure remaining.”<div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351527613-ezgif-4-7e8be04a50e7.jpg" style="width: 788px;" class="fr-fic fr-dib">Finished 3D printed prototype in the Ultimaker S3&nbsp;</div><div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1626351600118-ezgif-4-14928e22f90b.jpg" style="width: 788px;" class="fr-fic fr-dib">Camello autonomously delivers groceries around Singapore&nbsp;</div>For the Camello to be a success, its design had to be intuitive and accessible at first glance. The design process, therefore, involved divergent ideation, exploring all possibilities, which were then carefully narrowed in focus. Development speed was also critical for stakeholders' requests.3D printing enabled these stakeholders to see and touch a physical product, deepening their understanding of the Camello’s concept and design – and streamlining the decision-making process.</section>

Yasuhide “Yasu” Yokoi is the cofounder of design and technology firm Final Aim Inc., which works with laboratories, startups, and multinational companies to transform ideas into tangible solutions. 

Yasuhide Yokoi and Final Aim Inc.: Rapid iterations of an autonomous delivery robot

What sensors do we need for building a fully autonomous robot?Autonomous Robots are equipped with numerous sensors to perceive its surroundings as well as be aware of its own movements. The first step for achieving autonomy of robots i.e., robots moving from point A to point B on its own without colliding with anything, is awareness of the surrounding environment. Autonomous robots have a stack of sensors, among them, Wheel Odometers, IMU, GPS, Lidar, and Multiple Cameras being the most common. The current developments in the autonomous vehicles space also make use of sensors like Radar, Stereo Cameras in combination with the above stack.&nbsp;What is localization?<a href="http://www.cs.cmu.edu/~rasc/Download/AMRobots5.pdf" rel="noopener noreferrer" target="_blank">Localization</a> means to determine the current position and orientation of a body with respect to some coordinate system.How humans localize, is it a difficult task?Humans very naturally tend to determine their &nbsp;current position with respect to the different environmental landmarks/features around them. So, when we localize ourselves we tend to understand we are at some given distance and at certain angle from some house/tree/lamp post or any other landmarks. Given an empty featureless space even humans cannot localize. Thus, features are important for this localization task and thus we need a map filled with features/landmark to localize ourselves in that map, else it is an impossible task to perform.Then how do robots do it?The SLAM algorithm has two parts; the first is mapping and the second is localization. Autonomous ground robots have visual sensors like Lidar and Camera which can pretty well map its environment around. Then with 3D reconstruction from their data, robots generate something called a HD map. HD maps differ from normal maps, the former has a lot more features than the later. Once this map is ready, the robot starts localizing itself in this map. <a href="http://robots.stanford.edu/papers/thrun.pf-in-robotics-uai02.pdf" rel="noopener noreferrer" target="_blank">Particle Filter</a>, <a href="https://www-users.cs.umn.edu/~isler/pub/tase10.pdf" rel="noopener noreferrer" target="_blank">Triangulation</a>, <a href="http://www.cs.toronto.edu/~urtasun/courses/CSC2541/03_odometry.pdf" rel="noopener noreferrer" target="_blank">Visual Odometry</a> are some methods used for this purpose.&nbsp;Another widely used method for localization is <a href="https://www.cs.cmu.edu/~motionplanning/lecture/Chap8-Kalman-Mapping_howie.pdf" rel="noopener noreferrer" target="_blank">Extended Kalman Filter</a>. An EKF is a non-linear version of the linear Kalman Filter. It's a state-space estimator, what that means is that it can help in estimating the current state given input of the previous state. It's is used as a data fusion filter for localization tasks in robotics. It takes inputs from the IMU, Wheel Odometers and GPS and performs its computation based on a CTRV (Constant Turn Rate Velocity) model for a wheeled ground vehicle, to estimate the current position and orientation of the vehicle. Often this localization information is fused with visual odometry to achieve an accuracy of 100mm in the localization task.Once the robots know where they are in a map they can now start planning their path for the destination point B. Thus, invoking another interesting field of research called Path Planning. &nbsp; More resources on SLAM :1. <a href="https://blog.cometlabs.io/teaching-robots-presence-what-you-need-to-know-about-slam-9bf0ca037553" rel="noopener noreferrer" target="_blank">Teaching robots presense</a>2. <a href="https://en.wikipedia.org/wiki/Simultaneous_localization_and_mapping" rel="noopener noreferrer" target="_blank">SLAM</a>3. <a href="https://ieeexplore.ieee.org/abstract/document/1638022" rel="noopener noreferrer" target="_blank">Simultaneous Localization and Mapping</a>&nbsp;

Image: Highway image using LIDAR - Oregon State University (CC BY-SA 2.0)

A brief introduction to localization and mapping, and how these two functions are performed simultaneously during SLAM (Simultaneous Localization and Mapping).

4 wheeled robots

Latest Posts