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/43cda683-a88c-47b4-8a89-45b950f15e08?dark=false" class="fr-draggable" data-gtm-yt-inspected-9="true" 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-24="true"></iframe> The full article will continue below.<hr><h3 id="isPasted">Background</h3>Global water pollution presents a formidable challenge, with traditional remediation methods often falling short due to their inefficacy, high costs, and environmental burden. This context <a href="https://pubs.rsc.org/en/content/articlelanding/2023/NR/D3NR03592A" target="_blank" rel="noopener noreferrer">underscores</a> the urgent need for innovative solutions that are both effective and sustainable. <h3>The Team and Their Inspiration</h3>"CoffeeBots" are a <a href="https://www.wusa9.com/article/news/local/virginia/rusty-coffee-cleaning-water-george-mason-university/65-0de9e05b-b8ed-4b5c-863d-de7323f75a09" target="_blank" rel="noopener noreferrer">collaborative invention</a> by Jeff Moran, an Assistant Professor of Mechanical Engineering at George Mason University, Amit Kumar Singh, a postdoctoral researcher at GMU, and Tarini Basireddy, an undergraduate student at Johns Hopkins University. Together, they engineered a low-cost and environmentally friendly solution to address severe water contamination issues using everyday materials. <iframe width="640" height="360" src="https://www.youtube.com/embed/cDSJA1JBTNk?&amp;wmode=opaque&amp;rel=0&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" data-gtm-yt-inspected-9="true" id="838150768" title="Magnetically-Propelled CoffeeBots for wastewater decontamination" data-gtm-yt-inspected-24="true">&nbsp;</iframe><h3>Technical Details of CoffeeBots</h3>Composition and Manufacturing: CoffeeBots <a href="https://www.youtube.com/watch?v=cDSJA1JBTNk" target="_blank" rel="noopener noreferrer">consist</a> of spent coffee grounds coated with iron oxide nanoparticles. The synthesis of these nanoparticles employs green chemistry principles, ensuring an eco-friendly production process. The nanoparticles adhere to the coffee grounds, leveraging the grounds’ natural porous and hydrophobic surface, which is ideal for adsorbing oil and microplastics.Functionalization: Further enhancing their pollutant-binding capabilities, CoffeeBots are <a href="https://www.youtube.com/watch?v=cDSJA1JBTNk" target="_blank" rel="noopener noreferrer">functionalized</a> with ascorbic acid. This addition targets the removal of methylene blue dye, a common pollutant in industrial wastewater. The ascorbic acid acts both as a bioadsorbent and a reducing agent, facilitating the breakdown of the dye into less harmful compounds.Magnetic Navigation and Recovery: The integration of iron oxide nanoparticles allows for the magnetic manipulation of CoffeeBots. This feature enables the remote guidance of CoffeeBots through contaminated waters and their subsequent retrieval via magnetic forces once the cleanup task is completed. This magnetic property not only simplifies the operation but also allows for the reuse of CoffeeBots, significantly <a href="https://www.gmu.edu/news/2024-01/mason-engineers-develop-rusty-coffee-grounds-remove-pollutants-water" target="_blank" rel="noopener noreferrer">reducing</a> the cost and environmental impact of the cleanup process.Performance and Efficiency: In practical applications, CoffeeBots demonstrate a high efficacy in capturing and removing oil, microplastics, and dye pollutants from seawater. Their movement, driven by external magnetic fields, increases their contact with pollutants, enhancing the efficiency of pollutant uptake compared to static methods. Laboratory tests confirm that CoffeeBots can be recycled multiple times without significant loss of functionality, <a href="https://www.gmu.edu/news/2024-01/mason-engineers-develop-rusty-coffee-grounds-remove-pollutants-water" target="_blank" rel="noopener noreferrer">showcasing</a> their durability and long-term usability. <h3>Significance of the Solution</h3>CoffeeBots <a href="https://www.gmu.edu/news/2024-01/mason-engineers-develop-rusty-coffee-grounds-remove-pollutants-water" target="_blank" rel="noopener noreferrer">exemplify</a> a breakthrough in water purification technology by combining low-cost materials, innovative nano-engineering, and environmental sustainability. This technology not only addresses the immediate need for effective water purification but also aligns with global sustainability goals by repurposing waste products and minimizing chemical inputs.<h3>Future Prospects and Applications</h3>Ongoing research <a href="https://www.wusa9.com/article/news/local/virginia/rusty-coffee-cleaning-water-george-mason-university/65-0de9e05b-b8ed-4b5c-863d-de7323f75a09" target="_blank" rel="noopener noreferrer">aims</a> to extend the capabilities of CoffeeBots, including the exploration of solar-activated propulsion mechanisms that would eliminate the need for external magnetic controls, thereby enhancing the autonomy of the CoffeeBots for more extensive and less supervised water treatment operations. <h3>Conclusion</h3>The creation of CoffeeBots by the team at George Mason University marks a meaningful advancement in nano- and environmental engineering. By harnessing simple yet innovative materials and methods, they have developed a promising solution to combat the pervasive issue of water pollution. As this technology evolves, it holds the <a href="https://pubs.rsc.org/en/content/articlelanding/2023/NR/D3NR03592A" target="_blank" rel="noopener noreferrer">potential</a> to revolutionize water purification practices globally, offering a potential beacon of hope for millions affected by polluted water sources.

How George Mason University's Nanotechnology Research Is Turning Waste From Your Daily Brew into a Powerful Pollution Solution

How to Turn Used Coffee Grounds into Water-Cleaning Superbots

NVIDIA Jetson AGX Orin Module and Developer Kit

Nvidia Jetson and Edge Impulse facilitate Edge AI development, offering computational power and model training platforms for real-world applications.

Building High-Performance Edge AI Solutions with Nvidia Jetson and Edge Impulse

In the ever-evolving landscape of production and logistics, robotics &amp; automation play an increasingly vital role, driven by the wave of digitization. However, as with any technology, there are also hurdles which have to be overcome, especially when it comes to the production of customized and lightweight parts in a cost-efficient manner. This is where 3D printing steps in. Join us in this blog article as we explore the benefits and diverse applications of 3D printing for robotic parts and learn about the connection of those two technologies.<h2>Understanding 3D Printing</h2>Before exploring their interconnection, let’s understand 3D printing, also known as additive manufacturing. Additive manufacturing enables the conversion of digital designs into tangible objects by building up layers of material. You just need the right design and production can start without any huge production ramp-up. This freedom enables intricate designs, rapid prototyping, and on-demand production of customized parts, offering a level of flexibility and innovation that has redefined the manufacturing landscape.<figure><img width="1024" height="299" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzMjc0NzI1NjAzLTE3MTMyNzQ3MjU2MDMucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" alt="3D-Printing-How-it-Works" srcset="https://replique.io/wp-content/uploads/2024/03/3D-Printing-How-it-Works-1024x299.jpg 1024w, https://replique.io/wp-content/uploads/2024/03/3D-Printing-How-it-Works-300x88.jpg 300w, https://replique.io/wp-content/uploads/2024/03/3D-Printing-How-it-Works-768x224.jpg 768w, https://replique.io/wp-content/uploads/2024/03/3D-Printing-How-it-Works-1536x449.jpg 1536w, https://replique.io/wp-content/uploads/2024/03/3D-Printing-How-it-Works.jpg 1900w" sizes="(max-width: 1024px) 100vw, 1024px" class="fr-fic fr-dii">From digital file to printed parts in hours.</figure><h2>Custom Parts with 3D Printing</h2>Robotics is one of the industries, where these benefits of 3D printing can play a crucial role. And there are many reasons for it. One is the possibility to create custom parts of robotics and automation machinery using 3D printing. Traditional manufacturing methods often fall short when it comes to creating parts, such as grippers, tailored to specific tasks without incurring exorbitant costs due to the creation of specialized tools and molds. Thanks to 3D printing, even small players (SMEs), can use 3D printing to create budget-friendly robot parts, as there are no minimum order quantity, meaning they can produce parts starting from lot-size one. <img width="1024" height="768" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzMjc1MDQ2OTM1LTE3MTMyNzUwNDY5MzUucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" alt="" srcset="https://replique.io/wp-content/uploads/2024/03/3D-printed-caps-robot-automation-1024x768.jpg 1024w, https://replique.io/wp-content/uploads/2024/03/3D-printed-caps-robot-automation-300x225.jpg 300w, https://replique.io/wp-content/uploads/2024/03/3D-printed-caps-robot-automation-768x576.jpg 768w, https://replique.io/wp-content/uploads/2024/03/3D-printed-caps-robot-automation-1536x1152.jpg 1536w, https://replique.io/wp-content/uploads/2024/03/3D-printed-caps-robot-automation.jpg 1900w" sizes="(max-width: 1024px) 100vw, 1024px" class="fr-fic fr-dii" style="width: 758px;">Robot caps can be cost efficiently produced in small volumes via 3D printing.<h2>Lightweight Parts Thanks to Intricate Designs</h2>Weight is a critical factor in optimizing robotic performance. Traditional manufacturing often results in excess weight due to subtractive processes. 3D printing revolutionizes this by allowing engineers to design intricate, hollow structures, optimizing weight without compromising strength. This newfound agility finds applications in drones, exoskeletons, and various robotic systems.<h2>Part Consolidation and Modulation</h2>3D printing’s technical benefit extends to the consolidation of multiple parts into a single, complex structure. This not only reduces overall weight but also minimizes assembly challenges and inventory complexity. On the other side, 3D printing allows the separation of a single part into distinct components, simplifying modifications if needed.<h2>Quick Prototyping and Design Changes</h2>Compared to traditional methods, 3D printing offers unparalleled agility in prototyping and design alterations. Engineers and designers can swiftly translate conceptual ideas into tangible prototypes. This means they can test a prototype out almost immediately to see if it’s a good fit. And if they want to tweak or change the design, they can easily do that thanks to the flexibility of 3D printing, empowering innovators to adapt and optimize robotic components with unprecedented speed. This not only accelerates the product development cycle and reduces time-to-market considerably, but also fosters a culture of continuous improvement in the ever-evolving field of robotics.<img width="1024" height="768" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzMjc0ODUwNjU0LTE3MTMyNzQ4NTA2NTQucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" alt="" srcset="https://replique.io/wp-content/uploads/2024/03/3D-printing-prototyping-robotics-1024x768.jpg 1024w, https://replique.io/wp-content/uploads/2024/03/3D-printing-prototyping-robotics-300x225.jpg 300w, https://replique.io/wp-content/uploads/2024/03/3D-printing-prototyping-robotics-768x576.jpg 768w, https://replique.io/wp-content/uploads/2024/03/3D-printing-prototyping-robotics-1536x1152.jpg 1536w, https://replique.io/wp-content/uploads/2024/03/3D-printing-prototyping-robotics.jpg 1900w" sizes="(max-width: 1024px) 100vw, 1024px" class="fr-fic fr-dii">3D printing can be used for prototyping and visualizing products and ideas.<h2>Spare Parts On-Demand</h2>The wear and tear faced by robotics and automation machinery can lead to costly downtime. Traditional methods of obtaining spare parts involve a time-consuming process of ordering, shipping, and, in some cases, custom manufacturing. 3D printing provides a rapid and cost-effective solution for local or even on-site production of spare parts, just on-demand. Instead of waiting for shipments or relying on extensive inventories, robots can be quickly restored to operational status with 3D printed replacements. This capability significantly minimizes downtime, ensuring continuous robot functionality. At an automation fair for example, Replique was able to get needed spare parts of an exhibitor within a day.Learn more about the benefits of <a href="https://replique.io/3d-printed-spare-parts/" target="_blank">3D printing for the production of spare parts.</a><h2>Application examples</h2><h3>Grippers</h3>Especially, grippers, are undergoing a revolution thanks to additive manufacturing. It enables the creation of grippers in small volumes that are not only cost-efficient but also remarkably lightweight and optimized. When the need arises to change grippers, 3D printing facilitates a swift process with short development and production times. This capability translates into faster movements, reduced cycle times, and an overall more agile manufacturing process.<figure><img width="1024" height="768" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzMjc0NzI2Mzc4LTE3MTMyNzQ3MjYzNzgucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" alt="3D printing for robotic parts_gripper" srcset="https://replique.io/wp-content/uploads/2024/03/3D-printed-grippers-1024x768.jpg 1024w, https://replique.io/wp-content/uploads/2024/03/3D-printed-grippers-300x225.jpg 300w, https://replique.io/wp-content/uploads/2024/03/3D-printed-grippers-768x576.jpg 768w, https://replique.io/wp-content/uploads/2024/03/3D-printed-grippers-1536x1152.jpg 1536w, https://replique.io/wp-content/uploads/2024/03/3D-printed-grippers.jpg 1900w" sizes="(max-width: 1024px) 100vw, 1024px" class="fr-fic fr-dii">Cobot gripper designed by struktur.form.design Engineering GmbH for 3D printing.</figure>In a recent cooperation with struktur.form.design Engineering GmbH for example, we were able to reduce weight of a cobot gripper by 78%, part count by 84% and overall production cost savings by 30%, just via redesigning and producing via additive manufacturing.And the benefits extend beyond industrial automation, making a significant impact on healthcare robotics as well. In surgical robots, for instance, 3D printed grippers can handle specialized instruments and execute delicate tasks.<h3>Embedded sensors and electronic components</h3>Beyond these core connections, the collaboration between 3D printing and robotics unfolds into an expansive canvas of possibilities. For example, embedding sensors and electronic components directly into robotic structures using 3D printing enhances their functionality and streamlines assembly processes.<h3>Soft robotics</h3>For soft robotics – those dealing with flexible and deformable structures – 3D printing opens avenues for the creation of parts that move and adapt like real muscles. Researchers from the Delft University of Technology, for instance, have pioneered the use of <a href="https://pure.tudelft.nl/ws/portalfiles/portal/142950401/s41563_022_01429_5.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">3D printing in manufacturing soft robots with intricate viscoelastic hydrogels</a>. These materials withstand high pressures and open new possibilities in fields like medical prosthetics.<h3>Innovation and Education</h3>Moreover, 3D printing serves as a catalyst for innovation and education in robotics. It fosters creativity among students and researchers, accelerating the learning curve and driving advancements in the development of robotic systems.<h2>Robots as 3D Printers</h2>The marriage of robotics and 3D printing can even extend beyond conventional roles. Here, robots themselves become integral 3D printers, amplifying the scope and scale of additive manufacturing. Especially noteworthy in large-scale 3D printing, robotic arms deposit materials layer by layer to create objects. This facilitates the creation of parts on a scale previously unattainable in 3D printing.<figure><img width="1024" height="576" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzMjc0NzI2MDYxLTE3MTMyNzQ3MjYwNjEucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" alt="robots-as-3D-printers" srcset="https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers-1024x576.jpg 1024w, https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers-300x169.jpg 300w, https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers-768x432.jpg 768w, https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers-1536x864.jpg 1536w, https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers-1200x675.jpg 1200w, https://replique.io/wp-content/uploads/2024/03/robots-as-3D-printers.jpg 1920w" sizes="(max-width: 1024px) 100vw, 1024px" class="fr-fic fr-dii">Thanks to the use of robots, even houses can now be 3D printed.</figure><h2>Conclusion</h2>The intersection of 3D printing and robotics reshapes how we conceive, design, and build robotic systems. From lightweight components to customized grippers and on-demand spare parts, this collaboration represents a paradigm shift, offering tailored solutions that enhance the efficiency and adaptability of robotic systems.

Explore the benefits of 3D printing for light-weight, customized and on-demand parts.

How to Leverage 3D Printing in Robotics and Automation

<blockquote>“For a new product to be successful, it is not enough for it to work—almost everything around us works quite well. The design matters.”</blockquote>This is what Iván Arakistain, a technologist and researcher at Tecnalia said. After winning the Connect for Good challenge, we interviewed Arakistain to discuss his award-winning project on sustainable logistics infrastructure and his insights into the logistics industry, particularly that of perishable goods.Logistics is a dynamic field fraught with challenges, and sustainability is a growing concern, particularly in transporting perishable goods. Iván Arakistain, representing Tecnalia, won first place in the Connect for Good challenge with an innovative concept that leverages a low-power IoT solution to monitor and enable eco-friendly transport of perishable goods.The&nbsp;<a href="https://www.wevolver.com/article/connect-for-good-low-power-wireless-sustainability-challenge" target="_blank">Connect for Good Challenge</a> is a joint initiative by Nordic Semiconductor, Mouser Electronics, Soracom, and Crowd Supply aimed at fostering innovation for social and environmental good. It brought together a worldwide network of engineers, entrepreneurs, and developers around one mission: “to devise low-power wireless solutions that contribute towards achieving the United Nations Sustainable Development Goals.”&nbsp;Arakistain's winning project is a game-changer in sustainable logistics. Through advanced monitoring and anomaly detection, this innovative solution optimizes the transport of perishable goods while eliminating the need for energy-intensive refrigerated cargo trailers. Thus, it significantly reduces carbon emissions and operational costs while ensuring the integrity of the cold chain. Through the integration of IoT technology, including low-energy sensors and GPS and coupled with mini solar panels for autonomy, the project sets a new standard for eco-friendly transport in the logistics industry, with broad implications for global sustainability efforts. The key component of this project is the integration of the&nbsp;<a href="https://www.wevolver.com/specs/nrf9160-development-kit" target="_blank">nRF9160 Development Kit</a>, chosen specifically for its low energy consumption and reliable cellular connectivity.In this exclusive interview, Arakistain sheds light on his journey, the inspiration behind his project, and the impact he envisions on the logistics industry's future.<h2 dir="ltr">Interview with Iván Arakistain of Tecnalia</h2><h3 dir="ltr">Can you briefly describe your winning project and the main problem it addresses in the logistics industry?</h3>One of the main challenges of the logistics industry is the sustainable transport transition. This focuses on decarbonizing the transport industry, especially because today, at least in Spain, it’s heavily based on trucks; most of the logistics happen on the road, and trucks consume a lot of fuel. So, we have to shift from that to a cleaner way of transport.Some years ago, we had a customer who sold precooked food.&nbsp;They mentioned something to us that sparked this idea process: If they could deliver the food in one day from their factory to the end customer, they would be able to avoid refrigerated transportation, especially since it’s relatively expensive, requires a lot of fuel, and is very complex.So, we started exploring that. At that time, the technology was not quite ready for the application, mainly for areas like the south of Spain, where it's very hot in the summer. The logistics were not as fast as today, but as things have evolved, we are now able to transport food—or perishable goods—in proper condition to the end customer in a short a time as needed so it arrives safely.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1713160590293-0_Ivan+Arakistain.jpg" style="width: 100%px;" class="fr-fic fr-dib"><h3 dir="ltr">What inspired you to focus on developing a more sustainable method for transporting perishable goods?</h3>Well, the main goal is to deliver goods fast and with as low carbon emissions as possible. For that, we must change from only using transport by trucks to combining truck and train, which is obviously much cleaner environmentally. By doing so we can ensure more availability, lower cost per kilometer, and a smaller cargo footprint.&nbsp;Let’s look at how your project aligns with the Sustainability Development Goals. Could you tell us how your solution targets these goals?Our solution’s practical implications impact goals 7 (Affordable and Clean Energy), 11 (Sustainable Cities and Communities), and 13 (Climate Action). We are very focused on energy efficiency and sustainability goals for cities and districts. Our application can help reduce the cargo footprint and accelerate the transition from the current fuel-based transport to a more electrified way of transport.&nbsp;Of course, we cannot transition directly from 0 to 100%, so we must ensure the transition is smooth. In our area of focus, the technology background is in artificial intelligence for microcontrollers and small devices. We embed this intelligence into the embedded device so that we can know via our electronic sensors if the transported food is in good condition. We can also sense whether any volatile compounds can impact the condition of the food.By making those changes, we estimate that up to 10% of carbon reduction is possible. And that also applies to energy consumption, even though I’m not sure if it’s a linear relationship. However, the estimation stands.<h3 dir="ltr">Let's move onto the technical side. How does your solution work? Is embedded AI the differentiator from traditional energy-intensive refrigeration?</h3>As I said, we are focused on AI for microcontrollers. So, first, we develop the AI models in servers and powerful computers. Then, we reduce those models so that they can run in a small controller with a few kilobytes or a small RAM. For this application, we are focused on two types of inference.The first type of inference is air quality to determine the state of the product. The second inference type is AI for vibration analysis, which is something we have implemented here and in other projects. In this case, we can analyze if the vibration of products in the truck matches the orientation to make sure everything is good. In other cases, we also do this AI analysis of vibration for structural health and many other applications.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1713160621737-1_Manufactured+PCB+Top.jpg" style="width: 100%px;" class="fr-fic fr-dib"><h3 dir="ltr">How accurate and precise are the AI model results in a real-world application?&nbsp;</h3>There are two processes that we do. First, we collect all the data, and then we perform model training and model testing on our computers. We split the data set into two parts: about 80% of the data is used for training the model, and the remaining 20% or so is used for testing the model.In our computer simulation, the results were very good; you can get up to 96% accuracy. But we both know that’s not the reality. Getting a very high score virtually means the model is quite good. However, when you go into the real world and flash the firmware into the microcontroller you’re using in the actual sensor, the accuracy decreases a bit. Still, we can get good enough accuracy with this model.Were there any particular challenges you faced in the development process, and how did you overcome them?As I said earlier, the original idea came some years ago with this customer we were working with. They produced precooked food, and we did some real testing with them. We sent the food with a trucker and other things to actual customers. At that moment, we realized that the technology was not quite ready, not because of the electronics but because of the isolation and insulation challenges. For that, you’d need excellent isolating materials so that temperatures are kept in the correct range.&nbsp;This was about eight to nine years ago. At that point, we did develop a complete solution, and we knew the idea was good, but it was not quite ready because of the isolation challenge. Since then, we have kept thinking and working on it, and now we know that it is a feasible application, especially since there are much more efficient containers for food transport than years ago. There are better isolation materials, which helped this improve.<h3 dir="ltr">Looking into the next decade, what are the biggest hurdles in scaling and implementing your solution across different regions and logistics networks?</h3>The main difficulty is the limited time for delivery: It has to be done within the first 24 to 48 hours and the products need a low temperature range.Of course, I think it's scalable. Still, one of the biggest challenges is the container. We need to use special containers with good insulation for this. Basically, once we are able to prove to customers that they are going to save so much on each transportation, then it makes sense.So far, we have tested with first-class precooked food, which is already prepared and ready for eating upon reheating in a restaurant or somewhere else. We are not so focused on uncooked food.<h3 dir="ltr">Let’s dive a bit into the economic side of things. What are the economic benefits of your solution for logistics companies and end users?</h3>The economic benefits mainly rely on the use of nonrefrigerated transportation. As a result, you can save about 10% of the transportation cost. It consumes less fuel and energy. It's simply more efficient. We are also very interested in combining ways of transportation: using not only trucks but also trains. Here in Spain, we have quite a robust train infrastructure, but nowadays, it is more focused on passengers than goods. So, I think we must leverage the train infrastructure and combine it with trucks in the future.Also, for international shipments, combining the truck with the train is important so that the driver does not need to drive so far. The truck driver would simply mount the truck with the goods from a train carriage, move onto another carriage to collect goods from there, and then deliver them locally.This is a standard logistics process. We are simply using the existing infrastructure. The only additional requirement would be the special containers for the food that I mentioned earlier.<h3 dir="ltr">You mentioned one customer already.&nbsp;Have you discussed this with other members of your target market? How have your target customers responded to your solution so far?</h3>Yes. 15 days ago, I was at a logistics and transportation fair in Bilbao. I gave a speech there and talked to potential customers. Clearly, there is some potential, but of course, we need to keep the focus on the end customer.<h3 dir="ltr">By focusing on the end customer, what strategies are you employing to encourage the adoption of your technology within the market?&nbsp;</h3>In Tecnalia, we work with different approaches to ensure the technology adoption. We identify and manage deep-tech business opportunities, through a venture building process to accelerate their industrial commercialization. We create new startups or commercialize licenses, accelerating the incubation of technological assets until they are turned into investment opportunities capable of generating economic and social value.&nbsp;<h3 dir="ltr">How do you see your solution evolving in the next five years?</h3>I think that it has quite a lot of potential. We are still in a transition stage, where not everything is well-defined. The path is clear: we have to shift to the electrification of transport. But the speed at which this is going to happen is yet to be clear. Yet, I think that it has significant potential for the future because logistics is a fast-growing sector.<h3 dir="ltr">Is there close competition to your technology from bigger companies already established in the logistics market?</h3>Yes, there is. For example, some years ago, big companies like Amazon tried to sell perishable food to end customers in a very short time. However, they were not very successful because it’s not easy to deliver that fast in a cost-efficient way.Our case is a little different. It focuses on precooked food for industrial partners. The customer I mentioned earlier is not selling to end customers but rather to restaurants and other businesses. So yes, there are big players, but they are not entirely in the same market niche as ours.<h3 dir="ltr">Are there other applications or industries where your technology could be applied beyond the niche cold chain logistics?</h3>Yes, we use embedded AI for structural health monitoring in various cases. Here, you would need to know the condition of a structure. In Tecnalia, for example, we have some dedicated lab equipment, such as sensitive accelerometers. But the cost of such devices is typically quite high. They are not devices you can leave on a structure but rather devices you use within a specific timeframe.So, we are developing small, affordable devices that can use MEMS accelerometers, inexpensive microcontrollers, and embedded AI to provide early warnings if there is an anomaly, failure, or any other event on which the model is trained.The new devices we are developing would cost as much as an order of magnitude less than the typical measuring and monitoring equipment. They would only provide an early warning, after which the experts could go and perform more extensive measurement and testing.Another example of our embedded AI would be audio detection. Consider a large dataset of street sounds that can take over six gigabytes – that is a lot of information. For this, it's possible to train an AI model that takes no more than kilobytes – which is significantly less – and embed it into a microcontroller to classify the sounds. We tested this, and the model was able to accurately identify and classify the sounds of a car horn, for example, a dog barking or children playing. This is a solution to tackle problems with lots of data using a compressed model that can accurately classify the data without requiring so much power.<h3 dir="ltr">Going back to the project experience, what have you learned from working on this project that you think is crucial for innovation in sustainable technologies?</h3>At Tecnalia, we are experts in many different fields. The most interesting thing about working in an applied research and technological development centre like Tecnalia is that I can collaborate with experts in multiple fields, such as electronics, logistics, structures, and energy efficiency. For such projects to work, I have to work with lots of people to solve the problem.&nbsp;Also, experts in AI are not all the same. Some of them are more focused on big processors like NVidia devices, and we need to collaborate with them to understand the models and be able to quantize and reduce the models down to the microcontroller level.What advice would you give to other entrepreneurs or innovators looking to make a difference in the green technology space?&nbsp;My advice would be to prototype as much as they can. In electronics, we are quite used to prototyping fast. That's a good thing for our sector. But in other areas, it might be more difficult to prototype. I would also encourage people to collaborate with other experts and learn from them.<h2 dir="ltr">Conclusion</h2>Iván Arakistain's winning project exemplifies the potential for low-power IoT solutions to revolutionize the transportation of perishable goods. By leveraging advanced monitoring and anomaly detection, Arakistain's project offers a promising avenue for reducing carbon emissions and operational costs while maintaining the integrity of the cold chain.&nbsp;As we look to the future, the scalability and adoption of such solutions present ongoing challenges. Yet the momentum generated by initiatives like the Connect for Good Challenge signals a promising trajectory towards more innovation and sustainable solutions and systems. For more information about the challenge and its winners, check out our dedicated article:&nbsp;<a href="https://www.wevolver.com/article/connect-for-good-challenge-winners-logistics-infrastructure-monitoring-smart-bees-and-bioreactors" target="_blank">Connect for Good Challenge Winners: Logistics Infrastructure Monitoring, Smart Bees and Bioreactors</a>.

Introducing the Winner of the Connect for Good Challenge 2023


Towards Sustainable Logistics Infrastructure: An Interview with Tecnalia

Are you an EE looking for a new podcast?  Here's a list of MacroFab Circuit Break episodes to get you started. 

The Perfect Binge! Top 8 Circuit Break Episodes for New Listeners

The integration of robotics into manufacturing has radically boosted efficiency and quality and lowered costs. However, large industrial robots also pose a threat to human safety due to their size, weight, and ‘on/off’ programming. In an effort to solve this problem, collaborative robots, or cobots, have been introduced to manufacturing facilities. These lightweight robots are designed to work alongside human workers. However, cobots cannot do the same grunt work as their more industrial cousins, leaving a gap between the small save robots and the caged larger machines.&nbsp;Blue Danube Robotics, the company behind <a href="https://www.airskin.io/" target="_blank" rel="noopener noreferrer">AIRSKIN®</a>, aims to solve this industrial automation problem. Their innovative product, AIRSKIN®, is a breakthrough technology designed as a soft, tactile skin for industrial robots, enabling them to work alongside humans safely. This patented solution allows robots to perform a broader range of tasks in close proximity to human workers, revolutionizing how robotic automation integrates into human-centric work environments.&nbsp;<h1 dir="ltr">AIRSKIN® enables an open workplace with robots</h1>The integration of robots into the industrial workforce presents a unique set of safety challenges. The limitations of traditional safety measures and even the most advanced cobots have made it clear that a new approach is needed to harmonize human-robot collaboration. This is where AIRSKIN® enters the scene, offering a solution that addresses these challenges.AIRSKIN® seamlessly integrates with industrial robots and transforms traditional manufacturing setups into collaborative environments. This reduces hazardous collision areas and ensures maximum safety with PLe / Cat. 3 certification.<h3 dir="ltr">Upgrade to Collaborative Robots</h3>AIRSKIN® transforms standard industrial robots into fenceless, collaborative &nbsp;robots. This transformation allows robots to operate in close proximity to humans and other machinery, enhancing productivity and efficiency while maintaining a safe working environment. By eliminating the need for physical barriers, AIRSKIN® enables seamless collaboration between humans and robots, optimizing workflow and reducing downtime. AIRSKIN® works with all robots, already off-the-shelves products exist for KUKA (Agilus 2, Cybertech 2, Iontec, Quantec 2), Stäubli (TX2touch) and Epson (Scaraflex).&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEyNzM5Mzg3MDk5LXNlY29uZC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib">AIRSKIN® transforms standard industrial robots into fenceless, collaborative robots. Credit: AIRSKIN.<h3 dir="ltr" id="isPasted">Innovative Design and Functionality</h3>AIRSKIN® comprises soft and robust air-filled pads mounted on the robot, with embedded safety electronics that monitor internal air pressure and instantly react to contact anywhere on the robot. Dual-channel pressure sensors detect pressure changes, ensuring precise and rapid response to potential collisions in a maximum of 8ms.Equipped with intelligent sensors and real-time monitoring capabilities, AIRSKIN® detects and responds to potential hazards with precision and speed, mitigating the risk of accidents and injuries. Certified according to ISO 13849 with the highest safety performance level PLe / Cat.3, AIRSKIN® meets all industrial requirements, including high durability and IP54 rating.AIRSKIN® offers adaptability to various industrial environments and applications, seamlessly integrating into existing workflows. Its space-saving design eliminates the need for physical barriers, optimizing floor space by up to 90% compared to traditional fencing systems, thereby unlocking new possibilities for layout optimization and production line flexibility.<h1 dir="ltr">How&nbsp;AIRSKIN® is used</h1>AIRSKIN® can be added to industrial robot applications to enable them to have ‘collaborative’ status by effectively covering all hazardous collision areas. The maximum speed for the robot is based on a risk assessment and can reach up to 2m/s in collaborative mode.AIRSKIN® can help large payload robots achieve movement speed of beyond 1 m/s, while still maintaining operator safety. The AIRSKIN® Modules help absorb energy and distribute the contact forces associated, helping them avoid serious injury.<h3 dir="ltr">Clamping/shearing collisions</h3>For clamping/shearing collisions the robot’s stopping distance must be shorter than the thickness of the soft AIRSKIN®. In order to accommodate these stringent application areas, a risk assessment needs to be done to determine the permissible speed. It must be obtained by measuring contact forces occurring in the collision using an ISO/TS 15066 compliant measurement device.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEyNzM5NDIyODQyLXRoaXJkLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 100%px;" class="fr-fic fr-dib">Safer workplaces enable more agile and customized workflows. Credit: AIRKSIN.<h1 dir="ltr" id="isPasted">Advancing Industry 4.0</h1>Robotics is a pivotal component of Industry 4.0. AIRSKIN® enables companies to convert existing robotic setups to collaborative, human-safe zones. This can radically increase efficiency by reducing downtime usually created by safety cage protocols. It also enables more agile and customized workflows, which are integral to meeting industry 4.0 goals.&nbsp;Industry 4.0 benefits With AIRSKIN®<ul><li dir="ltr">Speed:&nbsp;Up to 6 times faster than applications with cobots, achieving speeds of up to 2 m/s for collaboration.</li><li dir="ltr">Flexibility:&nbsp;Safety system mounted on the robot offers flexibility in location and task execution.</li><li dir="ltr">Space Optimization:&nbsp;Optimizing installation footprint by up to 90%, maximizing operational efficiency.</li><li dir="ltr">Payload &amp; Reach: Supporting a wide range of payloads and reaches for various robotic applications. – like AIRSKIN for KUKA Quantec – up to 300 kg payload&nbsp;</li><li dir="ltr">Precision:&nbsp;Offering highest accuracy, repeatability, and path consistency for precise operations.</li><li dir="ltr">Risk Assessment: Prepared safety concept simplifies application assessments, ensuring compliance with safety standards.</li></ul><h3 dir="ltr">AIRSKIN Safetyflange: Advancing Safety and Efficiency</h3>AIRSKIN Safetyflange, a compliant robotic collision sensor, extends the safety benefits of AIRSKIN® technology to protect tools, workpieces, and individuals from potential hazards. Designed for easy mounting with any robot and end-of-arm tool, AIRSKIN Safetyflange ensures compliance with safety standards while maximizing workplace safety without compromising productivity.Key Features:<ul><li dir="ltr">Finger-Safe Applications:&nbsp;Eliminates crushing and clamping risks, ensuring compliance with safety standards.</li><li dir="ltr">Adjustable Break-Away Forces:&nbsp;Absorbs energy and reduces pressure and force during collisions in collaborative applications.</li><li dir="ltr">Compliance in All Directions:&nbsp;Adjustable compliance minimizes contact forces, maximizing workplace safety.</li><li dir="ltr">Easy Mounting Compatibility:&nbsp;Simplifies integration with any robot and tool using exchangeable ISO 9409-1 adapters.</li><li dir="ltr">Safety Certification: Complies with the PLe / Cat. 3 ISO 13849 safety certification, setting a new standard for safe and efficient operations.</li></ul><iframe width="640" height="360" src="https://www.youtube.com/embed/5ljMxWZMLvc?&amp;feature=youtu.be&amp;wmode=opaque&amp;rel=0&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">&nbsp;&nbsp;&nbsp;&nbsp;</iframe><h1 dir="ltr">Versatile Applications</h1>AIRSKIN Safetyflange is suitable for a wide range of applications, including palletizing, machine tending, visual inspection, gluing, and more, making it a versatile solution for enhancing safety and efficiency in industrial environments.AIRSKIN® marks a pivotal advancement in the sphere of industrial automation, fundamentally transforming how safety and efficiency are perceived and implemented in collaborative workspaces. By integrating AIRSKIN® into your operations, your business can set new benchmarks for what is possible to achieve with human-robot collaboration. There is immense potential for AIRSKIN®-equipped robots to redefine and enrich collaborative workspaces, allowing a future where robots and humans can work side by side with unprecedented efficiency and safety.As we move further into the Industry 4.0 era, the impact of <a href="https://www.airskin.io/" target="_blank" rel="noopener noreferrer">AIRSKIN®</a> represents the endless possibilities at the intersection of innovation, safety, and collaboration. It fosters a new period of industrial productivity and human-centric automation.

AIRSKIN® revolutionizes industrial automation by adding air-powered tactile skin for to robots to create safe, collaborative environments, ensuring maximum safety with PLe / Cat. 3 certification.

Bringing Freedom into Factories: How Air-Powered Tech Paves the Way for Human-Robot Harmony

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

When it comes to mating, two things matter for Heliconius butterflies: the look and the smell of their potential partner. The black and orange butterflies have incredibly small brains, yet they must process both sensory inputs at the same time — which is more than current artificial intelligence (AI) technologies can achieve without significant energy consumption. To make AI as smart as the butterflies, a team of Penn State researchers has created a multi-sensory AI platform that is both more advanced and uses less energy than other AI technologies. &nbsp;Current AI technologies often fall short in mimicking the multi-sensory decision-making processes that humans and animals use, the researchers said. This can limit AI’s potential for uses in robotics and smart sensors that detect dangers like faulty structures or imminent chemical leaks. &nbsp;“If you think about the AI we have today, we have very good image processors based on visual or excellent language processors that use audio,” said Saptarshi Das, associate professor of engineering science and mechanics and corresponding author of the study published today (March 28) in&nbsp;<a href="https://onlinelibrary.wiley.com/doi/10.1002/adma.202307380" rel="noreferrer noopener" target="_blank">Advanced Materials</a>. “But when you think about most animals and also human beings, decision-making is based on more than one sense. While AI performs quite well with a single sensory input, multi-sensory decision making is not happening with the current AI.” &nbsp;Heliconius butterflies choose a mate via a simultaneous visual cue — seeing that the potential mate’s wing pattern is indeed one of a Heliconius butterfly — and chemical cue of pheromones released by the other butterfly. Of note, Das said, the butterfly manages this with a tiny brain that uses minimal energy. This is in direct contrast to modern computing, which consumes a significant amount of energy. &nbsp;“Butterflies and many other animal brains are very tiny, and they use low amounts of resources, both in terms of energy used and physical size of the brain,” Das said. “And yet they perform computational tasks that rely on multiple sensory inputs at once.”&nbsp;To mimic this behavior electronically, the researchers turned to a possible solution that involves 2D materials, which are one to a few atoms thick. The researchers developed a hardware platform made of two 2D materials, molybdenum sulfide (MoS2) and graphene. The MoS2 portion of the hardware platform is a memtransitor, an electronic that can perform both memory and information processes. The researchers chose MoS2 for its light-sensing capabilities, which mimic the visual capabilities of the butterfly. The graphene portion of the device is a chemitransistor that can detect chemical molecules and mimic the pheromone detection of the butterfly’s brain.&nbsp;"The visual cue and the pheromone chemical cue drive the decision whether that female butterfly will mate with the male butterfly or not,” said co-author Subir Ghosh, second year doctoral student in engineering science and mechanics. “So, we got an idea inspired by that, thinking how we have 2D materials with those capabilities. The photoresponsive MoS2 and the chemically active graphene could be combined to create a visuochemical-integrated platform for AI and neuromorphic computing.” &nbsp;The researchers tested their device by exposing their dual-material sensor to different colored lights, mimicking the visual cues, and applying solutions with varying chemical compositions resembling the pheromones released by butterflies. The goal was to see how well their sensor could integrate information from both the photo detector and chemisensor, similar to how a butterfly's mating success relies on matching wing color and pheromone strength. &nbsp;By measuring the output response, the researchers determined that their devices could seamlessly integrate visual and chemical cues. This highlights the potential for their sensor to process and interpret diverse types of information simultaneously, they said.&nbsp;“We also introduced adaptability in our sensor's circuits, such that one cue could play a more significant role than the other,” said Yikai Zheng, a fourth-year doctoral student in engineering science and mechanics and co-author of the study. “This adaptability is akin to how a female butterfly adjusts her mating behavior in response to varying scenarios in the wild."&nbsp;The dual sensing in a single device is also more energy efficient, the researchers said, when contrasted with the current way AI systems operate. They collect data from different sensor modules and then shuttle it to a processing module, which can cause delays and excessive energy consumption. &nbsp;Next, the researchers said they plan to expand from integrating two senses into their device to three senses, mimicking how a crayfish uses visual, tactile, and chemical cues to sense prey and predators. The goal is to develop hardware AI devices capable of handling complex decision-making scenarios in diverse environments. &nbsp;“We could have sensor systems in places such as a power plant, that would detect potential issues such as leaks or failing systems based on multiple sensory cues,” Ghosh said. “Such as a chemical odor, or a change in vibration, or detecting weaknesses visually. This would then better help the system and staff determine what they need to do to fix it quickly because it was not just relying on one sense, but multiple ones.”&nbsp;

How Heliconius butterflies process two sensory inputs, pheromones and vision, at once to find a mate may inspire improved, multi-sensory artificial intelligence, according to a team of Penn State researchers. Credit: Adobe Stock image file #417010228 / lidiia. All Rights Reserved.

To make AI as smart as the butterflies, a team of Penn State researchers has created a multi-sensory AI platform that is both more advanced and uses less energy than other AI technologies.  

Butterfly-inspired AI technology takes flight

SKYRON is revolutionizing ship inspections by seamlessly conducting ultrasonic and visual testing in a single day,&nbsp;leveraging&nbsp;its advanced capabilities and efficient payload exchange system. This streamlined approach ensures thorough inspections within expedited timelines, which is crucial for ships needing to return to operations swiftly&nbsp;&nbsp;In the video above,&nbsp;SKYRON&nbsp;showcased&nbsp;its ability to navigate through a ship's cargo hold, conducting both ultrasonic thickness measurements and high-definition visual inspections with unparalleled speed and precision. The urgency to complete inspections before a ship's departure underscores the importance of swift yet thorough assessments, a challenge SKYRON meets effortlessly.&nbsp;Equipped with a precision-oriented SONY A7 camera featuring 3x optical zoom, adjustable LED lighting, and a laser pointer for pinpoint accuracy, SKYRON captured detailed visuals of critical areas prone to corrosion. Additionally, the integration of an Olympus 38DL Plus gauge and a robotic arm for ultrasonic readings guaranteed precise measurements within expedited timelines.&nbsp;The streamlined operations&nbsp;facilitated&nbsp;by SKYRON's proprietary&nbsp;Avesoft&nbsp;software allowed for real-time data processing and location tagging,&nbsp;providing&nbsp;immediate&nbsp;insights&nbsp;and ensuring that inspections are completed efficiently. This combination of advanced technology and expedited operations ensures that ship inspections are thorough,&nbsp;accurate, and aligned with the industry's demand for prompt assessments without compromising on quality.&nbsp;With SKYRON's ability to perform dual ultrasonic and visual testing within expedited timelines, the maritime industry can rely on efficient inspections that enable ships to return to operations swiftly and safely.&nbsp;

Witness how SKYRON's advanced tech and rapid testing capabilities revolutionize ship inspections, ensuring thorough assessments in record time for ships returning to operations.

SKYRON: Revolutionizing Ship Inspections with Dual Testing Efficiency

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/f153920a-aca0-4937-863a-2cc925d11434?dark=false" class="fr-draggable" data-gtm-yt-inspected-9="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>Columbia engineers build Emo, a silicon-clad robotic face that makes eye contact and uses two AI models to anticipate and replicate a person’s smile before the person actually smiles -- a major advance in robots predicting human facial expressions accurately, improving interactions, and building trust between humans and robots.<section id="isPasted">What would you do if you walked up to a robot with a human-like head and it smiled at you first? You’d likely smile back and perhaps feel the two of you were genuinely interacting. But how does a robot know how to do this? Or a better question, how does it know to get you to smile back?While we’re getting accustomed to robots that are adept at verbal communication, thanks in part to advancements in large language models like ChatGPT, their nonverbal communication skills, especially facial expressions, have lagged far behind. Designing a robot that can not only make a wide range of facial expressions but also know when to use them has been a daunting task.&nbsp;</section><section><h2>Tackling the challenge</h2>The <a href="http://engineering.columbia.edu/" rel="nofollow" target="_blank">Creative Machines Lab</a> at <a href="http://engineering.columbia.edu/" rel="nofollow" target="_blank">Columbia Engineering</a> has been working on this challenge for more than five years. In a new study published today in <a href="https://www.science.org/doi/10.1126/scirobotics.adi4724" rel="nofollow" target="_blank">Science Robotics</a>, the group unveils Emo, a robot that anticipates facial expressions and executes them simultaneously with a human. It has even learned to predict a forthcoming smile about 840 milliseconds before the person smiles, and to co-express the smile simultaneously with the person.The team, led by <a href="https://www.engineering.columbia.edu/faculty/hod-lipson" rel="nofollow" target="_blank">Hod Lipson</a>, a leading researcher in the fields of artificial intelligence (AI) and robotics, faced two challenges: how to mechanically design an expressively versatile robotic face which involves complex hardware and actuation mechanisms, and knowing which expression to generate so that they appear natural, timely, and genuine. The team proposed training a robot to anticipate future facial expressions in humans and execute them simultaneously with a person. The timing of these expressions was critical -- delayed facial mimicry looks disingenuous, but facial co-expression feels more genuine since it requires correctly inferring the human's emotional state for timely execution.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzExNTg1NTM0ODUxLXl1aGFuZy1odWEtb2YtY3JlYXRpdmUtbWFjaGluZXMtbGFiLWZhY2UtdG8tZmFjZS13aXRoLWVtby5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib">Yuhang Hu of Creative Machines Lab face-to-face with Emo. Image: Courtesy of Creative Machines Lab<h2 id="isPasted">How Emo connects with you</h2>Emo is a human-like head with a face that is equipped with 26 actuators that enable a broad range of nuanced facial expressions. The head is covered with a soft silicone skin with a magnetic attachment system, allowing for easy customization and quick maintenance. For more lifelike interactions, the researchers integrated high-resolution cameras within the pupil of each eye, enabling Emo to make eye contact, crucial for nonverbal communication.The team developed two AI models: one that predicts human facial expressions by analyzing subtle changes in the target face and another that generates motor commands using the corresponding facial expressions.To train the robot how to make facial expressions, the researchers put Emo in front of the camera and let it do random movements. After a few hours, the robot learned the relationship between their facial expressions and the motor commands -- much the way humans practice facial expressions by looking in the mirror. This is what the team calls “self modeling” – similar to our human ability to imagine what we look like when we make certain expressions.Then the team ran videos of human facial expressions for Emo to observe them frame by frame. After training, which lasts a few hours, Emo could predict people’s facial expressions by observing tiny changes in their faces as they begin to form an intent to smile.“I think predicting human facial expressions accurately is a revolution in HRI. Traditionally, robots have not been designed to consider humans' expressions during interactions. Now, the robot can integrate human facial expressions as feedback,” said the study’s lead author Yuhang Hu, who is a PhD student at Columbia Engineering in Lipson’s lab. “When a robot makes co-expressions with people in real-time, it not only improves the interaction quality but also helps in building trust between humans and robots. In the future, when interacting with a robot, it will observe and interpret your facial expressions, just like a real person.”<iframe width="640" height="360" src="https://www.youtube.com/embed/pWTTzR_wXuQ?&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" data-gtm-yt-inspected-9="true" id="556492795" title="Human-Robot Facial Co-expression">&nbsp;</iframe>Go inside the Creative Machines Lab to watch Emo's facial co-expression. Video Credit: Yuhang Hu, Columbia Engineering<h2 id="isPasted">What’s next</h2>The researchers are now working to integrate verbal communication, using a large language model like ChatGPT into Emo. As robots become more capable of behaving like humans, Lipson is well aware of the ethical considerations associated with this new technology.“Although this capability heralds a plethora of positive applications, ranging from home assistants to educational aids, it is incumbent upon developers and users to exercise prudence and ethical considerations,” says Lipson, James and Sally Scapa Professor of Innovation in the Department of <a href="https://www.me.columbia.edu/" rel="nofollow" target="_blank">Mechanical Engineering</a> at Columbia Engineering, co-director of the <a href="https://make.columbia.edu/" rel="nofollow" target="_blank">Makerspace</a> at Columbia, and a member of the <a href="https://datascience.columbia.edu/" rel="nofollow" target="_blank">Data Science Institute</a>. “But it’s also very exciting -- by advancing robots that can interpret and mimic human expressions accurately, we're moving closer to a future where robots can seamlessly integrate into our daily lives, offering companionship, assistance, and even empathy. Imagine a world where interacting with a robot feels as natural and comfortable as talking to a friend.”&nbsp;</section>

The study's lead author, Yuhang Hu, a PhD student at Columbia Engineering in Hod Lipson’s lab. Credit: John Abbott/Columbia Engineering

Columbia engineers build Emo, a silicon-clad robotic face that makes eye contact and uses two AI models to anticipate and replicate a person’s smile before the person actually smiles 

Robot, can you say 'Cheese'?

<a href="https://r2-labs.io/" target="_blank">R2 Labs</a>’ goal is to make modern automation equipment systems more accessible by providing today’s software engineers with a tool that makes interaction and control easier, regardless of the specific application. Successful projects – such as the development of an AI-powered agricultural robot for Padma AgRobotics with Arduino products – encouraged the team to pursue a combination of versatility and customization, making the range of applications they can tackle almost limitless.  Clear Requirements to Lower BarriersWanting to create a “general-purpose controller”, R2 Labs knew it had to be programmable with modern languages, extensible, and have the computational power to manage motor control, I/O control, machine vision, and more. They decided to keep exploring with Arduino Pro hardware to <iframe id="67e601e88697e927ea2b0551" width="250" class="specs-iframe" height="440" src="https://wevolver.com/iframe/specs/portenta-machine-control?iframe=true" frameborder="0" scrolling="no"></iframe> find an innovative solution that would be open-source, extensible without vendor lock-in, and capable of providing a host of common functionalities customers need in almost any autonomy application.With these requirements in mind and previous positive experience using Arduino microcontrollers, R2 Labs decided to develop their project with the <a href="https://www.arduino.cc/pro/portenta-machine-control" target="_blank">Portenta Machine Control</a>. This allowed them to cut down on time-to-market and quickly integrate robust, industrial-grade features – from the dual-core processor that allows for the segmentation of critical sections, to CAN bus support. Unlocking Opportunities for All, with Open SourceInstead of spending huge internal resources on developing their own control unit or going through complex sales processes, by partnering with Arduino R2 Labs immediately gained access to support, documentation, and high-quality products tested by a community of millions.“We achieved exactly what we were aiming for: a solution well-suited for both modern robotics and industrial automation applications. Thanks to the Portenta Machine Control’s advanced features and Arduino’s prompt support, we can now enable any software engineer to tackle a broad range of applications and solve challenges that are common to most control systems,” says CEO Roby Lynn, who co-founded R2 Labs with Sulisay Phonekeo and Rebecca Peterson.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzExMjY3ODczNjAzLWNvbnRyb2xsZXIgMS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width:100%px" class="fr-fic fr-dib" />Meet RAC: A Paradigm Shift in Control SystemsR2 Labs’ vision led to the launch of the RAC, a fully integrated ROS 2-native autonomy control solution that supports multi-axis motion control and is able to easily interface with a wide range of sensors and actuators. The device simplifies development with an array of digital and analog I/O, advanced vision processing, and standard connectivity (HDMI, Ethernet, USB). It allows users to effortlessly program with Python® and C++ and control/manage the project with the included interactive web HMI. All in all, the RAC is a game-changing product for control and monitoring – both in robotics and industrial automation applications. The Arduino Portenta Machine Control is the brain of this brilliant solution to make Industry 4.0 and 5.0 accessible to software engineers, ready to tackle any specific application they may need.Creating New Solutions for Modern Robotics and ControlWith a clear vision of the challenges in their field, R2 Labs is committed to creating modern robotics and control system solutions that champion flexibility and ease of use.Pairing professional expertise with outside-the-box thinking, the company is now ready to tackle bigger deployments, new customers, and different industries. Choosing open source is key to this growth path, allowing them to expand their portfolio by focusing on the work they do without constraints.

R2 Labs: democratizing robotics and industrial automation with Arduino

Manufacturing, agriculture, healthcare, and more: each industry needs specific robots and specific solutions to run and control them. But “Robotics for the Real World” provider R2 Labs, based in the United States, has set out to change that.

R2 Labs Presents RAC: An Industry-Agnostic Controller

If a robot traveling to a destination has just two possible paths, it needs only to compare the routes’ travel time and probability of success. But if the robot is traversing a complex environment with many possible paths, choosing the best route amid so much uncertainty can quickly become an intractable problem.MIT researchers developed a method that could help this robot efficiently reason about the best routes to its destination. They created an algorithm for constructing roadmaps of an uncertain environment that balances the tradeoff between roadmap quality and computational efficiency, enabling the robot to quickly find a traversable route that minimizes travel time.The algorithm starts with paths that are certain to be safe and automatically finds shortcuts the robot could take to reduce the overall travel time. In simulated experiments, the researchers found that their algorithm can achieve a better balance between planning performance and efficiency in comparison to other baselines, which prioritize one or the other.This algorithm could have applications in areas like exploration, perhaps by helping a robot plan the best way to travel to the edge of a distant crater across the uneven surface of Mars. It could also aid a search-and-rescue drone in finding the quickest route to someone stranded on a remote mountainside.“It is unrealistic, especially in very large outdoor environments, that you would know exactly where you can and can’t traverse. But if we have just a little bit of information about our environment, we can use that to build a high-quality roadmap,” says Yasmin Veys, an electrical engineering and computer science (EECS) graduate student and lead author of a&nbsp;<a href="https://groups.csail.mit.edu/rrg/papers/veys_icra_24.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">paper on this technique</a>.Veys wrote the paper with Martina Stadler Kurtz, a graduate student in the MIT Department of Aeronautics and Astronautics, and senior author Nicholas Roy, an MIT professor of aeronautics and astronautics and a member of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). The research will be presented at the International Conference on Robotics and Automation.<h2>Generating graphs</h2>To study motion planning, researchers often think about a robot’s environment like a graph, where a series of “edges,” or line segments, represent possible paths between a starting point and a goal.Veys and her collaborators used a graph representation called the Canadian Traveler’s Problem (CTP), which draws its name from frustrated Canadian motorists who must turn back and find a new route when the road ahead is blocked by snow.In a CTP, each edge of the graph has a weight associated with it, which represents how long that path will take to traverse, and a probability of how likely it is to be traversable. The goal in a CTP is to minimize travel time to the destination.The researchers focused on how to automatically generate a CTP graph that effectively represents an uncertain environment.“If we are navigating in an environment, it is possible that we have some information, so we are not just going in blind. While it isn’t a detailed navigation plan, it gives us a sense of what we are working with. The crux of this work is trying to capture that within the CTP graph,” adds Kurtz.Their algorithm assumes this partial information — perhaps a satellite image — can be divided into specific areas (a lake might be one area, an open field another, etc.)Each area has a probability that the robot can travel across it. For instance, it is more likely a nonaquatic robot can drive across a field than through a lake, so the probability for a field would be higher.The algorithm uses this information to build an initial graph through open space, mapping out a conservative path that is slow but definitely traversable. Then it uses a metric the team developed to determine which edges, or shortcut paths through uncertain regions, should be added to the graph to cut down on the overall travel time.<h2>Selecting shortcuts</h2>By only selecting shortcuts that are likely to be traversable, the algorithm keeps the planning process from becoming needlessly complicated.“The quality of the motion plan is dependent on the quality of graph. If that graph doesn’t have good paths in it, then the algorithm can’t give you a good plan,” Veys explains.After testing the algorithm in more than 100 simulated experiments with increasingly complex environments, the researchers found that it could consistently outperform baseline methods that don’t consider probabilities. They also tested it using an aerial campus map of MIT to show that it could be effective in real-world, urban environments.In the future, they want to enhance the algorithm so it can work in more than two dimensions, which could enable its use for complicated robotic manipulation problems. They are also interested in studying the mismatch between CTP graphs and the real-world environments those graphs represent.“Robots that operate in the real world are plagued by uncertainty, whether in the available sensor data, prior knowledge about the environment, or about how other agents will behave. Unfortunately, dealing with these uncertainties incurs a high computational cost,” says Seth Hutchinson, professor and KUKA Chair for Robotics in the School of Interactive Computing at Georgia Tech, who was not involved with this research. “This work addresses these issues by proposing a clever approximation scheme that can be used to efficiently compute uncertainty-tolerant plans.”

MIT researchers developed an algorithm that can automatically select the best shortcuts for a robot to take on its way to a destination that will reduce the overall travel time while limiting the likelihood that the robot will meet an impassable obstacle. Image: Jose-Luis Olivares, MIT; iStock

A new algorithm reduces travel time by identifying shortcuts a robot could take on the way to its destination.

Researchers help robots navigate efficiently in uncertain environments

<h3 id="isPasted">Who are we?&nbsp;</h3>Team Polar is an Eindhoven-based student team filled with students from different disciplines. Our mission is to facilitate and improve the research going on in Antarctica. We aim to achieve this by building an autonomous, affordable, and electric rover. The reason we go with Antarctica is that the current research going on is led by human-driven vehicles using fossil fuels. Building an autonomous vehicle means it is safer and less expensive since there is no&nbsp;driver to pay.&nbsp;&nbsp;<h3>The Ice Cube&nbsp;</h3>After working for more than a year, Team Polar came up with the&nbsp;Ice Cube. Ice Cube was just the first step towards our vision of building a sustainable and affordable research environment in Antarctica. Ice Cube has 2 square meters of&nbsp;solar panels&nbsp;which helps Ice Cube to go up to 65 kilometers (about half the distance from Washington, D.C. to New York City) per day. With its 28' wheels, the Ice Cube weighs around 350 kilograms (about 771.62 lb).&nbsp;&nbsp;<h3>Progress on Ice Cube&nbsp;</h3>Team Polar is&nbsp;in&nbsp;the second prototype's design process, and the Ice Cube is only used for testing.&nbsp;Since the Ice Cube was built in&nbsp;a short time, some features were missing, such as autonomy.&nbsp;Our software team is using&nbsp;the Ice Cube&nbsp;to test their software and the new sensors&nbsp;that&nbsp;we are aiming to implement on our second prototype.&nbsp;While these tests are&nbsp;being made, new structural components are also being tested. Such as gas springs, hinges, handles, etc.&nbsp;Meanwhile, we are developing a force balance that helps&nbsp;determine&nbsp;possible ranges&nbsp;of mass of the next vehicle. We&nbsp;are also looking into the location of research, which will help&nbsp;determine&nbsp;the&nbsp;driving range and strategy for the energy balance (which will&nbsp;probably be&nbsp;made next year).&nbsp;<h3>Processing REMA Image&nbsp;</h3>Under the “Autonomous Department”, our engineers successfully developed and implemented code to process &nbsp; Reference Elevation Model of Antarctica (REMA) images.&nbsp;REMA provides the first, high-resolution (2-meter) terrain map of&nbsp;nearly the&nbsp;entire continent. Since each REMA grid point has a timestamp, any past or future point observation of elevation provides a measurement of elevation change.&nbsp;REMA may provide corrections for a wide range of remote sensing processing activities, such as image orthorectification, and interferometry, and provide constraints for geodynamic and ice flow modeling, mapping of grounding lines, and surface processes. REMA also provides a powerful new resource for field logistics planning.&nbsp;This is an important step for the autonomy of the Ice Cube. The goal is to calculate the altitudes in Antarctica to find out the clearest and most optimized path for the rover.&nbsp;&nbsp;The next step for these images is to transform the processed REMA images into a format that is compatible with our A* algorithm.&nbsp;&nbsp;<h3>A* Algorithm&nbsp;</h3>The A* search algorithm is one of the best techniques used in path-finding and graph traversals. The path we derived will be the shortest of all the other options or the most efficient by all parameters considered. &nbsp;A* works by making a lowest-cost path&nbsp;<a href="https://brilliant.org/wiki/trees-basic/" target="_blank" rel="noreferrer noopener">tree</a>&nbsp;from the start node to the target node. What makes A* different and better for many searches is that for each node, A* uses a function f(n) that gives an estimate of the total cost of a path using that node.The environment of Antarctica and the conditions are the hardest part of our project. We need to come up with innovative and technical solutions. Understanding the altitudes and general geography of Antarctica is crucial.&nbsp;&nbsp;Furthermore, the design of the rover plays a huge role in our path to success. Our Dynamics Sub team is trying to come up with new ideas for the newest version of the Ice Cube.&nbsp;&nbsp;<h3>Suspension&nbsp;</h3>Unlike the Ice Cube, the new vehicle will use a suspension system. The test in Norway in 2022 showed that; the main purpose of having a suspension is important for keeping all wheels on the ground, for improved traction. Also, it will dampen vibrations to keep the vehicles' most important components as stable as possible.&nbsp;&nbsp;The suspension system the new vehicle will be using is a so-called double wishbone suspension. For this suspension, every wheel is connected to two-wishbone-shaped arms. Every wheel is independently controlled.&nbsp;&nbsp;The main advantage of the double-wishbone configuration is its good ratio of kinematic versatility vs. complexity, it being slightly more complex than other systems like the McPherson strut and slightly simpler than others like multi-link suspensions.&nbsp;&nbsp;<h3>Ground pressure&nbsp;</h3>Getting the right ground pressure is extremely crucial for the environment the vehicle will operate. A ground pressure that is too high will cause the vehicle to get stuck in the snow or even fall into crevasses. To prevent this, the ground pressure that will be aimed for in the new vehicle is 0.1 bar. This value is also used by Artic Trucks or other snow vehicles such as the tracked vehicles made by Mattracks. In comparison, the average human exerts a pressure of 0.17 bar on the ground.&nbsp;The low ground pressure is achieved by maximizing the contact area using large and not fully inflated&nbsp;tires.&nbsp;Next Steps?&nbsp;

Facilitating the human-led and autonomous research in the Antarctic continent.

Pioneering Autonomous Antarctic Research

A pick and place robot in an industrial setup

robotics

Latest Posts