<section id="isPasted">In order to deploy mobile robots, self-driving cars, or drones into the real world, they need to be able to observe and understand the world around them, just like humans do. PhD candidate at TU/e Daan de Geus developed algorithms for automatic image recognition that are faster and more accurate than existing models. Last Wednesday, he obtained his PhD (with honors) at the Department of Electrical Engineering.</section><section tabindex="-1">De Geus thumbs through his dissertation and shows us a photo of a street, featuring different objects such as people, vehicles, traffic posts, and traffic lights (see image below). “Mobile robots and self-driving cars need to know what’s happening around them,” he says.Among other things, they need to be able to recognize and localize objects, so they can take these into account. “This allows them to move around or toward a certain object, and maybe pick it up to carry out a task.”<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637661762-csm_frankfurt_000001_030669_images_0a92c1e725.jpg" style="width: 100%px;" class="fr-fic fr-dib">Traffic in Frankfurt. Image: Daan de GeusTo make robots aware of their environment, different computer vision techniques are used. It concerns an area of research that revolves around automatic extraction of relevant information from camera footage. “Simply put, we try to make models that can distill as much information from a photo as possible,” the PhD candidate explains.“The goal of computer vision is to make a system that mimics our own visual system, allowing computers to see in the same way humans do and, as a result, interact properly with the world around them.”His research focuses on improving image recognition techniques in the area of scene understanding. This is a small, but crucial part of computer vision. “Its goal is to recognize different objects and regions in an image and to give them a semantic label, such as ‘streetlight’, ‘road’, ‘car’, or ‘person’,” he explains.In other words, the objects are given a significance that is clear to humans.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637694452-csm_scene_understanding_example_189e7cc585.jpg" style="width: 100%px;" class="fr-fic fr-dib">An example of scene understanding. Objects (person, traffic light, car) and image regions (the road) are automatically identified, color-coded, and semantically labeled. Image: Daan de Geus<h2 id="isPasted">Accuracy and efficiency</h2>For automatic image analyses, neural networks are used – systems that learn to carry out a certain task by receiving training involving a large amount of data. By training these neural networks in a focused manner, you end up with different models that specialize in specific tasks, such as identifying all cars in an image.In the first part of his dissertation, De Geus looked at how you can improve the accuracy and efficiency of those models. “Improving one aspect is often at the expense of another. To get more accurate results, existing methods tend to lose some of their efficiency, and vice versa,” he explains.“Which makes sense, because greater accuracy often demands more computing power, which directly impacts efficiency.” The big question, therefore, is: how can you improve these aspects without having to compromise?He came up with several solutions to this conundrum. “Efficiency is important for two reasons. You want the algorithm to use as little energy as possible and to make a prediction as quickly as possible,” he says. Speed is of the essence in self-driving vehicles, as cars must be able to respond to situations that arise in a timely manner.“If the calculation takes a second, it may already be too late to take action.”Using a process known as model unification, he combined two models to create a more efficient one. “Some tasks focus on the objects in the foreground, such as cars and people; others on ‘background regions’ such as vegetation and the sky. These tasks are performed by two different neural network modules, as each module specializes in a different task,” he explains.“Using two network modules isn’t very efficient, because you have to run them parallel to each other.” He found out that you can supply extra information to the network module processing the background information, allowing it to also identify foreground objects.“As a result, the module for foreground objects is no longer necessary, which greatly enhances efficiency. This makes this model twice as fast as its precursors, while its accuracy is comparable.”<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637727049-csm_image_with_patches_0ce2b38ff7.jpg" style="width: 100%px;" class="fr-fic fr-dib">Image with image regions. Image: Daan de GeusAnother way of improving efficiency is based on the observation that many regions in an image are very similar. For instance, the sky generally takes up a large part of any picture you take outside. “In spite of the fact that a lot of information is similar, neural networks process each image region separately, which is very inefficient,” says De Geus.The entire image is divided up into patches consisting of pixels (see image below). Normally, these would be labeled and assessed individually, but the PhD candidate developed a method for clustering patches with comparable information, reducing the total number of patches and, by extension, requiring less computing power.“This allows us to improve speed by as much as 110%, without taking away from the accuracy.”Incidentally, this method for grouping similar image regions is widely applicable to many different models and a great many applications other than self-driving cars and mobile robots. For example, you could use these algorithms to segment medical images. “Pretty much in any situation where you need to automatically analyze images.”<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637752641-csm_token_sharing_diagram_c977af3012.jpg" style="width: 100%px;" class="fr-fic fr-dib">To improve efficiency, semantically comparable patches can be clustered. Image: Daan de Geus<h3 id="isPasted">Multiple abstraction levels</h3>In the second part of his dissertation, he focused on what he calls multiple abstraction levels. “Existing algorithms either focus on entire objects, such as cars, or on their components, such as car tires or the license plate,” he explains.His goals was to develop an algorithm that can simultaneously understand an image at multiple abstraction levels. “This will allow a mobile robot to observe both the car and its components, as well as other objects and the background, all at the same time, which gives it a comprehensive picture of the surroundings,” says De Geus.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637778377-csm_frankfurt_000001_030669_panoptic_5abb4ba438.jpg" style="width: 100%px;" class="fr-fic fr-dib">Automatic recognition of objects and image regions. Image: Daan de GeusYou can have both algorithms carry out their work separately and merge the results afterwards, but this is cumbersome. And it can also lead to conflicts between the two calculations. Instead, he developed a new algorithm that can identify objects and components all at once.“That’s not only more accurate, but also more efficient.” What’s more, this improved model is widely applicable and has many advantages. “It means, for instance, that a robot isn’t just able to recognize a door, but also the door handle, and to understand that the latter is part of the door. Which, in turn, allows it to open the door,” he says to illustrate.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1714637801563-csm_frankfurt_000001_030669_pps_3b32a5d47d.jpg" style="width: 100%px;" class="fr-fic fr-dib">A more detailed segmentation, where components of objects are also identified. Image: Daan de GeusTo be able to use self-driving cares or mobile robots in practice, there’s a lot left to do still. “Image recognition is just a tiny part of the puzzle,” he admits.&nbsp;And there are plenty of remaining challenges in the area. For one thing, models could be developed that can recognize more objects at once and that operate even faster and more accurately.The generalization of the model could also be improved, so it also produces good results when the data are different from the data sets with which the network was trained, allowing it to perform better in real-world scenarios.But at least his dissertation constitutes a step forward in making the system more capable, accurate, and efficient.<hr>Source: <a href="https://www.cursor.tue.nl/en/news/2024/april/week-3/home-stretch-teaching-robots-to-see-better/" target="_blank" rel="noreferrer">Cursor/Martina Silbrníková</a>Daan de Geusdefended his thesis“<a href="https://research.tue.nl/en/publications/characterization-of-abdominal-aortic-aneurysms-using-time-resolve" target="_blank" rel="noreferrer">Advances in Scene Understanding - Towards Efficient Image Segmentation at Multiple Abstraction Levels</a>” at the Department of Electrical Engineering on April 17th, 2024.Supervisors: Gijs Dubbelman en Peter de With</section>

In his doctoral research, Daan de Geus worked on advanced image processing methods that allow robots and cars to better recognize what they see around them.

Teaching robots to see better

<h1 id="isPasted">Wired for Autonomy: Confronting PCBA Complexities in Mobile Robotics</h1><section>The field of untethered robotics is booming, and across industries, autonomous robots are rapidly assuming responsibility for an increasing number of tasks. In their expansion into increasingly diverse industries, these robots place additional demands on their internal workings, specifically the PCBAs that help them function.However, developing PCBAs for autonomous robot systems presents several unique challenges that electrical engineers must overcome to succeed. We take a deep dive into these challenges by exploring design considerations beyond those associated with conventional PCBAs.<h3>Beyond the Basics: Design Considerations for Autonomous Robots</h3>While core electrical principles remain a top priority, autonomous robotics introduces additional complexity to PCBA design that electrical engineers must consider from day one. To function properly, these machines must anticipate and plan for the unexpected in harsh, changing conditions.Intuitive Machines’ Odysseus moon lander recently brought this to light, when the private spacecraft <a href="https://www.reuters.com/technology/space/moon-lander-described-alive-well-day-after-white-knuckle-lunar-touchdown-2024-02-23/" target="_blank">landed on the moon’s surface</a>. As much as the sideways landing attracted media attention, few reports focused on last-minute troubleshooting that kept the mission afloat, a testament to the quick-thinking nature of the engineers involved.Here are some of the important factors to consider when designing PCBAs for untethered robotics:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1713979758192-1713979758192.png" alt="Autonomous robot design considerations" class="fr-fic fr-dii"><ul><li>PCBAs Must Prioritize Efficiency: Untethered robots almost entirely rely on batteries, so PCBAs must focus on efficiency. The key to this is meticulous component selection, such as using low-power microcontrollers and efficient voltage regulators, as well as excellent circuit design that minimizes standby currents. Using clock gating also maximizes battery life and reduces heat generation.</li><li>Maintain Signal Integrity Amid Noise: Robots operate in dynamic environments with <a href="https://www.macrofab.com/blog/bypass-caps-decouple-your-way-to-cleaner-power/" target="_blank">potential electrical noise</a> from motors, sensors, and external sources. EMI can wreak havoc on robotic sensors, causing glitches, calibration issues, or even complete sensor failure. Consider layout strategies in detail to cut crosstalk and ground loops and maintain clear signal transmission.</li><li>Build for Endurance: Many robots are subjected to extreme temperatures, temperature fluctuations, vibrations, and shocks. Use ruggedized PCBA boards that have components with adequate vibration and temperature ratings. To prevent overheating, soldering must be properly performed to handle thermal expansion and contraction, mechanical fatigue, and dust and moisture infiltration. Enclosures need to protect against dust and moisture egress.</li><li>Size Matters: Robots must be mobile, so PCBAs must also be compact and lightweight to minimize robot weight. Choose wisely when choosing mechanisms within your robot, like vacuum track-based models or electromagnetic ones. They may increase the mass of your robot and reduce maneuverability. High-density interconnect (HDI) techniques and minimizing wasted space become crucial.</li><li>Don’t Compromise Reliability: Autonomous robots, operating alone, demand ultra-reliable PCBAs to minimize failure. Filtering tackles this by reducing sensor noise for cleaner data, smoothing data for fewer errors, extracting key features for better navigation, and even lowering processing load for faster decision-making. Redundancy and fail-safe features further enhance reliability.</li><li>Play by the Rules: Robots must comply with <a href="https://www.macrofab.com/blog/safeguarding-pcba-design-from-electromagnetic-interference/" target="_blank">Electromagnetic Compatibility (EMC) regulations</a> to ensure proper operation and avoid interfering with other electronic devices. Shielding techniques and filtering components become necessary.</li><li>Ensure Maintainability: After assembling, it’s crucial to diagnose faults and perform maintenance. Make sure test points are conveniently accessible after the final assembly. Consider implementing Built-in Test (BIT) features on the PCBA for self-diagnostic features or options for wireless troubleshooting.</li></ul><h2> </h2><h3>The Unexpected Factors: When Biology Interferes</h3>Biological influences are often overlooked when designing PCBAs for autonomous robotics but are an important factor. Autonomous robotics may work in many different environments, encountering biological challenges that can undermine even the most robust and reliable designs.<h3>Biofouling</h3>Biofouling, or the accumulation of microorganisms on surfaces, happens most frequently in aquatic environments. However, this issue can also occur within humid industrial settings or food processing facilities. Biofouling causes issues in many ways including:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1713979758511-1713979758511.png" alt="Biofouling" class="fr-fic fr-dii"><ul><li>Reduced Performance: Fouling on sensors, thrusters, and hulls can decrease efficiency and accuracy. As a result, sensors become less sensitive, propellers drag more, and overall power consumption increases. Special coatings applied to surfaces can deter organism attachment.</li><li>Problems with Navigation: Fouling on navigational equipment leads to positioning and localization errors, which make it difficult for the robot to map its surroundings, keep its trajectory, and reach its destination.</li><li>Maintenance Issues: Regular cleaning to remove biofouling is essential, particularly in remote locations. As a result, downtime occurs and reduces operational efficiency. Prevent biofouling with brushes or wipers, as well as scheduled cleaning protocols.</li><li>Damage and Disruption: Biofouling can cause physical damage by promoting barnacle growth and corroding structures. Choosing materials that discourage organism growth is a passive defense, and monitoring systems can detect biofouling early and trigger automatic cleaning.</li></ul>Especially within industrial and food processing industries, biofouling can create a surprising but challenging issue for logistics robotics in order fulfillment, for example, or other autonomous vehicles. Make sure to consider this possibility when designing for specific applications.<h3> </h3><h3>Biological Challenges Across Environments</h3>While biofouling dominates aquatic environments, other biological factors impact robots in other settings:<ul><li>On Land: Dust, dirt, and debris can accumulate on sensors and cameras in terrestrial robots, hindering performance. Agricultural robots may encounter challenges with mud and plant debris.</li><li>Airborne: Airborne robots face issues with dust, pollen, insects, and other airborne particles that can increase drag, reduce lift, and affect sensor accuracy.</li></ul>To address animal-related challenges, EEs can employ design strategies like:1. Physical Resilence:&nbsp;<ul><li>Challenge: Animals may chew on cables or antennas, causing malfunctions.</li><li>Solution: Employ ruggedized components, reinforced substrates, and protective enclosures to enhance PCBA durability against physical damage from animal interactions. Additionally, utilize encapsulation and conformal coatings to safeguard critical components from moisture, dust, and possible damage by animals.</li></ul>2. Sensor Integrity:<ul><li>Challenge: Animals brushing against sensors can distort sensor inputs, leading to navigation errors.</li><li>Solution: Design sensors with robust shielding, noise filtering capabilities, and redundancy features to ensure reliable operation and accurate data despite potential interference from animals. Develop strategies for preventing animals from brushing against sensors to keep distortions and navigational errors from happening. For example, anti-fouling paints or cages around the robot could prevent fouling, or sensors might be placed where animals cannot access them.</li></ul>3. Mobility Optimization:<ul><li>Challenge: Animals blocking pathways or obstructing movement can impede the robot’s forward progress.</li><li>Solution: Develop strategies to address mobility constraints caused by animals blocking pathways or obstructing movement, ensuring that robots can navigate effectively and complete their objectives. This could include low-power LEDs or subtle sounds that encourage animals to move away. Optimize power management systems to maximize operational autonomy and extend battery life in resource-constrained environments where robots may interact with animals.</li></ul><h3>Security: The Next Level in AMR PCBA Design</h3><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1713979758575-1713979758575.png" alt="AMR PCBA security" class="fr-fic fr-dii">AMR PCBA securityPCB design traditionally focuses on protecting against electrical malfunctions and physical damage. However, for AMRs (autonomous mobile robots) connected to the internet, cybersecurity emerges as a key concern. Hacking hazards present significant security risks. A compromised robot can open the door to major security breaches. Thus, incorporating encryption and secure boot mechanisms in PCBA design is essential to block unauthorized access.Hardware Trojan Horses also pose a silent yet profound threat. These sneaky modifications, made during manufacturing, can go almost unnoticed. To counteract this, it’s critical to partner with trustworthy suppliers and employ hardware authentication methods.Consider working with a partner with a connected technology platform that keeps you in touch with your manufacturing process from start to finish. Moreover, work with a partner that employs robust security practices and can provide proof of such, such as ISO and ITAR certifications, or membership in the ERAI, an organization established to <a href="https://www.macrofab.com/blog/electronics-industry-counterfeit-parts-problem/" target="_blank">combat counterfeit electronics</a> and high-risk components in the electronics industry. MacroFab holds these standards, and it is a member of ERAI.Another challenge is the theft of PCBAs after robot deployment, especially those containing valuable intellectual property. Consider using tamper-evident seals or protective enclosures if you will be installing robotics in an unsupervised area.Want to read more about designing PCBAs for robotics? Read <a href="https://www.macrofab.com/documents/reshaping-robotics-how-pcba-advances-drive-tomorrows-autonomous-solutions/" target="_blank">Reshaping Robotics: How PCBA Advances Drive Tomorrow's Autonomous Soutions</a> now.<h2> </h2><h3>Conclusion: Embracing the Challenge</h3>The realm of PCBA design for autonomous robots transcends the traditional electrical engineer’s domain. While electrical fundamentals remain the cornerstone, navigating the complexities of this field necessitates venturing beyond the confines of the schematic. It’s a world where understanding environmental stresses, mitigating biological influences, and safeguarding against security vulnerabilities are equally critical.By embracing these unique challenges and fostering a spirit of relentless innovation, electrical engineers will become the architects of a new era in robotics. The future holds immense potential for these autonomous machines, with robust, adaptable PCBAs serving as their foundation.Need PCBAs for your robotics project?&nbsp;</section><a href="https://factory.macrofab.com/quick_quote?mbsy_source=c2dfbfd3-8c8b-4098-87b7-c7e0e06119ec&campaignid=62990&mbsy=6DBV3m" target="_blank">GET AN INSTANT QUOTE NOW</a><section><h5> </h5></section>

Autonomous robotics must anticipate and plan for the unexpected, often in harsh, changing environments. We take a deep dive into these challenges by exploring design considerations beyond those associated with conventional PCBAs.

Wired for Autonomy: Confronting PCBA Complexities in Mobile Robotics

What could small robots on earth have to do with exploration on the moon?Quite a lot, as it turns out. Professors and engineering students at Polytechnique Montréal have been busy writing algorithms and running experiments with robots and drones with one goal in mind: To enable them to explore unfamiliar and even hostile surroundings far beyond the reach of GPS or other forms of precision location technology.“What we want to do is to explore environments including caves and surfaces on other planets or satellites using robotics,” explains Dr. Giovanni Beltrame (Ph.D.), a full professor at Polytechnique’s Departments of Computer Engineering and Software Engineering.Before we get to the how, let’s address the why.“Caves and lava tubes can be ideal places for settlement: They can be&nbsp;sealed and provide radiation shielding. There’s also a chance of finding&nbsp;water ice in them,” says Dr. Beltrame.Of course, it’s also less risky – and less expensive –&nbsp;to send robots to other planets and moons rather than human beings. They don’t require life support, don’t get tired (with the exception of having to recharge), and they can gather and process data quickly.Just think of all the data that’s been acquired on Mars by the twin Rovers and the Mars helicopter.Below: A selfie taken by NASA’s Perseverance rover November 1, 2023, during the the 960th Martian day of its mission. The rover was built with a focus on astrobiology, searching for signs of ancient microbial life on the red planet. Image courtesy of NASA.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYxNzQ0OTYwLVBJQTI2MjAyLWpwZy53ZWJwIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="NASA's Perseverance"><h3 id="isPasted">Prepare on Earth, Deploy in Space</h3>It’s a pretty ambitious vision. But for Beltrame and his team, it’s also very real. And it requires a lot of work and research here on earth.“So to get there (space) and do this with&nbsp;multiple robots, we’ve developed all sorts of technologies –&nbsp;navigation, perception, communication, coordination between the robots, and human-robot interfaces,” he says.“We’re doing all these things,&nbsp;because our goal is to use a swarm of robots to do planetary exploration. There’s more, but that’s it in a nutshell.”When you go to the moon, there’s no equivalent of GPS. And environments like caves can be really tricky – both in terms of robots understanding where they are, and also communicating with other robots beyond line of sight.With the right technologies and algorithms, that communication is possible. And much of Beltrame’s research has involved testing this on earth. In particular, he’s focusing on how groups of robots could take on such tasks collaboratively.“So our primary activities focus on swarm robotics,” he says.Generally that starts with simulation models. But there are limits to simulations – and real-world testing is a big part of what’s going on at Polytechnique.“So we do have this deployment philosophy that we try our technologies in simulation, but then we want to go to deploying robots. You can have the best simulation in the world, but there’s still a reality gap and it’s very extremely important to try things on the real robots,” he says.“We have a saying in the lab, which is: ‘Everything works in simulation’.&nbsp;You can always make your algorithm work in simulation, and then you get out in the field and things go wrong. So&nbsp;one thing we do in the lab is we always do the full stack. That’s why we need to have real robots.&nbsp;And we don’t only do experiments with real robots in the lab, we do them in the field.” <h3>MIST</h3>The lab he’s referring to is known as Polytechnique’s MIST, which stands for Making Innovative Space Technology. Dr. Beltrame is the director of the lab, which focuses on computer engineering targeted towards space technologies. In addition to the researchers, the lab is home to a *lot* of robots. There are big ones, small ones, wheeled ones, flying ones (drones) – literally “hundreds” of robots at the lab.But as Dr. Beltrame emphasised, proving that something will truly work requires testing in environments that are similar to what might be found on the moon or elsewhere. Locations where he’s carried out fieldwork include:<ul><li>Lava Beds National Monument in California (with <a href="https://www.jpl.nasa.gov/" target="_blank">NASA&nbsp;</a><a href="https://www.jpl.nasa.gov/" target="_blank">JPL</a>)</li><li>The Kentucky mega-cave with the <a href="https://costar.jpl.nasa.gov/" target="_blank">CoSTAR</a> team</li><li>Tequixtepec&nbsp;in Mexico with SpéléoQuébec</li></ul>Just check out the images below of field work, courtesy of Dr. Beltrame:<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYyNDU0NzUyLUlNRy0yMDIzMDMyMy1XQTAwMDAuanBnLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="Tight Space Exploration">Tight Spaces<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYyNDYyOTQyLWx1bmFyc2V0dGluZy1qcGcud2VicCIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib">ESA Photo<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYyNDg0ODU3LWltYWdlLXNjYWxlZC53ZWJwIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="Cave Drone">Cave Drone<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYyNTAzNzAwLWRyb25ldGVhbS1qcGcud2VicCIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib" alt="ESA Team">ESA Photo<h3 id="isPasted">The InDro Connection&nbsp;</h3>Some of the robots used in the MIST lab – and perhaps eventually on the moon – arrived via InDro Robotics, a North American distributor for AgileX. In fact, Polytechnique has purchased a number of AgileX products, including platforms that InDro has modified to help speed the R&amp;D process. These include:<ul><li>24 LIMOs and simulation table</li><li>AgileX Scout Mini</li><li>AgileX Scout 2.0</li><li>Two AgileX Bunker Mini platforms, with custom builds by InDro</li></ul>We’ve <a href="https://indrorobotics.ca/new-limo-pro-ros2-models-bring-advanced-abilities-to-rd/" target="_blank">written about the LIMO before</a> – a small, affordable and versatile robot capable of perceiving its environment and even Simultaneous Localization and Mapping out of the box. It’s also an ideal size, particuarly when doing multi-agent/swarm robotics, for use in the lab. (You’d run out of space pretty fast with something much larger).“The LIMOs are a very good platform for Simultaneous Localization and Mapping &nbsp;– and perception in general,” says Beltrame.He says they’re a good choice “because they have a 3D camera, they’re lighter, agile, and are sufficiently low in cost. So we can use them in large numbers.&nbsp;Another good thing about the LIMOs is that once you have a lot of similar robots that are reasonably agile, you can actually make a full deployment of software (across all robots).”That makes them an ideal platform for multi-agent research and development.“For example, we developed this tool called Swarm SLAM where many robots collaborate to have a better perception of the environment. We’re currently testing it with the full fleet of LIMOs. That’s&nbsp;something we would have believed impossible with larger robots for logistical reasons.”Though the focus is firmly on space, the Polytechnique Montréal research has applications on earth. Swarms of robots could aid in disaster response, Search &amp; Rescue, and more.<h3>&nbsp;</h3><h3>Favourite Robot</h3>The LIMO isn’t the only AgileX product in Polytechnique’s stable. And while Beltram likes all of them, he has a soft spot for one in particular.“I would say that my favorite robot is the <a href="https://indrorobotics.ca/scout-mini-2/" target="_blank">Scout Mini</a>,” he says. “It’s fast, it’s agile and the control is extremely precise.”In fact, Beltrame often takes the Scout Mini with him when doing school presentations. It’s small enough to be carried in the trunk of his car and hand-carried to classrooms. His team has also used the platform to test a new code for path planning and sophisticated energy calculations. It’s capable of tracking the additional energy required for climbing inclines, for example, then calculating when the robot needs to return home to wirelessly recharge.As always, InDro works with clients to deliver precisely what they need. This saves time for those institutions and corporations on builds, allowing them to get on with the business of R&amp;D.“We’ve done quite a bit of integration for them,” says <a href="mailto:lcorbeth@indrorobotics.com" target="_blank">Luke Corbeth</a>, InDro’s Head of R&amp;D Sales.“For example (see picture below), we provide a top plate with all required hardware mounted and integrated. They then add their own sensors, protective structure, etc. So this is a great example of how we work with clients on a case-by-case basis depending on their needs as robotics isn’t one-size-fits-all.”<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzA2NTYyODUzMDA0LWltYWdlLnBuZy53ZWJwIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="Tracker Robots"> <h3 id="isPasted">One Small Step...</h3>With all of this research, what comes next? Will the work being done today at Polytechnique eventually find its way off this planet?“The answer is it’s going to happen very soon,” says Beltrame.&nbsp;Sometime later this year, a rocket will head toward the moon carrying three small robots. It’s called the Cadre mission.A trio of small rovers will work as a team to explore the moon autonomously, mapping the subsurface in 3D, collecting distributed measurements, and showing the potential of multirobot missions,” says <a href="https://www.jpl.nasa.gov/missions/cadre" target="_blank">NASA’s JPL website.&nbsp;</a>One of Beltrame’s students is working on that mission with JPL.“This is one example of how the work that we’ve been doing in this lab, in the end – through students that were here – become real missions,” says Beltrame.And that’s not all. As early as 2026, a Canadian-built rover could land on the moon in Canada’s first moon mission.Its task? To explore the moon’s south polar region in search of “water ice.” This ice is critical to long-term human habitation on the moon – and can also be converted to fuel, both for energy on the moon and potentially to refuel other spacecraft with destinations further afield.“I have an engineer from the Canadian Space Agency that’s a student of mine that’s developed the Mission Planner. So the idea is that we – our lab – developed the Mission Planner for the Canada rover that’s going to the moon.”Here’s a look at that planned mission, from the CSA:<iframe width="640" height="360" src="https://www.youtube.com/embed/Ti4a0oiWsMk??si=gdkI-fUB2n3fT89r&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">&amp;lt;span class="fr-mk" style="display: none;"&amp;gt;&amp;amp;nbsp;&amp;lt;/span&amp;gt;&amp;amp;lt;span class="fr-mk" style="display: none;"&amp;amp;gt;&amp;amp;amp;nbsp;&amp;amp;lt;/span&amp;amp;gt;&amp;amp;amp;amp;lt;span class="fr-mk" style="display: none;"&amp;amp;amp;amp;gt;&amp;amp;amp;amp;amp;nbsp;&amp;amp;amp;amp;lt;/span&amp;amp;amp;amp;gt;&amp;amp;amp;amp;amp;lt;span class="fr-mk" style="display: none;"&amp;amp;amp;amp;amp;gt;&amp;amp;amp;amp;amp;amp;nbsp;&amp;amp;amp;amp;amp;lt;/span&amp;amp;amp;amp;amp;gt;</iframe><h3 id="isPasted">And There's More</h3>There was some big news this week from Polytechnique Montréal. On January 24 it announced the formation of ASTROLITH, a body for “research in space resource and infrastructure engineering.”It’s the first Canadian group dedicated to lunar engineering, according to a news release.“Comprising experts from all seven Polytechnique departments, ASTROLITH will pursue the mission of helping to develop next-generation technologies and training the engineers of tomorrow to ensure Canada’s presence in space and lunar exploration, as well as addressing critical needs on our planet within the context of climate change, resource management and sustainable development,” reads the release.So while the emphasis is on the moon, ASTROLITH will also result in some very practical – and urgent – use-cases on our home planet.“As encapsulated in its Latin motto Ad Lunam pro Terra, ASTROLITH is dedicated to developing technologies with direct impacts here on Earth: enabling development of infrastructure in the Far North or facilitating the energy transition, for example,” says the release.“Indeed, the research unit’s founding members are already involved in developing technologies in various areas related to space and extreme environments, from design of resilient habitats and infrastructures for remote regions to deployment of cislunar communications technologies to development of advanced robotics systems for prospecting and mining, among many others. Their work is bolstered by contributions from specialists in life-cycle analysis, sustainable development and space-related policy development.”The team is composed of academics and researchers that span all seven Polytechnique departments. Beltrame, not surprisingly, is on the team – which is pictured below. (He’s in the back row, centre.)<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1706563288421-Screenshot-2024-01-26-at-9.03.42-AM.png.webp" style="width: 300px;" class="fr-fic fr-dib" alt="Research Team"><h3 id="isPasted">INDRO’S TAKE</h3>We find the work being carried out at Polytechnique Montréal, the MIST lab – and now ASTROLITH – both fascinating and important. It’s also a terrific example of how dedicated researchers and students can develop and test projects in the lab that eventually have real-world (and off-world) applications.“I’m incredibly impressed with the work being carried out here, and the fact it can be put to positive use-cases both on earth and in space,” says InDro Robotics CEO Philip Reece.“We wish Dr. Beltrame and his colleagues well, and we’ll certainly be watching these lunar missions with great interest. It’s always a pleasure when InDro can support teams doing important work like this.”You can find more about the MIST lab <a href="http://mistlab.ca/" target="_blank">here</a>. And if you’d like to talk about AgileX robots (or any other robotic solution), connect with the InDro experts <a href="https://indrorobotics.ca/connectwithanexpert/" target="_blank" rel="noopener noreferrer">here</a>.&nbsp;

Bridging Earth and Lunar Exploration with Advanced Research

Robots on Earth Help Prepare for Research on the Moon

There’s nothing like synergy. And a new high-precision solution for location and heading – a collaboration between <a href="https://indrorobotics.ca" target="_blank" rel="noopener noreferrer">Indro Robotics</a> and <a href="https://www.tallysman.com" target="_blank" rel="noopener noreferrer">Tallysman Wireless</a> – is the result.As you likely know, while GPS is great – and good enough for us driving around using WAZE – its accuracy can leave something to be desired. Traditional Global Navigation Satellite System (GNSS) solutions generally are accurate to around 2.5 metres Circular Error Probability (CEP). That means the reported location has a 50 per cent chance of being within 2.5 metres of where it actually is. What’s more, that error rate exists under ideal conditions – with the detection system stationary and with an unobstructed view of satellites.That’s good enough for a car with a driver, or a cargo ship. But many robotic applications require far greater precision. If you’re running a remote inspection robot using GPS waypoints, 2.5 metres isn’t good enough.Think about it. In the example of a remote inspection robot, the device is generally operating at the location of a high-value asset. You might want a repeatable routine where the robot can get up close to look at gauges, valves, or anything else requiring inspection. You might want it to pass through a doorway, or get very close to – without touching – a highly energised electrical component. So accuracy matters, whether in this application or many other use-cases.Now, InDro and Tallysman Wireless, a Calian company, are pleased to announce a solution.Below: An InDro Sentinel inspection robot<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5NDY1MzQ4MzgwLTIwMjIwNDI3XzE2NDU0NDAwOF9pT1MgY29weS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib"><h3>Location, Location, Location</h3>That real estate phrase certainly applies when it comes to high-level robotics. But how do you get from a potential error of 2.5 metres down to, say, 2.5 centimetres – two orders of magnitude?In this case, the solution came by partnering with Tallysman Wireless.The company is known for its leading-edge GNSS and Iridium antennas. Tallysman also has an enviable reputation for customising those antennas for global clients seeking specific GNSS solutions. Ships, aircraft, trains and even drones carry out critical missions daily while relying on Tallysman solutions. InDro, meanwhile, is known for its R&amp;D work, robots and custom innovations in the aerial and ground robotics world. So the potential was there for collaboration.Because – and we know this well – it’s not just as simple as plugging antennas and receivers together and hoping for the best.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5NDY1Njg1Njk5LVNjcmVlbnNob3QtMjAyMy0wOS0yNi1hdC0xLjUzLjE4LVBNLnBuZy53ZWJwIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib"><h3 id="isPasted">The Issue(s)</h3>Antennas – even really good ones – are finicky pieces of equipment. Depending on what you’re mounting them on, they can be subject to interference that diminishes their performance. The type of connector attaching them to a receiver, even the length of the cable used in that connection, can also detract from optimal signal acquisition and accuracy. That’s why you want someone like Tallysman Wireless on board.“We are experts in Global Navigation Satellite System (GNSS) solutions, specifically the antennae side of &nbsp;things,” explains Gord Echlin, Tallysman’s Director of Business Development.“A lot of people assume, unless you use the term GPS, that it’s a fairly easy thing to implement and get accurate results. Nothing could be farther from the truth.”As Tallysman Wireless explains in a brochure:“The problem is that keeping the antenna to system interface in the analog domain requires a lot of RF expertise to manage, expertise that is not widely available, and these issues amplify with long signal transmission over cables.&nbsp;Digital systems with built-in LTE communication links, common components of autonomous systems, are direct threats to the integrity of the GNSS signal.&nbsp;“Tallysman Wireless has solved this problem by integrating their sensitive, high performance, GNSS antennas in the same package as advanced GNSS receivers, in what is commonly called a ‘Smart’ Antenna. The GNSS processing solution is in compact, carefully engineered to mitigate the potential impairments between the antenna and receiver, and the Position/Navigation/Timing (PNT) information is now communicated to application system over in the digital domain, over a serial interface (UART, USB, CANbus, or Automotive Ethernet).”Or, as Echlin puts it: “We take the receiver, and we take the antenna and put it in the same package to mitigate the outside interference such that you get less than two centimetres of error. That, along with very precise heading information – with accuracy to 0.3 degree.” <h3>The InDro Connection</h3>With the Tallysman Wireless integrated solution, there was just one more piece of the puzzle remaining. How to integrate this into a robot? That’s where InDro’s engineering team came along.The package required a software interface where none had existed before. InDro engineers created a ROS2 coding solution and integrated the Tallysman smart antenna onto our InDro Backpack – which we use with Unitree quadrupeds.InDro Backpack is our system for remote teleoperations over 5G (and 4G), which also allows for rapid sensor integration and other customization using ROS1 and ROS2 software libraries (which, along with an EDGE computer and high-speed modem, are on-board).The complete solution – hardware and software – enable consistent, high-accuracy positioning. InDro Plans to offer this complete solution to clients in need of precision positioning.Below: The Tallysman Smart Antenna solution, integrated with new ROS2 coding into the InDro Backpack<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk5NDY1ODE5MjkyLTIwMjMwOTA2XzEzNDcxOS1qcGVnLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">InDro was pleased to partner with Tallysman Wireless on this integration project. With robots increasingly used for remote inspection of high-value assets, accurate positioning and heading data has become essential.“Being able to tap into the expertise of Tallysman Wireless – and combine their solution with software from InDro engineers – has resulted in a powerful solution,” says InDro Robotics CEO Philip Reece.“We’ve already begun integrating this onto our own robots, and look forward to offering this to clients in need of the most accurate and reliable positioning possible.”Looking for more information? <a href="https://indrorobotics.ca/connectwithanexpert/" target="_blank" rel="noopener noreferrer">Connect with us HERE</a>.&nbsp;

GNSS Solution for Ground Robots

InDro Robotics and Tallysman Partner on a New Precision GNSS Solution for Ground Robots

The safety of pedestrians and cyclists is important in any major city.Bike lanes and crosswalks are the most obvious signs that we create infrastructure for this purpose. But there are limits to what that infrastructure can do.Winter, for example, creates additional threats. Ice and snow are the most obvious problems, but potholes and deep puddles can also cause havoc – particularly for cyclists. Snow can accumulate quickly in a storm – and it’s not uncommon for snow plowed from the roadway to sometimes spill over into bike lanes (and even on sidewalks).That’s part of the reason why Indro Robotics has built an innovative solution that will be put to the test this winter. It’s called the Street Smart Robot, or SSR – and it’s been designed from the ground up to help ensure safe winter cycling.Below: A Wikimedia Commons image, taken in Whitehorse by <a href="https://www.flickr.com/people/71902268@N00" rel="nofollow" target="_blank">Anthony DeLorenzo</a>. Cyclists in Canada are a hardy bunch.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk4Njg1MjA5MDA1LTQwX2JlbG93X2NvbW11dGVfNjczNDE1NzExOS1qcGcud2VicCIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 745px;" class="fr-fic fr-dib"><h3> </h3><h3 id="isPasted">Street Smart Robot</h3>The catalyst for the SSR is a research and development partnership fund called the <a href="https://www.ovinhub.ca/programs/wintertech-av-development/" target="_blank" rel="noopener noreferrer">Wintertech Development Program</a>. &nbsp;Wintertech is run by <a href="https://www.oc-innovation.ca/programs/ontario-vehicle-innovation-network-ovin/" target="_blank" rel="noopener noreferrer">OVIN, the Ontario Vehicle Innovation Network</a>. That’s a province of Ontario initiative which “capitalizes on the economic potential of advanced automotive technologies and smart mobility solutions such as connected and autonomous vehicles (CAVs), and electric and low-carbon vehicle technologies, while enabling the province’s transportation and infrastructure networks to plan for and adapt to this evolution.”And while bicycles aren’t connected and autonomous vehicles yet, we felt robotics could play a role in helping to ensure the safety of cyclists in the Smart City of the future. Specifically, we thought an autonomous robot equipped with the right sensors and processing might help to detect safety issues in bike lanes in the winter.“The idea behind the robot is we want to prolong the use of bike lanes in Ottawa, but also ensure the safety of bike lanes,” explains Indro Robotics Account Executive Luke Corbeth.“There’s really two parts to this: The&nbsp;first is a machine vision element to see if conditions are good enough for biking – no ice, not too many leaves, etc. On the safety side, the Street Smart Robot is more concerned with detecting things like potholes and cracks. And the idea is if you’re able to identify those things, the right resources can be deployed faster and more efficiently to solve the problem in a timely manner.”So that’s the idea behind the SSR. Now, let’s take a look at the technology.Below: A look at the specs of the AgileX&nbsp;Bunker Pro platform, used in SSR. We’ve upgraded the battery for a four-hour run time:<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk4Njk0NDA5MjE1LVNTUiBQb3N0IC0gQnVua2VyIFBybyBTcGVjcy5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib" alt="Bunker Pro Specs"><h3 id="isPasted">Built Tough</h3>If you’re going to be out and about in an Ottawa winter – where temperatures have reached as low as -33°C – you need a platform suitable for the environment. InDro selected the AgileX <a href="https://indrorobotics.ca/bunker-pro/" target="_blank" rel="noopener noreferrer">Bunker Pro</a> as the starting point.With an IP67 Ingress Protection rating, the Bunker Pro is highly impervious to water and particulate matter – which it will encounter in abundance on Ottawa streets. The treads give an edge over wheels when it comes to navigating over ice, snow and potholes. With a full charge, the platform can run for some four hours – even when it’s cold out.But the platform is just the start. InDro engineers had to put considerable thought into the kinds of sensors that would help the Street Smart Robot carry out its task while safely avoiding cyclists, pedestrians, or other obstacles it might encounter. And that began with four wide-angle pinhole cameras. “The pinholes are just to give the operator a better understanding of their environment and situational awareness,” explains Corbeth. And while we say “operator” here, it might be more appropriate to say “observer.” Though initial deployments will involve teleoperation, the SSR has been built to carry out its tasks autonomously. We anticipate that down the road (or bike path), a person will simply be involved in monitoring missions in case human intervention is required.That autonomy will be carried out by a combination of computing power, our InDro Autonomy software stack, and a plethora of sensors.&nbsp;<h3>Sensors, Sensors, Sensors</h3>The Street Smart Robot is equipped with front- and rear-facing depth cameras. These cameras have two visual sensors each, placed roughly the same distance apart as human eyes. That separation – as in human vision – allows the SSR to perceive the world in depth. Onboard computation (we’ll get to that) calculates how far obstacles might be in the robot’s immediate surroundings, and whether it needs to slow down, stop or change course to avoid obstacles.The depth cameras are supplemented by two 270° 2D LiDAR sensors – which are devoted almost exclusively to obstacle avoidance and safety. There are two additional 3D LiDARS, placed to assist with Simultaneous Localization and Mapping, as well as a GPS and IMU (Inertial Measurement Unit). There’s even a Range Finder that can detect how far an object is off the ground.“If you have an overhanging tree branch, for example, you could see where it is and see if it obscures the bike lane,” says Corbeth.&nbsp;In addition, there’s a thermal/30X optical Pan-Tilt-Zoom camera, complete with a windshield wiper for those sloppy days.Below: Check out what the SSR has on board.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk4NjkzMTY5NTcwLVNTUiBQb3N0IC0gU1NSIFNwZWNzLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib"> <h3 id="isPasted">Sensing, and Making Sense of its Environment</h3>All of those sensors are great. But they don’t do a lot on their own. They require software and computational power to give their data meaning. Here, the SSR has a Jetson ORIN AGX for EDGE computing. The ROS2 operating system software lives onboard in <a href="https://indrorobotics.ca/commander/" target="_blank" rel="noopener noreferrer">InDro Commander</a> – a module we’ve created for rapid integration of sensors and 5G remote operations. Commander can be thought of as the glue that holds everything together.But still, there’s the issue of making sense of the data. How will the Street Smart Robot identify ice, water, leaves, snow, potholes, debris etc? And how will it determine whether they are significant enough to require a City of Ottawa maintenance crew to take action?Here, the SSR will be going to school. And by that, we mean a combination of Machine Vision and Machine Learning will teach it what’s worth reporting and what isn’t. One way is to take actual images you expect to see on the bike path and identify which ones are significant and which can be ignored.“For example, you could mount a camera on an actual bicycle and then use that dataset to train the robot,” says Corbeth. “But there are a couple of approaches. There’s also obviously the simulation element. You can use specific engines that have high-fidelity graphics to simulate possible different environments in high resolution. And you can use that simulated data for training.”&nbsp;<h3>Then what?&nbsp;</h3>In the early stages, there will be a human operator at the helm. They’ll likely see some of those obstacles with the pinhole cameras, but from the start we anticipate that the onboard AI will trigger an alert for the operator. Once the operator confirms that the image is worthy of the attention of a maintenance crew, they will contact the city directly.That’s how things will start. Once we’ve established a high confidence level that the Machine Vision is correctly identifying anomalies, that process can be automated. The SSR will be programmed to automatically send an alert to the city, complete with a captured image of the potential problem and GPS coordinates.“It’s the idea of anomaly detection – detecting and flagging anomalies. The SSR will also likely be able to identify the severity of the anomaly on a one-to-five scale. And because you have the GPS onboard, the exact location of the problem can be relayed to the city.”Below: The SSR, during its public unveiling at the TCXpo exhibition in June. Front and rear view, to show off all its bits…<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk4NjkzNjI1Nzk5LVNTUiBQb3N0IC0gRnJvbnQgYW5kIEJhY2sgVmlldy5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"> <h3 id="isPasted">On The Shoulders of Sentinel</h3>Every technical achievement owes something to its predecessors. And that’s no different with the Street Smart Robot.InDro Robotics previously built <a href="https://indrorobotics.ca/indro-robotics-sentinel/" target="_blank">Sentinel</a>, a workhorse for remote asset inspection. That robot incorporated an AgileX <a href="https://indrorobotics.ca/bunker-4/" target="_blank" rel="noopener noreferrer">Bunker platform</a>, an InDro <a href="https://indrorobotics.ca/commander/" target="_blank" rel="noopener noreferrer">Commander</a> integration module for sensors and remote teleoperations, and several other sensors. It’s a great robot that has proven itself in the most demanding conditions.The Street Smart Robot builds on the success and learnings of Sentinel with additional compute power, many more sensors, a more robust design and extended operational range. And that opens the SSR up to many other tasks beyond bicycle paths.“That’s what really excites me about this project – the idea that this technology is transferable across other inspection verticals,” says Corbeth. “This particular robot could be used in agriculture, and the track platform is really good in mining. I could envision this exact same robot in those two verticals, and others.”&nbsp;<h3>The 5G Connection</h3>When dealing with multiple sensors in real-time, a solid data bandwidth is crucial. Here, SSR is outfitted with a high-speed modem and special antennaes for optimizing 5G and 4G signals. And while the Street Smart Robot can be operated over 4G, it’s 5G that offers the pipeline necessary for the data to really flow. &nbsp;InDro's continuing partnership with Rogers will ensure that the SSR has access to Canada’s largest and most reliable 5G network.<span data-ccp-props='{"134233117":false,"134233118":false,"134245417":true,"134245418":false,"134245529":false,"201341983":0,"335551550":1,"335551620":1,"335559685":0,"335559731":0,"335559737":0,"335559740":240}'>Below: Innovations in the InDro Sentinel paved the way for the Street Smart Robot. This image was taken at the opening of the Drone and Advanced Robot Training and Testing facility (DARTT) in June of 2023. That’s Luke Corbeth holding the microphone.<span data-ccp-props='{"134233117":false,"134233118":false,"134245417":true,"134245418":false,"134245529":false,"201341983":0,"335551550":1,"335551620":1,"335559685":0,"335559731":0,"335559737":0,"335559740":240}'><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk4NjkzODgwNzA5LVNlbnRpbmVsLVdhdGVyLU9uZS1zY2FsZWQuanBnLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><h3> </h3><h3 id="isPasted">InDro's Take</h3>We’re pretty excited about the SSR. As Luke Corbeth says: “It’s a bad-ass robot.”And it is. But we’re also excited about the project itself.The Smart City of the future will have connected, embedded sensors (including on robots) helping with everything from traffic flow to updated weather and road conditions. Cyclists are a big part of any major urban centre, and the prospect of helping to ensure their safety appeals to us. It’s also an opportunity to really hone in on Machine Vision and Machine Learning as InDro trains the SSR for its task.“Smart Cities are on their way, and it’s great to be involved in yet another project as we build the capacity for the future,” says InDro Robotics CEO Philip Reece.“The Street Smart Robot has an important role to play, and could well be the template for anomaly detection and road maintenance at scale in the future. We’re grateful to OVIN and its Wintertech program for selecting this project for development; we’re excited to see what the SSR can do.”InDro plans to start testing the SSR during the winter, with the project stretching to June of 2024. We’ll be writing more once the robot hits the bike paths.Interested in learning more about how SSR could work for your inspections? &nbsp;Contact InDro <a href="https://indrorobotics.ca/contact-us/" target="_blank" rel="noopener noreferrer">HERE</a>.

For Safer Cycling in the Winter

InDro Robotics Builds Street Smart Inspection Robot

Enhancing Efficiency with AGVs and AMR

AGV vs AMR: A Comprehensive Comparison in the World of Automation

<h2 id="isPasted">Its impact on Visual SLAM and beyond</h2>It is clear that Artificial Intelligence (AI) is here to stay and there is a need for an open discussion, to bring some light into the AI black box.At Sevensense Robotics we strongly believe that transparency builds trust, this is why we decided to tackle the elephant in the room and dissect the role that AI plays in our offering.Let’s start by exploring what AI is and the difference between Machine Learning (ML) and Deep Learning (DL).The original definition of AI, coined in 1955 by John McCarthy -one of the founding fathers of the discipline- was really broad: “The science and engineering of making intelligent machines.”Nowadays, we conceive AI as a subset of computer science focused on creating systems that can replicate human intelligence and problem-solving abilities. It involves any technique that enables machines to mimic human intelligence, using logic, if-then rules, decision trees, and machine learning -including deep learning.Machine Learning (ML) is a subset of AI that intersects with statistics. It involves the development of algorithms and statistical models that enable computers to learn and make predictions or decisions without being explicitly programmed; instead, they recognize patterns in the data and make predictions once new data arrives.Deep Learning (DL) is a specialized subset of Machine Learning that analyzes data with a logical structure similar to how a human would draw conclusions.&nbsp;To achieve this, DL applications use a layered structure of algorithms called an Artificial Neural Network (ANN). It is characterized by its deep layers of interconnected nodes or neurons, which allows it to automatically learn hierarchical representations of data, making it well-suited for tasks like image and speech recognition.The three technologies are nested one within the next:<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk3MDIxMTQzOTQ1LURpZmZlcmVuY2VzIGJldHdlZW4gQUksIE1hY2hpbmUgTGVhcm5pbmcgYW5kIERlZXAgTGVhcm5pbmcgKDIpLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib" alt="Differences between AI, ML and DL">Visual AI refers to Artificial Intelligence applications that focus on enabling machines to interpret, understand, and process visual information, such as images and videos. Visual AI technologies employ advanced Machine Learning algorithms, Deep Learning models, and computer vision techniques to analyze and extract meaningful insights from visual data.AI-Powered Robot AutonomySevensense uses Visual AI to allow robots to identify, understand, and act on imagery and visual data -captured by cameras- just like humans so that they can navigate autonomously.By processing camera images with AI, the process known as Visual Simultaneous Localization and Mapping (SLAM) builds a rich 3D map of the environment and precisely localizes within it.Sevensense’s Visual SLAM technology comprises proprietary and lightweight AI sensor fusion algorithms to enable robots to precisely estimate their position. This is achieved by extracting distinctive elements from the images, for example, a corner of a window, and using these to build a representative yet compact 3D model of the environment.&nbsp;To deliver robust localization under all conditions, including lighting and environmental changes, Sevensense employs AI -more concretely Deep Convolutional Neural Networks- for feature extraction. Incorporating AI for this purpose makes it possible to overcome a limiting constraint of legacy SLAM technology, which until now could not cope with significant illumination and other environmental changes, leading to failures during autonomous navigation in difficult settings.Sevensense also uses machine learning to maintain the visual maps of dynamic spaces to ensure robust localization and reusability of the initial map of the environment. The solution known as Lifelong Visual SLAM is basically a multi-session map that uses the initial map as the basis and later on, the changes in the environment are added to it to enrich it. All of this, without the need to run Visual SLAM from scratch on each session, increases operational efficiency.The Lifelong Visual SLAM solution enables building and maintaining always-up-to-date maps. These maps incorporate data from multiple conditions of the environment, such as during cloudy- and sunny weather, bright and dark lighting situations, and changes in the elements present in the area, e.g. changes in factory floor layouts, or simply in the warehouse or shop inventory. All of these changes are detected automatically and incorporated into the lifelong map.This allows the maps to be used for visual positioning in environments that change considerably over time.To enable autonomous navigation even in complex and ambiguous environments, a Convolutional Neural Network is employed to perform Semantic Scene Understanding making it possible to detect, classify, determine the position, -and when applicable, predict the movement of obstacles e.g. people and vehicles, and other objects of interest such as pallets, trolleys, floor markings, docking or charging stations.After the robots have gained insights into their environment and the expected behavior of the elements around them, it is time for them to plan their next move. Reinforcement Learning makes it possible for robots to adapt their navigation behavior -stopping, slowing down, or overtaking obstacles, based on real-time perception, allowing them to interact with the environment, for example, docking, picking, or charging, while safely sharing the floor with moving elements like people and other vehicles.All of these processes happen on the Edge, on the multi-camera Alphasense Edge AI device -a GPU-accelerated compute unit- embedded in the robot. By bringing computational power closer to the data source, Sevensense minimizes latency challenges -enabling nearly simultaneous, real-time perception and decision-making- and addresses security and privacy issues typically present in solutions purely based on cloud computing, where visual data needs to be recorded and transmitted to remote servers for processing.&nbsp;AI-Powered Continuous Performance ImprovementTo exceed the ever-increasing performance requirements of the market, both in terms of accuracy and robustness, Sevensense leverages ongoing cutting-edge developments in the fields of AI, computer vision, and robotics.&nbsp;Sevensense uses AI models to enrich its simulation, training, and testing infrastructure.Combining Generative AI and Digital Twins, Sevensense is able to create the most challenging training and testing environments to continuously validate its software stack.Visual AI AnalyticsThe visual data captured by the cameras, apart from providing inputs for best-in-class localization and autonomy performance, also unlocks the potential for providing ground-breaking additional services.The rich visual data captured by the cameras allows Sevensense to offer further Visual AI analytic services focused on providing organized data and insights -beyond Visual SLAM- such as asset tracking, stocktaking, surveillance, and inspection, as an additional safety or reporting data layer.

Visual AI enables autonomous navigation and an array of object-recognition-based applications

Its impact on Visual SLAM and beyond

AI in Robotics Perception and Autonomous Navigation

<h2>Challenges of self-localization in mixed in- and outdoor environments</h2>Knowing its own location or position within an operating environment (a.k.a. self-localization) is one of the key capabilities any mobile robot must master to be able to get from A to B. Yet, depending on the environment the robot is operating in, self-localization can impose vastly different challenges, rendering the choice of sensor technology and software algorithms far from a trivial task.Indoors, 2D LiDAR technology is widely used, as an example, on AGVs and AMRs for material handling operations. Such a technology allows to measure the geometric structure of the near-by environment (e.g. walls, shelves) to localize in pre-built maps. However, it shows its limitations in environments which do not have unique geometric features (e.g. a long corridor) or are highly dynamic especially if shared with people.&nbsp;On autonomous vehicles for outdoor environments, instead, satellite navigation systems such as GPS or Galileo are often the first choice of sensor technology for self-localization, for good reasons: The GPS receivers are very cheap, and they yield an easily interpretable position in a known global reference coordinate system (e.g., WGS84).&nbsp;However, an accurate GPS position requires unobstructed skies. This is a limitation that is violated in several circumstances like urban surroundings, company campuses, &nbsp;logistic yards and airport tarmac. In fact, these outdoor places often require to operate close to or even inside buildings or tunnels. Due to these restrictions, mobile robots operating outdoors or in mixed indoor-outdoor settings cannot rely solely on GPS for self-localization.&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk1MTMxNTk3MzM0LU1peGVkIGluZG9vciBhbmQgb3V0ZG9vciBwb3NpdGlvbmluZy5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib">Mixed indoor and outdoor environments are challenging for GPS and LiDAR solutions aloneEven though 2D LiDAR sensors can be employed outdoors too, using them in the open only works in well-structured spaces of limited extent or requires additional infrastructure such as laser reflectors in order to work better., or to a better extent thanks to the installation of additional infrastructure such as laser reflectors. 3D LiDARs, on the other hand, remain a very expensive sensor gear, despite all efforts in cutting down the costs in recent years.<h3>The strength and challenges of visual localization</h3>As an alternative to GPS and LiDAR sensors, cameras are able to reliably sense the environment both indoors and outdoors. Vision thus has the capability to bridge this gap left uncovered by GPS or LIDAR sensors. It offers highly accurate and reliable self-localization in both indoor and outdoor environments with a very cost effective sensor gear.&nbsp;Visual self-localization does not come without its very own challenges. Cameras naturally provide good images in well illuminated surroundings, while during night time outdoors, or in dim indoor areas, visual self-localization becomes more difficult. However, the selection of camera sensor chips with a high dynamic range &nbsp;has shown to allow proper images to be taken even under challenging illumination conditions.<blockquote>Instead, LiDAR sensors can be employed. However, using 2D LiDARs outdoors only works in well-structured spaces of limited extent. As an alternative to GPS and LiDAR sensors, cameras are able to reliably sense the environment both indoors and outdoors.</blockquote>Further, and in contrast to GPS or LiDAR sensor data, images taken by cameras of the same environment can look vastly different under varying seasonal, weather, or lighting conditions. This change in appearance renders accurate localization difficult. Additionally, geometric characteristics are often unfavorable for visual localization outdoors compared to indoors, as there is often less stable, human-made structure visible, plus it is often located at a considerably farther distance. Therefore, smart algorithms to work with visual data are paramount.<h3>Tackling the challenges of visual localization with AI</h3>To master these challenges, Sevensense employs a smart AI algorithm based on lifelong visual mapping that enables building and maintaining always-up-to-date maps of the environment. These maps incorporate data from multiple appearances of the environment, such as before- and after remodeling of a room, during cloudy- and sunny weather, or bright and dark lighting conditions. This allows the maps to be used for visual localization under practically any appearance condition.&nbsp;At the core of this lifelong mapping process is a software algorithm capable of merging visual data from multiple traversals through the same environment, recorded under potentially very different appearance conditions, into a single, geometrically consistent map. This process is fully automated, resulting in having a multi-appearance map ready for reliable localization after traversing through the environment only a handful of times beforehand.&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk1MTMxNzMxMTk3LUxpZmVsb25nIHZpc3VhbCBtYXBwaW5nIGFsZ29yaXRobXMgdXNlZCBieSBTZXZlbnNlbnNlLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib">Smart lifelong visual mapping algorithms allow for always-up-to-date mapsFurther, continuously updating this map over time naturally captures structural change in the environment. This way events like remodeling of rooms, construction sites or temporary modifications in street or room layouts don&rsquo;t disrupt everyday operations. These changes are detected automatically and swiftly incorporated into the lifelong map.&nbsp;In particular, no expert knowledge or intervention is necessary at any point in the process. Just as generating the initial map of the environment can be done by anyone without any prior training or expert know-how, updating the maps at any later point is done automatically by Alphasense Position. This considerably lowers the costs of maintaining the system in a long-term horizon.&nbsp;<h3>Vision is the optimal solution for indoor- and outdoor self-localization</h3>By employing this lifelong mapping technique, vision overcomes its limitations and turns out to be the go-to technology for cost-effective, but still reliable and accurate self-localization both indoors and outdoors. In particular, it offers seamless transition from indoor to outdoors and vice-versa, as the same camera sensors and the same map can be used to localize in both types of environments. This is a fundamental advantage over any technology primarily relying on GPS for outdoor localization and navigation that can revolutionize the logistics, delivery, cleaning or supply chain processes.<blockquote>By employing this lifelong mapping technique, vision turns out to be the go-to technology for cost-effective, but still reliable and accurate self-localization both indoors and outdoors.</blockquote>Sevensense has already successfully demonstrated the unique benefits of visual localization in a <a href="https://www.sevensense.ai/blog/kyburz" target="_blank" rel="noopener noreferrer">proof-of-concept study in partnership with KYBURZ Switzerland AG</a>. By equipping a mail delivery robot with Alphasense Position, accurate and reliable self-localization of the vehicle became possible at any time indoors, as well as outdoors, where LiDAR and GPS solutions alone failed.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1695132745402-Reliable+positioning+indoors+and+outdors+cameras+overcome+LiDAR+and+GPS+limitations+Sevensense.jpeg" style="width: 300px;" class="fr-fic fr-dib">Delivery robot used to benchmark Alphasense Position, 3D LiDAR and GPS localization performance[the missing image will go here once the CMS issue is fixed]<blockquote>By equipping a mail delivery robot with Alphasense Position, accurate and reliable self-localization of the vehicle became possible at any time indoors, as well as outdoors, where LiDAR and GPS solutions failed.</blockquote>Along a similar vein, the indoor- and outdoor capabilities of Alphasense Position will open up countless other opportunities for bringing cost-effective autonomy to robotic platforms operating in challenging environments. Delivering goods across multiple buildings on a campus, or material handling in warehouses undergoing frequent layout change have never been simpler before.<h3>With vision towards a fully autonomous future</h3>Self-localization is essential for robots to safely navigate in changing environments and achieve full autonomy. By employing cameras for this task together with smart algorithms for building and maintaining maps, autonomy can be provided at a fraction of the costs - be it for the sensor gear itself, as well as operating costs over the robot&rsquo;s lifetime.&nbsp;At Sevensense we are constantly pushing cutting edge technologies forward to deliver affordable autonomy solutions for new application fields.You can find more informative material about Alphasense Position on its <a href="https://www.sevensense.ai/product/alphasense-position" target="_blank" rel="noopener noreferrer">product page</a>.

Test vehicle benchmarking cameras, LiDAR and GPS systems

Breaking Free from LiDAR and GPS Constraints: Harnessing Vision for Reliable Positioning, Indoors and Outdoors

Why reliable positioning indoor and outdoor requires cameras

Sevensense Robotics builds the eyes and brains of mobile robots. &nbsp;We strive to provide the most flexible and robust Visual AI solutions to give robots the ability to identify, understand, and act on imagery and visual data -captured by cameras- just like humans so that they can navigate autonomously.Our technology enables robots to adapt their navigation behavior based on real-time perception, allowing them to complete their missions, for example, docking, picking, or charging, while sharing the floor with moving elements like people and other vehicles.To ensure everything we ship has the high performance our customers expect, we stress-test our technology in different challenging settings.

Sevensense Robotics pushes the boundaries of Visual SLAM technology

This is how Sevensense tests its curring-edge Visual SLAM technology to ensure robust performance.

The Sevensense Labs

In terms of simplicity and logistics, people were always the obvious choice for moving something from A to B. Whether it was a push cart, trolley or forklift truck, a human operator was there to do the job. But increased automation and streamlining means that this isn&rsquo;t usually the most efficient use of human time. The outcome is unsurprising &ndash; to develop an automated replacement for such tasks.Mobile robots are becoming increasingly common in manufacturing facilities, as they replace human beings in repetitive transfer tasks. Most of them can be found in warehouses, but they&rsquo;re also finding a place in assembly and manufacturing plants. This is mainly due to continuing developments in sensor technology, and computer intelligence. Their safety and flexibility have also improved.Implementing the use of mobile robots in such environments has become much easier and is one of the benefits of bringing&nbsp;<a href="https://www.rowse.co.uk/blog/post/ai-warehouse-management" title="6 Ways AI Will Transform Warehouse Management " target="_blank">artificial intelligence into manufacturing</a>.<h2>What Is a Mobile Robot?</h2>Mobile robots combine electrical and mechanical systems into a vehicular design, with an integral package of software capabilities. The basic designs tend to be simple &ndash; often just a platform on wheels or caterpillar tracks &ndash; but the software applications open up lots of innovative possibilities. Using their advanced sensory capabilities, mobile robots are able to perceive their own surroundings. This enables more effective and efficient navigation, and control capabilities for a whole fleet of mobile robots.The basic applications of mobile robots in manufacturing start with moving raw materials, parts, tools, etc. For example, mobile platforms can be programmed to transport a production item from a storage area to workstations where further processes take place. After completion, mobile robots can transport items to a manual quality inspection area, before taking them on to a different storage location.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1691772059795-what-you-need-to-know-about-mobile-robots-1.jpg" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">What Else Can Mobile Robots Do?</h2>Production plants have been using automated guided vehicles (AGVs) since the 1950s. This is one of the easiest tasks to automate. Their designs and operation are typically very robust as they&rsquo;ve evolved over decades. They frequently carry large and heavy objects, like vehicle chassis, engines and large components for aeroplanes or ships.The more advanced versions are now called autonomous mobile robots, or AMRs. Many of their applications reflect the way that humans operate vehicular transport, on a road or railway. In factories, humans operate a tug vehicle to pick up and deliver materials on the factory or warehouse floor. They may transport a train of carts all over the facility, stopping off at various locations as required.AGVs mimic a similar format of travel to a tram or train route. They&rsquo;re constrained to follow defined pathways around the facility, always proceeding in the same direction. Like a tram, they travel a fixed route, on a predetermined schedule with predetermined stops for picking up or dropping off. They use simple navigation technologies, like magnetic tape tracking and magnets embedded in the floor.More advanced technologies have introduced laser targets or fiducial markers, which are objects placed in the AGV&rsquo;s field of view. The AGV&rsquo;s optical sensors use these as a measure or point of reference to navigate safely around the building. Most AGVs can sense an obstacle blocking their path and not drive into it. Instead, they&rsquo;ll come to an emergency stop and set off an alarm. What they&rsquo;re not capable of doing is to navigate around an obstacle. Production or warehouse facilities therefore set aside designated AGV paths, which people and all other aisle traffic are expected to keep out of.<h2>How AMR Beats AGV</h2>As well as embedded tracking, an AMR has various transit options, similar to other classic transportation patterns. A bus, for example, doesn&rsquo;t follow physical tracks and may have either a circular or a linear route. People may get on at one stop and off at another, which is too advanced for a basic AGV. Even more complex, a taxi service may cover a certain area, but not use any predetermined route or stops.Modern mobile robots have been designed to incorporate this kind of agility. To do this, they need to be programmed with an accurate map of the warehouse or production facility. They must have several types of sensors installed, and the additional intelligence required to navigate the environment autonomously. Equipped with this information and capabilities, AMRs are able to determine the best path from any given point to another.AGVs are no longer thought of as mobile robots, because they lack advanced sensor technology, navigation capabilities and control intelligence. Similarly, mobile robots are not thought of as AGVs for the opposite reasons. They&rsquo;re capable of roaming freely through the production facility and making independent navigation choices. This means they can assess the environment conditions and use onboard control systems to spot and avoid obstacles.<h2>Should I Switch To AMRs?</h2>If you&rsquo;re thinking about implementing mobile robots in your manufacturing environment, you need to consider how best to integrate them with other machinery. You&rsquo;ll have to consider what human manual processes and functions can be automated, and how they&rsquo;ll need to be adapted for machinery or robots.Make a list that specifies these processes and tasks, and use it to evaluate what kind of mobile solution you need:<ul><li>What machinery would a mobile robot have to interact with?</li><li>What model of mobile robot is best for your application&rsquo;s size and payload?</li><li>How can the mobile robot be safely loaded, secured and unloaded?</li><li>What degree of driving precision will the mobile robot need?</li><li>Will it be able to move safely throughout the facility?</li><li>Will it have to take other vehicles into account?</li><li>How will you ensure that humans working in the area are always safe?</li></ul>AMR systems usually cost more than AGVs of a similar size and payload, but their control system and functional design are far more complex. Robots can&rsquo;t read or refer to paper instructions, so you&rsquo;ll have to evaluate your data flow and determine what&rsquo;s the best software solution for your requirements.Figure out how the robots are going to get their orders, whether it&rsquo;s via a programmable logic controller (PLC) or a warehouse management system. You&rsquo;ll need to work out how to design a human-machine interface and the best&nbsp;<a href="https://www.rowse.co.uk/blog/post/five-key-automation-concepts" title="Five Key Concepts In Automation" target="_blank">means of communication</a>between different systems. You should also decide whether and how you want to handle things like right-of-way rules, prioritising orders and battery charging.Both AGVs and AMRs operate on battery power, but AMRs use more expensive, modern battery chemistry. Continuously-operated systems are usually provided with automatic battery swap stations. One set of batteries can be put on charge there while a ready-charged set keeps the vehicle running. Human operators may also do this if the system isn&rsquo;t automated, or sometimes even take the vehicle offline to recharge.<h2>What Other Advances Have Been Made In Mobile Robotics?</h2>Technological advances have led to the development of the IMR, or industrial mobile robot. An IMR takes the basic AGV or AMR platform and combines it with a robotic arm. The AMR&rsquo;s machine vision and control capabilities are integrated for registration and guidance. The mobile platform or conveyor navigates the robotic arm to and from operational waypoints, where it can put down or pick up items.This area of robotics is sometimes called mobile manipulation. It expands the range of potential applications from basic transportation to processes such as tool changing, machine tending, unloading&nbsp;<a href="https://www.rowse.co.uk/blog/post/3d-printing-trends" title="3D Printing Trends" target="_blank">3D printers</a>, parts processing and inspection. IMRs have a wide range of uses, especially in warehousing and logistics. Workflow programs have been introduced that enable an IMR to travel through a warehouse to fill customer orders, picking items direct from inventory shelving.For example, one model of IMR has a robot arm equipped with a vacuum gripper mounted onboard. It&rsquo;s able to locate and unload packages directly from a vehicle stationed at a loading dock. It actually digs its way into the delivery vehicle, picking up each carton and dropping it onto a gravity conveyor. This conveyor then transports the packages out of the trailer, while the IMR carries on picking until the vehicle is empty.Another concept utilising two AMRs in tandem is called robot-to-goods workflow or mobile palletising. In this operation, one AMR travels to different inventory locations. It can pick an item from stock shelves and place it on an empty pallet carried by a second AMR. The two robots can then move to second and subsequent locations to create a unit load pallet. This operation uses the capabilities of dual control and thus becomes an IMR.Distribution centres could also deploy IMRs for cross-docking operations, where they&rsquo;d break down unit loads and reassemble them to send out elsewhere.<h2>Invest for the Future</h2>For some business owners, the employment situation in manufacturing might demand a greater level of automation to keep afloat. IMRs can deliver improvements in many areas, including flexibility and quality, safety and ergonomics, process optimisation and traceability.They&rsquo;re still finding their robotic feet as new potential applications arise, so the potential is only going to get greater. If you decide to invest in IMRs, you&rsquo;ll not only achieve short-term gains but also increase throughput and reduce your payroll.

Mobile robots are becoming increasingly common in manufacturing facilities, as they replace human beings in repetitive transfer tasks. Most of them can be found in warehouses, but they’re also finding a place in assembly and manufacturing plants. This is mainly due to continuing developments in sensor technology, and computer intelligence. Their safety and flexibility have also improved.

What You Need To Know About Mobile Robots

Accerion-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

Accerion-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Accerion-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Accerion-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

Accerion-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Unitree Robotics

READY Robotics-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

READY Robotics-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

READY Robotics-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

READY Robotics-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

READY Robotics-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Sevensense Robotics

READY Robotics

Wiferion GmbH-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

Wiferion GmbH-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Wiferion GmbH-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Wiferion GmbH-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

Wiferion GmbH-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

DEEP Robotics

University of Michigan-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

University of Michigan-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

University of Michigan-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

University of Michigan-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

University of Michigan-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

THINC Lab-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

THINC Lab-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

THINC Lab-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

THINC Lab-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

THINC Lab-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Rozum Robotics-Fri Jun 30 2023 23:59:59 GMT+0200 (Central European Summer Time)

Rozum Robotics-Mon Jul 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Rozum Robotics-Thu Aug 31 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

Rozum Robotics-Thu Aug 31 2023 23:59:59 GMT+0200 (Central European Summer Time)

Rozum Robotics-Sat Sep 30 2023 23:59:59 GMT+0300 (Eastern European Summer Time)

mobile robots

Mobile Robots

Profiles