Luca Scheuer

Hey, robotics developers! Did you know a new CAD-based toolkit for robotic motion planning, modeling, and execution is in town? We are talking about the SwRI Workbench for Offline Robotics Development (SWORD). Learn more about it at the link. https://lnkd.in/e6_Z_F45. #RoboticsDeveloper #RobotDesign #EngineeringExcellence #RoboticsInnovation #IndustrialAutomation

1

Developing embedded systems is an exciting, complex, and sometimes maddening journey. Recently, we’ve highlighted how LLMs can quickly generate example codes for STM32 devices, creating initialization functions, base classes, and toy examples to help you get started. But here’s the million-dollar question: Will it work in the real world? In a real product, success isn’t just about code compiling or peripherals initializing. It’s about ensuring that timings are precise, interrupts are caught and handled correctly, and everything runs smoothly without blocking or missing functionality. Let me paint a familiar scenario: Imagine you’re building a device that plays MP3 audio over SPI, reads data from an SD card via SDMMC, and displays content on an LCD. One microcontroller, one core—juggling all these tasks. At first, you test each feature individually. The audio plays beautifully. The LCD looks perfect. The SD card reads and writes flawlessly. Great, right? But then you combine everything, and chaos ensues. The audio starts skipping samples, riddled with clicks and pauses. The SD card randomly fails, freezing functionality. The LCD screen stops updating. And now, you’re deep in the weeds of debugging. This is where the honeymoon phase with LLMs ends. While LLMs can generate functional code snippets, they won’t magically fix real-world integration problems. At this point, relying on LLM recommendations often feels like running in circles—it suggests solutions you’ve already tried a dozen times. The only way forward? Back to the lab. Armed with an oscilloscope or logic analyzer, you dig into the signals, timings, and interactions. You discover that SPI is too slow to keep up with audio sampling, and the timer triggering the SPI transfer is misconfigured. You patch the firmware, but new problems crop up—SDMMC interrupts are causing conflicts, so you switch to DMA to keep things running smoothly. This process can take days, even weeks. It’s a grind. But it’s also why experienced embedded engineers are indispensable. They understand that debugging isn’t just about fixing code—it’s about peeling back layers of complexity to uncover the root cause of failures. The takeaway? LLMs are fantastic for accelerating the early stages of development. They help you write boilerplate code, experiment, and prototype faster. But when it comes to fine-tuning, integration, and real-world reliability, nothing beats the expertise of a seasoned engineer with a scope in hand and the patience to see it through. #EmbeddedSystems #FirmwareDevelopment #Debugging #STM32 #EngineeringChallenges #LLM #Prototyping #Oscilloscope

1

Embark on a fascinating exploration of Courtney Fernandez's remarkable career journey, delving deep into her unexpected transition from the world of embedded systems design to the dynamic realm of industrial automation. Hailing from the heart of Silicon Valley, Courtney's early career was marked by a quest to find her niche in the tech industry, navigating through opportunities and challenges along the way. Initially drawn to the intricacies of circuitry and basic electronics, Courtney's interest took a transformative turn when she ventured into the domain of electric vehicles. Here, she found herself captivated by the sheer power and complexity of motors, igniting a passion for larger-scale systems and machinery that would shape her future endeavors. A pivotal moment came when Courtney joined a company specializing in refinery inspections, where she was introduced to the world of robotics. Working on a project involving a water-powered robo crawler designed for ultrasonic pipe inspections, she was tasked with overcoming a myriad of technical challenges, from robust design to resilient engineering solutions. Through hands-on experience and a thirst for knowledge, Courtney honed her skills in industrial automation, relishing the opportunity to see tangible results of her work in action. Unlike traditional electronics, where feedback might be delayed or abstract, automation offered immediate gratification as she witnessed machines respond to her programming with precision and efficiency. Driven by a passion for systems thinking, Courtney's career trajectory has been characterized by a relentless pursuit of understanding the interconnectedness of components within a larger framework. Whether it's optimizing manufacturing processes or automating tasks to enhance efficiency, she finds fulfillment in orchestrating harmonious systems that yield tangible outcomes. Join us on this captivating journey as Courtney Fernandez shares her insights into the transformative power of automation and the exhilarating experience of seeing the world come to life through the lens of industrial engineering. Through her story, we discover the boundless possibilities that await those who dare to embrace curiosity, adaptability, and the relentless pursuit of innovation.

5

🚀 Bringing AI to Aerospace Flight Hardware Engineering—Beta Test The Aerospace Chatbot Now 🚀 A few folks close to me know I’ve had a personal interest in exploring how AI can make aerospace hardware engineering easier and more efficient. I’ve been working on a project to build a tool that could help engineers quickly access critical information hidden deep in technical documents. It's a common problem in this industry: a wealth of information buried in obscure documents (usually PDFs) from 20+ years ago. My first cut at solving a small cross section of this problem is an AI-powered chatbot that pulls from aerospace mechanisms symposia papers dating back to 2000. I’ve just launched the beta version and would love to get feedback from engineers who work on aerospace systems or flight hardware. Try the tool out below. A few days after you register to access, you'll get a survey to share your experience. ✅ Register to to access the aerospace mechanisms chatbot here: https://bit.ly/406Dco0 ✅ Sign up for updates on future tools or newsletters here: https://bit.ly/3YgekYx #Aerospace #Engineering #AI #FlightHardware #AerospaceMechanisms

35

How MIT’s Clio Enhances Scene Understanding for Robotics - Robotic perception has long been challenged by the complexity of real-world environments, often requiring fixed settings and predefined objects. MIT engineers have developed Clio, a groundbreaking system that allows robots to intuitively understand and prioritize relevant elements in their surroundings, enhancing their ability to perform tasks efficiently. Understanding the Need for Smarter Robots Traditional robotic systems struggle with perceiving and interacting with real-world environments due to inherent limitations in their perception capabilities. Most robots are designed to operate in fixed environments with predefined objects, which limits their ability to adapt to unpredictable or cluttered settings. This “closed-set” recognition approach means […] - https://lnkd.in/epjwYfd3

1

🚀Amazon's Space Race: Project Kuiper Gears Up for Satellite Launch The e-commerce giant is reaching for the stars! This April, a new satellite facility in Kirkland, Washington, opened its doors, promising to supercharge Amazon's satellite production. 📊 The goal? To ship their first completed production satellites this summer! At peak capacity, this cutting-edge facility could produce up to five satellites per day. 🔍 Want to know the technical details behind Amazon's satellite production? Discover the full scope of Project Kuiper in our article: https://lnkd.in/eeUrgnDd

2

🚀 Beyond the Hardware Bottleneck: Advancing Humanoid Robotics with High-Precision Drives Excited to share that we'll be hosting a breakout session at the Humanoids Summit next week in Mountain View, California. Diving into one of robotics' most pressing challenges—overcoming current actuator hardware limitations. While software and AI have made incredible strides, hardware lags behind, bottlenecking what humanoid robots can achieve in real-world, complex environments. Enter the Archimedes Drive: a high-precision drive system that tackles these bottlenecks with true zero-backlash technology, enabling humanoids to move with accuracy, efficiency, and resilience. Join us as Thibaud Verschoor will explore: 🔹 The engineering principles behind this groundbreaking innovation 🔹 How high-precision mechanics unlock next-gen humanoid capabilities 🔹 Real-world applications pushing the boundaries of robotics Whether you're an engineer, roboticist, or just curious about the future of humanoid technology, this session will highlight how overcoming hardware constraints can redefine what's possible. Let’s rethink the limits of robotics together. See you there! 💡 #Robotics #Humanoids #PrecisionEngineering #Innovation

32

Drone Operations Boosted with ROS2 Developments on VOXL 2 >> https://hubs.ly/Q02-vCl_0 Ascend Engineering has written a comprehensive software package that integrates the power of ROS2 (Robot Operating System 2) with the VOXL 2 platform from ModalAI. By converting MPA data pipelines to ROS2 messages, the package ensures that operators can leverage the powerful tools and libraries available within the ROS2 ecosystem, unlocking new possibilities for data processing, visualization, and control. Find out more about the Ascend Engineering ROS2 code on the VOXL 2-SDK package on the UST website.

13

2 Comments

What would happen if a small-scale robot could generate a large force? Researchers from City University of Hong Kong design a triple-magnet system that enables reversible and repeatable magnetic collisions to generate large force outputs in a recent T-RO paper. https://lnkd.in/gvcm8BUr Paper title: MINRob: A Large Force-Outputting Miniature Robot Based on a Triple-Magnet System Authors: Yuxuan Xiang, Ruomao Liu, ZIHAN WEI, 王新亮, Weida Kang, Min Wang, Jun Liu, Ph.D., Xudong Liang, and Jiachen Zhang #RoboticSystems #MedicalRobots #Robots

23

We're developing application tools based on ROS (Robot Operating System) to democratize access to robotics and remove development barriers. Developers throughout the automation ecosystem will be able to program robotic devices and integrate their hardware with other automated equipment and production systems. Learn more: https://lnkd.in/eRnD7rwY #robotics #robots #ROS #developers #automation

11

🎙️ Solving the Pain Points of Robotics with Eclipse Zenoh For years, DDS has been the backbone of the ROS ecosystem in robotics. Despite its strengths, it struggles with scaling down to small devices and wireless networks. Join Julien Enoch and Angelo Corsaro as they delve into these challenges on our podcast. Listen now and leave thoughts ⬇️ https://buff.ly/3yjXr5Q #DDS #robotics #ROSCon

7

▶ Robotics Programming One of the most fundamental bases of a robotic system is motion and cartesian positioning in 3D space. To correctly program your robot, you need to understand how a robot interprets the space surrounding it. This tutorial will cover the basics of robot positions, how you define them in a robotic system, and the standard robot coordinate frames. By the end of this tutorial, you will have a basic understanding of the skills you will need as a Robotics Engineer. #robotics #industrialrobotics #plcprogramming #plctraining #manufacturing #plcs #industrialautomation #industrialengineering

29

3 Comments

▶ Robotics Programming One of the most fundamental bases of a robotic system is motion and cartesian positioning in 3D space. To correctly program your robot, you need to understand how a robot interprets the space surrounding it. This tutorial will cover the basics of robot positions, how you define them in a robotic system, and the standard robot coordinate frames. By the end of this tutorial, you will have a basic understanding of the skills you will need as a Robotics Engineer. #robotics #industrialrobotics #plcprogramming #plctraining #manufacturing #plcs #industrialautomation #industrialengineering

22

1 Comment

Researchers at Johns Hopkins APL have made significant progress toward tackling the fundamental challenges preventing fieldable multi-robot teams from becoming a reality. 🤖 https://jhuapl.link/ac7 One key challenge the team is addressing is the immense computational complexity involved. Each robot must not only navigate unpredictable environments and perform tasks but also synchronize its movements and actions with its team. On top of that, both teams must coordinate their movements and actions in real-time, adapting to dynamic, fluid situations. As each additional robot contributes exponentially to the complexity of the calculations involved, it’s easy to see how the problem quickly becomes intractable. Joseph Moore, chief scientist for the Robotics Group in APL’s Research and Exploratory Development Department, and his team applied a creative spin to topological graph techniques used for multirobot collision avoidance. They discovered a relationship between a robot’s location on a graph and the characteristics of the graph itself. For example, if a robot is currently at point A and can navigate to either point B or C, the relative risk of each choice differs quantifiably from the risks if the robot were navigating from point D. In other words, the robot’s current state directly relates to the relative risks of each possible action, and these risks can be represented as “costs” for each action — and crucially, those costs are quantifiable. The team successfully implemented a framework called Stratified Topological Autonomy with Learned Contexts (STALC) in simulations of real-world missions using multi-robot teams. This framework manages everything from high-level planning to individual robot actions. They also demonstrated their algorithms on live robots during an exercise in Texas this past June. #JHUAPL | U.S. Army DEVCOM Army Research Laboratory | #Robotics | #MultiRobotSystems | #ArtificialIntelligence | #Automation

71

In "Prototypes to Production", I interview Tom Ryden, Executive Director of MassRobotics while at Robotics Invest. Tom discussed the vital role MassRobotics plays in supporting the thriving robotics community in Boston. Founded nearly a decade ago, MassRobotics provides a comprehensive space for young startups, offering lab and prototyping facilities, essential networking opportunities, and connections to industry leaders. Their mission is to help startups grow and stay in Massachusetts, fostering innovation and economic development. MassRobotics collaborates closely with entities like MassChallenge and venture capital firms, ensuring that startups have the resources and support needed to scale their ideas. Tom highlighted the importance of networking and the invaluable insights gained from events like Robotics Invest, where investors and startups come together to share knowledge and forge partnerships. Massachusetts continues to be a hotbed for robotics, with established companies like Amazon Fulfillment Technologies & Robotics and Boston Dynamics, a vibrant startup community, and cutting-edge research from top universities. This ecosystem creates a unique and fertile ground for innovation. For those interested in learning more about MassRobotics or getting involved as a mentor or partner, visit their website at massrobotics.org. Whether you’re a startup looking for support or an expert eager to share your knowledge, MassRobotics offers numerous opportunities to engage and contribute to the robotics community. Thank you for introducing us, Ben Linville-Engler! 📺 Watch “Prototypes to Production: How MassRobotics Supports Startups | Tom Ryden” https://lnkd.in/epDENXQS

7