Advances in Self-Modifying Robotics Technology

🚀 New paper from our lab: Sym2Real: a data-efficient way to train adaptive robot controllers. With only ~10 trajectories (80 seconds!!!) in total (most from a low-fidelity and untuned sim + 2–3 real runs), we achieve robust real-world control of a palm-sized drone and a 1/10 racing car. No expert priors on dynamics or heavy sim tuning needed. 📹 The video below shows the entire 80-second demo video, from the beginning to flying. The key intuition is to capture the shared core physics in a simplified setting with concrete equations (in our case, differential equations!), then adapt with a lightweight residual from just a handful of real-world samples. This continues our line of work on robot self-models for resilient behaviors: - Visual self-modeling of full bodies (Science Robotics 2022) - Self-modeling animatronic face control (ICRA 2021, Science Robotics 2024) 📄 Read our preprint: https://lnkd.in/eZrb6i3d 🎥 Video: https://lnkd.in/e3dMUs3J 🔬 Code + data: https://lnkd.in/e24ayhJ2 Led by our amazing Easop Lee at the General Robotics Lab at Duke University!

Humanoid robots need to adapt to different tasks, like moving around, handling objects while walking, and working on tables, each requiring a unique way to control the robot’s body. For instance, moving around focuses on tracking how fast the robot's base is moving, while working at a table relies more on controlling the robot's arm movements. Many current methods train robots with specific controls for each task, making it hard for them to switch between tasks smoothly. This new approach suggests using whole-body motion imitation to create a common base that can work for all tasks, helping robots learn general skills that apply to different types of control. With this idea, researchers developed HOVER (Humanoid Versatile Controller), a system that combines different control modes into one shared setup. HOVER allows robots to switch between tasks without losing the strengths needed for each one, making humanoid control easier and more flexible. This approach removes the need to retrain the robot for each task, making it more efficient and adaptable for future uses. The diverse team of researchers that developed HOVER come from: NVIDIA,  Carnegie Mellon University, University of California, Berkeley, The University of Texas at Austin, and UC San Diego. 📝 Research Paper: https://lnkd.in/eMatAxMu 📊 Project Page: https://lnkd.in/eY4gzmme #robotics #research

Three minutes. No humans. Walker S2 walked itself to a docking station, swapped its own battery, and walked back That’s not a demo. It’s the world’s first humanoid robot doing it autonomously. What impressed me isn’t the agility, it’s the maturity. Walker S2’s hot-swap system and dual-battery logic mean a robot can now operate 24/7, adjusting its energy levels proactively based on task priorities. That’s infrastructure-level autonomy. Here’s what this means for the future: • Operational Resilience – No more downtime waiting for humans to recharge robots. Imagine warehouses, clean rooms, or hospitals—robots that never clock out. • Scalability on Autopilot – Teams won’t need constant oversight. They can scale deployments knowing the system handles its own uptime. • New Design Paradigm – This isn’t about a single task. It’s about embedding autonomy in the fabric of systems—robots that manage themselves as we manage our time. For me, Walker S2 is a milestone not just in robotics, but in design thinking. If machines can handle their own power logistics, it frees us to focus on creativity, strategy, and the uniquely human work that machines can’t touch… yet. #ArtificialIntelligence #AI #Robotics #Technology #Innovation #WalkerS2

Teaching robots to build simulations of themselves allows the robot to detect abnormalities and recover from damage. We naturally visualize and simulate our own movements internally, enhancing mobility, adaptability, and awareness of our environment. Robots have historically been unable to replicate this visualization, relying instead on predefined CAD models and kinematic equations. Free Form Kinematic Self-Model (FFKSM) allows the 𝗿𝗼𝗯𝗼𝘁 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗶𝘁𝘀𝗲𝗹𝗳: 1) Robots autonomously learn from their morphology, kinematics, and motor control directly from 𝗯𝗿𝗶𝗲𝗳 𝗿𝗮𝘄 𝘃𝗶𝗱𝗲𝗼 𝗱𝗮𝘁𝗮 -> Like humans observing their reflection in a mirror 2) Robots perform precise 3D motion planning tasks 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗽𝗿𝗲𝗱𝗲𝗳𝗶𝗻𝗲𝗱 𝗸𝗶𝗻𝗲𝗺𝗮𝘁𝗶𝗰 𝗲𝗾𝘂𝗮𝘁𝗶𝗼𝗻𝘀 -> Simplifies complex manipulation and navigation tasks 3) Robots 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀𝗹𝘆 𝗱𝗲𝘁𝗲𝗰𝘁 morphological changes or damage and rapidly recover by retraining with new visual feedback -> Significantly enhances resilience. The model is also 𝗵𝗶𝗴𝗵𝗹𝘆 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁, requiring minimal memory resources of just 333kB, making it broadly applicable for resource constrained robotic systems. 𝗧𝗵𝗶𝘀 𝗶𝘀 𝗮𝗹𝘀𝗼 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗮𝗰𝗵𝗶𝗲𝘃𝗲 𝘀𝘂𝗰𝗵 𝗰𝗼𝗺𝗽𝗿𝗲𝗵𝗲𝗻𝘀𝗶𝘃𝗲 𝘀𝗲𝗹𝗳-𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝘂𝘀𝗶𝗻𝗴 𝗼𝗻𝗹𝘆 𝟮𝗗 𝗥𝗚𝗕 𝗶𝗺𝗮𝗴𝗲𝘀, 𝗲𝗹𝗶𝗺𝗶𝗻𝗮𝘁𝗶𝗻𝗴 𝗰𝗼𝗺𝗽𝗹𝗲𝘅 𝗱𝗲𝗽𝘁𝗵-𝗰𝗮𝗺𝗲𝗿𝗮 𝘀𝗲𝘁𝘂𝗽𝘀 𝗮𝗻𝗱 𝗶𝗻𝘁𝗿𝗶𝗰𝗮𝘁𝗲 𝗰𝗮𝗹𝗶𝗯𝗿𝗮𝘁𝗶𝗼𝗻𝘀. I believe the next phase of robotic automation inevitably comes with self-awareness of robots. Self-reflection is a major part of how we as humans improve upon ourselves; as 'general purpose robots' emerge, so would their self-reflection. This enables robots to continuously monitor and update their internal models, thereby refining their performance in real time. This is a huge step towards robot self-awareness! Congratulations to Yuhang Hu, Jiong Lin, and Hod Lipson on this impressive advancement! Paper link: https://lnkd.in/gJ-bkU8N I post the latest and interesting developments in robotics—𝗳𝗼𝗹𝗹𝗼𝘄 𝗺𝗲 𝘁𝗼 𝘀𝘁𝗮𝘆 𝘂𝗽𝗱𝗮𝘁𝗲𝗱!

🌊 A new kind of machine — liquid, adaptive, and self-healing. Researchers have developed a liquid robot that can deform, merge, split, and squeeze through narrow spaces — yet maintain its structure. It’s built with a liquid core wrapped in super-hydrophobic particles, creating what they call a Particle-armored liquid robot. It can move, adapt, and even heal itself when broken apart. At millimeter scale today, its potential future applications are fascinating — not just in biomedicine but also in infrastructure and energy systems: ⚙️ Data centers: Imagine self-adaptive micro-robots managing liquid cooling systems, repairing micro-leaks, or optimizing thermal transfer in high-density racks — autonomously. ☀️ Renewables: In solar and battery energy storage systems, liquid robotics could support real-time micro-maintenance, self-healing coatings, or fluid-based efficiency optimization in thermal and chemical storage processes. As AI gave machines a brain, liquid robotics might give them a body capable of evolving — flexible, resilient, and efficient. The boundary between biology and engineering keeps getting thinner.