Autonomous Robotics for Advanced Applications

Happy to share our latest paper, "Enabling Novel Mission Operations and Interactions with ROSA: The Robot Operating System Agent". This work was led by Rob R. in collaboration with Marcel Kaufmann, Jonathan Becktor, Sangwoo Moon, Kalind Carpenter, Kai Pak, Amanda Towler, Rohan Thakker and myself. Please find the #OpenSource code, paper, and video demonstration linked below. Operating autonomous robots in the field is often challenging, especially at scale and without the proper support of Subject Matter Experts (SMEs). Traditionally, robotic operations require a team of specialists to monitor diagnostics and troubleshoot specific modules. This dependency can become a bottleneck when an SME is unavailable, making it difficult for operators to not only understand the system's functional state but to leverage its full capability set. The challenge grows when scaling to 1-to-N operator-to-robot interactions, particularly with a heterogeneous robot fleet (e.g., walking, roving, flying robots). To address this, we present the ROSA framework, which can leverage state-of-the-art Vision Language Models (VLMs), both on-device and online, to present the autonomy framework's capabilities to operators in an intuitive and accessible way. By enabling a natural language interface, ROSA helps bridge the gap for operators who are not roboticists, such as geologists or first responders, to effectively interact with robots in real-world missions. In our video, we demonstrate ROSA using the NeBula Autonomy framework developed at NASA Jet Propulsion Laboratory to operate in JPL's #MarsYard. Our paper also showcases ROSA's integration with JPL's EELS (Exobiology Extant Life Surveyor) robot and the NVIDIA Carter robot in the IsaacSim environment (stay tuned for ROSA IssacSim extension updates!). These examples highlight ROSA's ability to facilitate interactions across diverse robotic platforms and autonomy frameworks. Paper: https://lnkd.in/g4PRjF4V Github: https://lnkd.in/gwWXmmjR Video: https://lnkd.in/gxKcum27 #Robotics #Autonomy #AI #ROS #FieldRobotics #RobotOperations #NaturalLanguageProcessing #LLM #VLM

Researchers at EPFL have unveiled an innovative robot bird that blends terrestrial and aerial locomotion through advanced physics and engineering principles. Inspired by the biomechanics of avian species, it features lightweight, robust materials and multifunctional legs that store and release energy efficiently, enabling powerful jumps for rapid takeoffs. These legs are modeled to mimic the spring-like motion of tendons and muscles, leveraging principles of elastic potential energy to convert stored energy into kinetic energy during liftoff. This allows for faster, more energy-efficient flight initiation compared to traditional propeller-driven systems, which rely on continuous motor operation to achieve lift. The robot also integrates advanced aerodynamics for stable flight, utilizing biomimetic wing designs that optimize lift-to-drag ratios. Its ability to walk and hop over obstacles stems from precision actuators and sensors that calculate optimal force and trajectory, ensuring smooth transitions between ground and air mobility. These features make it highly adaptive to complex terrains, from rocky landscapes to dense forests, where conventional drones and robots would struggle. Future prospects for this #technology are promising. Its multi-modal capabilities could be applied in search-and-rescue missions, where navigating through collapsed structures or dense vegetation requires both ground movement and aerial maneuverability. In planetary exploration, it could traverse rugged terrains on Mars or the Moon, combining the efficiency of walking with the flexibility of flight. Further advancements may include incorporating solar-powered systems for extended autonomy, swarm robotics for collaborative tasks, and machine learning algorithms to enhance decision-making and obstacle avoidance. This groundbreaking #design not only bridges the gap between terrestrial and aerial robotics but also sets the stage for a new era of versatile, energy-efficient robotic systems capable of tackling a wide range of environmental and industrial challenges. 🎥@EPFL Video rights are reserved for the respective owner. #innovation #whatinspiresme

Robots are leaving the lab. In our Tech Trends 2026 report, I was privilege to be one of the co-authors of the Physical AI chapter (with Jim Rowan, Tim Gaus)—looking at how vision‑language‑action models, onboard NPUs, and modern robotics are pushing autonomous systems from pilots into production. What’s changing: • Physical AI turns robots into adaptive machines that perceive, reason, and act in real time—far beyond preprogrammed automation.  • Onboard compute allows split‑second decisions without cloud dependency, which is critical for safety‑critical environments.  • Economics are improving fast: component commoditization and advanced manufacturing are bringing reliability and scale. Where it’s real: • Amazon’s millionth robot—coordinated by DeepFleet AI—improved fleet travel efficiency ~10%.  • BMW plants have vehicles driving themselves through testing and finishing routes.  • Waymo has passed 10 million paid robotaxi rides; Aurora is hauling freight driverlessly between Dallas and Houston.  • Cities are using AI‑powered drones for bridge inspections; Detroit launched an accessible autonomous shuttle service. Humanoids on the horizon: UBS estimates ~2 million humanoids in workplaces by 2035 and a US$30–50B TAM—driven first by logistics and health care use cases, then consumer scenarios as cost curves fall. What still needs work: Sim‑to‑real training gaps, comprehensive safety governance, cybersecurity for connected fleets, and orchestration across heterogeneous robots. The next 18–24 months will be defined by organizations that tackle these fundamentals. https://lnkd.in/esiAtMN6 Firms like Agility Robotics • Apptronik • Figure • Sanctuary AI • 1X • Cobot • Tesla Optimus • Boston Dynamics • Diligent Robotics • NVIDIA are paving the way to the future. #PhysicalAI #Robotics #Humanoids #Logistics #Manufacturing #Healthcare #SmartCities

Robotics and Physical AI are moving our industry beyond deterministic automation toward adaptive, physics-aware, self-optimizing production systems. A new ASME framework on Physical Artificial Intelligence for Engineering Systems formalizes the stack for this including multimodal perception, physics-grounded world models, learning-based control, simulation-to-reality transfer, and cloud–edge autonomy for real industrial environments. By integrating this stack into next-generation automation we can achieve: • Embodied AI for manipulation, dexterity, compliant control, logistics, assembly • Robotics foundation models for perception, task planning, motion generation, grasp synthesis • High-fidelity digital twins + real-time MPC + model-based RL for closed-loop optimization • Industrial Edge + deterministic control for latency-critical robotic autonomy • Safe HRC with runtime monitoring, verification, and safety-certified architectures • Autonomous, polyfunctional robotic cells capable of reconfiguration, self-calibration, and rapid changeover https://lnkd.in/ghTqd7G2 #PhysicalAI #EmbodiedAI #Robotics #IndustrialRobotics #AutonomousRobots #PolyfunctionalRobots #RobotLearning #ReinforcementLearning #FoundationModels #RoboticsFoundationModels #MultimodalPerception #3DVision #SceneUnderstanding #MotionPlanning #TrajectoryOptimization #ModelPredictiveControl #MPC #DigitalTwin #IndustrialDigitalTwin #CyberPhysicalSystems #CPS #Sim2Real #SimulationToReality #IndustrialEdge #EdgeComputing #DistributedControl #RealTimeControl #AdaptiveAutomation #FlexibleManufacturing #HighMixLowVolume #HRC #HumanRobotCollaboration #SafetyEngineering #FunctionalSafety #Verification #RuntimeMonitoring #GenerativeDesign #AutonomousMachining #PrecisionAssembly #SelfCalibration #ZeroTouchDeployment #IndustrialMetaverse #StochasticAutomation #ResilienceEngineering #Industry4_0 #Industry5_0 #SmartFactory #FutureOfManufacturing #Siemens

We hear it constantly: “Humanoid robots are coming.” For some, that sparks anxiety. For researchers at Georgia Tech, it’s an engineering challenge and an exciting one. A team led by Ye Zhao at Georgia Tech’s Laboratory for Intelligent Decision and Autonomous Robots has developed a new real-time planning and control framework that significantly improves how two-legged robots maintain balance and recover from instability. Why does this matter? Bipedal robots offer incredible advantages — navigating uneven terrain, working in dynamic environments, and operating in spaces designed for humans. But stability has always been the Achilles’ heel. Their new approach gives robots a kind of “thinking layer”: ✅ Real-time decision-making when plans fail ✅ Adaptive step adjustments for stability ✅ Faster recovery when unexpected disturbances occur ✅ An 81% improvement in recovery performance Tested on the Cassie robot, the framework allowed stable walking on moving platforms and unpredictable terrain — key milestones if humanoids are to move beyond demos and into real-world deployment. The bigger lesson here: Progress in humanoids isn’t just about better motors or mechanical design. It’s about intelligence — planning, adaptability, and safe interaction with dynamic environments. If humanoid robots are going to work alongside us in factories, logistics, or even offshore environments, this kind of foundational research is exactly what will make them reliable. Read the research here: https://lnkd.in/eJ5EKm45

DARPA Redefines Space Construction with Autonomous Robots Space exploration is about to get a major upgrade. The Defense Advanced Research Projects Agency (DARPA) is gearing up to test orbital construction through its Novel Orbital Moon Manufacturing, Materials, and Mass-efficient Design (NOM4D) program, launched in 2022. Forget bulky, pre-built components constrained by rocket size—DARPA’s goal is to assemble large, lightweight structures directly in space. Now, in early 2025, NOM4D’s third phase is moving from labs to orbit, with demonstrations slated for 2026 spotlighting a revolutionary technology: autonomous robotic assembly. Orbital Tests Take Shape Two university teams are leading the charge. The California Institute of Technology (Caltech) will send a free-flying robot aboard a Momentus Vigoride vehicle, launched via SpaceX Falcon 9, to autonomously build a 1.4-meter truss in low-Earth orbit. Meanwhile, the University of Illinois Urbana-Champaign (UIUC) will test frontal polymerization—a method to harden composites in space without heavy equipment—aboard the International Space Station. These experiments aim to show that massive structures like antennas, solar arrays, or refueling stations can be crafted efficiently beyond Earth, unshackling design from launch limitations. How Autonomous Robotic Assembly Works Caltech’s test hinges on autonomous robotic assembly: robots building complex frameworks without human oversight. Imagine a robotic system with arms and sensors, floating in microgravity, guided by onboard intelligence. It scans its surroundings with cameras or lasers, plans each move with precision, and uses mechanical arms to connect parts—often within razor-thin tolerances. If a piece shifts mid-process, the robot adapts instantly. In orbit, this could mean turning compact materials into a sturdy truss, all hundreds of miles above Earth, no Earthside controller required. Why It’s a Game-Changer Rockets can’t haul giant structures, but they can carry raw materials. Autonomous assembly is like shipping IKEA flat-packs instead of a fully built desk—only the desk builds itself. This unlocks possibilities like sprawling solar panels for satellites, deep-space antennas, or orbital fuel depots, all constructed where they’re needed. For DARPA, it’s a strategic edge; for commercial space, it’s a blueprint for lunar bases or asteroid mining hubs. Faster, cheaper, and more adaptable, this tech could redefine space infrastructure. Looking to the Stars As February 24, 2025, ticks closer to these 2026 trials, anticipation builds. Caltech’s truss and UIUC’s material tests are small steps with big potential—proofs of concept that could scale up dramatically. If NOM4D succeeds, DARPA may not just transform how we build in space but where we dream humanity’s future lies: out there, with robots paving the way. https://lnkd.in/eZwet6Va UI Urbana-Champaign

A single robot that can drive like a car, stand upright to get a better view, crawl over tricky terrain, and even take off like a drone - all by adjusting the same four “limbs.” That’s what the M4 Morphobot from Caltech accomplishes. Each wheel can swivel and fold into different positions: as standard wheels for rolling, as “legs” to step over uneven ground, or as propellers for flight. In doing so, this machine sidesteps the limitations that often come with single-purpose designs. How does it work? The M4 carries sensors and an onboard AI processor (NVIDIA Jetson Nano) that help it monitor its surroundings and plan routes in real time. For instance, it uses SLAM (Simultaneous Localization and Mapping) to create a map of the area on the fly, then relies on path-planning algorithms (like A*) to pick the best way forward. If it meets a gap or obstacle that rolling wheels can’t handle, it can switch modes - standing up to get a better look or converting into a drone to fly over the blockage. In real-world situations like search-and-rescue, one type of movement isn’t always enough. Think about collapsed buildings, rugged wilderness, or areas struck by natural disasters. A robot with such adaptability could roll quickly across clear ground, crawl under rubble, and then lift off to reach otherwise inaccessible places - all without specialized add-ons or multiple machines. For space exploration, a “rover-drone hybrid” could tackle rocky planetary surfaces, then take flight to jump over craters or cliffs. NASA’s interest in multi-modal designs hints at a future where one shape-shifting robot might replace several single-mode explorers. What do you think about the future of multi-modal robots with the power of AI? #innovation #technoloy #future #management #startups

What if robots could handle heavy logistics over rough terrain, without tracks or human help? [⚡Join 2300+ Robotics enthusiasts - https://lnkd.in/dYxB9iCh] A paper by Marco Arnold, Lukas Hildebrandt, Kaspar Janssen, Efe Ongan, Pascal Bürge, Ádám Gyula Gábriel, James Kennedy, Rishi Lolla, Quanisha Oppliger, Micha Schaaf, Joseph Church, Michael Fritsche, Victor Klemm, Turcan Tuna, Giorgio Valsecchi, Cedric Weibel, Michael Wüthrich, and Marco Hutter Introduces LEVA: a high-payload, high-mobility robot for autonomous logistics across varied terrains. "LEVA: A high-mobility logistic vehicle with legged suspension" • Integrates a legged suspension system using parallel kinematics for enhanced mobility • Traverses stairs and uneven terrain using a reinforcement learning controller • Features steerable wheels and a specialised box pickup mechanism for autonomous payload handling • Transports up to 85 kg across uneven surfaces, steps, and inclines • Achieves a cost of transport as low as 0.15 • Demonstrates off-road capabilities and reliable payload transport through extensive experimental validation LEVA combines the adaptability of legged locomotion with the efficiency of wheeled systems. It addresses the challenge of autonomous material transportation over challenging terrains with significant economic implications. If robots can autonomously handle logistics in unstructured environments, what new applications could this unlock? Paper: https://lnkd.in/gapBPZmr Video - https://lnkd.in/gbE7HNYH #Robotics #AutonomousVehicles #Logistics #ReinforcementLearning #ICRA2025

 🚀 The Secret to Autonomy: Why Every High-Performance Robot Needs a Digital Twin Did you know that the only reason complex robots and drones function reliably in the real world is because they were first trained in a digital clone? Full autonomy requires AI agents that can handle the unpredictable chaos of reality. Simple simulations fail; the solution is combining Reinforcement Learning (RL) with Digital Twins.  🧠 The Core Training Unlock A Digital Twin is a hyper-accurate virtual copy of a real system, mirroring physics and sensor noise. This risk-free environment is where the magic happens:  Reward Shaping: We teach the AI morality and efficiency. Precise feedback—like high Rewards for progress and escalating Penalties for collisions—sculpts the safe, reliable policy.  Physics Check: The twin guarantees the learned behavior will transfer successfully.  🌍 Why This Matters: Real-World Use Cases This high-fidelity training is essential for critical applications:  Logistics: Training AMRs for zero-collision efficiency in dynamic warehouses.  Search & Rescue: Creating resilient AI pilots that fly safely through smoke and wind.  Space Exploration: Ensuring rovers achieve autonomous survival on distant planets.  📈 My Focus: Building the Future This synthesis of RL, Digital Twins, and advanced Physics is why I'm learning in public and dedicating my time to mastering these skills. My interest is shifting from traditional cloud infrastructure toward physical AI because the challenge and potential are immensely compelling. By building this expertise now, I am creating a unique lane to help teach and mentor others in 2026 and beyond, providing the core skills needed for the next wave of automation. The ability to combine the digital and the physical is the big unlock for AI. #AI #DigitalTwins #ReinforcementLearning #Robotics #Autonomy #CredibleSkills

Robots are moving into new kinds of work. Tasks that were once too variable, manual, or uneconomical to automate are now being handled across environments like security, food processing, and field services. This month’s news surfaced signals like these: 🐕 Faraday Future’s FX Aegis quadruped cleared U.S. compliance testing and is moving into formal sales, designed for security, patrol, and companionship use cases that require mobility across complex environments. 🥩 Chef Robotics expanded its platform into meat tray assembly, applying robotic picking systems to one of the more difficult categories in food processing, where products vary in shape, size, and texture. 🧼 Lucid Bots is scaling autonomous exterior cleaning through a robotics-as-a-service model, with close to 1,000 robots deployed across commercial jobs ranging from building washing to pressure cleaning. Why this matters: Robotics is showing up across more industries, not just a few controlled environments. The same advances in perception, manipulation, and autonomy are now being used in very different kinds of work. Adoption is starting to move faster across more categories. Read more: https://lnkd.in/g4Y6evXU #spatialcomputing #physicalAI #robotics