Introducing Universal Manipulation Exoskeleton (UME) A low-cost exoskeleton with... real-time haptic torque feedback for learning autonomous policies that perform highly force-mediated, tightly space-constrained, visually occluded, whole-body, and long-horizon mobile manipulation tasks. Using UME, the teleoperator can unsheathe a heavy metal sword completely blindfolded. 🧵1/Nshow more

Learning bimanual, contact-rich robot manipulation policies that generalize over... diverse objects has long been a challenge. Excited to share our work: Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation! 🧵1/nshow more

Using the classic trick of scrap metal, teleportation, and... time manipulation to create a completely safe elevator... 😏show more

How can non-experts quickly teach robots a variety of... tasks? Introducing HAND ✋, a simple, time-efficient method of training robots! Using just a **single hand demo**, HAND learns manipulation tasks in under **4 minutes**! 🧵show more

Seeing ≠ feeling in robotics🤖. Collecting data without force... feedback is not only frustrating but also doesn’t work for contact-rich tasks. Introducing FACTR: a low-cost teleop that lets users feel what the robot feels + a simple algo to integrate force into autonomous policies. Video doesn't do justice, but feels magical in person!🚀 Also removes the need for gravity compensation strings.show more

Innovative Autonomous Exoskeleton Helping People with Disabilities

Track2Act: Our latest on training goal-conditioned policies for diverse... manipulation in the real-world. We train a model for embodiment-agnostic point track prediction from web videos combined with embodiment-specific residual policy learning 1/nshow more

exoskeleton suit controlling a robot in real-time

Humanoids 🤖 will do anything humans can do. But... are state-of-the-art algorithms up to the challenge? Introducing HumanoidBench, the first-of-its-kind simulated humanoid benchmark with 27 distinct whole-body tasks requiring intricate long-horizon planning and coordination. 🧵👇show more

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA... Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵show more

GR-RL Going Dexterous and Precise for Long-Horizon Robotic Manipulation

ManiFeel is a benchmark for contact-rich manipulation tasks. Force-... and tactile-based tasks with occlusions and partially-observable state are going to be crucial for true general purpose robotics. Website:show more

✨ Any static 3D assets ➡️ 4D dynamic worlds.... Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs. It generalizes surprisingly well across a wide range of objects 🤯 and can even be used to learn robotics manipulation policy 🤖! Project page: Dive deeper in a 🧵: 1/nshow more

A behind-the-scenes video on how teleoperation is done. Whole-body... manipulation with only a VisionPro.show more

Long-horizon visual goals remain surprisingly hard for robot manipulation.... We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.show more

You can rent a robotic exoskeleton to hike a... mountain for just $8.50.show more

A Zimbabwean merchant using crutches walked normally at the... 139th Canton Fair -- thanks to a wearable exoskeleton. He bought it on the spot and now aims to bring the technology to Africa. Innovation meets opportunity. #CantonFair #exoskeleton #roboticsshow more

Can we robustly track an object’s 6D pose in... contact-rich, occluded scenarios? Yes! Our solution, V-HOP, fuses vision and touch through a visuo-haptic transformer for precise, real-time tracking. arXiv: Project:show more

🚀 Introducing Frank 🤖—a whole-body robot control system for... day-to-day household chores. Frank has been in works for the past year—a tightly coupled hardware and a remote teleoperation interface co-led by Michelle, Nandini, and Pulkit Agrawal. Thanks to Aditya Agarwal and Shankara Narayanan for the awesome help with recording the videos! 🎥 🧵[1/6]show more

Meet #HillbotAlpha, the first fully autonomous mobile manipulation robot... trained using sim-to-real technology. Designed in Hillbot’s San Diego headquarters, Hillbot Alpha represents the potential of data synthesis via simulation in robotics. Through a robust strategy that combines a small sample of real-world data with synthetic data, Hillbot Alpha can effectively adapt to evolving task requirements and environments while working safely beside humans. #Hillbot #AGI #EmbodiedAI #AI #Sim2Real #ArtificialIntelligence #Simulation #Simtorealshow more

A Rerun Viewer for the DROID Dataset! DROID: A... Large-Scale In-The-Wild Robot Manipulation Dataset is a robot manipulation dataset by Alexander Khazatsky et al. with 76k demonstration trajectories or 350h of interaction data, collected across 564 scenes and 86 tasks.show more