We present🌊AquaBot🤖: a fully autonomous underwater manipulation system powered by visuomotor policies that can continue to improve through self-learning to perform tasks including object grasping, garbage sorting, and rescue retrieval. aquabot.cs.columbia.edu more details👇

This project was led by my stellar PhD student Georgios Papagiannis (George Papagiannis), and we will both be in Munich next week to present this at CoRL 2024. Come and say hi! 😀 To read the full paper and see further videos, please visit: robot-learning.uk/miles. Thanks for reading! 👋

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N

Introducing TAX3D, in which we extend relative-placement methods to generalizable deformable manipulation! #CoRL2024 (1/🧵) Our approach generalizes to: - Diverse unseen objects - Diverse unseen configurations - Multimodal placements

[1/N] Ambiguities are common in manipulation: objects can be inherently multimodal (e.g., fully-closed doors🚪), and severe occlusions add uncertainty! This poses challenges to deterministic models. Check out FlowBotHD🤖, a history-aware diffusion handling ambiguities #CoRL2024

🚀Excited to share SceneComplete: an open-world 3D scene completion system for constructing a complete, segmented 3D model of a scene from a single RGB-D image.🖼️🤖 SceneComplete enables dexterous grasping and robust robot manipulation in highly cluttered scenes - a short 🧵

Our technical report is here: arxiv.org/abs/2411.00704 🔊🔊 SOUND ON!! Here's a clip of you coming back home to 🤖 Frank 🤖setting up your dinner table 🫘😋🍲🥘🍢

Prof. Madhava Krishna briefly explains the way IIITH’s self-driving car works and what is novel about it. This is an edited excerpt from the TechForward research seminar series. blogs.iiit.ac.in/ai-classical-r…

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Unitree B2-W Talent Awakening! 🥳 One year after mass production kicked off, Unitree’s B2-W Industrial Wheel has been upgraded with more exciting capabilities. Please always use robots safely and friendly. #Unitree #Quadruped #Robotdog #Parkour #EmbodiedAI #IndustrialRobot

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning

"The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise." — Edsger Dijkstra

Here you go! Tangible is putting robots to real use!! Tangible is solving dexterity—this is a hard problem, WHICH IS WHY—Tangible is HIRING 🚨!! Tangible is making robots that can go into your cluttered sink, cluttered fridge, and get you the apple you wanted that was

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

Despite great advances in learning dexterity, hardware remains a major bottleneck. Most dexterous hands are either bulky, weak or expensive. I’m thrilled to present the RUKA Hand — a powerful, accessible research tool for dexterous manipulation that overcomes these limitations!

📷 Can AI understand camera motion like a cinematographer? Meet CameraBench: a large-scale, expert-annotated dataset for understanding camera motion geometry (e.g., trajectories) and semantics (e.g., scene contexts) in any video – films, games, drone shots, vlogs, etc. Links

You don't need humanoids to do dexterous manipulation. Robots are limited by intelligence, not because they're not shaped like humans.

Exciting new work from Yufei and co. !!

Check out our new work Points2Reward: Robotic Manipulation Rewards from Just One Video at #RSS2025 Workshop on Semantic Reasoning and Goal Understanding in Robotics (SemRob)! Points2Reward computes dense rewards from a single human video. To do this, P2R tracks task-relevant

Very cool work Sungjae Park !!