🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

what's the move? a question i ask the group chat when i’m bored... and now, my robot too. enter SPHINX: a hybrid IL agent that dynamically selects its action space (waypoints / dense actions) and input type (point clouds / wrist images) for precise, generalizable manip! 🧵 1/7

When will robots help us with our household chores? TidyBot++ brings us closer to that future. Our new open-source mobile manipulator makes it more accessible and practical to do robot learning research outside the lab, in real homes!

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics

There are great tokenizers for text and images, but existing action tokenizers don’t work well for dexterous, high-frequency control. We’re excited to release (and open-source) FAST, an efficient tokenizer for robot actions. With FAST, we can train dexterous generalist policies

Human videos contain rich data on how to complete everyday tasks. But how can robots directly learn from human videos alone without robot data? We present MT-π, an IL framework that takes in human video and predicts actions as 2D motion tracks. portal.cs.cornell.edu/motion_track_p… 🧵1/6

Time to democratize humanoid robots! Introducing ToddlerBot, a low-cost ($6K), open-source humanoid for robotics and AI research. Watch two ToddlerBots seamlessly chain their loco-manipulation skills to collaborate in tidying up after a toy session. toddlerbot.github.io

Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoints in our new openpi repository! We tested the model on a few public robots, and we include code for you to fine-tune it yourself.

Two months ago, we introduced TidyBot++, our open-source mobile manipulator. Today, I'm excited to share our significantly expanded docs: • Assembly guide: tidybot2.github.io/docs • Usage guide: tidybot2.github.io/docs/usage Thanks to early adopters, TidyBot++ can now be fully

Introducing NEO Gamma. Another step closer to home.

What happens when vision🤝 robotics meet? Happy to share our new work on Pretraining Robotic Foundational Models!🔥 ARM4R is an Autoregressive Robotic Model that leverages low-level 4D Representations learned from human video data to yield a better robotic model. Berkeley AI Research😊

We made π0 “think harder”: our new Hierarchical Interactive Robot (Hi Robot) method “thinks” through complex tasks and prompts, directing π0 to break up complex tasks into basic steps, handling human feedback, and modifying tasks on the fly.

Introducing OFT—an Optimized Fine-Tuning recipe for VLAs! Fine-tuning OpenVLA w/ OFT, we see: -25-50x faster inference ⚡️ -SOTA 97.1% avg SR in LIBERO 💪 -high-freq control w/ 7B model on real bimanual robot -outperforms π₀, RDT-1B, DiT Policy, MDT, Diffusion Policy, ACT 🧵👇

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids toruowo.github.io/recipe/ TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Join our team at Cambridge! We have fully funded PhD positions in robot learning, novel robot hardware design, and reinforcement learning. Looking for applicants with a strong background in dexterous manipulation & hardware prototyping. Interested? Please send me a message/email.

Introducing Phantom 👻: a method to train robot policies without collecting any robot data — using only human video demonstrations. Phantom turns human videos into "robot" demonstrations, making it significantly easier to scale up and diversify robotics data. 🧵1/9

Video generation is powerful but too slow for real-world robotic tasks. How can we enable both video and action generation while ensuring real-time policy inference? Check out our work on the Unified Video Action Model (UVA) to find out! unified-video-action-model.github.io (1/7)

🤖 Ever wondered what robots need to truly help humans around the house? 🏡 Introducing 𝗕𝗘𝗛𝗔𝗩𝗜𝗢𝗥 𝗥𝗼𝗯𝗼𝘁 𝗦𝘂𝗶𝘁𝗲 (𝗕𝗥𝗦)—a comprehensive framework for mastering mobile whole-body manipulation across diverse household tasks! 🧹🫧 From taking out the trash to

PostDoc Opportunity in my lab through Stanford HAI: hai.stanford.edu/research/fello… Application Deadline: April 3rd

🚀 We're hosting the #RSS2025 Mobile Manipulation (MoMA) Workshop! Join us to explore how mobility + dexterity unlock general-purpose robots in dynamic, human-centric spaces. 📅 Share your latest work with us by May 25 🔗 rss-moma-2025.github.io

Excited to announce the 1st Workshop on Robot Hardware-Aware Intelligence @ #RSS2025 in LA! We’re bringing together interdisciplinary researchers exploring how to unify hardware design and intelligent algorithms in robotics! Full info: rss-hardware-intelligence.github.io Robotics: Science and Systems