So I hear that behavior cloning is all the rage now. What if we could do better, but with the same data? :) In CCIL, we show that imitation via BC is improved by synthesizing corrective labels to account for compounding error, without interactive oracles. Lets you do 👇! 🧵(1/9)

Imagine a future where you can ask humanoid robots to clean your room, but some items, like heavy sofas, are too challenging for just one robot to move. Introducing CooHOI, a learning-based framework designed for the cooperative transportation of objects by multiple humanoid

So you’ve trained your favorite diffusion/flow based policy, but it’s just not good enough 0-shot. Worry not, in our new work DSRL - we show how to *steer* pre-trained diffusion policies with off-policy RL, improving behavior efficiently enough for direct training in the real

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the

[ICRA'25] One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation github.com/KTH-RPL/OneMap

🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.

We're organizing a workshop at humanoids about RL and model based control. Please submit an extended abstract for the poster session!!

With the right design decisions, value-based RL admits predictable scaling. value-scaling.github.io We wrote a blog post on our two papers challenging conventional wisdom that off-policy RL methods are fundamentally unpredictable.

learn-to-calibrate [IROS2025] The World's First RL-based Sensor Calibration Method: A Targetless, User-friendly, and Robust Approach. github.com/APRIL-ZJU/lear… L2Calib: SE(3)-Manifold Reinforcement Learning for Robust Extrinsic Calibration with Degenerate Motion Resilience

we compressed this worker's job into 18 lines of code

📢 The CoRL 2025 accepted papers are now live on OpenReview! Check out the list of exciting contributions in robot learning: openreview.net/group?id=robot… #CoRL2025 #RobotLearning

Introducing Tetra Dynamics. We’re building robots that can perform dextrous manipulation autonomously. Here’s 7 minutes of our hand putting the block into the box using in-hand manipulation.

youtu.be/ytWO7lldN4c 😮

Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution arxiv.org/abs/2509.14816 Having priorities in RL optimization for control

Rough terrain, high-speed, side hopping, standing, etc.

I'm super excited to announce mjlab today! mjlab = Isaac Lab's APIs + best-in-class MuJoCo physics + massively parallel GPU acceleration Built directly on MuJoCo Warp with the abstractions you love.

Spot is playing Ping Pong! Spin is a crucial part of the game, but few robots can handle it. We show receiving and generating significant spin using MPC. Collaboration with David Nguyen and Zulfiqar Zaidi! Video: youtu.be/3GrnkxOeC14?si…. Paper: arxiv.org/pdf/2510.08754.

«Unitree robodogs have no use case outside research»

🤖 Robots rarely see the true world's state—they operate on partial, noisy visual observations. How should we design algorithms under this partial observability? Should we decide (end-to-end RL) or distill (from a privileged expert)? We study this trade-off in locomotion. 🧵(1/n)