RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Data collection part for ARCap

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

world modeling challenge for humanoid robots

[RSS 2024]: Expressive Whole-Body Control for Humanoid Robots

UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers

Project Page for Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models

Implementation of "MADiff: Offline Multi-agent Learning with Diffusion Models"

Unified Reinforcement Learning Framework

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Datasets with baselines for offline multi-agent reinforcement learning.

Code for BAKU: An Efficient Transformer for Multi-Task Policy Learning

Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans

A multi-agent quadruped environment, supporting learning of locomotion control or merely high-level planning.

Google Research Football MARL Benchmark and Research Toolkit

[RSS 2024] Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation

Train a loco-manipulation dog with RL

CoTracker is a model for tracking any point (pixel) on a video.

code for the paper Predicting Point Tracks from Internet Videos enables Diverse Zero-Shot Manipulation

Tools for converting ROS messages to and from numpy arrays

Web Based Visualizer for Simulation Environments