Lists (20)
Behaviour cloning and RL
Control
Games
Holy
Humanoid Retargetting
Localisation and Mapping
Manipulation - models and layers
ML Tools
Motion planning tools
New Models
Perception for manipulation
Robot Descriptions
Robot grasping
robot learning stack
Robot manipulation datasets
Sensors and drivers
Simulation
Teleop tools
[Vision] Language Models
Visualisation tools
Stars
Official repository for "CUPID: Curating Data your Robot Loves with Influence Functions," accepted to CoRL 2025.
A modular buffer with data storage and data loading components for robot learning
ROBOTIS Physical AI Tools: Physical AI Development Interface with LeRobot and ROS 2
GUI for marking bounded boxes of objects in images for training neural network YOLO
Humanoid robot arms retarget algorithm with VisionPro app
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).
Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
Connect AI models like Claude & GPT with robots using MCP and ROS.
Official code of the paper "VideoMolmo: Spatio-Temporal Grounding meets Pointing"
world modeling challenge for humanoid robots
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Provide teleop (video streaming, desktop control of robot) using WebRTC over ROS2
Given one example of an annotated part, this model finds its semantic correspondences in a target image. Thus you get - one-shot semantic part correspondence!
Access 100+ robot descriptions from the main Python robotics frameworks
eaa3 / grip
Forked from dyson-ai/gripA research toolbox for prototyping robot manipulation environments and applications.
Allows for communication between MuJoCo and ROS2.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
Code for Ditto: Building Digital Twins of Articulated Objects from Interaction
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling