LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark

API for controlling LEAP Hand for Inhand Manipulation tasks

Lets make video diffusion practical!

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Imitation Learning from Observation Through Generative Modelling

[ICRA'24] Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning

Distilling Diffusion Policy into consistency models

[ICLR'25] Official Implementation for Consistent Flow Distillation for Text-to-3D Generation

Code for P3PO

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

Learning Optimal Policies Through Contact in Differentiable Simulation

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

EdgeVLA: An open-source edge vision-language-action model for robotics.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

Example of ros_control without Gazebo

Generic robotic controllers to accompany ros_control