[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)

Minimal package to run locomotion policies on a Kangaroo robot in MuJoCo

ROS2 package implementing a teleoperation interface using QT

Isaac Lab locomotion tasks for the Kangaroo robot

An Open Source Task Solving library with Constraints

GPU-friendly, auto-differentiable LQR solver with JAX.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Pointcloud compression library

An open-source implementation of GPTZero

JSAC is a Soft Actor-Critic (SAC) based Reinforcement Learning (RL) system designed for high-performance and stable learning from images. JSAC is well-suited for real-world, vision-based robotic ta…

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

Whole-Body Nonlinear MPC for Realtime Humanoid Loco-Manipulation Planning and Control

Sensor Fusion ROS2 Package enabling dynamic simplified tuning of an Extended Kalman Filter

Openwalker main project

[CVPR 2025] Any6D: Model-free 6D Pose Estimation of Novel Objects

Implementation of all RL algorithms in a simpler way

DayDreamer: World Models for Physical Robot Learning

A curated list of awesome robot descriptions (URDF, MJCF)

NVIDIA Isaac GR00T N1.5 is the world's first open foundation model for generalized humanoid robot reasoning and skills.

Impedance controllers for franka emika robots used in TU Delft for a safer human robot interaction

MUKCa: Minimal and Userfriendly Kinematics Calibration for Redundant Manipulators

This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym

This is a Behavior Tree library meant to be an alternative to SMACH, FlexBE and the like. It includes a ReactJS-based web GUI and all the building blocks you need to build moderately advanced missi…

Open Duck Project's reference motion generator

Rhoban Planning and Control

Open Duck Project's Mujoco playground RL environments

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

Universal calibration toolbox for assisted, target-based multi-sensor calibration with ROS 1 and ROS 2 support.

A ROS2 package that allows rapid digitization of robotic work cells and ease of efficient path-planning of manipulators.