Download
MuJoCo Menagerie, developed by Google DeepMind, is a curated collection of high-quality simulation models designed for use with the MuJoCo physics engine. It serves as a comprehensive library of accurate and ready-to-use robotic, biomechanical, and mechanical models, ensuring users can perform reliable simulations without having to build or tune models from scratch. The repository aims to improve reproducibility and quality across robotics research by providing verified models that adhere to consistent design and physical standards. Each model directory contains its 3D assets, MJCF XML definitions, licensing information, and example scenes for visualization and testing. The collection spans a wide range of categories including robotic arms, humanoids, quadrupeds, mobile manipulators, drones, and biomechanical systems. Users can access models directly via the robot_descriptions Python package or by cloning the repository for use in interactive MuJoCo simulations.
Features
- Curated library of physically accurate models for the MuJoCo simulator
- Supports categories like arms, humanoids, quadrupeds, drones, and manipulators
- Compatible with both MJCF and MJX model formats
- Direct integration through the robot_descriptions Python package
- Includes detailed documentation, licensing, and visualization assets for each model
- Quality grading system for model realism and stability assessment
Project Samples
