一个用于机器人研发的物理引擎,旨在帮助机器人、生物力学、图形和动画等领域的研究和开发(也包括其他需要快速准确模拟的领域)。

Saran Tunyasuvunakool d49d4bf64c Make unsupported feature checking optional in put_model. 1 day ago
.github 44be878e7e Enable inter-procedural optimization by default in cmake 3 weeks ago
cmake cb4cb7d09b Update version hashes in MuJoCo CMake files ahead of the 3.2.0 release. 5 days ago
dist 22ce22ac8a Update the MuJoCo version number ahead of the 3.2.0 release. 5 days ago
doc 796173170c Add support in mjModel for tagging textures with different roles, and use the slot index of a texture to designate its role. 1 day ago
include 796173170c Add support in mjModel for tagging textures with different roles, and use the slot index of a texture to designate its role. 1 day ago
introspect 796173170c Add support in mjModel for tagging textures with different roles, and use the slot index of a texture to designate its role. 1 day ago
mjx d49d4bf64c Make unsupported feature checking optional in put_model. 1 day ago
model 27b9ddda5b Add attach tag to MJCF. 1 week ago
plugin 393895bb29 Explicitly specify actdim on PID plugin actuators, to allow them to be used with keyframes. 1 week ago
python db1d51a1f5 Add more fields to mjx.Option and mjx.Statistic for MuJoCo compatibility. 1 day ago
sample 22ce22ac8a Update the MuJoCo version number ahead of the 3.2.0 release. 5 days ago
simulate 22ce22ac8a Update the MuJoCo version number ahead of the 3.2.0 release. 5 days ago
src b3f79e561d Fix bug in pre-counting equality constraints. 1 day ago
test 8a8a44a4db Refactor numerical parsing in XML. 1 day ago
unity 796173170c Add support in mjModel for tagging textures with different roles, and use the slot index of a texture to designate its role. 1 day ago
.gitignore 60afda949c Merge pull request #1714 from abhihjoshi:tendons 1 week ago
.readthedocs.yml b1e185bb9e Fix ReadTheDocs config. 2 years ago
CMakeLists.txt 22ce22ac8a Update the MuJoCo version number ahead of the 3.2.0 release. 5 days ago
CONTRIBUTING.md 7e5a7b76fc Change GitHub org name to `google-deepmind`. 10 months ago
LICENSE 1f7eaae62e Version 2.1: documentation, public API headers, and sample programs. 2 years ago
README.md 1eb708646d Update the `simulate` tutorial video. 1 month ago
SECURITY.md 8ec3dd97a4 Add SECURITY.md. 2 years ago
STYLEGUIDE.md 6067048537 Deprecate `mju_rotVecMat` and `mju_rotVecMatT` in favor of `mju_mulMatVec3` and `mju_mulMatTVec3`. 1 month ago
banner.png 00576a3bf9 Update icons to match the new banner and add Windows version info. 1 year ago

README.md

MuJoCo

MuJoCo stands for Multi-Joint dynamics with Contact. It is a general purpose physics engine that aims to facilitate research and development in robotics, biomechanics, graphics and animation, machine learning, and other areas which demand fast and accurate simulation of articulated structures interacting with their environment.

This repository is maintained by Google DeepMind.

MuJoCo has a C API and is intended for researchers and developers. The runtime simulation module is tuned to maximize performance and operates on low-level data structures that are preallocated by the built-in XML compiler. The library includes interactive visualization with a native GUI, rendered in OpenGL. MuJoCo further exposes a large number of utility functions for computing physics-related quantities.

We also provide Python bindings and a plug-in for the Unity game engine.

Documentation

MuJoCo's documentation can be found at mujoco.readthedocs.io. Upcoming features due for the next release can be found in the changelog in the latest branch.

Getting Started

There are two easy ways to get started with MuJoCo:

  1. Run simulate on your machine. This video shows a screen capture of simulate, MuJoCo's native interactive viewer. Follow the steps described in the Getting Started section of the documentation to get simulate running on your machine.

  2. Explore our online IPython notebooks. If you are a Python user, you might want to start with our tutorial notebooks running on Google Colab:

    • The introductory tutorial teaches MuJoCo basics: Open In Colab
    • The LQR tutorial synthesizes a linear-quadratic controller, balancing a humanoid on one leg: Open In Colab
    • The least-squares tutorial explains how to use the Python-based nonlinear least-squares solver: Open In Colab
    • The MJX tutorial provides usage examples of MuJoCo XLA, a branch of MuJoCo written in JAX: Open In Colab
    • The differentiable physics tutorial trains locomotion policies with analytical gradients automatically derived from MuJoCo's physics step: Open In Colab

Installation

Prebuilt binaries

Versioned releases are available as precompiled binaries from the GitHub releases page, built for Linux (x86-64 and AArch64), Windows (x86-64 only), and macOS (universal). This is the recommended way to use the software.

Building from source

Users who wish to build MuJoCo from source should consult the build from source section of the documentation. However, please note that the commit at the tip of the main branch may be unstable.

Python (>= 3.8)

The native Python bindings, which come pre-packaged with a copy of MuJoCo, can be installed from PyPI via:

pip install mujoco

Note that Pre-built Linux wheels target manylinux2014, see here for compatible distributions. For more information such as building the bindings from source, see the Python bindings section of the documentation.

Contributing

We welcome community engagement: questions, requests for help, bug reports and feature requests. To read more about bug reports, feature requests and more ambitious contributions, please see our contributors guide and style guide.

Asking Questions

Questions and requests for help are welcome on the GitHub Issues page and should focus on a specific problem or question.

Discussions should address wider concerns that might require input from multiple participants.

Here are some guidelines for asking good questions:

  1. Search for existing questions or issues that touch on the same subject.

You can add comments to existing threads or start new ones. If you start a new thread and there are existing relevant threads, please link to them.

  1. Use a clear and specific title. Try to include keywords that will make your question easy for other to find in the future.

  2. Introduce yourself and your project more generally.

If your level of expertise is exceptional (either high or low), and it might be relevant to what we can assume you know, please state that as well.

  1. Take a step back and tell us what you're trying to accomplish, if we understand you goal we might suggest a different type of solution than the one you are having problems with

  2. Make it easy for others to reproduce the problem or understand your question.

If this requires a model, please include it. Try to make the model minimal: remove elements that are unrelated to your question. Pure XML models should be inlined. Models requiring binary assets (meshes, textures), should be attached as a .zip file. Please make sure the included model is loadable before you attach it.

  1. Include an illustrative screenshot or video, if relevant.

  2. Tell us how you are accessing MuJoCo (C API, Python bindings, etc.) and which MuJoCo version and operating system you are using.

Related software

MuJoCo forms the backbone of many environment packages, but these are too many to list here individually. Below we focus on bindings and converters.

Bindings

These packages give users of various languages access to MuJoCo functionality:

First-party bindings:

Third-party bindings:

:arrow_right: Click here for a live demo of MuJoCo running in your browser.

Converters

  • OpenSim: MyoConverter converts OpenSim models to MJCF.
  • SDFormat: gz-mujoco is a two-way SDFormat <-> MJCF conversion tool.
  • OBJ: obj2mjcf a script for converting composite OBJ files into a loadable MJCF model.

Citation

If you use MuJoCo for published research, please cite:

@inproceedings{todorov2012mujoco,
  title={MuJoCo: A physics engine for model-based control},
  author={Todorov, Emanuel and Erez, Tom and Tassa, Yuval},
  booktitle={2012 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages={5026--5033},
  year={2012},
  organization={IEEE},
  doi={10.1109/IROS.2012.6386109}
}

License and Disclaimer

Copyright 2021 DeepMind Technologies Limited.

Box collision code (engine_collision_box.c) is Copyright 2016 Svetoslav Kolev.

ReStructuredText documents, images, and videos in the doc directory are made available under the terms of the Creative Commons Attribution 4.0 (CC BY 4.0) license. You may obtain a copy of the License at https://creativecommons.org/licenses/by/4.0/legalcode.

Source code is licensed under the Apache License, Version 2.0. You may obtain a copy of the License at https://www.apache.org/licenses/LICENSE-2.0.

This is not an officially supported Google product.