English | Simplified Chinese

MATRiX

A High-Fidelity Robot Simulation Platform Powered by Unreal Engine and MuJoCo

Promotional Demo · Quick Start · Documentation · Robots & Maps · Contributing

MATRiX is a ready-to-run robot simulation platform. Unreal Engine provides high-fidelity rendering, MuJoCo runs the robot physics, and Zenoh carries ROS 2-compatible sensor and control payloads. The current source supports runtime MJCF loading, configurable sensor suites, embedded motion control, and DLC-based map discovery without requiring a ROS installation for the core simulator.

Important

The current release is v1.0.7. The source targets 64-bit Windows (DX12/SM6) and Linux (Vulkan/SM6). Hardware and driver requirements can vary by packaged release; see the Getting Started guide.

🎥 Promotional Demo

MATRiX 2.0 Simulation Showcase
_{High-fidelity environments · Multi-robot simulation · Reinforcement learning · Real-world scene reconstruction}

✨ Core Capabilities

• Runtime MuJoCo integration: Load MJCF/XML models at runtime and step physics on a dedicated worker (500 Hz target by default).
• Complete sensor stack: RGB, infrared, depth, fisheye, panorama, generic LiDAR, Mid360, Airy, IMU, GPS, and odometry with a unified ROS 2 timestamp model.
• Embedded motion control: Bundled control cores for xgb, xg2, xgw, xgw2, zgws, zgwt, and zgwsarm, plus a Linux shared-memory hardware-simulation path.
• Runtime map DLCs: Discover maps from Saved/DLCs or Content/DLCs; installed packages can be mounted at startup or loaded at runtime.
• Zenoh and LAN networking: ROS 2-compatible CDR payloads over Zenoh, fixed mujoco/state and mujoco/cmd control keys, and optional LAN state/event synchronization.
• Graphical configuration: Configure robot models, maps, initial poses, networking, motion control, and dynamic sensor arrays through the launcher-backed JSON configuration.

🎬 Simulation Gallery

Town10 Urban Environment	Venice Canal Environment
Warehouse Environment	Courtyard Environment

🚀 Quick Start

1. Download a runtime package: Linux (access code: 6sth) or Windows (access code: s9iy).
2. Download the required map DLC packages and place the .pak files in Windows/UeSim/Saved/DLCs/.
3. Start MATRiX on Windows:

.\Windows\UeSim\Binaries\Win64\UeSim.exe

Use the launcher to select a robot and scene, then configure the required sensors. The Getting Started guide covers platform requirements, runtime layout, and verification steps.

If your runtime package includes the optional Tools/ directory, a typical receiver setup is:

pip install eclipse-zenoh opencv-python numpy
cd Tools
python zenoh_sensor_receiver.py

📚 Documentation

Topic	Documentation
Installation and startup	Getting Started (Chinese)
Robots and environments	English · Chinese
Sensors and Zenoh	Sensor and Communication (Chinese)
Sensor configuration	Sensor Configuration Tutorial
Data tools	Python Tools (Chinese)
Motion control	Motion Control (Chinese)
Controllers	Controller Guide · Chinese
Manual configuration	Advanced Configuration (Chinese)
Architecture and maintenance	Maintainer Guide
Troubleshooting	FAQ (Chinese)
Docker	Docker Support Status
Pixel Streaming	Pixel Streaming Guide
Chinese documentation index	Simplified Chinese

💬 Community

Add the GENISOM AI WeChat assistant for MATRiX simulation discussions and support:

Scan to add XinQi Robo; mention MATRiX to join the simulation community.

🤝 Contributing

Bug reports, documentation improvements, and runtime tooling changes are welcome. Start with CONTRIBUTING.md, and review the architecture and maintainer guide before changing launch or release scripts. Security issues should follow SECURITY.md rather than being filed as public issues.

🙏 Acknowledgements

This project builds upon the incredible work of the following open-source projects:

• MuJoCo-Unreal-Engine-Plugin
• MuJoCo
• Unreal Engine
• CARLA