srb 0.0.6

Robot Learning Beyond Earth

Space Robotics Bench

Space Robotics Bench (SRB) is a comprehensive collection of environments and tasks for robotics research in the challenging domain of space. It provides a unified framework for developing and validating autonomous systems under diverse extraterrestrial scenarios. At the same time, its design is flexible and extensible to accommodate a variety of development workflows and research directions beyond Earth.

Key Features

• Parallelized Simulation: Highly parallelized simulation instances for accelerated workflows
• Procedural Generation: On-demand generation of diverse simulation assets and scenes
• Domain Randomization: Extensive randomization for robustness and generalization
• Gymnasium API: Compatibility with standard API and frameworks for robot learning
• ROS 2 Interface: Seamless interoperability with ROS 2 and Space ROS ecosystems
• Abstract Architecture: Flexibility across different robots and space domains

Documentation

SRB documentation with detailed installation instructions, usage guides, and development resources is available online.

License

This project is dual-licensed under either the MIT or Apache 2.0 licenses.

All assets created by contributors of this repository and those generated from SimForge procedural pipelines are licensed under the CC0 1.0 Universal license. Resources from third-party sources are listed under attributions.