BSK-RL: Environments for Spacecraft Planning and Scheduling

Warning

The 1.0.0 release has significant changes from previous versions. See the Release Notes for more information.

BSK-RL (Basilisk + Reinforcement Learning) is a Python package for constructing Gymnasium environments for spacecraft tasking problems. It is built on top of Basilisk, a modular and fast spacecraft simulation framework, making the simulation environments high-fidelity and computationally efficient. BSK-RL also includes a collection of utilities and examples for working with these environments.

A whitepaper on the design philosophy behind BSK-RL and an example use case can be downloaded here.

Quickstart

Installation

Complete installation instructions and common troubleshooting tips can be found here. To install BSK-RL:

1. Install the Basilisk spacecraft simulation framework.

2. Clone BSK-RL.

   $ git clone git@github.com:AVSLab/bsk_rl.git && cd bsk_rl
   

3. Install BSK-RL in the same virtual environment as Basilisk.

   (.venv) $ python -m pip install -e . && finish_install
   

4. Test the installation.

   (.venv) $ pytest .
   

Construct an Environment

A quick but comprehensive tutorial can be found at Getting Started.

Acknowledgements

BSK-RL is developed by the Autonomous Vehicle Systems (AVS) Lab at the University of Colorado Boulder. The AVS Lab is part of the Colorado Center for Astrodynamics Research (CCAR) and the Department of Aerospace Engineering Sciences.

Development has been supported by NASA Space Technology Graduate Research Opportunity (NSTGRO) grants, 80NSSC20K1162 and 80NSSC23K1182. This work has also been supported by Air Force Research Lab grant FA9453-22-2-0050.

Development of this software has utilized the Alpine high performance computing resource at the University of Colorado Boulder. Alpine is jointly funded by the University of Colorado Boulder, the University of Colorado Anschutz, and Colorado State University.