RANS: Highly-Parallelised Simulator for Reinforcement Learning based Autonomous Navigating Spacecrafts

TL;DR

This paper introduces RANS, a GPU-accelerated, highly parallelized simulation library for reinforcement learning-based autonomous spacecraft navigation, enabling efficient training and validation of complex space maneuvers.

Contribution

It presents an open-source, GPU-based simulation tool tailored for RL in space navigation, filling a gap in existing robotics simulation libraries.

Findings

Supports thousands of parallel spacecraft simulations

Enables training for complex maneuvers like docking and landing

Facilitates validation of space trajectory optimization

Abstract

Nowadays, realistic simulation environments are essential to validate and build reliable robotic solutions. This is particularly true when using Reinforcement Learning (RL) based control policies. To this end, both robotics and RL developers need tools and workflows to create physically accurate simulations and synthetic datasets. Gazebo, MuJoCo, Webots, Pybullets or Isaac Sym are some of the many tools available to simulate robotic systems. Developing learning-based methods for space navigation is, due to the highly complex nature of the problem, an intensive data-driven process that requires highly parallelized simulations. When it comes to the control of spacecrafts, there is no easy to use simulation library designed for RL. We address this gap by harnessing the capabilities of NVIDIA Isaac Gym, where both physics simulation and the policy training reside on GPU. Building on this tool, we provide an open-source library enabling users to simulate thousands of parallel spacecrafts, that learn a set of maneuvering tasks, such as position, attitude, and velocity control. These tasks enable to validate complex space scenarios, such as trajectory optimization for landing, docking, rendezvous and more.