Run Time Assured Reinforcement Learning for Six Degree-of-Freedom Spacecraft Inspection

TL;DR

This paper demonstrates how run time assurance can be integrated into reinforcement learning to safely train a spacecraft inspection agent controlling 6 degrees of freedom, balancing safety and performance.

Contribution

It introduces a method for applying control barrier functions as RTA during RL training for complex spacecraft tasks, ensuring safety constraints are met.

Findings

RTA improves safety during training without significantly hindering learning.

Simulating RTA at different frequencies affects training efficiency and safety.

The trained agent achieves high inspection success with optimized fuel use.

Abstract

The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety of the agent during training, allowing it to safely explore the environment. This paper investigates the application of RTA during RL training for a 6-Degree-of-Freedom spacecraft inspection task, where the agent must control its translational motion and attitude to inspect a passive chief spacecraft. Several safety constraints are developed based on position, velocity, attitude, temperature, and power of the spacecraft, and are all enforced simultaneously during training through the use of control barrier functions. This paper also explores simulating the RL agent and RTA at different frequencies to best balance training performance and safety assurance. The agent is trained with and without RTA, and the performance is compared across several metrics including inspection percentage and fuel usage.