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

TL;DR

This work addresses safe exploration in reinforcement learning for autonomous spacecraft inspection by integrating Run Time Assurance (RTA) through an Active Set Invariance Filter (ASIF) with Control Barrier Functions (CBFs). It develops a 6-DoF deputy-spacecraft model in Hill’s frame, coupling attitude and translation with thermal and energy dynamics, and enforces nine safety constraints simultaneously during RL training. The study demonstrates that ASIF RTA can guarantee safety with minimal controller intervention, while also examining the impact of RTA on training efficiency and final policy performance, including higher fuel and torque use for safety. The findings highlight the practical value of high-frequency RTA during RL training for complex, safety-critical space tasks, enabling safe exploration and robust policy learning in challenging environments.

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.

Figures (12)

• Figure 1: RL feedback control loop.
• Figure 2: Feedback control system with RTA.
• Figure 3: Hill's reference frame.
• Figure 4: Sun incidence angle.
• Figure 5: Attitude exclusion zone.