On-orbit Servicing for Spacecraft Collision Avoidance With Autonomous Decision Making

TL;DR

This paper presents an AI-driven autonomous on-orbit servicing system using reinforcement learning to detect potential collisions, rendezvous with endangered satellites, and execute optimal collision avoidance maneuvers.

Contribution

It introduces a novel RL-based framework for autonomous collision avoidance and servicing in space, integrating risk estimates and decision policies for the first time.

Findings

Feasibility demonstrated for autonomous collision avoidance with a single servicer and satellite.

Reinforcement learning effectively generates optimal maneuver policies.

Identifies key challenges in merging rendezvous and collision avoidance tasks.

Abstract

This study develops an AI-based implementation of autonomous On-Orbit Servicing (OOS) mission to assist with spacecraft collision avoidance maneuvers (CAMs). We propose an autonomous `servicer' trained with Reinforcement Learning (RL) to autonomously detect potential collisions between a target satellite and space debris, rendezvous and dock with endangered satellites, and execute optimal CAM. The RL model integrates collision risk estimates, satellite specifications, and debris data to generate an optimal maneuver matrix for OOS rendezvous and collision prevention. We employ the Cross-Entropy algorithm to find optimal decision policies efficiently. Initial results demonstrate the feasibility of autonomous robotic OOS for collision avoidance services, focusing on one servicer spacecraft to one endangered satellite scenario. However, merging spacecraft rendezvous and optimal CAM presents significant complexities. We discuss design challenges and critical parameters for the successful implementation of the framework presented through a case study.