Spacecraft Chase and Escape Game Based on PPO Algorithm

This paper addresses the pursuit-evasion game problem for spacecraft using pulse propulsion, uses Particle Swarm Optimization (PSO) and Proximal Policy Optimization (PPO) algorithms as pursuit and evasion strategies for the spacecraft. The distance between the spacecraft is employed as the optimization objective for the PSO algorithm, aiming to minimize the distance between them. Similarly, the distance between the spacecraft is used as the reward function for the PPO algorithm, aiming to maximize the distance between them. Additionally, the paper takes into account that the spacecraft use pulse propulsion with a maximum velocity increment constraint. Through simulation examples, the effectiveness of using the PPO algorithm as a spacecraft strategy-solving method is validated.