Satellite Chasers: Divergent Adversarial Reinforcement Learning to Engage Intelligent Adversaries on Orbit

As space becomes increasingly crowded and contested, robust autonomous capabilities for multi-agent environments are gaining critical importance. Current autonomous systems in space primarily rely on optimization-based path planning or long-range orbital maneuvers, which have not yet proven effective in adversarial scenarios where one satellite is actively pursuing another. The authors introduce Divergent Adversarial Reinforcement Learning (DARL), a two-stage Multi-Agent Reinforcement Learning (MARL) approach designed to train autonomous evasion strategies for satellites engaged with multiple adversarial spacecraft. This method enhances exploration during training by promoting diverse adversarial strategies, leading to more robust and adaptable evader models. The authors validate DARL through a cat-and-mouse satellite scenario, modeled as a partially observable multi-agent capture-the-flag game, where two adversarial ‘“cat’” spacecraft pursue a single ‘“mouse’” evader. DARL’s performance is compared against several benchmarks, including an optimization-based satellite-path planner, demonstrating its ability to produce highly robust models for adversarial multi-agent space environments.