Evaluating Robustness and Adaptability in Learning-Based Mission Planning for Active Debris Removal
This addresses the problem of robust and adaptable mission planning for autonomous Active Debris Removal in space, but it is incremental as it compares existing methods without introducing a new paradigm.
This work compared three planners for Active Debris Removal mission planning, finding that nominal PPO performed best under matched conditions but degraded sharply with distributional shift, while domain-randomized PPO improved adaptability with moderate performance loss, and MCTS handled constraints best but with much higher computation time.
Autonomous mission planning for Active Debris Removal (ADR) must balance efficiency, adaptability, and strict feasibility constraints on fuel and mission duration. This work compares three planners for the constrained multi-debris rendezvous problem in Low Earth Orbit: a nominal Masked Proximal Policy Optimization (PPO) policy trained under fixed mission parameters, a domain-randomized Masked PPO policy trained across varying mission constraints for improved robustness, and a plain Monte Carlo Tree Search (MCTS) baseline. Evaluations are conducted in a high-fidelity orbital simulation with refueling, realistic transfer dynamics, and randomized debris fields across 300 test cases in nominal, reduced fuel, and reduced mission time scenarios. Results show that nominal PPO achieves top performance when conditions match training but degrades sharply under distributional shift, while domain-randomized PPO exhibits improved adaptability with only moderate loss in nominal performance. MCTS consistently handles constraint changes best due to online replanning but incurs orders-of-magnitude higher computation time. The findings underline a trade-off between the speed of learned policies and the adaptability of search-based methods, and suggest that combining training-time diversity with online planning could be a promising path for future resilient ADR mission planners.