Distributed Multi Robot Lunar Cargo Transportation via Phase Decomposed Reinforcement Learning
This work addresses the challenge of cooperative cargo transport for lunar missions, but the results are demonstrated in controlled experiments without quantitative comparison to baselines, making it an incremental step.
The paper tackles cooperative cargo transportation for modular reconfigurable lunar robots, proposing a phase-decomposed reinforcement learning framework that decomposes the task into lifting, transportation, and placement. The method achieves reliable cooperative transport across all stages in both simulation and hardware experiments at a JAXA test facility.
Modular reconfigurable robotic systems provide a scalable solution for cooperative surface operations in future lunar missions. However, cooperative cargo transportation remains challenging due to morphology-dependent topology changes, strong payload-induced coupling, long-horizon decision making, and safety constraints. This paper proposes a phase-decomposed reinforcement learning framework for cooperative cargo transport with distributed robotic units. The task is decomposed into lifting, transportation, and placement, each optimized with a dedicated joint-state policy capturing inter-agent coupling. Centralized training promotes stable convergence, while deployment uses onboard proprioception for control and OptiTrack motion capture for ground-truth evaluation and post-processed metrics. A deterministic phase controller expressed in Markov state representation regulates transitions between stages, and a failure-sensitive synchronization mechanism ensures coordinated progression and safety-aware halting during real-world execution. The framework is evaluated in simulation and through controlled field experiments at a JAXA space exploration test facility. Results demonstrate reliable cooperative transport across all stages in both simulation and hardware experiments.