Distributed Multi Robot Lunar Cargo Transportation via Phase Decomposed Reinforcement Learning

2026-06-30

AI Summary

This work addresses the challenges of morphological adaptation, strong payload coupling, long-horizon decision-making, and safety constraints in multi-robot cooperative lunar transport. To tackle these issues, the authors propose a phase-decomposed reinforcement learning framework that partitions the task into three sequential stages—lifting, transporting, and placing—each modeled with a dedicated joint-state policy to capture agent couplings. Smooth phase transitions and operational safety are ensured through a Markovian state-based phase controller, proprioceptive mechanisms, and a fault-aware synchronization strategy. Leveraging a centralized training with decentralized execution architecture, the approach achieves highly reliable end-to-end cooperative transport, as demonstrated in both high-fidelity simulations and physical experiments conducted at JAXA’s space exploration test facility.

Abstract

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.

Problem

• cooperative cargo transportation
• morphology-dependent topology
• payload-induced coupling
• long-horizon decision making
• safety constraints

Innovation

• Phase-Decomposed Reinforcement Learning
• Distributed Multi-Robot Coordination
• Morphology-Dependent Coupling
• Failure-Sensitive Synchronization
• Modular Reconfigurable Robotics