Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System
For spacecraft-manipulator systems, this work addresses the critical problem of dynamic coupling-induced attitude instability, improving mission safety and control precision.
This paper proposes a Dual-Agent Coordinated Manipulation Planning (DACMP) framework for spacecraft-manipulator systems that achieves high-precision end-effector positioning and base attitude stabilization. The method outperforms baseline DRL algorithms in task success rate and control precision, validated under various challenging scenarios.
The strong dynamic coupling between the manipulator and the base poses a significant challenge to maintaining spacecraft attitude stability, potentially compromising mission safety. In this paper, we propose a Dual-Agent Coordinated Manipulation Planning (DACMP) framework that simultaneously achieves high-precision end-effector pose reaching for a 6-DoF space manipulator and attitude stabilization of the base spacecraft. To enhance learning efficiency, we present a prior policy-guided Deep Reinforcement Learning algorithm incorporating the Timestep-level Expert Switching Guidance (TESG) mechanism, thereby promoting global convergence and improving task success rates. Extensive experiments demonstrate that DACMP significantly outperforms baseline DRL algorithms in terms of task success rate and control precision. Furthermore, the robustness of DACMP is validated under various challenging scenarios, including system constraints, environmental disturbances, and perception uncertainties. The code and simulation configurations are available on GitHub: https://github.com/HIT-YuhuiHu/DACMP.