Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System

2026-05-24

AI Summary

This study addresses the attitude instability of spacecraft caused by strong dynamic coupling between space manipulators and their base platform. To simultaneously achieve high-precision end-effector positioning and base attitude stabilization, the authors propose a Dual-Agent Collaborative Manipulation Planning (DACMP) framework. DACMP integrates deep reinforcement learning with system dynamics modeling and introduces a novel time-step-level expert switching mechanism guided by prior policies (TESG), which substantially enhances algorithmic convergence and task success rates. Experimental results demonstrate that DACMP outperforms existing deep reinforcement learning baselines across multiple challenging scenarios, achieving significant improvements in control accuracy, task success rate, and robustness against system constraints, environmental disturbances, and perceptual uncertainties.

Abstract

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.

Problem

• spacecraft-manipulator system
• dynamic coupling
• attitude stability
• manipulation planning
• mission safety

Innovation

• Dual-Agent Coordination
• Prior Policy Guidance
• Deep Reinforcement Learning
• Space Manipulator
• Attitude Stabilization