RAPSO: An Integrated PSO with Reinforcement Learning and an Adaptive Weight Strategy for the High-Precision Milling of Elastic Materials.

Abstract

This study tackles the challenge of achieving high-precision robotic machining of elastic materials, where elastic recovery and overcutting often impair accuracy. To address this, a novel milling strategy, RAPSO, is introduced by combining an adaptive particle swarm optimization (APSO) algorithm with a reinforcement learning (RL)-based compensation mechanism. The method builds a material-specific milling model through residual error characterization, incorporates a dynamic inertia weight adjustment strategy into APSO for optimized toolpath generation, and integrates a Proximal Policy Optimization (PPO)-based RL module to refine trajectories iteratively. Experiments show that RAPSO reduces residual material by 33.51% compared with standard PSO and APSO methods, while offering faster convergence and greater stability. The proposed framework provides a practical solution for precision machining of elastic materials, offering improved accuracy, reduced post-processing requirements, and higher efficiency, while also contributing to the theoretical modeling of elastic recovery and advanced toolpath planning.