Deep reinforcement learning-based variable impedance control for grinding workpieces with complex geometry

作     者：Li, Yanghong Wang, Yahao Li, Zhen Lv, Yingxiang Chai, Jin Dong, Erbao 

作者机构：Univ Sci & Technol China Humanoid Robot Inst Dept Precis Machinery & Precis Instrumentat State Key Lab Precis & Intelligent ChemCAS Key La Hefei Peoples R China 

出 版 物：《ROBOTIC INTELLIGENCE AND AUTOMATION》 (Robot. Intell. Autom.)

年 卷 期：2025年第45卷第1期

页      面：159-172页

核心收录：

基　　金：National Key R&D Program of China [2018YFB1307400] Fundamental Research Funds for the Central Universities 

主　　题：Robotic machining Model learning for control Compliance and impedance control Force tracking in workpieces 

摘      要：PurposeThis paper aims to design a deep reinforcement learning (DRL)-based variable impedance control policy that supports stability analysis for robot force tracking in complex geometric ***/methodology/approachThe DRL-based variable impedance controller explores and pre-learns the optimal policy for impedance parameter tuning in simulation scenarios with randomly generated workpieces. The trained results are then used as feedforward inputs to improve the force-tracking performance of the robot during contact. Based on Lyapunov s theory, the stability of the proposed control policy is analysed to illustrate the interpretability of the *** and experiments are performed on different types of complex environments. The results show that the proposed method is not only theoretically feasible but also has better force-tracking effects in ***/valueCompared with most other DRL-based control policies, the proposed method possesses stability and interpretability, effectively avoids the overfitting phenomenon and thus has better simulation-to-real deployment results.