基于深度强化学习的机器人轴孔装配策略仿真研究  

Simulation of Robotic Peg-in-hole Assembly Strategy Based on DRL

作　　者：朱子璐 刘永奎[1] 张霖[2] 王力翚 林廷宇 Zhu Zilu;Liu Yongkui;Zhang Lin;Wang Lihui;Lin Tingyu(School of Mechano-Electronic Engineering,Xidian University,Xi'an 710071,China;School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191,China;Department of Production Engineering KTH Royal Institute of Technology,Stockholm 25175,Sweden;Beijing Complex Product Advanced Manufacturing Engineering Research Center,Beijing Simulation Center,Beijing 100854,China)

机构地区：[1]西安电子科技大学机电工程学院,陕西西安710071 [2]北京航空航天大学自动化科学与电气工程学院,北京100191 [3]瑞典皇家理工学院生产工程系,斯德哥尔摩25175 [4]北京仿真中心北京市复杂产品先进制造系统工程技术研究中心,北京100854

出　　处：《系统仿真学报》2024年第6期1414-1424,共11页Journal of System Simulation

基　　金：国家自然科学基金(61973243)。

摘　　要：针对现有轴孔装配方法存在的依赖于精确的接触状态模型、数据采集困难、采样效率低、安全性差等问题,提出了一种基于DRL的机器人轴孔装配策略仿真研究方法。搭建了基于ROSGazebo机器人轴孔装配仿真环境,提出了基于最小二乘法对力/力矩传感器进行重力补偿的方法;基于RL的范式对轴孔装配问题建模,并提出了一种基于SAC(soft actor-critic)算法的机器人轴孔装配方法;通过ROS建立了仿真环境与深度强化学习算法的通信机制。实验结果表明:该算法能够使机器人自主且柔顺地完成轴孔装配任务,并具有较好的泛化性。Aiming at the existing peg-in-hole assembly method problems of dependence on accurate contact state models,difficulties in data acquisition,low sampling efficiency,and poor security,a simulation research method for robot peg-in-hole assembly strategy based on DRL is proposed.A simulation environment of robot peg-in-hole assembly based on ROS-Gazebo is built,and a method of gravity compensation for force/torque sensor based on a least square method is proposed.The reinforcement learning paradigm is employed to model the robot peg-in-hole assembly,and a method based on soft actor-critic(SAC)algorithm is proposed.The communication mechanism between the simulation environment and the deep reinforcement learning algorithm is established through ROS.Simulation experiments show that the proposed SAC algorithm enables robots to accomplish the peg-inhole assembly task autonomously and compliantly with good generalization ability.

关 键 词：轴孔装配 DRL 柔顺控制 装配策略仿真 ROS-Gazebo仿真环境 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]