协作机器人运动轨迹模仿学习方法研究  

Research on Imitation Learning Method of Cooperative Robot Motion Trajectory

作　　者：李平[1] 李利娜 侯志利 LI Ping;LI Lina;HOU Zhili(Department of Mechanical and Electrical Engineering,Shanxi Institute of Economic Management,Taiyuan 030024,China;College of Mechanical Engineering,Ministry of Education,Taiyuan University of Technology,Taiyuan 030024,China;Key Laboratory of Advanced Transducers and Intelligent Control System,Ministry of Education,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]山西经济管理干部学院机电工程系,太原030024 [2]太原理工大学机械与运载工程学院,太原030024 [3]太原理工大学新型传感器与智能控制教育部重点实验室,太原030024

出　　处：《组合机床与自动化加工技术》2024年第10期120-125,共6页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：山西省应用基础研究计划青年科技研究基金项目(202103021223090)。

摘　　要：在人机协作领域,模仿学习是广泛使用的机器人编程方法。在机器人对运动轨迹进行技能学习过程中,针对基于动态运动基元方法(dynamic movement primitives,DMP)只能从单条示教轨迹建模动作的局限性,提出了一种新的将高斯混合模型(gaussian mixture model,GMM)、高斯混合回归(gaussian mixture regression,GMR)和改进的DMP三者相结合的运动轨迹模仿学习方法。该方法先将高斯噪声引入示教轨迹,消除由于示教数据中不可避免存在噪声等不平滑特征带来的不利影响;然后,为了减少单条示教轨迹的不确定性带来的动作建模误差,采用GMM从多条示教轨迹中对运动特征进行编码,使用GMR进行概率轨迹回归;其次,利用改进的DMP算法将轨迹进行泛化,提高机器人技能学习的适应性;最后,通过手写字母轨迹和协作机器人拖动轨迹技能学习试验验证了所提算法的有效性。In the field of human-machine collaboration,imitation learning is a widely used robotic programming method.Aiming at the limitation that the dynamic movement primitives(DMP)can only model the action from a single demonstration trajectory,a new trajectory imitation learning method combining gaussian mixture model(GMM),gaussian mixture regression(GMR)and improved DMP is proposed.This method firstly introduces Gaussian noise into the demonstration trajectory to eliminate the adverse effects caused by the inevitable noise and other non-smooth features in the teaching data.Then,in order to reduce the action modeling error caused by the uncertainty of a single demonstration trajectory,GMM is used to encode the motion features from multiple teaching trajectories,and GMR is used for probabilistic trajectory regression.Secondly,the improved DMP algorithm is used to generalize the trajectory in space and improved the adaptability of robot skill learning.Finally,the effectiveness of the proposed algorithm is verified by handwritten letter imitation learning simulation and cooperative robot dragging experiment.

关 键 词：模仿学习 轨迹建模 动态运动基元 高斯混合模型 高斯混合回归 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]