• •    下一篇

基于DMP-RRT的机械臂轨迹学习与避障方法

金宇强1, 仇翔1,2, 刘安东1,2, 张文安1,2   

  1. 1. 浙江工业大学信息工程学院, 杭州 310023;
    2. 人机协作技术浙江省国际科技合作基地, 杭州 310023
  • 收稿日期:2020-06-15 修回日期:2020-10-12 出版日期:2022-02-25 发布日期:2022-03-21
  • 通讯作者: 张文安,Email:wazhang@zjut.edu.cn.
  • 基金资助:
    浙江省自然科学基金重大项目(LD21F030002),国家自然科学基金优青项目(61822311)资助课题.

金宇强, 仇翔, 刘安东, 张文安. 基于DMP-RRT的机械臂轨迹学习与避障方法[J]. 系统科学与数学, 2022, 42(2): 193-205.

JIN Yuqiang, QIU Xiang, LIU Andong, ZHANG Wen'an. A Trajectory Learning and Obstacle Avoidance Method for Manipulators Based on DMP-RRT[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(2): 193-205.

A Trajectory Learning and Obstacle Avoidance Method for Manipulators Based on DMP-RRT

JIN Yuqiang1, QIU Xiang1,2, LIU Andong1,2, ZHANG Wen'an1,2   

  1. 1. College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023;
    2. Zhejiang Provincial International Science and Technology Cooperation Base, Human-Robot Collaboration Technology, Hangzhou 310023
  • Received:2020-06-15 Revised:2020-10-12 Online:2022-02-25 Published:2022-03-21
针对机械臂在工作空间中运动轨迹规划难的问题,文章提出了一种基于示教学习的轨迹学习与避障方法,该方法融合了高斯混合模型(GMM)、动态运动基元(DMP)和快速扩展随机树(RRT)方法.通过GMM表征预处理后的轨迹数据集,提取运动特征,优化轨迹点分布并回归生成示教轨迹.利用DMP模型对优化轨迹进行编码,学习生成复现轨迹,并具有一定的轨迹泛化能力.同时,在工作空间中存在障碍物的情况下,采用RRT算法在DMP生成轨迹的基础上进行修正,快速得到避障路径.最后在Franka-Panda七自由度机械臂平台上进行物块搬运实验,实现了机械臂抓取-放置作业的快速部署与精准操作,结果验证了文章所设计方法的有效性.
In order to avoid the shortcomings of the commonly used trajectory planning methods, such as the cubersome model coupling and the difficulties in the model operation, a trajectory generation and obstacle avoidance method is proposed for manipulators based on the Learning from Demonstration (LfD). This method combines Gaussian mixture model (GMM), dynamic motion primitive (DMP) and rapid extended random tree (RRT) methods after pretreating the data recorded by the robot platform. The gaussian mixture model, aiming to optimize the set of demonstration data, is employed to generate trajectories containing as many motion features as possible. DMP is used to model and generalize the movements. And then, the trajectory can be adjusted by RRT algorithm to meet the operation requirements in cases of complex environments with obstacles in different shapes. Finally, the pick-and-place experiments based on Franka manipulator validate the effectiveness of the proposed method.

MR(2010)主题分类: 

()
[1] Craig J J. Introduction to Robotics:Mechanics and Control. New Jersey:Prentics Hall, 2009.
[2] 曾超, 杨辰光, 李强, 等.人-机器人技能传递研究进展.自动化学报, 2019, 45(10):1813-1828. (Zeng C, Yang C G, Li Q, et al. Research progress on human-robot skill transfer. it Acta Automatic Sinica, 2019, 45(10):1813-1828.)
[3] Muhlig M, Gienger M, Hellbach S, et al. Task-level imitation learning using variance-based movement optimization. Proceedings of the IEEE International Conference on Robotics and Automation, Kobe, Japan, 2009, 1177-1184.
[4] Khansari-Zadeh S M, Billard A. Learning stable nonlinear dynamical systems with Gaussian mixture models. it IEEE Transactions on Robotics, 2011, 27(5):943-957.
[5] Asfour T, Azad P, Gyarfas F, et al. Imitation learning of dualarm manipulation tasks in humanoid robots. it International Journal of Humanoid Robotics, 2008, 5(2):183-202.
[6] Levine S, Pastor P, Krizhevsky A, et al. Learning hand-eye coordination for robotic grasping with large-scale data collection. Proceedings of the 25th International Symposium on Experimental Robotics, Cham:Springer, 2016, 173-184.
[7] Li C, Yang C, Ju Z, et al. An enhanced teaching interface for a robot using DMP and GMR. it International Journal of Intelligent Robotics and Applications, 2018, 2(1):110-121.
[8] 陈友东, 刘嘉蕾, 胡澜晓. 一种基于高斯过程混合模型的机械臂抓取方法. 机器人, 2019, 41(3):343-352.(Chen Y D, Liu J L, Hu L X. A manipulator grasping method based on mixture of Gaussian process model. it Robot, 2019, 41(3):343-352.)
[9] Park D H, Hoffmann H, Pastor P, et al. Movement reproduction and obstacle avoidance with dynamic movement primitives with potential field. IEEE/RAS International Conference on Humanoid Robots, Piscataway, USA, 2009, 91-98.
[10] Rai A, Meier F, Ijspeert A, et al. Learning coupling terms for obstacle avoidance. IEEE/RAS International Conference on Humanoid Robots, Piscataway, USA, 2014, 512-518.
[11] 刘维惠, 陈殿生, 张立志.人机协作下的机械臂轨迹生成与修正方法.机器人, 2016, 38(4):504-512.(Liu W H, Chen D S, Zhang L Z. Trajectory generation and adjustment method for robot manipulators in human-robot collaboration. it Robot, 2016, 38(4):504-512.)
[12] Petitjean F, Forestier G, Webb G I, et al. Dynamic time warping averaging of time series allows faster and more accurate classification. IEEE International Conference on Data Mining, Shenzhen, China, 2014, 470-479.
[13] 郭岩, 罗珞珈, 汪洋, 等.一种基于DTW改进的轨迹相似度算法.国外电子测量技术, 2016, 35(9):66-71.(Guo Y, Luo L J, Wang Y, et al. Improved DTW algorithm for trajectory similarity. it Foreign Electronic Measurement Technology, 2016, 35(9):66-71.)
[14] 于建均, 门玉森, 阮晓钢, 等. 基于Kinect的Nao机器人动作模仿系统的研究与实现. 智能系统学报, 2016, 11(2):180-187. (Yu J J, Men Y S, Ruan X G, et al. The research and implementation of behavior imitation system about Nao robot based on Kinect. it CAAI Transactions on Intelligent Systems, 2016, 11(2):180-187.)
[15] Burnham K P. Multimodel inference:Under-standing AIC and BIC in model selection. it Sociological Method and Research, 2004, 33(2):261-304.
[16] Cohen G, Afshar S, Tapson J, et al. EMNIST:An extension of MNIST to handwritten letters. 2017 International Joint Coference on Neural Networks (IJCNN), Anchorage, 2017, 2921-2926.
[17] Calinon S. Continuous extraction of task constraints in a robot programming by demonstration framework, Switzerland:EPFL, 2007.
[18] Ijspeert A J, Nakanishi J, Schaal S. Movement imitation with nonlinear dynamical systems in humanoid robots. Proceedings 2002 IEEE International Conference on Robotics and Automation, Washington, 2002, 1398-1403.
[19] Melchior N A, Simmons R. Particle RRT for path planning with uncertainty. Proceedings 2007 IEEE International Conference on Robotics and Automation, Roma, 2007, 1617-1624.
[20] 胡喜玲, 国海涛. 基于正反馈自适应遗传算法的机器人路径滚动规划. 计算机应用研究, 2010, 27(6):2037-2039. (Hu X L, Guo H T. Robot path planning based on positive feedback adaptive genetic algorithm. it Application Research of Computers, 2010, 27(6):2037-2039.)
[1] 李文博, 秦小林, 罗刚. 基于无障碍凸区域的无人机在线航迹规划[J]. 系统科学与数学, 2021, 41(6): 1493-1506.
阅读次数
全文


摘要