基于多种群协同进化算法的绳索牵引并联机器人末端位置误差补偿

doi:10.13973/j.cnki.robot.200054

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2713 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
李国江, 张飞, 李露, 尚伟伟, 陶猛. 基于多种群协同进化算法的绳索牵引并联机器人末端位置误差补偿[J]. 机器人, 2021, 43(1): 81-89.DOI: 10.13973/j.cnki.robot.200054. LI Guojiang, ZHANG Fei, LI Lu, SHANG Weiwei, TAO Meng. Error Compensation of End-effector Position for the Cable-Driven Parallel Robot Based on Multi-Group Co-evolutionary Algorithm. ROBOT, 2021, 43(1): 81-89. DOI: 10.13973/j.cnki.robot.200054.

摘要对于绳索牵引并联机器人来说，影响其末端位置精度的模型不确定性主要包括几何参数误差和非几何参数误差．这两种不同类型的误差具有非常强的非线性且相互耦合，难以通过传统的标定手段来进行参数标定．针对这一问题，提出了一种基于神经网络的末端位置误差补偿方法．将两种不同类型的参数误差等效视作伪误差，通过神经网络来逼近伪误差造成的末端位置误差曲线，建立末端位置误差与绳索长度之间的映射关系，并在关节空间中进行位置误差补偿．为了提高神经网络的拟合精度，设计了基于多种群协同进化算法和反向传播算法的神经网络优化方法，该优化方法能够同时优化网络的权值、阈值和结构，提高神经网络的泛化能力和拟合精度．在实际3自由度绳索牵引并联机器人上进行了位置误差补偿实验，结果表明补偿后的位置误差均值从6．64 mm下降到1．08 mm，轨迹误差均值从7．5 mm下降到1．6 mm，末端位置的精度得到了显著提高．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李国江
	张飞
	李露
	尚伟伟
	陶猛

关键词 ：绳索牵引并联机器人, 位置误差补偿, 伪误差理论, 多种群协同进化算法

Abstract：For the cable-driven parallel robot, the main model uncertainties that effect the accuracy of end-effector position include geometric parameter error and non-geometric parameter error. The two kinds of errors have strong nonlinearity and are coupled with each other, so it is difficult to calibrate parameters by traditional calibration methods. To solve it, a compensation method for end-effector position error based on neural network is proposed. The above two types of parameter errors are regarded as pseudo errors equivalently, and the curve of the end-effector position error caused by pseudo errors is approached by neural network. The mapping relationship between the end-effector position error and the cable length is established, and the position error is compensated in joint space. In order to improve the fitting accuracy of the neural network, a neural network optimization method is designed by the multi-group co-evolutionary algorithm and the backpropagation algorithm. The optimization method can optimize the network weight, threshold and structure at the same time, and improve the generalization ability and fitting accuracy of the neural network. The position error compensation experiment is carried out on the 3-DOF (degree of freedom) cable-driven parallel robot. The experimental results indicate that the mean value of the position error after compensation is reduced from 6.64 mm to 1.08 mm, the mean value of the trajectory error is reduced from 7.5 mm to 1.6 mm, and the position accuracy of the end-effector is significantly improved.

Key words： cable-driven parallel robot position error compensation pseudo error theory multi-group co-evolutionary algorithm

收稿日期: 2020-02-22 录用日期: 2020-10-16

TP27

基金资助:国家自然科学基金（51675501， 51275500）．

通讯作者: 尚伟伟,wwshang@ustc.edu.cn E-mail: wwshang@ustc.edu.cn

作者简介: 李国江(1995-),男,硕士生.研究领域:绳索机器人,标定与标识,计算机视觉.
张飞(1991-),男,博士,工程师.研究领域:绳索机器人,机器人标定,机构设计.
李露(1981-),女,博士,副研究员.研究领域:机构设计,仿生机器人,多体动力学.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.200054 或 https://robot.sia.cn/CN/Y2021/V43/I1/81

[1] 冯李航,张为公,龚宗洋,等. Delta系列并联机器人研究进展与现状[J].机器人, 2014, 36(3):375-384. Feng L H, Zhang W G, Gong Z Y, et al. Developments of Deltalike parallel manipulators-A review[J]. Robot, 2014, 36(3):375-384.
[2] Qian S, Zi B, Shang W W, et al. A review on cable-driven parallel robots[J]. Chinese Journal of Mechanical Engineering, 2018, 31(4):37-47.
[3] 张彬,张飞,周烽,等. 绳索牵引并联机器人的双空间自适应同步控制[J].机器人, 2020, 42(2):139-147. Zhang B, Zhang F, Zhou F, et al. Dual-space adaptive synchronization control of cable-driven parallel robots[J]. Robot, 2020, 42(2):139-147.
[4] Yao R, Tang X Q, Wang J S, et al. Dimensional optimization design of the four-cable-driven parallel manipulator in FAST[J]. IEEE/ASME Transactions on Mechatronics, 2010, 15(6):932941.
[5] 王文杰,于凌涛,杨景,等. 基于关节转角估计器的绳驱动手术微器械位置全闭环控制[J].机器人, 2018, 40(2):231-239. Wang W J, Yu L T, Yang J, et al. Full closed-loop position control of the surgical cable-driven micromanipulator based on joint angle estimator[J]. Robot, 2018, 40(2):231-239.
[6] 宋达,张立勋,王炳军,等. 柔索牵引式力觉交互机器人控制策略[J].机器人, 2018, 40(4):440-447. Song D, Zhang L X, Wang B J, et al. The control strategy of flexible cable driven force interactive robot[J]. Robot, 2018, 40(4):440-447.
[7] 张立勋,李来禄,姜锡泽,等. 柔索驱动的宇航员深蹲训练机器人力控与实验研究[J].机器人, 2017, 39(5):733741. Zhang L X, Li L L, Jiang X Z, et al. Force control and experimental study of a cable-driven robot for astronaut deep squat training[J]. Robot, 2017, 39(5):733-741.
[8] Gouttefarde M, Collard J F, Riehl N, et al. Geometry selection of a redundantly actuated cable-suspended parallel robot[J]. IEEE Transactions on Robotics, 2015, 31(2):501-510.
[9] Khosravi M A, Taghirad H D. Dynamic modeling and control of parallel robots with elastic cables:Singular perturbation approach[J]. IEEE Transactions on Robotics, 2014, 30(3):694704.
[10] Cverly R J, Forbes J R. Flexible cable-driven parallel manipulator control maintaining positive cable tensions[J]. IEEE Transactions on Control Systems Technology, 2018, 26(5):18741883.
[11] Surdilovic D, Radojicic J, Bremer N. Efficient calibration of cable-driven parallel robots with variable structure[M]. Cham, Switzerland:Springer, 2015:113-128.
[12] Kamali K, Joubair A, Bonev I A, et al. Elasto-geometrical calibration of an industrial robot under multidirectional external loads using a laser tracker[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2016:4320-4327.
[13] Chellal R, Laroche E, Cuvillon L, et al. An identification methodology for 6-DoF cable-driven parallel robots parameters application to the INCA 6D robot[M]. Berlin, Germany:Springer, 2013.
[14] Zhang F, Shang W W, Cong S. Choosing measurement configurations for kinematic calibration of cable-driven parallel robots[C]//3rd International Conference on Advanced Robotics and Mechatronics. Piscataway, USA:IEEE, 2018:397-402.
[15] Zhang B, Zhou F, Shang W W, et al. Auto-calibration and online-adjustment of the kinematic uncertainties for redundantly actuated cable-driven parallel robots[C]//4th International Conference on Advanced Robotics and Mechatronics. Piscataway, USA:IEEE, 2019:280-285.
[16] Riehl N, Gouttefarde M, Krut S, et al. Effects of non-negligible cable mass on the static behavior of large workspace cabledriven parallel mechanisms[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2009:2193-2198.
[17] 王坤. 工业机器人运动学参数标定及误差补偿研究[D].武汉:华中科技大学, 2018. Wang K. Research on calibration and error compensation of kinematics parameters of industrial robots[D]. Wuhan:Huazhong University of Science and Technology, 2018.
[18] 戴厚德,曾现萍,游鸿修,等. 基于光学运动跟踪系统的机器人末端位姿测量与误差补偿[J].机器人, 2019, 41(2):206-215. Dai H D, Zeng X P, You H X, et al. Pose measurement and error compensation of the robot end-effector based on an optical tracking system[J]. Robot, 2019, 41(2):206-215.
[19] Chen X Y, Zhang Q J, Sun Y L. Non-kinematic calibration of industrial robots using a rigid-flexible coupling error model and a full pose measurement method[J]. Robotics and Computer Integrated Manufacturing, 2019, 57:46-58.
[20] Bai Y, Wang D L. On the comparison of an interval type-2 fuzzy interpolation system and other interpolation methods used in industrial modeless robotic calibrations[C]//IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications. Piscataway, USA:IEEE, 2016. DOI:10.1109/CIVEMSA.2016.7524323.
[21] Jang J H, Kim S H, Kwak Y K. Calibration of geometric and non-geometric errors of an industrial robot[J]. Robotica, 2001, 19(3):311-321.
[22] Wang D, Bai Y, Zhao J Y. Robot manipulator calibration using neural network and a camerabased measurement system[J]. Transactions of the Institute of Measurement and Control, 2012, 34(1):105-121.
[23] 何文凯,费燕琼,陈萌. 绳索牵引式并联机器人误差分析及补偿[J].机械设计与制造, 2018(S2):171-174. He W K, Fei Y Q, Chen M. Error analysis and compensation of cable-driven parallel robot[J]. Machinery Design & Manufacture, 2018(S2):171-174.
[24] Zhang D, Gao Z. Optimal kinematic calibration of parallel manipulators with pseudoerror theory and cooperative coevolutionary network[J]. IEEE Transactions on Industrial Electronics, 2012, 59(8):3221-3231.
[25] Varun K O, Ajith A, Václav S. Metaheuristic design of feedforward neural networks:A review of two decades of research[J]. Engineering Applications of Artificial Intelligence, 2017(60):97-116.
[26] Pu X C, Lin Y Q, Sun P F. A pruned cooperative co-evolutionary genetic neural network and its application on stock market forecast[C]//The 26th Chinese Control and Decision Conference. Piscataway, USA:IEEE, 2014:2344-2349.
[27] 吴伟. 基于改进遗传算法的神经网络结构优化研究[D].苏州:苏州大学, 2012. Wu W. The study on structural optimization of neural networks based on an improved genetic algorithm[D]. Suzhou:Soochow University, 2012.
[28] Potter M A, Kenneth A J. A cooperative coevolutionary approach to function optimization[M]//Lecture Notes in Computer Science, Vol.866. Berlin, Germany:Springer, 1994:249-257.