Adaptive Online Compensation for Industrial Robot Positioning Error

被引：0
|
作者：
Zhou J. [1 ]
Zheng L. [1 ,2 ,3 ]
Fan W. [1 ,2 ,3 ]
Zhang X. [1 ]
Cao Y. [1 ]
机构：
[1] School of Mechanical Engineering and Automation, Beihang University, Beijing
[2] MIIT Key Laboratory of Intelligent Manufacturing Technology for Aeronautics Advanced Equipments, Ministry of Industry and Information Technology, Beijing
[3] Beijing Key Laboratory of Digital Design and Manufacturing Technology, Beijing
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2023年 / 59卷 / 05期
关键词：
adaptive optimization mechanism; fixed-length memory window; incremental learning; industrial robot; online positioning error compensation;
D O I：
10.3901/JME.2023.05.053
中图分类号：
学科分类号：
摘要：
Due to the geometric and non-geometric errors of the robot body structure, the actual trajectory of the robot has a big deviation from its nominal trajectory, which seriously limits the application of the robot in machining. Note that the positioning accuracy of the robot will be significantly deteriorated with the degradation of the working performance of the robot during the service time, in addition to the differential distribution of the positioning error levels in the workingspace of the robot. To cope with this problem, an adaptive online compensation method based on fixed-length memory window incremental learning is proposed to compensate the positioning errors of the industrial robot during long-term service. Firstly, the correlation between positioning errors and robot poses is quantitatively studied, and the workspace is divided into several pose blocks and a calibration sample library is created, thus an adaptive optimization mechanism of mapping model is established to address the problem of differential distribution of error levels in workingspace. Secondly, the incremental learning algorithm with fixed-length memory window is designed to overcome the catastrophic forgetting of neural network model and balance the accuracy and efficiency of establishing the mapping relationship between new and old robot pose data in online mode, solving the problem that robot performance degradation aggravates positioning errors and affects the applicability of pose mapping model. Finally, the proposed method is applied to long-term compensation case of Stäubli robot and UR robot, and experimental result shows the proposed method reduces the positioning error of the Stäubli robot from 0.85 mm to 0.13 mm and UR robot from 2.11 mm to 0.17 mm, respectively, outperforming similar methods. © 2023 Editorial Office of Chinese Journal of Mechanical Engineering. All rights reserved.
引用
收藏
页码：53 / 66
页数：13
相关论文
共 23 条
  • [11] SHI Xiaojia, ZHANG Fumin, QU Xinghua, Et al., Position and attitude measurement and online errors compensation for KUKA industrial robots[J], Journal of Mechanical Engineering, 53, 8, pp. 1-7, (2017)
  • [12] SHI Zhanghu, HE Xiaoxu, ZENG Debiao, Et al., Error compensation method for mobile robot positioning based on error similarity[J], Acta Aeronautica et Astronautica Sinica, 41, 11, pp. 428-439, (2020)
  • [13] DIYAR K B, MUSTAFA U, LUTFI T T, Et al., Development of a vision based pose estimation system for robotic machining and improving its accuracy using LSTM neural networks and sparse regression[J], Robot. Comput.-Integr. Manuf, 74, (2022)
  • [14] DENG Kenan, GAO Dong, MA Shoudong, Et al., An efficient error compensation method for milling robot based on transfer learning[J], Journal of Mechanical Engineering, 58, 14, pp. 170-180, (2022)
  • [15] ABELE E, WEIGOLD M., Modeling and identification of an industrial robot for machining applications[J], CIRP Annals - Manufacturing Technology, 56, 1, pp. 387-390, (2007)
  • [16] ZHAO Gang, ZHANG Pengfei, XIAO Wenlei, Et al., System identification of the nonlinear residual errors of an industrial robot using massive measurements[J], Robot. Comput.-Integr. Manuf, 59, pp. 104-114, (2019)
  • [17] Tao SUN, Chaoyu LIU, LIAN Binbin, Et al., Calibration for precision kinematic control of an articulated serial robot[J], IEEE Trans. Ind. Electron, 68, 7, (2021)
  • [18] Guanglong DU, Yinhao LIANG, Boyue GAO, Et al., A cognitive joint angle compensation system based on self-feedback fuzzy neural network with incremental learning[J], IEEE Trans. Ind. Inform, 17, 4, (2021)
  • [19] LANGE M D, ALJUNDI R, MASANA M, Et al., A continual learning survey ： Defying forgetting in classification tasks[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 7, pp. 3366-3385, (2022)
  • [20] MCCLOSKEY M, COHEN N J., Catastrophic interference in connectionist networks ： The sequential learning problem[J], Psychology of Learning and Motivation, 24, pp. 109-165, (1989)
123