文献类型：期刊文献

英文题名：A Data-Driven Cyclic-Motion Generation Scheme for Kinematic Control of Redundant Manipulators

作者：Xie, Zhengtai[1,2];Jin, Long[1,2];Luo, Xin[3,4,5];Li, Shuai[1,2];Xiao, Xiuchun[6]

机构：[1]Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Peoples R China;[2]Acad Plateau Sci & Sustainabil, Xining 810016, Peoples R China;[3]Chinese Acad Sci, Chongqing Engn Res Ctr Big Data Applicat Smart Ci, Chongqing 400714, Peoples R China;[4]Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Big Data & Intelligent Comp, Chongqing 400714, Peoples R China;[5]Cloudwalk, Dept Big Data Analyses Tech, Chongqing 401331, Peoples R China;[6]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524000, Peoples R China

年份：2021

卷号：29

期号：1

起止页码：53

外文期刊名：IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY

收录：SCI-EXPANDED(收录号：WOS:000600848100005)、、EI(收录号：20202408802398)、Scopus(收录号：2-s2.0-85081134569)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61703189, in part by the Natural Science Foundation of Gansu Province, China under Grant 18JR3RA264, in part by the Natural Science Foundation of Chongqing (China) under Grant cstc2019jcyjjqX0013, in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciences, in part by the Sichuan Science and Technology Program under Grant 19YYJC1656, in part by the National Key Research and Development Program of China under Grant 2017YFE0118900, in part by the Innovation and Strength Project in Guangdong Province (Natural Science) under Grant 230419065, in part by the Industry-UniversityResearch Cooperation Education Project of Ministry of Education under Grant 201801328005, and in part by the Fundamental Research Funds for the Central Universities under Grant lzujbky-2019-89.S

语种：英文

外文关键词：Manipulator dynamics; Kinematics; Task analysis; Jacobian matrices; Neural networks; Redundancy; Cyclic-motion generation (CMG); data driven; dynamic neural network (DNN); learning and control; redundant manipulator

外文摘要：Redundant manipulators are no doubt indispensable devices in industrial production. There are various works on the redundancy resolution of redundant manipulators in performing a given task with the manipulator model information known. However, it becomes knotty for researchers to precisely control redundant manipulators with unknown model to complete a cyclic-motion generation (CMG) task, to some extent. Inspired by this problem, this article proposes a data-driven CMG scheme and the corresponding novel dynamic neural network (DNN), which exploits learning and control simultaneously to complete the kinematic control of manipulators with model unknown. It is worth mentioning that the proposed method is capable of accurately estimating the Jacobian matrix in order to obtain the structure information of the manipulator and theoretically eliminates the tracking errors. Theoretical analyses prove the convergence of the learning and control parts under the necessary noise conditions. Computer simulation results and comparisons of different controllers illustrate the reliability and superior performance of the proposed method with strong learning ability and control ability. This article is greatly significant for redundancy resolution of redundant manipulators with unknown models or unknown loads in practice.