Robot Arm Task Imitation System Based on RNN [基于RNN的机械臂任务模仿系统] - 文章详情页

作者：

Yu, J. (Yu, J..) | Wu, P. (Wu, P..) | Zuo, G. (Zuo, G..) | Ruan, X. (Ruan, X..) | Zhang, Y. (Zhang, Y..) (学者：张勇)

收录：

Scopus PKU CSCD

摘要：

To　simplify　the　complex　motion　planning　problem　of　robot　arm　and　make　the　robot　arm　have　the　generalization　ability　to　adapt　to　the　new　task,　a　robot　arm　task　imitation　system　based　on　recurrent　neural　network(RNN)　was　researched　and　implemented　in　this　paper.　First,　the　original　task　was　taught　by　the　teacher,　and　the　teaching　data　was　collected.　Second,　by　constructing　RNN　to　train　the　original　teaching　data,　the　control　strategy　of　the　robot　arm　imitation　was　obtained.　Then,　when　the　task　changes,　the　movement　of　the　new　task　was　observed　and　the　movement　information　was　collected.　Finally,　the　motion　information　was　generalized　via　the　robot　arm　control　strategy　based　on　RNN,　and　the　control　information　of　robot　arm　of　imitating　the　new　task　was　obtained,　completing　the　imitation.　Experimental　results　show　that　the　method　can　obtain　strategy　simply　and　efficiently　and　has　preferable　generalization　ability,　which　make　the　robot　arm　not　only　can　imitate　the　original　task,　but　also　can　imitate　the　new　task　when　the　task　changes.　©　2018,　Editorial　Department　of　Journal　of　Beijing　University　of　Technology.　All　right　reserved.

关键词：

Control strategy; Generalization; Motion planning; Recurrent neural network (RNN); Robot arm

作者机构：

[ 1 ] [Yu, J.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 2 ] [Yu, J.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 3 ] [Wu, P.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 4 ] [Wu, P.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 5 ] [Zuo, G.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 6 ] [Zuo, G.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 7 ] [Ruan, X.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 8 ] [Ruan, X.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 9 ] [Zhang, Y.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 10 ] [Zhang, Y.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China

通讯作者信息：

[Zuo, G.]Faculty of Information Technology, Beijing University of TechnologyChina

电子邮件地址：

zuoguoyu@bjut.edu.cn

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至