標題: Robot motion classification from the standpoint of learning control
作者: Shiah, SJ
Young, KY
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: robot motion classification;robot learning control;learning space complexity;motion similarity analysis
公開日期: 1-Jun-2004
摘要: In robot learning control, the learning space for executing the general motions of multi-joint robot manipulators is very complicated. Thus, when the learning controllers are employed as major roles in motion governing, the motion variety requires them to consume excessive amount of memory. Therefore, in spite of their ability to generalize, the learning controllers are usually used as subordinates to conventional controllers or the learning process needs to be repeated each time a new trajectory is encountered. To simplify learning space complexity, we propose, from the standpoint of learning control, that robot motions be classified according to their similarities. The learning controller can then be designed to govern groups of robot motions with high degrees of similarity without consuming excessive memory resources. Motion classification based on using the PUMA 560 robot manipulator demonstrates the effectiveness of the proposed scheme. (C) 2003 Elsevier B.V. All rights reserved.
URI: http://dx.doi.org/10.1016/S0165-0114(03)00071-X
http://hdl.handle.net/11536/26750
ISSN: 0165-0114
DOI: 10.1016/S0165-0114(03)00071-X
期刊: FUZZY SETS AND SYSTEMS
Volume: 144
Issue: 2
起始頁: 285
結束頁: 296
Appears in Collections:Articles


Files in This Item:

  1. 000221375200002.pdf