Robot motion classification from the standpoint of learning control

Shaw Ji Shiah, Kuu-Young Young*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)285-296
Number of pages12
JournalFuzzy Sets and Systems
Volume144
Issue number2
DOIs
StatePublished - 1 Jun 2004

Keywords

  • Learning space complexity
  • Motion similarity analysis
  • Robot learning control
  • Robot motion classification

Fingerprint

Dive into the research topics of 'Robot motion classification from the standpoint of learning control'. Together they form a unique fingerprint.

Cite this