Application of N-step-ahead neurocontrol on articulated manipulators

Hountras, A; Antoniadis, I; Kanarachos, A

dc.contributor.author	Hountras, A	en
dc.contributor.author	Antoniadis, I	en
dc.contributor.author	Kanarachos, A	en
dc.date.accessioned	2014-03-01T01:15:29Z
dc.date.available	2014-03-01T01:15:29Z
dc.date.issued	2000	en
dc.identifier.issn	0741-2223	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13532
dc.subject.classification	Robotics	en
dc.subject.other	NEURAL NETWORKS	en
dc.subject.other	SYSTEM-IDENTIFICATION	en
dc.subject.other	DYNAMIC-SYSTEMS	en
dc.subject.other	CONTROLLERS	en
dc.subject.other	MODELS	en
dc.title	Application of N-step-ahead neurocontrol on articulated manipulators	en
heal.type	journalArticle	en
heal.identifier.primary	10.1002/(SICI)1097-4563(200003)17:3<127::AID-ROB1>3.3.CO;2-P	en
heal.identifier.secondary	http://dx.doi.org/10.1002/(SICI)1097-4563(200003)17:3<127::AID-ROB1>3.3.CO;2-P	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	The N-step-ahead control method, called chain-back-propagation, is applied to articulated manipulators. The method is based on a pair of: neural networks-the neural controller and the neural emulator-and focuses mainly in the appropriate design of the various global and chain-local penalty functions and the convergence control limitations, needed for the on-line training of the controller. No reference models or paths are needed for the implementation of the method, only set-points. The results, compared to conventional proportional-derivative (PD) control and to traditional one-step-ahead neural control, are quite satisfactory, indicating improved accuracy, faster response, and greater overall efficiency, (C) 2000 John Wiley & Sons, Inc.	en
heal.publisher	JOHN WILEY & SONS INC	en
heal.journalName	JOURNAL OF ROBOTIC SYSTEMS	en
dc.identifier.doi	10.1002/(SICI)1097-4563(200003)17:3<127::AID-ROB1>3.3.CO;2-P	en
dc.identifier.isi	ISI:000085562100001	en
dc.identifier.volume	17	en
dc.identifier.issue	3	en
dc.identifier.spage	127	en
dc.identifier.epage	148	en