File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Assembly skill acquisition via reinforcement learning

TitleAssembly skill acquisition via reinforcement learning
Authors
Lau, HYKLee, ISK
KeywordsAssembly
Control
Learning
Robots
Issue Date2001
PublisherEmerald Group Publishing Limited. The Journal's web site is located at http://www.emeraldinsight.com/aa.htm
Citation
Assembly Automation, 2001, v. 21 n. 2, p. 136-142 How to Cite?
DOI: http://dx.doi.org/10.1108/01445150110388522
AbstractA neural network controller is proposed for the motion control of robot manipulators with force/torque feedback signals. This controller is trained with reinforcement learning algorithms and a model is extracted from the synaptic weights within the neural network. This model is continuously refined by the feedback signals to ensure its validity even in a stochastic and non-stationary environment. With this model and the real-time force/torque feedback data, the robot can acquire a fine skill for a particular assembly task for which it is trained.
Persistent Identifierhttp://hdl.handle.net/10722/74375
ISSN
0144-5154
2021 Impact Factor: 2.373
2020 SCImago Journal Rankings: 0.345
ISI Accession Number ID
WOS:000168651800008
References
References in Scopus

 

DC FieldValueLanguage
dc.contributor.authorLau, HYKen_HK
dc.contributor.authorLee, ISKen_HK
dc.date.accessioned2010-09-06T07:00:42Z-
dc.date.available2010-09-06T07:00:42Z-
dc.date.issued2001en_HK
dc.identifier.citationAssembly Automation, 2001, v. 21 n. 2, p. 136-142en_HK
dc.identifier.issn0144-5154en_HK
dc.identifier.urihttp://hdl.handle.net/10722/74375-
dc.description.abstractA neural network controller is proposed for the motion control of robot manipulators with force/torque feedback signals. This controller is trained with reinforcement learning algorithms and a model is extracted from the synaptic weights within the neural network. This model is continuously refined by the feedback signals to ensure its validity even in a stochastic and non-stationary environment. With this model and the real-time force/torque feedback data, the robot can acquire a fine skill for a particular assembly task for which it is trained.en_HK
dc.languageengen_HK
dc.publisherEmerald Group Publishing Limited. The Journal's web site is located at http://www.emeraldinsight.com/aa.htmen_HK
dc.relation.ispartofAssembly Automationen_HK
dc.subjectAssemblyen_HK
dc.subjectControlen_HK
dc.subjectLearningen_HK
dc.subjectRobotsen_HK
dc.titleAssembly skill acquisition via reinforcement learningen_HK
dc.typeArticleen_HK
dc.identifier.emailLau, HYK:hyklau@hkucc.hku.hken_HK
dc.identifier.authorityLau, HYK=rp00137en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1108/01445150110388522en_HK
dc.identifier.scopuseid_2-s2.0-0035780951en_HK
dc.identifier.hkuros63115en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0035780951&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume21en_HK
dc.identifier.issue2en_HK
dc.identifier.spage136en_HK
dc.identifier.epage142en_HK
dc.identifier.isiWOS:000168651800008-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridLau, HYK=7201497761en_HK
dc.identifier.scopusauthoridLee, ISK=26663339300en_HK
dc.identifier.issnl0144-5154-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats