File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: An adaptive fuzzy approach to obstacle avoidance

TitleAn adaptive fuzzy approach to obstacle avoidance
Authors
KeywordsComputers
Cybernetics
Issue Date1998
PublisherIEEE.
Citation
IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings, San Diego, California, USA, 11-14 October 1998, v. 4, p. 3418-3423 How to Cite?
AbstractReinforcement learning based on a new training method previously reported guarantees convergence and an almost complete set of rules. However, there are two shortcomings remained: 1) the membership functions of the input sensor readings are determined manually and take the same form; and 2) there are still a small number of blank rules needed to be manually inserted. To address these two issues, this paper proposes an adaptive fuzzy approach using a supervised learning method based on backpropagation to determine the parameters for the membership functions for each sensor reading. By having different input fuzzy sets, each sensor reading contributes differently in avoiding obstacles. Our simulations show that the proposed system converges rapidly to a complete set of rules, and if there are no conflicting input-output data pairs in the training sets, the proposed system performs collision-free obstacle avoidance.
Persistent Identifierhttp://hdl.handle.net/10722/46151
ISSN

 

DC FieldValueLanguage
dc.contributor.authorYung, NHCen_HK
dc.contributor.authorYe, Cen_HK
dc.date.accessioned2007-10-30T06:43:35Z-
dc.date.available2007-10-30T06:43:35Z-
dc.date.issued1998en_HK
dc.identifier.citationIEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings, San Diego, California, USA, 11-14 October 1998, v. 4, p. 3418-3423en_HK
dc.identifier.issn1062-922Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/46151-
dc.description.abstractReinforcement learning based on a new training method previously reported guarantees convergence and an almost complete set of rules. However, there are two shortcomings remained: 1) the membership functions of the input sensor readings are determined manually and take the same form; and 2) there are still a small number of blank rules needed to be manually inserted. To address these two issues, this paper proposes an adaptive fuzzy approach using a supervised learning method based on backpropagation to determine the parameters for the membership functions for each sensor reading. By having different input fuzzy sets, each sensor reading contributes differently in avoiding obstacles. Our simulations show that the proposed system converges rapidly to a complete set of rules, and if there are no conflicting input-output data pairs in the training sets, the proposed system performs collision-free obstacle avoidance.en_HK
dc.format.extent605339 bytes-
dc.format.extent10863 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rights©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectComputersen_HK
dc.subjectCyberneticsen_HK
dc.titleAn adaptive fuzzy approach to obstacle avoidanceen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1062-922X&volume=4&spage=3418&epage=3423&date=1998&atitle=An+adaptive+fuzzy+approach+to+obstacle+avoidanceen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICSMC.1998.726539en_HK
dc.identifier.hkuros45906-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats