Show simple item record

dc.contributor.authorHanheide, M.en_US
dc.contributor.authorGretton, C.en_US
dc.contributor.authorDearden, R.en_US
dc.contributor.authorHawes, N.en_US
dc.contributor.authorWyatt, J.en_US
dc.contributor.authorPronobis, A.en_US
dc.contributor.authorAydemir, A.en_US
dc.contributor.authorG¨obelbecker, M.en_US
dc.contributor.authorZender, H.en_US
dc.contributor.editorToby Walshen_US
dc.date.accessioned2017-05-03T13:12:54Z
dc.date.available2017-05-03T13:12:54Z
dc.date.issued2011en_US
dc.date.modified2013-01-03T23:30:18Z
dc.identifier.doi10.5591/978-1-57735-516-8/IJCAI11-407en_US
dc.identifier.urihttp://hdl.handle.net/10072/46509
dc.description.abstractRobots must perform tasks efficiently and reliably while acting under uncertainty. One way to achieve efficiency is to give the robot commonsense knowledge about the structure of the world. Reliable robot behaviour can be achieved by modelling the uncertainty in the world probabilistically. We present a robot system that combines these two approaches and demonstrate the improvements in efficiency and reliability that result. Our first contribution is a probabilistic relational model integrating common-sense knowledge about the world in general, with observations of a particular environment. Our second contribution is a continual planning system which is able to plan in the large problems posed by that model, by automatically switching between decision-theoretic and classical procedures. We evaluate our system on object search tasks in two different real-world indoor environments. By reasoning about the trade-offs between possible courses of action with different informational effects, and exploiting the cues and general structures of those environments, our robot is able to consistently demonstrate efficient and reliable goal-directed behaviour.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_US
dc.format.extent1639528 bytes
dc.format.mimetypeapplication/pdf
dc.languageEnglishen_US
dc.language.isoen_US
dc.publisherAAAI Pressen_US
dc.publisher.placeUnited Statesen_US
dc.publisher.urihttp://ijcai.org/papers11/contents.phpen_US
dc.relation.ispartofstudentpublicationNen_US
dc.relation.ispartofconferencenameIJCAI-11en_US
dc.relation.ispartofconferencetitleTwenty-Second International Joint Conference on Artificial Intelligence Proceedingsen_US
dc.relation.ispartofdatefrom2011-07-16en_US
dc.relation.ispartofdateto2011-07-22en_US
dc.relation.ispartoflocationCatalonia, Spainen_US
dc.rights.retentionYen_US
dc.subject.fieldofresearchArtificial Intelligence and Image Processing not elsewhere classifieden_US
dc.subject.fieldofresearchcode080199en_US
dc.titleExploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviouren_US
dc.typeConference outputen_US
dc.type.descriptionE1 - Conference Publications (HERDC)en_US
dc.type.codeE - Conference Publicationsen_US
gro.rights.copyright© 2011 International Joint Conference on Artificial Intelligence. The attached file is reproduced here in accordance with the copyright policy of the publisher. Please refer to the Conference's website for access to the definitive, published version.en_US
gro.date.issued2011
gro.hasfulltextFull Text
gro.griffith.authorGretton, Charles


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record