On-line reinforcement learning for trajectory following with unknown faults

Show simple item record

dc.contributor.author Sohége, Yves
dc.contributor.author Provan, Gregory
dc.date.accessioned 2019-01-28T12:55:15Z
dc.date.available 2019-01-28T12:55:15Z
dc.date.issued 2018-12
dc.identifier.citation Sohége, Y. and Provan, G. (2018) 'On-line reinforcement learning for trajectory following with unknown faults', Proceedings of the 26th AIAI Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2018), Dublin, Ireland, 6-7 December, pp. 1-12. Available at: http://ceur-ws.org/Vol-2259/aics_27.pdf (Accessed: 28 January 2019) en
dc.identifier.startpage 1 en
dc.identifier.endpage 12 en
dc.identifier.issn 1613-0073
dc.identifier.uri http://hdl.handle.net/10468/7366
dc.description.abstract Reinforcement learning (RL) is a key method for providing robots with appropriate control algorithms. Controller blending is a technique for combining the control output of several controllers. In this article we use on-line RL to learn an optimal blending of controllers for novel faults. Since one cannot anticipate all possible fault states, which are exponential in the number of possible faults, we instead apply learning on the effects the faults have on the system. We use a quadcopter pathfollowing simulation in the presence of unknown rotor actuator faults for which the system has not been tuned. We empirically demonstrate the effectiveness of our novel on-line learning framework on a quadcopter trajectory following task with unknown faults, even after a small number of learning cycles. The authors are not aware of any other use of on-line RL for fault tolerant control under unknown faults. en
dc.format.mimetype application/pdf en
dc.language.iso en en
dc.publisher CEUR-WS.org en
dc.relation.ispartof 26th AIAI Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2018)
dc.relation.uri http://ceur-ws.org/Vol-2259/aics_27.pdf
dc.relation.uri http://ceur-ws.org/Vol-2259/
dc.rights © 2018, the Authors. Copying permitted for private and academic purposes. en
dc.subject Reinforcement learning en
dc.subject Fault-tolerant control en
dc.subject Quadcopter control en
dc.title On-line reinforcement learning for trajectory following with unknown faults en
dc.type Conference item en
dc.internal.authorcontactother Gregory Provan, Computer Science, University College Cork, Cork, Ireland. +353-21-490-3000 Email: g.provan@cs.ucc.ie en
dc.internal.availability Full text available en
dc.date.updated 2019-01-28T12:35:55Z
dc.description.version Published Version en
dc.internal.rssid 471472472
dc.description.status Peer reviewed en
dc.internal.copyrightchecked Yes en
dc.internal.licenseacceptance Yes en
dc.internal.conferencelocation Dublin, Ireland en
dc.internal.IRISemailaddress g.provan@cs.ucc.ie en


Files in this item

This item appears in the following Collection(s)

Show simple item record

This website uses cookies. By using this website, you consent to the use of cookies in accordance with the UCC Privacy and Cookies Statement. For more information about cookies and how you can disable them, visit our Privacy and Cookies statement