Show simple item record

dc.contributor.authorCAHILL, VINNYen
dc.contributor.authorSALKHAM, AS'ADen
dc.date.accessioned2009-09-15T13:38:48Z
dc.date.available2009-09-15T13:38:48Z
dc.date.created9-12 Decen
dc.date.issued2008en
dc.date.submitted2008en
dc.identifier.citationAs'ad Salkham, Raymond Cunningham, Anurag Garg, and Vinny Cahill., A collaborative reinforcement learning approach to urban traffic control, Proceedings of the Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on, IEEE/WIC/ACM International Conference on Intelligent Agent Technology: IAT '08, Sydney, NSW, 9-12 Dec, 2, IEEE Computer Society, 2008, 560-566en
dc.identifier.otherYen
dc.identifier.urihttp://hdl.handle.net/2262/32669
dc.descriptionPUBLISHEDen
dc.descriptionSydney, NSWen
dc.description.abstractThe high growth rate of vehicles per capita now poses a real challenge to efficient Urban Traffic Control (UTC). An efficient solution to UTC must be adaptive in order to deal with the highly-dynamic nature of urban traffic. In the near future, global positioning systems and vehicle-tovehicle/ infrastructure communication may provide a more detailed local view of the traffic situation that could be employed for better global UTC optimization. In this paper we describe the design of a next-generation UTC system that exploits such local knowledge about a junction?s traffic in order to optimize traffic control. Global UTC optimization is achieved using a local Adaptive Round Robin (ARR) phase switching model optimized using Collaborative Reinforcement Learning (CRL). The design employs an ARR-CRL-based agent controller for each signalized junction that collaborates with neighbouring agents in order to learn appropriate phase timing based on the traffic pattern. We compare our approach to non-adaptive fixed-time UTC system and to a saturation balancing algorithm in a largescale simulation of traffic in Dublin?s inner city centre. We show that the ARR-CRL approach can provide significant improvement resulting in up to ~57% lower average waiting time per vehicle compared to the saturation balancing algorithm.en
dc.description.sponsorshipThe work described in this paper was partly supported by Science Foundation Ireland (as Investigator award 02/IN1/I250) and by the Irish Higher Education Authority Programme for Research in Third Level Institutions (as the Networked Embedded Systems Centre). The authors would like to thank Vinny Reynolds for his work on the UTC simulator and Mikhail Volkov for implementing the SAT-like algorithm.en
dc.format.extent560-566en
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherIEEE Computer Societyen
dc.relation.ispartofseries2en
dc.rightsYen
dc.subjectComputer Scienceen
dc.titleA collaborative reinforcement learning approach to urban traffic controlen
dc.title.alternativeProceedings of the Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference onen
dc.title.alternativeIEEE/WIC/ACM International Conference on Intelligent Agent Technology: IAT '08en
dc.typeConference Paperen
dc.type.supercollectionscholarly_publicationsen
dc.type.supercollectionrefereed_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/vjcahillen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/salkhamaen
dc.identifier.rssinternalid61184en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record