dc.contributor.author | CAHILL, VINNY | en |
dc.contributor.author | SALKHAM, AS'AD | en |
dc.date.accessioned | 2009-09-15T13:38:48Z | |
dc.date.available | 2009-09-15T13:38:48Z | |
dc.date.created | 9-12 Dec | en |
dc.date.issued | 2008 | en |
dc.date.submitted | 2008 | en |
dc.identifier.citation | As'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, 560-566 | en |
dc.identifier.other | Y | en |
dc.identifier.uri | http://hdl.handle.net/2262/32669 | |
dc.description | PUBLISHED | en |
dc.description | Sydney, NSW | en |
dc.description.abstract | The 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.sponsorship | The 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.extent | 560-566 | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | IEEE Computer Society | en |
dc.relation.ispartofseries | 2 | en |
dc.rights | Y | en |
dc.subject | Computer Science | en |
dc.title | A collaborative reinforcement learning approach to urban traffic control | en |
dc.title.alternative | Proceedings of the Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on | en |
dc.title.alternative | IEEE/WIC/ACM International Conference on Intelligent Agent Technology: IAT '08 | en |
dc.type | Conference Paper | en |
dc.type.supercollection | scholarly_publications | en |
dc.type.supercollection | refereed_publications | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/vjcahill | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/salkhama | en |
dc.identifier.rssinternalid | 61184 | en |