Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Dynamic Lane Reversal in Traffic Management

Matthew Hausknecht, Tsz-Chiu Au, Peter Stone, David Fajardo, and Travis Waller. Dynamic Lane Reversal in Traffic Management. In Proceedings of IEEE Intelligent Transportation Systems Conference (ITSC), 2011.

Download

[PDF]127.0kB  [postscript]4.3MB  

Abstract

Contraflow lane reversal---the reversal of lanes in order totemporarily increase the capacity of congested roads---can effectivelymitigate traffic congestion during rush hour and emergencyevacuation. However, contraflow lane reversal deployed in severalcities are designed for specific traffic patterns at specific hours,and do not adapt to fluctuations in actual traffic. Motivated byrecent advances in autonomous vehicle technology, we propose aframework for dynamic lane reversal in which the lanedirectionality is updated quickly and automatically in response toinstantaneous traffic conditions recorded by traffic sensors. Weanalyze the conditions under which dynamic lane reversal is effectiveand propose an integer linear programming formulation and a bi-levelprogramming formulation to compute the optimal lane reversalconfiguration that maximizes the traffic flow. In our experiments,active contraflow increases network efficiency by 72\%.

BibTeX Entry

@InProceedings{ITSC11-hausknecht,
  author    = "Matthew Hausknecht and Tsz-Chiu Au and Peter Stone and David Fajardo and Travis Waller",
  title     = "Dynamic Lane Reversal in Traffic Management",
  booktitle = "Proceedings of IEEE Intelligent Transportation Systems Conference (ITSC)",
  year      = "2011",
  abstract = {
Contraflow lane reversal---the reversal of lanes in order to
temporarily increase the capacity of congested roads---can effectively
mitigate traffic congestion during rush hour and emergency
evacuation. However, contraflow lane reversal deployed in several
cities are designed for specific traffic patterns at specific hours,
and do not adapt to fluctuations in actual traffic. Motivated by
recent advances in autonomous vehicle technology, we propose a
framework for \emph{dynamic} lane reversal in which the lane
directionality is updated quickly and automatically in response to
instantaneous traffic conditions recorded by traffic sensors. We
analyze the conditions under which dynamic lane reversal is effective
and propose an integer linear programming formulation and a bi-level
programming formulation to compute the optimal lane reversal
configuration that maximizes the traffic flow. In our experiments,
active contraflow increases network efficiency by 72\%.
},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Sep 24, 2014 22:15:11