Advanced search
1 file | 1.34 MB

Distributed particle filter for urban traffic networks using a platoon based model

Nicolae-Emanuel Marinica (UGent) , Alain Sarlette (UGent) and René Boel (UGent)
Author
Organization
Project
Interuniversity Attraction Poles Programme DYSCO
Project
EUFP7 under Project CON4COORD
Abstract
Raw measurement data are too noisy to directly obtain queue and traffic flow estimates usable for feedback control of urban traffic. In this paper, we propose a recursive filter to estimate traffic state by combining the real-time measurements with a reduced model of expected traffic behavior. The latter is based on platoons rather than individual vehicles in order to achieve faster implementations. This new model is used as a predictor for real-time traffic estimation using the particle filtering framework. As it becomes infeasible to let a truly large traffic network be managed by one central computer, with which all the local units would have to communicate, we also propose a distributed version of the particle filter (PF) where the local estimators exchange information on flows at their common boundaries. We assess the quality of our platoon-based PFs, both centralized and distributed, by comparing their queue-size estimates with the true queue sizes in simulated data.
Keywords
hybrid systems, Bayesian estimation, parallel particle filters (PFs), stochastic systems, urban traffic networks

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.34 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Marinica, Nicolae-Emanuel, Alain Sarlette, and René Boel. 2013. “Distributed Particle Filter for Urban Traffic Networks Using a Platoon Based Model.” Ieee Transactions on Intelligent Transportation Systems 14 (4): 1918–1929.
APA
Marinica, N.-E., Sarlette, A., & Boel, R. (2013). Distributed particle filter for urban traffic networks using a platoon based model. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 14(4), 1918–1929.
Vancouver
1.
Marinica N-E, Sarlette A, Boel R. Distributed particle filter for urban traffic networks using a platoon based model. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. 2013;14(4):1918–29.
MLA
Marinica, Nicolae-Emanuel, Alain Sarlette, and René Boel. “Distributed Particle Filter for Urban Traffic Networks Using a Platoon Based Model.” IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 14.4 (2013): 1918–1929. Print.
@article{4292929,
  abstract     = {Raw measurement data are too noisy to directly obtain queue and traffic flow estimates usable for feedback control of urban traffic. In this paper, we propose a recursive filter to estimate traffic state by combining the real-time measurements with a reduced model of expected traffic behavior. The latter is based on platoons rather than individual vehicles in order to achieve faster implementations. This new model is used as a predictor for real-time traffic estimation using the particle filtering framework. As it becomes infeasible to let a truly large traffic network be managed by one central computer, with which all the local units would have to communicate, we also propose a distributed version of the particle filter (PF) where the local estimators exchange information on flows at their common boundaries. We assess the quality of our platoon-based PFs, both centralized and distributed, by comparing their queue-size estimates with the true queue sizes in simulated data.},
  author       = {Marinica, Nicolae-Emanuel and Sarlette, Alain and Boel, Ren{\'e}},
  issn         = {1524-9050},
  journal      = {IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS},
  keyword      = {hybrid systems,Bayesian estimation,parallel particle filters (PFs),stochastic systems,urban traffic networks},
  language     = {eng},
  number       = {4},
  pages        = {1918--1929},
  title        = {Distributed particle filter for urban traffic networks using a platoon based model},
  url          = {http://dx.doi.org/10.1109/TITS.2013.2271326},
  volume       = {14},
  year         = {2013},
}

Altmetric
View in Altmetric
Web of Science
Times cited: