A Belief Propagation Approach to Traffic Prediction using Probe Vehicles

Cyril Furtlehner; Jean-Marc Lasgouttes; Arnaud de la Fortelle

A Belief Propagation Approach to Traffic Prediction using Probe Vehicles

Cyril Furtlehner ¹ Jean-Marc Lasgouttes ² Arnaud de la Fortelle ^{2, 3}

1 TANC - Algorithmic number theory for cryptology

Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]

2 IMARA - Informatique, Mathématiques et Automatique pour la Route Automatisée

Inria Paris-Rocquencourt

3 CAOR - Centre de Robotique

Abstract : This paper deals with real-time prediction of traffic conditions in a setting where the only available information is floating car data (FCD) sent by probe vehicles. Starting from the Ising model of statistical physics, we use a discretized space-time traffic description, on which we define and study an inference method based on the Belief Propagation (BP) algorithm. The idea is to encode into a graph the \emph{a priori} information derived from historical data (marginal probabilities of pairs of variables), and to use BP to estimate the actual state from the latest FCD. The behavior of the algorithm is illustrated by numerical studies on a simple simulated traffic network. The generalization to the superposition of many traffic patterns is discussed.

Keywords : belief propagation algorithm Bethe approximation traffic prediction intelligent traffic systems floating car data

Document type :

Conference papers

Domain :

Physics [physics] / Condensed Matter [cond-mat] / Statistical Mechanics [cond-mat.stat-mech]

Computer Science [cs] / Machine Learning [cs.LG]

Complete list of metadatas

Cited literature [18 references] Display Hide Download

https://hal.inria.fr/hal-00175627
Contributor : Cyril Furtlehner <>
Submitted on : Friday, September 28, 2007 - 7:01:28 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on : Friday, April 9, 2010 - 3:08:19 AM

BPitsc-final.pdf

Files produced by the author(s)

A Belief Propagation Approach to Traffic Prediction using Probe Vehicles

File

Identifiers

Collections

Citation

Export

Metrics

637

354

Contact

A Belief Propagation Approach to Traffic Prediction using Probe Vehicles

File

Identifiers

Collections

Citation

Export

Share

Metrics

637

354

Contact