Travel time estimation on urban networks from traffic data and on-board trip characteristics
EL FAOUZI ; LESORT
Type de document
CHAPITRE D'OUVRAGE (CO)
Langue
anglais
Auteur
EL FAOUZI ; LESORT
Résumé / Abstract
The need for reliable travel time estimation models has become essential for the ongoing research into both advanced traveller information systems (atis) and in-vehicle dynamic route guidance systems (drgs) areas. Accurate travel time estimations are therefore an important issue for better efficiency of path determination algorithms and for on line atis, which are intended to give realistic travel-time estimates to road-users. We present in this paper a modelling framework for travel time estimation in the presence of data from different sources : - informations based on ground sensor data, - on-board travel time measurements and trip characteristics (stop time, number of stops, average time speed) from instrumented vehicles. The key-point of this work is how to combine this different data from various sources, which have different scales, different accuracies, issued from different experimental designs in order to improve travel time estimation. This problem is known as the data fusion process. We have considered statistical techniques to achieve this objective. Some travel time estimators from data listed herein are proposed.
