Urban network traffic state estimation using a data-based approach ?

摘要

In this paper we propose an estimator of vehicle density in every road section of a large urban traffic network. We assume a limited number of flow and turning ratio sensors can be installed, and that aggregate floating car data (FCD) is available, such that the space-mean speed of each road can be estimated. We propose a method to locate turning ratio sensors, which takes as input previous low-quality estimates of the turn rates, and then assigns to each intersection a weight according to the effect on the total density reconstruction error caused by perturbations between a priori and actual turning ratio values. We evaluate the models and estimator using data from the urban traffic network of Grenoble in France.