Freeway Traffic State Estimation and Uncertainty Quantification based on Heterogeneous Data Sources: Stochastic Three Detector Approach

摘要

In this study, we focus on how to use multiple data sources, including loop detector counts, AVI Bluetoothtravel time readings and GPS location samples, to estimate microscopic traffic states on a homogeneousfreeway segment. A multinomial probit model and an innovative use of Clark’s approximation method wereintroduced to extend Newell’s method to solve a stochastic three-detector problem. The mean and variance6covariance estimates of cumulative flow counts on both ends of a traffic segment were used as probabilisticinputs for the estimation of cell-based flow and density inside the space-time boundary and the constructionof a series of linear measurement equations within a Kalman filtering estimation framework. We present aninformation-theoretic approach to quantify the value of heterogeneous traffic measurements for specific fixedsensor location plans and market penetration rates of Bluetooth or GPS flow car data.