Predicting and Optimizing City-Scale Road Traffic Dynamics Using Trajectories of Individual Vehicles

Abstract

Internet of Things and mobile crowdsensing provide an unprecedented opportunity to collect big data that continuously track the dynamics of large populations. One very important application is to leverage these massive, noisy, and partially observed traffic data to recover road network dynamics and to improve travel efficiency for everyone on the road; however, this process is complicated by high-dimensional and non-linear system dynamics, as well as incomplete information. In this paper we propose a versatile framework for integrating simulation modeling and machine learning in the transportation domain. Our generative approach is related to the stochastic prediction of traffic dynamics in real time using particle filters and simulation. To cope with incomplete information, we use particle filter to empirically estimate the posterior distribution of road network dynamics, and use the particles to improve driving strategies. This integration leads to better accuracy in tracking and predicting vehicle dynamics, and higher future expected return as driving strategies improve.