Adaptive vehicle navigation with en route stochastic traffic information

This paper develops an adaptive approach for vehicle navigation in a stochastic network with real-time en route traffic information. This stochastic and adaptive approach is formulated as a probabilistic dynamic programming problem and is solved through a backward recursive procedure. The formulation, as a modeling framework, is designed to be able to incorporate various sources of information and real-time traffic states to improve routing quality. In this paper, we prove that the approach outperforms deterministic instantaneous shortest paths in a statistical sense. We also analyze the algorithm's computational efficiency. The results from numerical examples are included to illustrate the performance of the adaptive routing policy that was generated by the formulation.