Optimizing travel time of intelligent vehicles in any highway configuration

This paper presents a MILP (Mixed Integer Linear Programming) model to calculate and manage optimized trajectories of intelligent vehicles in a segment of highway. The objective is to reduce travel time for each vehicle while meeting velocity/acceleration constraints and avoiding collisions. The proposed model considers the main elements of a traffic system, such as topography of lanes, traffic rules and individual capacity of acceleration. It can deals with most traffic situations such as overtaking, obstacles, slopes, and speed reducers. The model uses centralized decision approach which guarantees optimal solution. Although the model cannot be used in a real time application due to high complexity, the optimal result provided can be used as a reference to evaluate the efficiency of other solutions. In this sense, a performance metric for microscopic traffic assessment is proposed. In order to provide a solution for a real time application, a heuristic algorithm is also proposed. Moreover, unlike previous approaches, we explain how individual priority can be respected when trajectories are computed. Several tests are carried out to validate both MILP model and the algorithm.