Optimal scheduling of autonomous vehicle arrivals at intelligent intersections via MILP

Abstract

We propose optimal scheduling of autonomous vehicle arrivals at intersections, eliminating the need for physical traffic signals. The proposed intersection control algorithm is assumed to have bi-directional communication links to approaching vehicles. After receiving subscription requests and status of approaching vehicles, the intersection control node calculates an arrival schedule that ensures safety while significantly reducing number of stops and intersection delays. The vehicle-intersection coordination problem is formulated as a Mixed-Integer Linear Program (MILP). A case study is presented and a customized traffic microsimulation environment is developed to demonstrate the effectiveness of the proposed intersection control scheme.