A Cooperative Algorithm for Lane Sorting of Autonomous Vehicles

In this paper, we propose a generalized algorithm that converts traffic composed of vehicles located randomly in a set of lanes into sorted traffic in which vehicles are moved into the lane corresponding to their destination group. Focus is placed on the cooperative behavior of vehicles. The proposed algorithm architecture divides the entire scenario into various independent sections (called frames) that can be processed in parallel at the same time. Processing each frame involves solving an optimization procedure of a nonlinear programming problem reducible to a linear programming problem. The performance of the proposed algorithm is tested using the Simulation of Urban MObility (SUMO) simulator. Results are obtained and presented for average sorting distance required for sorting all vehicles in the scenario for different traffic settings.