Optimizing Ride-Passenger Matching for Autonomous Vehicles Facilitating Combined Bus Services

This study focuses on optimizing passenger–vehicle matching for shared autonomous vehicles (SAVs) in combined bus services, aiming to develop an integrated travel service model that facilitates seamless connections between buses and SAVs. A multi-objective SAV passenger–vehicle matching optimization model was constructed, considering the minimization of passenger travel cost, transfer waiting time, vehicle deadheading distance, and loaded distance. A hybrid optimization algorithm, integrating the multi-objective nondominated sorting genetic algorithm (NSGA-II) and the multi-objective particle swarm optimization (MOPSO) algorithm, was designed. By utilizing data such as passenger destinations and SAV locations, the proposed model and algorithms generate optimal transfer stations and passenger–vehicle matching schemes for SAV operations. A case study of SAVs facilitating combined bus services for Hohhot Bus Line 1 is presented. The results demonstrate that the proposed model achieves a passenger–vehicle matching success rate of 98.4%, an average passenger transfer time of 1.48 min, and an average reduction of 18.3% in travel cost, effectively implementing an integrated “bus + SAV” travel service model with seamless connections.