On-demand ridesharing based on dynamic scheduling in urban air mobility

Urban Air Mobility (UAM) utilizes electric vertical take-off and landing (eVTOL) aircraft to provide fast, reliable air transport services in cities and surrounding areas. As a flexible mode of transportation service, UAM ridesharing can provide convenient and adaptive multi-modal on-demand travel. In this scenario, multi-modal mobility-on-demand service providers can offer traditional door-to-door ridesharing with an integrated solution, through connecting users to eVTOL vertiports. We establish the integrated dynamic scheduling model for UAM ridesharing, and develop a cloud-edge collaborative multi-modal mobility-on-demand service architecture. This architecture integrates ordinary, multi-hop ridesharing and air-ground integrated mobility, offering flexible travel combinations tailored to user needs. We propose a multi-modal transportation dynamic scheduling algorithm based on this architecture to solve the problem. The solution process is divided into four stages: travel service plan planning, available resource search, dynamic cooperative multiple task assignment, and vehicle rebalancing. In the first two stages, an improved pulse algorithm is used to search for feasible service plans and filter available transport resources. In the dynamic cooperative multiple task assignment stages, we use a hybrid adaptive large neighborhood search algorithm to select travel plans, allocate transport resources, and plan vehicle routes. The graph structure of the task network is used in the algorithm to decouple the original problem, thereby effectively controlling the problem size. Finally, in the vehicle rebalancing stage, idle vehicles are repositioned based on demand distribution to improve supply–demand matching efficiency. Experiments based on New York City travel data indicate that compared to traditional ridesharing, our system can significantly improve the service rate and reduce user travel time. In the best-case scenario, the service rate increased by approximately 25%, while the average detour time decreased by around 52%. This demonstrates the possibility of enhancing convenience and attractiveness of UAM, which can also provide support and reference for the design and operation of future multi-modal transportation systems.