An Efficient and Scalable Vehicle Dispatching Technique for Ridesharing

Mr. Benjamin Lartey

Friday, October 27, 2023

On-demand ridesharing could provide effective, low-cost transportation services to passengers while increasing the profit made by transit companies. Most of the existing research suffers from the lack of balance between the overall system profit and the response time. The main focus of existing works in the literature is generally optimizing the profit and service rate (i.e., the number of passengers served) and neglecting response time. This talk presents a computationally efficient (i.e., improved response time), dynamic vehicle dispatch framework while also optimizing the overall system’s profit. Our approach considers assigning vehicles to ride requests in a one-to-one manner. This assignment strategy improves the efficiency of the proposed algorithm. Extensive experiments conducted using the New York City taxicab open-source data demonstrate that the proposed framework is up to ten times faster than the state-of-the-art method and achieves comparable profit. Moreover, the proposed approach proves to be scalable and efficient when a large number of vehicles and requests are considered.