On-demand ridesharing is a promising avenue to transform urban mobility by providing effective, low-cost transportation services to passengers in real-time, while increasing the profit made by transit companies. Most existing works suffer from the lack of balance between the overall system profit and the response time. The main focus is generally on optimizing
the profit and service rate (i.e., number of passengers served) to the neglect of response time. Therefore, in this work, we propose 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 on the New York City taxicab open-source data demonstrates 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 proved to be scalable and efficient when a large number of vehicles and requests are considered.
Benjamin Lartey received the BSc. Degree in Electrical and Electronics Engineering from Kwame Nkrumah University of Science and Technology, Kumasi, Ghana in 2018. He is currently pursuing the PhD. Degree in Electrical Engineering at North Carolina A&T State University, NC, USA. His research interests include machine learning, mathematical optimization, and mobility on demand systems.