부산대학교 도서관

In a one-way mobility-on-demand system or distributed transportation system, customer requests for rides are served by a fleet of agents, e.g., taxis or even autonomous vehicles. We present a simplified three-node network model of such a transportation system in an urban agglomeration. The agents in this model play a non-cooperative game as each one tries to maximize their individual expected profit. We compute Nash equilibria in this game for different customer load cases, specifically the light- and heavy-load cases, and compare the social cost of a system with selfish agents to that of a system with coordinated agents. In particular, we establish a lower bound for the price of anarchy as a function of the system parameters, including taxi fares. We investigate the required mechanism design in the form of the fare ratio for a downtown core node and a city outskirts node that minimizes the social cost caused by selfish agents. Furthermore, we show that this optimal fare ratio is required to bring the social cost for the selfish agents as close as possible to that of the coordinated fleet. The chosen level of abstraction for the network with only three nodes is not intended to accomplish completeness; rather, it provides elementary insights into why mobility-on-demand systems with selfish agents in many cities operate at a sub-optimal level of performance. This paper motivates the investigation of the value of coordination in more complex systems, as well as the study and implementation of coordinated one-way mobility-on-demand transportation systems.