Autonomous mobility on demand (AMOD) systems, though still in their infancy, have very promising prospects in providing urban population with sustainable and safe personal mobility in the near future. Although numerous existing research addresses taxi dispatching problems using various methodologies including techniques in multi-agent systems, no real research has been performed that addresses methodologies on dispatching for a better user experience. Unlike conventional taxi dispatching systems where it is often difficult to coordinate because of human factors (e.g., the drivers may not follow the dispatcher’s instructions carefully) AMOD systems make it possible to implement a much higher level of autonomy through delicate, system-wide coordination. Moreover, it is challenging to achieve near instant availability using conventional approaches.
An agent-based simulation platform was implemented that integrated the EAT algorithm with six different scheduling strategies for dispatching autonomous vehicles. An empirical analysis was performed that compared both the average passenger waiting time and the trip success rate of the AMOD systems using the six different dispatching approaches with 2013 New York City Taxi Data.
Experimental results demonstrated that the algorithm significantly improved passengers’ experience by reducing the average passenger waiting time by up to 29.82 percent and increasing the trip success rate by up to 7.65 percent.
(Our website has many links to other organizations. While we offer these electronic linkages for your convenience in accessing transportation-related information, please be aware that when you exit our website, the privacy and accessibility policies stated on our website may not be the same as that on other websites.)