Simulation-based design and analysis of on-demand mobility services

On-demand mobility services - autonomous as well as human-driven - promise to transform transportation and urban living. Yet, designing such services involves an array of challenges: from demand data acquisition and processing, to building a versatile simulation framework, to finally evaluating a variety of service configurations and making recommendations. This article illustrates the process of designing and analyzing various types of on-demand mobility services using the City of Chicago, Illinois, as a test case. We start by surveying and categorizing a large number of articles on simulation-based design of on-demand mobility services. This is followed by an extensive experimental study, which analyzes how different service designs perform under real transportation demand patterns in terms of key performance indicators such as demand acceptance rate, excess ride time, deviation from the desired pickup time, vehicle occupancy, and various fleet efficiency metrics. This type of analysis helps mobility service providers and public transit authorities gain insights into the interplay of the different passenger-and fleet-related key performance indicators. Finally, we introduce the fundamental ridesharing diagram, which quantifies the relationship between passenger convenience and fleet efficiency, and helps identify socially optimal service designs.