This project aims to improve the efficiency of mobility-on-demand services with the help of machine learning. The goal is to create an algorithm that public paratransit services, private rideshare companies, and future autonomous vehicle fleets could use to improve operations and lower costs.
In previous years, the research team has developed and calibrated a base model implemented in MATSim and SUMO. This virtual testbed simulates an 8-million-person population and includes cars, trains, bus, bikeshare, taxi, and other for-hire vehicles calibrated to the year 2016. The team is building the architecture to host this virtual test bed and developing system design and user guide documentation.