Date of Award:
12-2025
Document Type:
Thesis
Degree Name:
Master of Science (MS)
Department:
Computer Science
Committee Chair(s)
Vicki Allan
Committee
Vicki Allan
Committee
Vladimir Kulyukin
Committee
Curtis Dyreson
Abstract
We propose an approach to coordinate a robotaxi fleet for an autonomous ride-hail service. This is a service similar to a traditional ride-hailing service (Uber, Lyft), where customers request a ride and are then picked up in a car and dropped off in a new location; except, driverless vehicles called robotaxis are used to transport the customers.
Our approach teaches helpful coordination strategies to a robotaxi fleet while taking into account the individual battery level of the robotaxis. Each robotaxi acts as an individual agent in our simulation and can choose to pick up a rider, reposition to a new area, or charge. Consider a group of robotaxis that needs to decide which nearby rider would be most valuable for each vehicle to pick up. Our approach maximizes the benefit of the overall system rather than any individual robotaxi’s reward.
Charging autonomous robotaxis is often more difficult than charging standard electric vehicles (EVs), as they do not have drivers who can plug them in at publicly available EV chargers. Because of this, our work focuses on a scenario in which robotaxis must return to a central Operations Depot to charge. We incentivize robotaxis with a higher battery level to pick up riders and reposition farther away from the Operations Depot.
We develop a real-world simulation that utilizes data from the City of Chicago to simulate realistic timing for trip requests around the city. Our results show that using our learning strategies to coordinate robotaxi actions significantly increases the service rate and earning potential for an autonomous ride-hail service.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Thompson, Paden, "Multi-Agent Robotaxi Dispatch Coordination in a Real-World Simulation – Optimizing Rider Assignment, Rebalancing, and Charging Using Battery-Dependent Rewards and Welfare Maximization" (2025). All Graduate Theses and Dissertations, Fall 2023 to Present. 652.
https://digitalcommons.usu.edu/etd2023/652
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .