Innovations in Transportation: CAVs, Generative AI, and the Future of Transit

Dr. Raphael Stern, Dr. Michael Levin, Dr. Seongjin Choi, and Dr. Alireza Khani

Department of Civil, Environmental, and Geo-Engineering

University of Minnesota

Friday, April 25, 2025

Zoom Link: https://ncat.zoom.us/j/93351380649?pwd=4rk9pCDOYn2OoutMuy9ZxcPhEp1sue.1 (Registration not required)

In-person (For NCA&T attendees): Room 226, McNair Building

SYNOPSIS

Join us for a compelling speaker series featuring distinguished researchers from the University of Minnesota, who will present cutting-edge work spanning shared autonomous vehicles, generative AI applications, traffic flow modeling, transit trends, and accessibility-driven solutions. Their talks explore how data, intelligent systems, and new technologies are reshaping the future of transportation—both in urban and rural contexts.

Talk 1: Modeling and Control of Mixed-Autonomy Traffic Flow | Speaker: Dr. Raphael Stern
Dr. Stern investigates how partially and fully automated vehicles affect traffic flow and interact with human drivers. His work focuses on how automation features like adaptive cruise control can be used to improve system-wide traffic behavior and stability.

Talk 2: Maximum-throughput Dispatch of Shared Automated Vehicles | Speaker: Dr. Michael Levin
As shared autonomous vehicles begin to serve public mobility needs, a key challenge is how to optimally assign vehicles to waiting passengers. Dr. Levin introduces a novel Markov decision process formulation that accounts for uncertainty in future demand, and derives policies with provable performance guarantees.

Talk 3: Generative AI for Transportation Operations and Management | Speaker: Dr. Seongjin Choi
Dr. Choi explores how Generative AI models can learn from transportation data to simulate pedestrian and vehicle movement and generate demand patterns. He highlights the use of large language and vision-language models as planning and control modules for traffic systems and autonomous vehicles.

Talk 4: Transit Gaps, Ridership Trends, and Opportunities for Technological Solutions | Speaker: Dr. Alireza Khani
Dr. Khani presents an analysis of transit ridership trends in the wake of COVID-19 and explores emerging technologies like AMoD, MaaS, and freight-on-bus systems. He discusses how these solutions could address evolving service needs and support accessible, resilient transit networks.

ABOUT THE SPEAKERS

Dr. Seongjin Choi is an Assistant Professor in the Department of Civil, Environmental, and Geo- Engineering, University of Minnesota.

Dr. Choi develops machine learning and generative AI models for transportation and mobility data, aiming to enhance both individual travel experiences and system-level performance. Prior to joining UMN, he was a postdoctoral researcher at McGill University in Canada and at KAIST in South Korea. He received his B.S., M.S., and Ph.D. degrees in Civil and Environmental Engineering from KAIST. His recent work focuses on integrating large language and vision-language models into traffic simulation and control.

Dr. Alireza Khani, Associate Professor, Department of Civil, Environmental, and Geo- Engineering, University of Minnesota

Dr. Alireza Khani’s research advances multimodal transportation system modeling and the integration of emerging technologies such as shared mobility and electric vehicles. He has led projects on transit accessibility, equity, and policy, funded by the NSF, FTA, and multiple state and local agencies. He earned his Ph.D. in Transportation Engineering from the University of Arizona and was previously a postdoc at UT Austin. At UMN, he holds a joint affiliation with the Department of Industrial and Systems Engineering.

Dr. Michael W. Levin, Associate Professor, Department of Civil, Environmental, and Geo- Engineering, University of Minnesota

Dr. Michael Levin’s research focuses on traffic flow and network modeling for connected and autonomous vehicles (CAVs) and intelligent transportation systems. He earned his B.S. in Computer Science and Ph.D. in Civil Engineering from the University of Texas at Austin. He serves on TRB’s Network Modeling Committee and is an editorial board member for Transportation Research Part B. His work appears in top journals such as Transportation Science and IEEE Transactions on ITS.

Dr. Raphael Stern, Assistant Professor, Department of Civil, Environmental, and Geo- Engineering, University of Minnesota

Dr. Raphael Stern studies mixed-autonomy traffic flow and data-driven traffic control strategies. He earned his B.S., M.S., and Ph.D. degrees in Civil Engineering from the University of Illinois at Urbana-Champaign and conducted postdoctoral research at the Technical University of Munich. His work examines how automated vehicles can influence emergent traffic behavior and enhance flow efficiency. He has also been a visiting researcher at Vanderbilt University’s Institute for Software Integrated Systems.