CEE Seminar: Pricing and Control in Emerging Mobility Systems

Abstract: Transportation systems are increasingly shaped by algorithms that influence both user behavior and system operations. This talk presents two studies on how algorithm design affects system-level in large-scale transportation networks. The first study develops a game-theoretic framework for High-Occupancy Toll (HOT) lane design, characterizing equilibrium regimes under heterogeneous travelers and quantifying how pricing and capacity choices affect congestion, welfare and carpooling incentives using California data. The second study develops a novel and scalable reinforcement learning algorithm for coordinated dispatch and charging of electric robo-taxi fleets. Together, these works illustrate how rigorous equilibrium modeling and scalable learning-based control can inform the design and operations of next-generation mobility systems.

Bio: Manxi Wu is an assistant professor in the Department of Civil and Environmental Engineering at UC Berkeley. Her research interests include game theory, multi-agent learning and market design with applications in urban systems. Previously, she was an assistant professor in the school of Operations Research and Information Engineering at Cornell University. Wu received the B.S. degree in applied mathematics from Peking University in 2015, and the Ph.D. degree in Social and Engineering Systems from MIT in 2021.