Human Mobility & Generative Modeling
Modeling how people travel, coordinate activities, and interact with urban environments. This work combines generative models, mobility data fusion, and semantic trajectory analysis.
Xishun Liao
Assistant Professor
Civil, Environmental, and Construction Engineering
University of Central Florida
My research integrates urban geospatial intelligence, human behavior, and artificial intelligence to model human mobility and develop digital twins for intelligent transportation and autonomous mobility. I study generative models of human activity and travel demand, mobility AI agents and networks, and personalized driving behavior. At UCF, I am affiliated with the Knights Digital Twin Initiative and the Center for Integrated Coastal Research.
I received my Ph.D. in Electrical and Computer Engineering from UC Riverside in 2023, advised by Matthew Barth and Guoyuan Wu. Before joining UCF, I was a Postdoctoral Scholar and Assistant Project Scientist at UCLA, working with Jiaqi Ma. I serve as an Associate Editor of the IEEE Open Journal of Intelligent Transportation Systems.
News
Co-organizing UrbanState: Multimodal Urban Sensing and Representation for Autonomous Mobility at WACV 2027. Website · Call for Papers.
Co-organizing WAM-AD: World Action Models for Autonomous Driving at WACV 2027. Website · Call for Papers.
Deep Activity Model published in IEEE Transactions on Intelligent Transportation Systems.
Serving as an Associate Editor of the IEEE Open Journal of Intelligent Transportation Systems.
Joined the University of Central Florida as an Assistant Professor.
Two recognitions at IEEE ITSC: Best Paper Honorable Mention and Best Student Paper Honorable Mention.
Semantic Trajectory Data Mining received the Best Paper Award at IEEE ITSC 2024.
Research
All projectsHuman-Centered Driving & Intelligent Vehicles
Understanding individual driving behavior to inform vehicle prediction and assistance. This work connects driver digital twins, personalized lane-change prediction, and driving profile modeling.
Transportation Digital Twins & Simulation
Connecting traffic networks, vehicles, and human behavior through data and simulation. This work includes traffic impact prediction, cooperative driving, and human-in-the-loop platforms.
Selected Publications
Full publication listDeep Activity Model: A Generative Approach for Human Mobility Pattern Synthesis
IEEE Transactions on Intelligent Transportation Systems, vol. 27, no. 6, pp. 6519-6536, June 2026.
Learning Universal Human Mobility Patterns with a Foundation Model for Cross-Domain Data Fusion
Transportation Research Part C: Emerging Technologies, vol. 180, article 105311, 2025.
Driver Digital Twin for Online Prediction of Personalized Lane Change Behavior
IEEE Internet of Things Journal, vol. 10, no. 15, pp. 13235-13246, August 2023.
Mobility AI Agents and Networks
IEEE Transactions on Intelligent Vehicles, vol. 9, no. 7, pp. 5124-5129, July 2024.