3/3/26: LLM-Powered Digital Twins for Interactive Urban Mobility Simulation

Описание: Urban mobility simulation platforms are widely used in transportation research but remain technically demanding for non-experts and disconnected from modern AI capabilities. This work presents an LLM-powered, web-based transportation digital twin that enables natural language interaction, dynamic scenario editing, and AI-assisted decision support. The framework allows users to conversationally specify simulation tasks, which are translated by an LLM agent into SUMO configuration and TraCI commands. This project demonstrates the system using Austin, TX as a case study, showcasing how LLM-augmented digital twins can support planners, policymakers, and researchers in testing interventions, evaluating resilience, and exploring sustainable mobility strategies.

Speaker: Yiming Xu, Postdoctoral Fellow, School of Architecture, UT Austin
Yiming Xu is a Postdoctoral Fellow in the School of Architecture at the University of Texas at Austin. He received his B.E. and M.E. degrees in transportation engineering from Tongji University, China in 2016 and 2019, and his Ph.D. in civil engineering from the University of Florida in 2023. His work focuses on developing and applying machine learning methods to tackle challenges in transportation systems. He specializes in trustworthy machine learning and deep learning applications in travel behavior analysis and time series modeling to support urban mobility management and operation.

Website: https://sites.utexas.edu/uil/yiming-xu/