ICITE2025 Keynote Speakers
Prof. Francisco Camara Pereira
Head of Intelligent Transportation Systems, Transportation Science SectionTechnical University of Denmark, Denmark
Francisco Camara Pereira is Professor at DTU, where he leads the Intelligent Transport Systems group. His research is about the methodological combination of Machine Learning and Transport Research, to address challenges such as demand modeling, traffic prediction, data collection, simulation metamodeling, or anomaly detection. He has been Marie Curie fellow for two times (2011 and 2016) and is currently a Novo Nordisk Data Science Distinguished Investigator. He has published over 70 articles in both Machine Learning and Transport Research. Before joining DTU, he was Senior Research Scientist with SMART/MIT (2011-2015) and Assistant professor in the University of Coimbra (2005- 2015).
Speech Title: Scalability and Generalization of Transport Modeling and Simulation With AI
Abstract: Large-scale transport simulation models face the critical challenge of computational complexity. This complexity significantly hampers calibration and model exploration, such as scenario discovery, due to the extensive time required for each simulation run. Traditionally, two approaches have been employed to mitigate this issue: model simplification through spatial and/or temporal aggregation and scope reduction by focusing on specific segments of the transport network or population subsets. Alternatively, analytical or statistical model approximations, known as metamodels, have been utilized. Recently, Machine Learning (ML)-based metamodels have gained popularity for their potential to streamline simulations. However, these models often struggle with out-of-distribution scenarios, failing to accurately represent the original simulation under new conditions, such as policy interventions. This headline presentation will introduce recent advancements in causal metamodeling, an approach that integrates ML-based metamodeling with domain-specific knowledge to produce simulation approximations that not only remain true to the original model but also operate with significantly enhanced speed. Drawing on the recent and ongoing research, I will outline the foundational concepts, share preliminary findings, and explore the challenges and opportunities this research presents. Through causal metamodeling, we aim to significantly improve the scalability and generalization capabilities of simulation models, opening new avenues for comprehensive and efficient scenario analysis and policy advisory.
Prof. Xiaobo Qu | 曲小波教授
欧洲科学院院士(Member, Academia Europaea-The Academy of Europe)Editor-in-Chief of Communications in Transportation Research
Tsinghua University, China | 清华大学
Xiaobo Qu is a Chair Professor with Tsinghua University, and an elected Member of the Academy of Europe. His research is focused on intelligent transportation systems, ground-air cooperation and vertical transportation systems, and emerging transport mode informed mobility services. He is the editor in chief of Communications in Transportation Research, the highest ranked journal in the category of transportation. He has been invited to serve as a panel/assessor for Australian Research Council grants including Centre of Excellence, Hong Kong Research Council, Singapore Ministry of Education Thematic Research Program, European Research Council, NSFC, Ministry of Education China etc.Since 2023, he serves as a board member of PICC group.
Speech Title: Future Public Transit: Autonomy and Verticalization
Abstract: As global urbanization rapidly advances, the management of traffic congestion in large cities has become an urgent challenge. However, urban transportation infrastructure (such as roads, buses, subways, etc.) lacks capacity elasticity and is unable to rapidly adapt to the dynamic fluctuations in travel demand, leading to phenomena such as congestion during peak hours and underutilization during off-peak hours. The intelligent connected vehicle-road-cloud system presents a potential solution to the supply-demand imbalance in transportation systems. Through the deep integration and collaboration among intelligent vehicles, road infrastructure, and cloud platforms, the system can effectively enhance the capacity elasticity, thereby optimizing traffic flow and mitigating congestion. As a typical application scenario of the vehicle-road-cloud system, the demand-responsive micro-transit provides a flexible travel service that bridges the gap between regular buses and ride-hailing cars through intelligent scheduling algorithms. Flying cars represent the ultimate solution to traffic system problems, capable of detaching from the reliance on infrastructure.
Prof. Hai Yang | 杨海教授
Chair Professor, Department of Civil and Environmental EngineeringThe Hong Kong University of Science and Technology, Hong Kong, China | 香港科技大学
Prof. Hai Yang is a Chair Professor at The Hong Kong University of Science and Technology, where he is recognized as a leading expert in transportation research. His work has been published in top-tier international journals, including Transportation Research, Transportation Science, and Operations Research, earning him a high ranking in both publications and citations within the transportation field. Throughout his career, Prof. Yang has received numerous prestigious awards, such as the 2020 Frank M. Masters Transportation Engineering Award and the 2021 Francis C. Turner Award from the American Society of Civil Engineers. In addition, he was honored with the National Natural Science Award by the State Council of the People's Republic of China in 2011. Prof. Yang was appointed as a Chang Jiang Chair Professor by the Ministry of Education of China and served as the Editor-in-Chief of Transportation Research (TR) Part B: Methodological from 2013 to 2018, a highly regarded journal in transportation studies. Currently, he is a member of the Distinguished Editorial Board for TR Part B and the Scientific Council for TR Part C: Emerging Technologies, and he also serves as an Advisory Editor for Transportation Science.
Speech Title: How AVs Grow Up: The Three Stages from Rule-Following Robots to Social Partners
Abstract: This presentation explores AVs' evolution toward social integration through human-like driving, vital for mixed traffic with human drivers. It defines human-like driving as understanding social behaviors, not just rules, contrasting issues from robotic driving (jerky moves, rigid compliance) that harm safety/efficiency. Three stages are outlined: socially perceptive AVs (current, recognizing signals but passive), compatible ones (5–10 years, data-learned human behaviors via V2X), and sensitive AVs (long-term, human-like cognition, ethical decisions). It distinguishes technical (SAE L0–L5, functional automation) and social classifications (social intelligence). Leveraging human-plausible cognitive encoding enhances safety/fairness. Future work includes ethical frameworks and global standards, advancing human-AI symbiosis in smart cities.