The rapid developing highly automated vehicles (HAVs) are evolving into core driving agents that collaborate with humans—both inside and outside the vehicle—shaping a cooperative interaction mode for the future transport systems. This paradigm shift is redefining the nature of autonomous driving tasks which increasingly rely on intelligent collaboration between humans and AI systems. Consequently, the traditional Human-Machine Interface (HMI 1.0), which has primarily focused on fast and unidirectional information delivery, is no longer sufficient to support the complexity of future mobility. Instead, there is a growing need for a new generation of Human-Machine Intelligent interface (HMI 2.0), characterized by proactive and context-aware information processing that aims to enhance overall performance through human-AI collaboration.
As the role of HMI/eHMIs evolves from a dashboard messenger to an orchestra conductor, its responsibilities extend beyond simply displaying vehicle and traffic conditions or offering an array of control switches. The next-generation HMI—HMI 2.0—targets three critical objectives: (1) recognizing HAVs as socially capable driving agents, (2) enabling rich, bi-directional interactions between humans and AI, and (3) supporting personalized, adaptive behaviors validated through real-world performance metrics. This workshop aims to provide a unique international platform for researchers, policymakers, and industry practitioners to explore and advance the design, modeling, and evaluation of HMI 2.0 in intelligent transport systems. Key topics include:
Showcasing innovative HMI/eHMI modes and designing frameworks;
Presenting SOTA models for modelling interactions in safety evaluation, decision-making, and traffic control;
Developing validation approaches of HMI/eHMI modes leveraging cutting-edge technologies such as VR/AR/MR and other HIL platforms;
Facilitating knowledge exchange and resource sharing among leading research groups, institutions, and industry partners working on related topics.
Cross-disciplinary research is highly encouraged in this workshop, allowing participants to communicate with researchers using diverse equipment and techniques and thinking from different perspectives. The initiative is to promote resources and technology sharing across multiple disciplines, disseminate valuable research among fields, and establish unified standards over research groups. Moreover, platforms, datasets, and related technology developments discussed in this workshop will be integrated into a GitHub repository for summarizing the outcomes.
Next-generation external/internal human-machine interface design
Bi-directional communication between humans and HAVs
Cooperative Scenario Generation for Human-HAV Interaction
Integrating eHMI design with safety-critical decision-making for VRUs
Evaluation through VR/AR/MR and Human-in-Loop (HIL) platforms for testing
How is the role of HMIs changing in highly automated vehicles?
What are the limitations of traditional HMI, and how does HMI 2.0 address them?
Leveraging VR/AR/MR and HIL platforms to validate HMI designs.
Bridging the gap between lab-based studies and real-world deployment.
Surfers Paradise 1, The Star Grand, PO Box 1515, Broadbeach, Australia 4218
November 18, 2025
Dr. Haoyang Liang, Tongji University
Understanding Human-Vehicle Interaction for Safe AV Deployment: A Conflict-Based Perspective
Prof. Tarek Sayed, University of British Columbia
13:40 — 14:10
Motion As a Language to Support Cooperation / Experimental Paradigms And Results
Prof. Klaus Bengler, Technische Universität München
14:10 — 14:40
(Online) Generation of Critical Pedestrian Scenarios for Autonomous Vehicle Testing
Prof. Shuo Feng, Tsinghua University
14:40 — 15:10
Presentation of OnSite Open Natural Driving Intelligence Automotive Simulation Test Challenge
15:10 — 15:30
(Online) The Role of LLMs in Traffic Management, from the Usability to Trustworthiness
Dr. Longchao Da, Arizona State University
16:00 — 16:20
(Online) Empowering Smart City Motion Sensing: An Online Continual Learning Perspective
Dr. Zirui Li, Nanyang Technological University
16:20 — 16:40
Every Scene All at Once: Exhaustive Multi-Agent Interaction Generation with Controlled Diffusion Model
Miss. Xiyan Jiang, Tongji University
16:40 — 17:00
Prof. Tarek Sayed, Prof. Klaus Bengler, Prof. Shuo Feng, Dr. Xiaolin He, Dr. Haoyang Liang, Dr. Xiaocong Zhao, Dr. Shaocheng Jia, Mr. Gabriel Lanzaro
Dr. Xiaocong Zhao, Tongji University
University of British Columbia gabriellanzaro@gmail.com
Delft University of Technology
X.He-2@tudelft.nl
Dr. Haoyang LIANG, Tongji University, lianghy@connect.hku.hk
Haoyang Liang is currently a Postdoc at Tongji University and a member of IEEE. He received his B.S. degree from the Department of Civil Engineering, Tsinghua University, and the Ph.D. degree from the University of Hong Kong, in 2018 and 2022, respectively. His research interests include crowd dynamics, pedestrian-vehicle interaction, virtual reality, and human factors. Haoyang has contributed to prestigious journals and conferences such as TR-Part B, PLoS ONE, and the International Symposium on Transportation and Traffic Theory (ISTTT). Currently, he is the principle investigator at Tongji University's CAVE VR lab, focusing on digital twin platforms for mixed traffic simulation and testing.
Dr. Xiaocong ZHAO, Tongji University, zhaoxc@tongji.edu.cn
Xiaocong Zhao is a Postdoc at the College of Transportation Engineering, Tongji University, China. From November 2022 to December 2023, he was a visiting researcher at Technische Universität Dresden, Germany. His primary research interests include computational cognitive behaviors modeling, decision-making in driving interaction, and social behaviour analysis. Xiaocong led the champion group in the 2022 Commonroad Motion Planning Competition for Autonomous Vehicles. He has contributed to notable journals such as IEEE T-ITS, TR-Part C, CACAIE, and AA&P. Since 2021, he has been a regular attendee and contributor at IEEE conferences, including the ITSC and IV, participating in seminars and workshops. Xiaocong has served as a reviewer for TR-Part C, IEEE T-ITS, T-VT, ITSC, and IV. He is currently the working group leader of an IEEE Intelligent Transportation Systems Society (ITSS) New Initiative Project.
Dr. Shaocheng JIA, National University of Singapore, The University of Hong Kong, shaochengjia@nus.edu.sg
Dr. Shaocheng Jia is currently a Research Fellow at National University of Singapore, and a member of IEEE, IEEE ITSS, INFORMS, INFORMS TSL, CHTS, IACIP, and ITS of HKU. He received his B.Eng. degree from the Department of Electronic Information Engineering, China University of Petroleum (Beijing), M.Eng. degree from the Department of Automation, Tsinghua University, and Ph.D. degree from the Department of Civil Engineering, The University of Hong Kong, in 2018, 2021, and 2025, respectively. His research interests include connected and automated transportation, intelligent perception and control, stochastic modeling and optimization, and artificial intelligence. Dr. Jia has published more than 20 papers in prestigious journals and conferences, including Transportation Science, TR-Part B, TR-Part C, IEEE TITS, ISTTT, IEEE ITSC, etc., and 6 national invention patents. He is a recipient of the Outstanding Master’s Dissertation Awards from CHTS and Tsinghua University. He has also actively participated in various professional events by serving as session chairs, workshop organizers, and reviewers for dozens of journals and conferences.
Prof. Jian SUN, Tongji University, sunjian@tongji.edu.cn
Sun Jian received the Ph.D. degree from Tongji University in 2006. Subsequently, he was at Tongji University as a Lecturer, and then promoted to the position as Professor in 2011, where he is currently a Professor with the College of Transportation Engineering and the Dean of the Department of Traffic Engineering. His main research interests include traffic flow theory, traffic simulation, connected vehicle-infrastructure system, and intelligent transportation systems. Sun Jian has published over 150 peer-reviewed articles, authored three monographs, and co-edited three provincial and ministerial standards. Additionally, he has filed more than 30 national invention patents and secured 6 software copyrights. He also contributes as the Associate Editor for the IET Intelligent Transportation Systems and the Journal of Intelligent and Connected Vehicles.
Prof. Tarek Sayed, University of British Columbia
Tarek Sayed is currently a Professor in the Department of Civil Engineering at the University of British Columbia (UBC), Canada, where he also holds the Tier 1 Canada Research Chair in Transportation Safety and Advanced Mobility. He received his Ph.D. in Civil Engineering from UBC and is a Fellow of the Canadian Academy of Engineering, the Engineering Institute of Canada, and the Canadian Society for Civil Engineering. His research interests include traffic safety, intelligent transportation systems, and data-driven safety analysis. Tarek has pioneered the use of automated video-based methods for real-time safety evaluation, with applications adopted by transportation agencies across North America and internationally. He has authored over 350 peer-reviewed articles in top-tier journals such as TR-Part C, Safety Science, and Accident Analysis and Prevention, and regularly contributes to conferences including TRB and WCTR.
Prof. Shuo Feng, Tsinghua University
Shuo Feng received the bachelor’s and Ph.D. degrees from the Department of Automation, Tsinghua University, China, in 2014 and 2019, respectively. He was a Post-Doctoral Research Fellow with the Department of Civil and Environmental Engineering and also an Assistant Research Scientist with the University of Michigan Transportation Research Institute (UMTRI), University of Michigan, Ann Arbor. He is currently an Associate Professor with the Department of Automation, Tsinghua University. His research interests include the development and validation of safety-critical machine learning, particularly for connected and automated vehicles. He was a recipient of the Best Ph.D. Dissertation Award from the IEEE Intelligent Transportation Systems Society in 2020, the ITS Best Paper Award from the INFORMS TSL society in 2021, MIT TR35 China, and DAMO Academy Young Fellow. He is an Associate Editor of IEEE TRANSACTIONS ON INTELLIGENT VEHICLES and an Academic Editor of the Automotive Innovation.
Prof. Klaus Bengler, Technische Universität München
Klaus Bengler graduated in psychology at the University of Regensburg in 1991 and received his Doctorate in 1994 in cooperation with BMW. After his diploma he was active on topics of software ergonomics and evaluation of human-machine interfaces. He investigated the influence of additional tasks on driving performance in several studies within EMMIS EU project and in contract with BMW. Multifunctional steering wheels, touchscreens and ACC-functionality are examples for the topics of these investigations.
In 1997 he joined BMW. From several projects he is experienced with experimental knowledge and experience with different kind of driving simulators and field trials. Within BMW Research and Technology he was responsible for projects on HMI research.
He was active as a coordinator for Subproject 2 “Evaluation und Methodology” within the EU funded integrated project AIDE. He is active member of ISO TC22 SC13 WG8 „Road vehicles - Ergonomic aspects of transport information and control systems“.
Since May 2009 he is leader of the Institute of Ergonomics at Technical University Munich which is active in research areas like digital human modeling, human robot cooperation, driver assistance, automated driving and human reliability. Among intensive industrial cooperation the Institute is engaged in the funded Projects INSAA on Digital Human Modeling and ECOMOVE, H-MODE and D3COS on automated driving. Further research focused on driver vehicle interaction in @city, Stadt:up and an evaluation of L2 driving automation systems in cooperation with RWTH Aachen. In UNICARagil the chair was responsible for anthropometric requirements of autonomous vehicles, their interaction and communication with other road users. The integration of driver models as cognitive digital twins into microsimulations of traffic is the topic in i4Driving (EU) and MIROVA (DFG).
National Natural Science Foundation of China
China Postdoctoral Science Foundation
Onsite Committee