Zhijie Yi bio photo

Email

My CV

Github

Google Scholar

ResearchGate

Zhijie Yi (易至捷)

PhD Student in Intelligent Transportation
Hong Kong University of Science and Technology (Guangzhou) · Systems Hub
Human-Integrated Systems Lab

About

I am a PhD student in Intelligent Transportation at the Hong Kong University of Science and Technology (Guangzhou). My research brings together intelligent transportation, artificial intelligence, and human-computer interaction.

I study how machine learning and deep learning can model human states and driving behaviors from multimodal data, how drivers, passengers, and pedestrians interact with autonomous vehicles and their systems, and how large language models (LLMs), vision-language models (VLMs), and other multimodal foundation models can support driving agents. Across these topics, I combine empirical research in real-world traffic with computational modeling and AI methods.

Before my PhD, I completed a Master of Design at Beijing Normal University. My earlier experience in user experience and interaction design, including work with OPPO and WritingPal, informs my approach to designing and evaluating intelligent systems.

Research

  • Multimodal state and behavior modeling: Applying machine learning and deep learning to infer driver alertness, workload, and behavior from physiological, visual, vehicle, and contextual data.
  • Human–autonomous vehicle interaction: Studying how drivers, passengers, and pedestrians interact with autonomous vehicles and their systems, including trust, comfort, behavior, and communication.
  • Multimodal foundation models for driving agents: Exploring how LLMs, VLMs, and related multimodal models can combine human driving knowledge with visual and contextual information to support driving-agent perception, reasoning, and decision-making.

Publications

Six recent works · Scroll or swipe to browse

Preprint · 2026 Alertness-Related Differences in Car-Following Strategy among Truck Drivers Based on Naturalistic Driving Data
Under review · CSCW 2026 From Driver to Passenger: Understanding Evaluation Gaps in Driving Behaviour Delivery
Figure 1: Layout of the real-world pedestrian–autonomous vehicle experiment site
Proceedings of HFES · 2025 The Formation of Trust in Autonomous Vehicles after Interacting with Robotaxis on Public Roads
Figure 1: The SurrealDriver framework
IROS · 2024 SurrealDriver: Designing LLM-Powered Generative Driver Agent Framework Based on Human Drivers’ Driving-Thinking Data
HCII · 2024 Improving Knowledge Asymmetry in Group Discussions with Smart Assistants
Figure 2: Emotional design model for future smart products
Systems · 2023 · 11(7), 377 An Emotional Design Model for Future Smart Product Based on Grounded Theory

Education

  • PhD in Intelligent Transportation, Hong Kong University of Science and Technology (Guangzhou)
  • Master of Design, Beijing Normal University, 2025
  • Bachelor of Arts, Hengyang Normal University, 2019

Contact

I welcome conversations and collaborations on intelligent transportation, multimodal modeling, human-computer interaction, and multimodal AI for autonomous driving.

Email · CV · Google Scholar · GitHub