About me
Jiawei Wang is a postdoctoral researcher in the Center for Spatial Information Science, The University of Tokyo. He received a Ph.D. in Civil Engineering (Transportation) from McGill University, supervised by Prof. Lijun Sun. His research connects machine learning with large-scale urban mobility systems, with a particular interest in creating deployable tools for cities and transit agencies.
Research Focus
- Data- and AI-driven modeling of network-level traffic states
- Reinforcement learning for intelligent transit and mobility operations
- Behavior modeling of emerging multimodal and electrified fleets
Data- and AI-driven Traffic Analysis
I develop interpretable learning pipelines that couple domain knowledge with deep neural architectures to provide reliable forecasts for complex transportation networks.
- Traffic speed prediction for urban transportation network: A path-based deep learning approach. Transportation Research Part C, 2019.
- Understanding the daily operations of electric taxis: From macro-patterns to micro-behaviors. Transportation Research Part D, 2024.
Reinforcement Learning for Transit and Mobility Operations
My work explores multi-agent reinforcement learning to coordinate fleets and optimize control policies under uncertainty, bridging algorithm design and operational constraints.
- Multi-agent graph reinforcement learning for connected automated driving. ICML AI for Autonomous Driving Workshop, 2020.
- MERCI: Multi-agent reinforcement learning for enhancing on-demand electric taxi operations. Computers & Industrial Engineering, 2024.
- Dynamic holding control to avoid bus bunching: A multi-agent deep reinforcement learning framework. Transportation Research Part C, 2020.
- Reducing bus bunching with asynchronous multi-agent reinforcement learning. IJCAI, 2021.
- Robust dynamic bus control: A distributional multi-agent reinforcement learning approach. IEEE Transactions on Intelligent Transportation Systems, 2022.
- Multi-objective multi-agent deep reinforcement learning to reduce bus bunching for multi-line services with a shared corridor. Transportation Research Part C, 2023.
Urban Mobility Behavior Modeling
I build fine-grained behavioral models that leverage emerging data modalities to understand how individuals and fleets navigate cities.
- Large language models as urban residents: An LLM agent framework for personal mobility generation. NeurIPS, 2024.
For a complete publication list, please visit my Google Scholar.
Contact
jiawei-dot-wang4-at-mail-dot-mcgill-dot-ca