|
Yuankai Wu
Sichuan University, China
|
Yong Wang
The University of Hong Kong
|
Renzong Lian
Fuzhou University, China
|
|
|
Intelligent connected transportation systems are entering a new stage driven by artificial intelligence, spatiotemporal data, vehicle-road-cloud integration, and autonomous decision-making. Unlike traditional vehicle electrification studies that focus primarily on power electronics and energy conversion, this topic emphasizes how intelligent algorithms, dynamic system modeling, and cooperative control can improve the safety, efficiency, robustness, and sustainability of future transportation systems.
Modern transportation systems involve complex interactions among vehicles, infrastructure, pedestrians, traffic signals, mobility services, and urban environments. These systems generate massive multimodal spatiotemporal data, including traffic flow, trajectories, sensor measurements, road networks, weather, events, and vehicle operation states. Effectively modeling these data and translating them into reliable prediction, planning, and control decisions remains a fundamental challenge.
This conference theme aims to provide a platform for cutting-edge research on spatiotemporal intelligence, intelligent vehicle modeling, multi-agent cooperation, traffic prediction, reinforcement learning, world models, vehicle-road-cloud collaborative control, and safety-aware autonomous mobility. Both theoretical advances and real-world applications are welcome, especially studies that bridge machine learning, transportation systems, vehicle dynamics, and intelligent control.
|
- Spatiotemporal data mining and forecasting for intelligent transportation systems
- Deep learning and foundation models for traffic prediction
- Graph neural networks for road networks, traffic flow, and mobility systems
- Vehicle trajectory prediction, behavior modeling, and intention recognition
- Intelligent vehicle dynamics modeling and control
- Reinforcement learning for traffic signal control, routing, and vehicle decision-making
- Multi-agent cooperation and game-theoretic modeling in mixed traffic systems
- World models and simulation-based learning for autonomous driving and traffic control
- Vehicle-road-cloud collaborative perception, prediction, and decision-making on
- Digital twins for urban mobility and intelligent transportation management
- Safety, robustness, and uncertainty quantification in autonomous mobility systems
- Human-in-the-loop and human-AI collaborative transportation systems
- Data-driven traffic emission, energy consumption, and low-carbon mobility analysis
- Large language models and multimodal agents for transportation reasoning and management
- Benchmark datasets, evaluation protocols, and real-world deployment of intelligent transportation AI
|
