Intelligent Transportation Systems

Intelligent Transportation Systems study how to monitor and manage road, rail, air, maritime, and public transit networks, with goals such as safer travel, less congestion, and reliable service. Common approaches include computer vision and multimodal sensing, graph-based traffic forecasting, trajectory prediction, reinforcement learning and model-predictive control, and optimization for routing, scheduling, and infrastructure. Methods are tested on trajectory and traffic datasets and in tools such as SUMO and CARLA, alongside field deployments for tasks including signal control, crash-risk assessment, and transit operations. Large language and multimodal models are beginning to support planning and control, but generalization across cities and changing networks, safety verification, privacy, and evidence from real-world deployment remain key challenges.