This $350,000 Project Grant award from the National Science Foundation's (NSF) Engineering program (CFDA 47.041) supports research on developing deep learning-based methodologies to automatically learn traffic dynamics, especially for traffic flow involving connected and automated vehicles (CAVs). The objective is to transform the conventional methods of studying traffic dynamics into an automated, data-driven paradigm enabled by the rapid advancement of artificial intelligence and the availability of ubiquitous traffic data. The project aims to design new deep learning structures to address data noise, develop a coordinated learning framework to handle diverse vehicle classes and driving behaviors, and formulate new metrics and methods to ensure accuracy, parsimony, interpretability, and generalizability of the learned traffic dynamics models. The research findings will be integrated into existing and new courses, provide research opportunities for students, and be broadly shared with transportation agencies, academic communities, and industry. This award, effective from May 1, 2025 to April 30, 2028, reflects NSF's mission to advance scientific discovery and technological innovation.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $350.0k | 7/1/25 |