Heavy-duty vehicles are responsible for a disproportionate share of fatal accidents and carbon emissions in the transportation system. This research focuses on creating a digital twin framework that integrates real-time data and telematics to model the physical and operational dynamics of heavy-duty vehicles, continuously monitoring vehicle behavior, predicting potential safety risks, and suggesting interventions to prevent crashes. The system provides transparent, data-driven insights for fleet managers, helping optimize vehicle operations, enhance safety, and reduce emissions, while informing regulatory standards and policy decisions.
Faculty advisor: Pingbo Tang