An AI-reinforced Traffic Digital Twin for Testing Emergency Vehicle Interventions

Emergency vehicle (EMV) response times have degraded due to increasing urbanization and resulting congestion. Evaluating interventions to mitigate this degradation is too costly to be done in the field. This project will build a traffic digital twin (TDT) to be developed in collaboration with FDNY as a virtual test bed to evaluate interventions and support decision-making and planning in a safe simulation environment. The TDT will be built on the open source Simulation of Urban Mobility (SUMO) microscopic continuous traffic simulation. Key challenges are incorporating AI to learn non-EMV driver responses to EMV signals (sirens, V2X technologies) and to train the TDT to different traffic states using historical traffic data and dispatch data from FDNY. The scope of work can be summarized as: (1) development and calibration of a baseline SUMO simulation for FDNY district M6 in Harlem, NYC; (2) combining traffic data and camera data at the same time to develop an AI model for traffic state prediction in the digital twin; (3) combining EMV global positioning system (GPS) data and the traffic state data to statistically learn non-EMV behavioral responses (response reaction time, etc.); and (4) developing simulation-based intervention optimization and test using out-of-sample observations