Initiated and developed at Inchor (SaferDrive AI). LLM/VLM agents mutate real logged drives into safety-critical corner cases, replay them in closed loop, and a video world model renders the result.
A dynamic robotaxi routing framework that turns centrally controlled fleets into cooperative drive-by sensors for urban traffic monitoring.
Project leader on a CCAT-funded cooperative perception system connecting roadside LiDAR and CAV sensors for improved road safety.
Integrating Intelligent Driving Model (IDM) into deep learning for robust car-following trajectory prediction.
Multiple projects funded by US-DOT, Michigan DOT, and Leidos Inc. on V2X-based transit signal priority and co-simulation platforms.