Digital Twin-Assisted Cooperative Driving at Non-Signalized Intersections

Digital Twin, as an emerging technology related to Cyber-Physical Systems (CPS) and Internet of Things (IoT), has attracted increasing attentions during the past decade. Conceptually, a Twin is digital replica physical entity in real world, this leveraged study design cooperative driving system at non-signalized intersections, allowing connected vehicles cooperate with each other cross intersections without any full stops. Within proposed framework, we developed enhanced first-in-first-out (FIFO) slot reservation algorithm schedule sequence crossing vehicles, consensus motion control calculate vehicles’ referenced longitudinal motion, model-based estimation tackle communication delay packet loss. Additionally, augmented reality (AR) human-machine-interface (HMI) designed provide guidance drivers vehicles. Agent-based modeling simulation conducted Unity game engine based on real-world map San Francisco, human-in-the-loop (HITL) results prove benefits algorithms 20% reduction travel time 23.7% energy consumption, respectively, when compared traditional signalized intersections.