Radar-vision-V2X fused perception based intelligent control mechanism for service-oriented traffic signals

Abstract

Traditional traffic signal systems lack the capability to perceive vehicle types and real-time traffic flow dynamics, particularly in identifying priority levels for emergency vehicles. To address this, an intelligent traffic flow decision-making and scheduling system based on radar-visual-V2X(Vehicle-to-Everything) multi-sensor fusion is proposed. A refined traffic model integrating connected vehicles with service priority is established, encompassing detailed elements such as roads and intersections. A hierarchical Radar-Vision-V2X fusion framework is developed to enable comprehensive traffic situation awareness and evaluation. Based on the assessment results, a hybrid intelligent signal control mechanism combining deep reinforcement learning with logical rules is designed to optimise real-time signal timing and efficiently handle priority vehicle passage. A prototype system is implemented and extensively tested in typical urban scenarios using a SUMO-CARLA co-simulation platform. Experimental results show that the proposed approach reduces average travel time by over 44.6% and average waiting time by 21.4% compared to conventional methods.