An Intelligent Parking System Based on Cooperative Vehicle Infrastructure System

In this paper, we design an automatic parking system based on roadside vision, computing and Vehicle-to-Road (V2R) network. We use ArUco marker and roadside cameras to establish the garage coordinate system and obtain the position of the intelligent vehicle. The parking reference trajectory from the entrance to available parking space is planned by the roadside computer according to the parking request. To tracking the parking reference trajectory, we utilize an increment P control and the pure pursuit algorithm, which are used to control the longitudinal speed and the steering angle, respectively. The control laws are calculated in the roadside computer, and then sent to the vehicle through the V2R network. The proposed method reduces the cost of intelligent hardwares equipped in the vehicles, and saves the time spent on looking for an available parking space. We implement this automatic parking system on a platform containing miniaturized vehicles and roadside equipments. Experimental results show that the parking system we design can achieve the required parking goal.