Autonomous Vehicle Parking Using Hybrid Artificial Intelligent Approach
Abstract This paper devotes to design and implement a hybrid artificial intelligent control scheme for a car-like vehicle to perform the task of optimal parking. The parallel parking control scheme addresses three issues: trajectory planner, decisional kernel, and trajectory tracking control. Design of the control scheme consists of several techniques: genetic algorithm, Petri net, and fuzzy logic control. The genetic algorithm is used to determine the feasible parking locations. The Petri net is used to replace the traditional decision flow chart and plan alternative parking routes especially in global space. The parking routine can be re-performed if the initially assigned route is interfered or when the targeted parking space has been occupied. The fuzzy logic controller is used to drive the vehicle along with the optimal parking route. The proposed scheme is put into several scenarios to test and verify its applicability and to manifest its distinguished features.