Autonomous Vehicle Parking Using Hybrid Artificial Intelligent Approach

• Main Authors: Chen-Kui Lee, 李偵魁
• Other Authors: 林俊良
• Format: Others
• Language: en_US
• Online Access: http://ndltd.ncl.edu.tw/handle/44431264557851950889

碩士 === 國立中興大學 === 電機工程學系所 === 96 === This thesis devotes to design and implement a hybrid artificial intelligent control scheme for a car-like mobile robot to perform the task of optimal parking. The control scheme consists of several techniques: genetic algorithm, Petri net and fuzzy control. The binary genetic algorithm is used to determine the feasible parking locations. The Petri-net is used to replace the traditional system flow chart and to plan alternative parking routes especially in global space. The parking routine can be performed if the initial assigned route is interfered or when targeted the parking space is occupied. The fuzzy control system is primarily used to derive along an optimal parking route. In this thesis, the overall configuration of the car parking system is introduced. An intelligent parallel parking control scheme is addressed next which includes a trajectory planner, a decisional kernel and a trajectory tracking controller. The optimal solution is then put into several computer simulations to verify the applicability of the proposed control scheme and to manifest the distinguished features of the proposed scheme.