Design and Implementation of Omni-Directional Vision-Based Parking Controller for Car-Like Mobile Robot

• Main Authors: Cheng-Hsianh Ho, 何程翔
• Other Authors: Tzuu-Hseng S. Li
• Format: Others
• Language: en_US
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/82514047454991731467

碩士 === 國立成功大學 === 電機工程學系碩博士班 === 93 === 　This thesis presents an omni-directional vision-based control scheme for car-like mobile robot (CLMR), which possesses autonomous parking capability. All the parking control and path tracking control system are developed on the basis of fuzzy logic schemes. In order to smoothly change the direction of the CLMR, a practicable reference trajectory is provided for the fuzzy controller to maneuver the steering angle of the CLMR. In the study, a path tracking problem is formulated as following a virtual parking lot, which is transformed with respect to the posture of the parking lot in panoramic images. At first, we apply the image processing technique to omni-directional images to filter out the noise and find the characteristic points of the parking lot. From the image information, one can estimate the position of the CLMR in the parking space and figure out a feasible reference trajectory. Then, we develop a fuzzy logic controller to manipulate the steering angle and increase the path tracking performance such that the CLMR can execute the parking missions, parallel parking and garage parking. Finally, the real-time experimental results demonstrate the practicability and effectiveness of the proposed image processing method and autonomous parking control scheme.