Design and Implementation of an Adaptive Network-Based Fuzzy controller for Car-Like Mobile Robots

• Main Authors: Zhi-Long Wang, 王志榮
• Other Authors: Chih-Hsiung Yang
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/08217002128189668476

碩士 === 國立高雄應用科技大學 === 電機工程系 === 98 === The thesis presents an autonomous parallel parking fuzzy controller for a car-like mobile robot (CLMR) which the parking space dimensions cannot be identified. Four ultrasonic sensors are mounted in the front right corner of the car to obtain the parking environmental information and a compass sensor is mounted at the centre position of the car to measure the posture of the car. Through the proposed mechanism, one of the four ultrasonic sensors and the compass sensor are used to decide on the turning angle. Fifth-order polynomial reference paths starting from three different parking widths to the same goal point have been used to generate the training data set. The controllers have been identified by the subtractive clustering algorithm and been trained by the adaptive network-based fuzzy inference systems (ANFIS) to obtain the optimal parameters of the controllers. The hardware design of the CLMR can be classified into two units which are the control unit and operation unit. The control unit includes the stepper motor rotation control, RC servo motor steering control, ultrasonic sensors and compass sensor measurement control, and RS-232 communication interface control. The operation unit utilizes the LabVIEW software to implement real-time computations of the front wheel steering angle of the CLMR. Before the hardware testing, the Matlab/Simulink software is first used to simulate and verify the feasibility of the proposed approach. The experiment results show that the proposed approach enable the CLMR to intelligently and successfully perform the parallel parking for a variety of parking widths.