Abstract

This study aims at developing an autonomous parallel parking controller for a Car-Like-Mobile-Robot. In this research we have presented a Neuro-Fuzzy control strategy to back drive the car to the parking lot based on the sonar data. We have focused on the case where the parking space dimensions are not known which has not been investigated by the previous approaches. Our controller is able to decide about the motion direction at each time interval by starting form the initial position and by processing the information obtained by the sensors. On the other hand, in the traditional approaches the path is planned in offline by knowing the parking space dimensions and then will be tracked based on path tracking algorithms. The simulation results demonstrate the effectiveness of the developed algorithm and show that the proposed scheme can be considered as a step towards autonomous intelligent vehicles which can successfully adapt their parking behavior in unknown parking spaces.