Autonomous parallel parking of a vehicle in a limited space using a RBF network and a feedback linearization controller

In this paper, the issue of autonomous parallel parking of a vehicle in a limited space has been considered based on a parked vehicle in front. A Radial Basis Function Network (RBFN) has been developed to online path generation according to the measured distance from the parked vehicle. These measurements are obtained by employing two sonar sensors mounted in the front left corner of the vehicle. Fifth order polynomial reference paths for three different initial positions have been used to generate training data for the network. In order to use feedback linearization controller for tracking the desired parking path, two timing laws have been proposed for forward and backward maneuvers and the control laws have been designed in timing laws-domain. These timing laws have been considered such that zero velocity is obtained for the vehicle at the initial and goal points of the parking maneuver, as well as, at the point that direction of motion must change, without occurrence singularity in the control laws. Furthermore, due to change of the desired path and direction of motion based on the vehicle´s configuration, the vehicle can be parked in limited area. Simulation results show the effectiveness of the proposed approach to use the nonlinear controller in order to intelligently perform the parallel parking in a limited space without knowing the parking space width and only based on distance measurements from the parked vehicle.