Abstract
An automatic vehicle parallel parking method, including path planning, controller design, and state estimation is proposed in this article. Accordingly, a path is planned using clothoid sequences along with a straight line which avoids stopping the car to reorient the wheels. This method also enables the car to park from different initial poses. The generated path is followed by adjusting control inputs. The control inputs, including speed and steering angle, are solely a function of traveled distance. Reduced parking time along with the ability of parking in one or two maneuvers is achieved, smaller than standard places. An evolutionary optimization algorithm is used to calculate the best speed parameter according to the defined criteria. Furthermore, the Unscented Kalman Filter (UKF) is proposed to estimate the traveled distance, resulting in a smaller error compared to the conventional Extended Kalman Filter (EKF). The research aims to propose an optimal automatic parking algorithm which considers the shortcomings of the existing methods such as parking duration, the required space size for parking in the maximum of two maneuvers, and path continuity. Finally, the fidelity and improved performance of the proposed method are assessed in various probable conditions using the powerful Monte Carlo simulations.

This publication has 33 references indexed in Scilit: