Path Planning based on Clothoid for Autonomous Valet Parking

Abstract

The problem of path planning of the autonomous valet parking can be explained as the planning of a path from the entrance of the parking lot to the parking space. Firstly, by collecting the location information of key nodes in the parking Iot, the topological map of the parking lot is defined, which is composed of parking space information and road topological network. Secondly, the reasonable parking space searching path and parking path are planned, and their curvature discontinuity is smoothed. The parking path adopts the C-shaped method, the path of searching for parking spaces adopts the line-arc-line splicing method, and use the clothoid curve to smooth the path. Finally, Stanley path tracking algorithm is used to follow the planned path based on MATLAB to verify the effectiveness of the path planning algorithm. The simulation results show that the proposed algorithm can realize the seamless splicing between the searching path and the parking path, and the planned path can be tracked better.