Abstract:Automatic parking system is an important part of the development of unmanned driving, and its path planning of a core technology of unmanned driving technology is the key to study unmanned driving. RRT algorithm was introduced to propose an improved automatic parking path planning algorithm for irregular parking spaces in complex environments. The strategy of searching for the target point was adopted, which made the search tree growing towards the parking target point easily. Then, the random node generating function and step size adjusting functions were introduced to avoid the parking obstacles effectively and accelerate the convergence speed of the path. Aiming at the problem of path unevenness, a path smoothing method based on cubic B-spline curve was proposed, which greatly improved the search efficiency and the quality of the path. Finally, the improved path planning algorithm was simulated in different complex parking spaces us, which proved the feasibility of the new algorithm.The simulation results shows that compared with the traditional RRT algorithm, the improved algorithm has shorter path length, smoother path and higher parking accuracy in complex environment. Key words: Irregular Automatic Parking; Path Planning; RRT algorithm;

CICTP