Research On Autonomous Parking Path Planning Based On Pseudospectral Method

In recent years, with the rapid growth of car ownership, narrow parking space and complex parking environment are making the parking task a great challenge, not only for the novice drivers but also for the skilled drivers. Autonomous parking system can effectively lighten the burden of parking, therefore, the autonomous parking technology has been paid more and more attention. And with the rise of self-driving cars, as part of the self-driving technology, autonomous parking technology has become one of the research hotspots.This thesis mainly studies the autonomous parking path planning. In view of the shortcomings of methods proposed in relevant researches, a general autonomous parking path planning method is proposed. The method formulate a time-optimal control problem of parking path planning with the vehicle kinematic constraint and path constraint. The pseudospectral method is used to solve the optimal control problem, and the obtained solution is guaranteed to be consistent with the path constraint. Finally the collision-free feasible parking path is obtained. The simulation results show that the proposed method has strong reliability and adaptability.In addition, in order to realize the function of autonomous parking, the parking space detection method based on ultrasonic sensor is studied. According to the framework of autonomous parking system, an autonomous parking control unit and its working process are designed. Finally, the parallel parking experiment was carried out on a real vehicle, and the parking task was successfully completed in experiments. The experimental results show that the proposed path planning method is feasible.