Path Planning and Tracking for Vehicle Parallel Parking Based on Preview BP Neural Network PID Controller  

作　　者：季学武 王健 赵又群 刘亚辉 臧利国 李波 

机构地区：[1]State Key Laboratory of Automotive Safety and Energy, Tsinghua University [2]College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics

出　　处：《Transactions of Tianjin University》2015年第3期199-208,共10页天津大学学报（英文版）

基　　金：Supported by the National Natural Science Foundation of China(No.11072106,No.51005133 and No.51375009)

摘　　要：In order to diminish the impacts of extemal disturbance such as parking speed fluctuation and model un- certainty existing in steering kinematics, this paper presents a parallel path tracking method for vehicle based on pre- view back propagation （BP） neural network PID controller. The forward BP neural network can adjust the parameters of PID controller in real time. The preview time is optimized by considering path curvature, change in curvature and road boundaries. A fuzzy controller considering barriers and different road conditions is built to select the starting po- sition. In addition, a kind of path planning technology satisfying the requirement of obstacle avoidance is introduced. In order to solve the problem of discontinuous curvature, cubic B spline curve is used for curve fitting. The simulation results and real vehicle tests validate the effectiveness of the proposed path planning and tracking methods.In order to diminish the impacts of external disturbance such as parking speed fluctuation and model uncertainty existing in steering kinematics, this paper presents a parallel path tracking method for vehicle based on preview back propagation(BP) neural network PID controller. The forward BP neural network can adjust the parameters of PID controller in real time. The preview time is optimized by considering path curvature, change in curvature and road boundaries. A fuzzy controller considering barriers and different road conditions is built to select the starting position. In addition, a kind of path planning technology satisfying the requirement of obstacle avoidance is introduced. In order to solve the problem of discontinuous curvature, cubic B spline curve is used for curve fitting. The simulation results and real vehicle tests validate the effectiveness of the proposed path planning and tracking methods.

关 键 词：parallel parking path tracking path planning BP neural network curve fitting 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP273[自动化与计算机技术—控制科学与工程]