基于模糊神经网络智能车辆循迹控制.pdfVIP

汽摇 车摇 工摇 程 2015年(第37卷)第1期 Automotive Engineering 2015(Vol.37)No.1 2015007 基于模糊神经网络的智能车辆循迹控制* 1,2 1 1 张摇 琨 ,崔胜民 ,王剑锋 (1郾 哈尔滨工业大学汽车工程学院,威海摇 264209;摇 2郾 华晨汽车工程研究院,沈阳摇 110141) [摘要]摇 为提高智能车辆自主循迹控制的精度,提出了一种基于模糊神经网络控制(FNNC)和神经网络预测 (NNP)的智能循迹控制策略。 转向控制器的输入量有3个:预瞄点处的横向循迹误差、汽车横摆角速度和侧向加速 度。 车速控制器的输入量有4个:预瞄点处的面积误差、侧向加速度、汽车侧偏角和转向盘转角。 网络训练采用误 差反向传播法。 仿真与试验结果表明,所设计的循迹控制器通过对驾驶员操作样本的训练,能实现对车辆的车速与 转向控制,横向循迹误差和目标车速均比较理想。 关键词:智能车辆;循迹控制;模糊神经网络 Path Tracking Control of Intelligent Vehicle Based on Fuzzy Neural Network 1,2 1 1 Zhang Kun ,Cui Shengmin Wang Jianfeng 1郾School of Automobile Engineering,Harbin Institute of Technology,Weihai摇 264209;摇 2郾BrillianceAutoRD Center,Shenyang摇 110141 [Abstract]摇 In order to improve the autonomous path tracking control accuracy of intelligent vehicle,an in鄄 telligent path tracking control strategy isproposed based onfuzzy neural network control and neural network predic鄄 tion. The inputs of steering controller are the transverse path tracking error at preview points and the yaw rate and lateral accelerationofvehicle,whilethosefor speedcontrolleraretheareaerroratpreview pointsandthelateralac鄄 celeration,side slip angle and steering wheel angle of vehicle,and error back propagation technique is adoptedfor network training. The results of simulation and test show that through the training of driver operation samples,the path tracking controller designedcanrealize speedand steering control of intelligentvehiclewithrelatively desirable transverse path tracking error and target speed. Keywords:intelligent vehicle;path tracking control;