汽车驾驶机器人车速跟踪神经网络控制方法  

Speed Control of Vehicle Robot Driver Based on Neural Network

作　　者：陈刚[1] 张为公[2] 

机构地区：[1]南京理工大学,南京210094 [2]东南大学,南京210096

出　　处：《中国机械工程》2012年第2期240-243,共4页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(51008143);中国博士后科学基金资助项目(2011M500922);高等学校博士学科点专项科研基金资助项目(200802861061);南京理工大学自主科研专项计划资助项目(2011YBXM43)

摘　　要：为了实现汽车驾驶机器人对给定车速的准确跟踪,提出了一种驾驶机器人车速跟踪神经网络控制方法。网络模型输入层变量为驾驶机器人油门和制动器、离合器机械腿、换挡机械手的位移;中间层为隐层,节点数为5,神经元传递函数为正切传递函数;输出层变量为试验车辆车速,神经元传递函数为线性传递函数。结果表明,该方法的收敛速度明显高于梯度下降法的收敛速度,且达到的控制精度更高,车速跟踪误差满足国家汽车试验标准的要求。To realize the vehicle speed tracking of given driving test cycle, a novel speed control method of vehicle robot driver based on neural network was proposed herein. The displacements of throttle pedal, brake pedal, clutch pedal and shift manipulator for vehicle robot driver were used as the input layer variables of the network model. The middle layer of the network model was used as hidden layer,which has five hidden nodes and whose neurons transfer function adopts tangent transfer func- tion. The test vehicle speed was used as the output layer variable of the network model, whose neurons transfer function adopts linear transfer function. Results show that the convergence rate and control accuracy of the proposed method is higher than that of traditional gradient descent method. The vehicle speed tracking errors of the proposed method meet the requirements of China vehicle test standards.

关 键 词：汽车试验 驾驶机器人 车速控制 神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] U467.5[自动化与计算机技术—控制科学与工程]