低速城市路况下驾驶员制动特性辨识研究  

Research on Driver Braking Characteristics Identification in Low Speed Urban Roads

作　　者：李刚[1] 杨志 LI Gang;YANG Zhi(College of Automobile and Traffic Engineering,Liaoning University of Technology,Liaoning Jinzhou 121001,China)

机构地区：[1]辽宁工业大学汽车与交通工程学院,辽宁锦州121001

出　　处：《机械设计与制造》2021年第12期14-18,23,共6页Machinery Design & Manufacture

基　　金：国家自然科学基金—考虑驾驶员特性的四轮独立驱动与转向电动汽车动力学控制研究(51675257);辽宁省创新人才项目(LR2016054)。

摘　　要：针对现代车辆的智能化、人性化发展的要求,研究"人—车—路"闭环系统中驾驶员在车辆控制中的主导地位。本文通过驾驶模拟器dSPACE实时仿真平台设计实验,通过模拟驾驶员在城市路况的跟车行为,采集驾驶员制动时的相关参数,运用高斯混合模型聚类算法将特征数据分类,并运用BP神经网络工具箱建立了该城市路况下驾驶员制动特性辨识模型,实现了驾驶员制动特性的在线辨识。实验结果表明:该辨识方法在实验设计的城市路况,具有良好的驾驶员制动特性辨识能力。In view of the requirements of intelligent and humanized development of modern vehicles,the pilot position of the driver in vehicle control is studied in the closed loop system of“people-vehicle-road”.Through the driving simulator dSPACE realtime simulation platform design experiment,by simulating the driver′s follow-up behavior in urban road conditions,the relevant parameters of the driver’s braking are collected,and the Gaussian mixture model clustering algorithm is used to classify the feature data. Finally,the BP neural network toolbox is used to establish the driver braking characteristic identification model under the city road condition,and the online identification of the driver′s braking characteristics is realized. The experimental results show that the identification method has good driver braking characteristic recognition ability in the experimental urban road conditions.

关 键 词：驾驶模拟器 驾驶员制动特性 高斯混合模型 BP神经网络 辨识研究 

分 类 号：TH16[机械工程—机械制造及自动化]