基于危险态势识别的智能车驾驶模式选择  

Driving Mode Selection of Intelligent Vehicles Based on Risky Situation Identification

作　　者：严利鑫 黄珍[4] 吴超仲[1,2] 秦伶巧 朱敦尧[1,2] 冉斌[3] YAN Li-xin HUANG Zhen WU Chao-zhong QIN Ling-qiao ZHU Dun-yao RAN Bin(Intelligent Transportation Systems Center, Wuhan University of Technology, Wuhan 430063, Hubei, China National Engineering Research Center for Water Transport Safety （WTSC）, Wuhan University of Technology, Wuhan 430063, Hubei, China Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Madison 53706, Wisconsin, USA School of Automation, Wuhan University of Technology, Wuhan 430070, Hubei, China)

机构地区：[1]武汉理工大学智能交通系统研究中心,湖北武汉430063 [2]武汉理工大学国家水运安全工程技术研究中心,湖北武汉430063 [3]威斯康星大学麦迪逊分校土木与环境工程学院,威斯康星麦迪逊53706 [4]武汉理工大学自动化学院,湖北武汉430070

出　　处：《华南理工大学学报（自然科学版）》2016年第8期139-146,154,共9页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家科技支撑计划项目(2014BAG01B03);国家自然科学基金资助项目(61104158);武汉理工大学教学研究项目(2011180)~~

摘　　要：人机共驾是智能车发展中必须经历的一个重要阶段,而人机切换时机选择是人机共驾需要解决的一个关键问题。为此,文中以实车实验采集的数据为依据,根据驾驶人经验及经K-均值聚类得出的危险态势等级对驾驶模式选择方式(安全驾驶、进行警示和自动切换)进行了标定。通过引入车速均值、加速度标准差、车头时距、前轮转角标准差、车道偏离量以及驾驶人经验等6项指标作为特征向量,提出了基于径向基核函数序列最小优化算法(SMO)的智能车驾驶模式选择模型。并以决策树、径向基神经网络、支持向量机(SVM)作为对照。研究结果表明,文中提出的基于SMO方法的驾驶模式识别模型的准确率达到91.7%,相较于其他3种识别方法具有较大的优越性.In the development process of intelligent vehicles, it is a necessary and important stage that manual dri- ving and automatic driving jointly play their roles, of which one key problem is selecting an appropriate take-over time from manual driving to automatic driving when a risky situation occurs. In order to improve the driving safety, according to the data collected from a real vehicle test, driving modes are divided into safe driving, warning driving and automatic driving, based on both the driver＇ s report and the risky situation levels obtained by means of the K-means clustering. Then, by selecting six impact factors （ namely, the average of speed, the time to headway, the standard deviation of steering, the standard deviation of acceleration, the distance away from the lane and the dri- ver＇s experience） as the feature vectors, a driving mode selection model of intelligent vehicles is constructed based on the sequential minimal optimization （SMO） algorithm with the radial basis function （RBF）. Moreover, the con- structed model is compared with the algorithms of ID3, RBF network and SVM. The results show that the construc- ted model achieves an accuracy of up to 91.7%, which is significantly superior to those of the other three algo- rithms.

关 键 词：智能车 驾驶模式 K-均值聚类 序列最小优化算法 交通安全 

分 类 号：U491[交通运输工程—交通运输规划与管理]