基于改进TOPSIS的驾驶行为实时安全性评估方法  

Real-Time Safety Assessment Method of Driving Behavior Based onImproved TOPSIS

作　　者：刘志强[1] 王涛[1] LIU Zhiqiang;WANG Tao(School of Automotive and Traffic Engineering,Jiangsu University,Zhenjiang 212013,China)

机构地区：[1]江苏大学汽车与交通工程学院,江苏镇江212013

出　　处：《重庆理工大学学报（自然科学）》2021年第11期58-66,共9页Journal of Chongqing University of Technology：Natural Science

摘　　要：为提高驾驶员安全意识,减少交通事故的发生,提出了一种通过马氏距离和联系向量距离结合改进的TOPSIS多属性决策方法,对不同驾驶行为的安全性进行评估。首先从3个方面分析建立了驾驶行为安全性评估指标体系,设计实车试验采集了10名驾驶人的各类型数据,并进行处理和分析。通过Pearson相关性分析确定了9个关键指标,接着利用AHP-Entropy方法对各评估指标赋权,最后通过改进的TOPSIS多属性决策方法对不同驾驶人行为的安全等级进行排序,与传统方法对比结果表明:该改进方法克服了欧氏距离的局限性,能有效提高评估的准确性。In order to improve the driver’s safety awareness and at the same time reduce the occurrence of traffic accidents,an improved Technique for Order Preference by Similarity to an Ideal Solution multi-attribute decision-making method is proposed by combining Mahalanobis distance and contact vector distance to evaluate the safety of different driving behaviors.First of all,a driving behavior safety evaluation index system is established from three aspects:the safety of the driver’s visual perception behavior,the safety of the driver’s manipulation behavior and the safety of the vehicle operating state,and a driving behavior safety evaluation index system is initially established.Secondly,in the actual vehicle test of the urban expressway design,various types of data during the driving process of 10 drivers are collected,including speed,acceleration,steering wheel angle,etc.and data is processed and analyzed.Nine key indicators are determined through Pearson correlation analysis:lane change visual perception behavior safety index,front obstacle perception safety index,braking amplitude change rate,steering wheel angle entropy,longitudinal speed standard deviation,longitudinal acceleration change rate,Steering wheel angle standard deviation,lateral acceleration standard deviation and lateral lane keeping safety indicators.Then the subjective and objective combination of AHP-Entropy method is used to weight each evaluation index to make the index weight more reasonable.Finally,the improved TOPSIS multi-attribute decision-making method is used to rank the safety levels of different driver behaviors.The results of comparison with traditional methods show:This improved method overcomes the limitations of Euclidean distance and can effectively improve the accuracy of evaluation.

关 键 词：驾驶行为 安全性评估 相关性分析 改进TOPSIS多属性决策方法 

分 类 号：U491[交通运输工程—交通运输规划与管理]