基于突变理论的人车碰撞风险实时预警模型  

Real-time early warning model of collision risk between human and vehicle based on catastrophe theory

作　　者：杨旭 周竹萍[1] 刘博闻 Yang Xu;Zhou Zhuping;Liu Bowen(School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China;Nanjing LES Information Technology CO.,Ltd.,Nanjing 210014,China)

机构地区：[1]南京理工大学自动化学院,江苏南京210094 [2]南京莱斯信息技术股份有限公司,江苏南京210014

出　　处：《南京理工大学学报》2021年第5期606-613,共8页Journal of Nanjing University of Science and Technology

基　　金：国家重点研发计划政府间国际科技创新合作重点专项项目(2019YFE0123800);华设设计集团股份有限公司开放课题;中央高校基本科研业务费专项资金(30920021142)。

摘　　要：人车碰撞风险预警是保证行驶安全的关键技术。该文基于突变理论提出一种动态系数的人车碰撞风险实时预警模型。通过行车记录仪图像分析及车辆仪表等设备实时获取车辆动态基本参数,针对行人位于车辆左右两侧的情形,建立行人过街决策概率Binary Logistic模型;基于突变级数法建立碰撞系数模型,根据突变级数计算结果确定模型系数,构建人车碰撞风险实时预警模型。将模型计算结果与TC&CS风险矩阵判定结果、人工评定结果进行对比,结果表明该模型准确率高,且符合安全导向原则。Early warning of human-vehicle collision risk is a key technology to ensure driving safety.This paper proposes a real-time warning model of human-vehicle collision risk based on catastrophe theory.The basic parameters of vehicle dynamics are obtained in real time through the image analysis of the driving recorder and the vehicle instrumentation.The Binary Logistic model of pedestrian crossing decision probability is established for the pedestrians on the left and right sides of the vehicle;and the collision coefficient model is established based on the catastrophe progression method.The calculation results of the catastrophe progression determine the model coefficients,and build a real-time warning model of human-vehicle collision risk.The calculation results of the model are compared with the judgment results of the TC&CS risk matrix and the manual evaluation results.The results show that the model has high accuracy and conforms to the safety-oriented principle.

关 键 词：交通安全 突变理论 人车碰撞预警 车辆动态 

分 类 号：U491.3[交通运输工程—交通运输规划与管理]