A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment

作     者：Xunjia Zheng Bin Huang Daiheng Ni Qing Xu 

作者机构：Tsinghua UniversityBeijingChina Department of Civil and Environmental EngineeringAmherst College of EngineeringUniversity of MassachusettsAmherstMassachusettsUSA 

出 版 物：《Journal of Intelligent and Connected Vehicles》 (智能网联汽车（英文）)

年 卷 期：2018年第1卷第2期

页      面：41-54页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Science Fund for Distinguished Young Scholars(51625503) the National Natural Science Foundation of China,the General Project(51475254) the Major Project(61790561) 

主　　题：Automated vehicles Advanced vehicle safety systems Autonomous driving Connected vehicles Environment perception Sensor information fusion 

摘      要：Purpose–The purpose of this paper is to accurately capture the risks which are caused by each road user in ***/methodology/approach–The authors proposed a novel risk assessment approach based on the multi-sensor fusion algorithm in the real traffic ***,they proposed a novel detection-level fusion approach for multi-object perception in dense traffic environment based on evidence *** approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object *** information of object type,position and velocity was accurately ***,they conducted several experiments in real dense traffic environment on highways and urban roads,which enabled them to propose a novel road traffic risk modeling approach based on the dynamic analysis of vehicles in a variety of driving *** analyzing the generation process of traffic risks between vehicles and the road environment,the equivalent forces of vehicle–vehicle and vehicle–road were presented and theoretically *** prediction steering angle and trajectory were considered in the determination of traffic risk influence ***–The results of multi-object perception in the experiments showed that the proposed fusion approach achieved low false and missing tracking,and the road traffic risk was described as afield of equivalent *** results extend the understanding of the traffic risk,which supported that the traffic risk from the front and back of the vehicle can be perceived in ***/value–This approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object *** information of object type,position and velocity was used to reduce erroneous data association between tracks and ***,the authors conducted several experiments in real dense traffic environment on highways and urban roads,which enabled them to propose a novel road traffic