Generation of a scenario library for testing driver-automation cooperation safety under cut-in working conditions  

作　　者：Hongyan Guo Jiaming Zhang Jun Liu Yunfeng Hu Wanqing Shi 

机构地区：[1]College of Communication Engineering,Jilin University,Renmin Street 5988,Changchun,130012,China [2]The State Key Laboratory of Automotive Simulation and Control,Jilin University,Renmin Street 5988,Changchun,130012,China [3]College of Automotive Engineering,Jilin University,Renmin Street 5988,Changchun,130012,China

出　　处：《Green Energy and Intelligent Transportation》2022年第2期1-8,共8页新能源与智能载运（英文）

基　　金：Major Project of Scientific and Technological Innovation 2030“New Generation Artificial Intelligence”(Grant No.2020AAA0108105);National Nature Science Foundation of China(Grants Nos.62103162 and U19A2069);Jilin Key Research and Development Program(Grant No.20200401088GX);the Jilin Major Science and Technology Projects(Grant No.20200501011GX).

摘　　要：To improve the efficiency of safety tests of driver-automation cooperation,a method for generating a scenario library is proposed that considers the probability of scenario occurrence and driver-handling challenges in real driving situations.First,the original scenario data under cut-in conditions stored in a time series are extracted from the scenario data set.Then,a mathematical performance index is used to model the scenario and a significance function in terms of the occurrence frequency of the scenario,and the performance challenge between the driver and the vehicle is established.Next,the important scenario set is extracted from the original scenario set by constructing and optimizing a significance auxiliary function.Finally,the extracted important scenario sets are filtered by using the significance function values of the scenarios to generate a scenario library.Simulation results show that the proposed method for scenario library generation can effectively identify scenarios with potential adventure during driver-automation cooperation and thus accelerate safety tests compared with traditional methods.

关 键 词：Scenario library generation Cut-in working condition Driver-automation cooperation Performance challenge Significance function 

分 类 号：U46[机械工程—车辆工程]