考虑风险场景的驾驶员紧急制动模型研究  

Driver Emergency Braking Model Considering Risk Scenarios

作　　者：郑建明 华一丁 张宇飞 路文豪 石佩鑫 覃斌 赵目龙 ZHENG Jianming;HUAYiding;ZHANG Yufei;LUWenhao;SHI Peixin;QIN Bin;ZHAO Mulong(General Research and Development Institute,China FAWCorporation Limited,Changchun 130000,China;China Automotive Technology&Research Center Co Ltd,Tianjin 300300,China)

机构地区：[1]中国第一汽车股份有限公司,研发总院,长春130000 [2]中国汽车技术研究中心有限公司,天津300300

出　　处：《交通运输系统工程与信息》2024年第6期219-231,253,共14页Journal of Transportation Systems Engineering and Information Technology

摘　　要：针对自动驾驶汽车安全性评估缺失与人类驾驶能力对比的问题,本文提出一种考虑风险场景的驾驶员紧急制动模型。首先,分析环境车辆行为位置及交通事故库,得到同车道前车紧急制动、相邻车道前车紧急切入以及同车道前车紧急切出后遇静止前前车3个风险场景;其次,总结得出最大减速度、制动效能提升时间及决策响应时间这3个制动模型关键参数及提取方法;通过场地实车及驾驶模拟器仿真两种实验方式联合标定关键参数;通过全集泛化风险场景变量,明确风险场景下碰撞与未碰撞的边界,构建驾驶员紧急制动模型;通过对泛化结果中的典型场景进行实车实验,结果表明,本文提出的模型与人类驾驶能力相似度为77.8%。本文采集参数可为后续其他驾驶模型研究提供参考,所构模型可对自动驾驶汽车的准入及安全性判断提供支撑。In order to address the issue of insufficient safety assessment of autonomous vehicles compared to human driving,this study presents a driver emergency braking model that takes into account various risk scenarios.Firstly,through an analysis of environmental vehicle behavior,positioning,and traffic accident databases,three risk scenarios are identified:emergency braking of the front vehicle in the same lane,emergency lane change of the front vehicle in the adjacent lane,and encountering a stationary front vehicle after emergency lane change of the front vehicle in the same lane.Secondly,the study summarizes three key parameters of the braking model:maximum deceleration,braking efficiency improvement time,and decision response time,along with their extraction methods.These parameters were calibrated using both real vehicle testing and driving simulator experiments.The study defines the boundary between collision and non-collision in the risk scenario through the generalization of risk scenario variables and constructs the driver emergency braking model.Real vehicle testing of the typical scenarios derived from the generalization result shows that the proposed model has a 77.8%similarity to human driving capability.The parameters collected in this study can serve as a reference for future research on other driving models,and the constructed model can provide support for the assessment of the access and safety of autonomous vehicles.

关 键 词：交通工程 紧急制动模型 泛化仿真 驾驶能力边界 风险场景 

分 类 号：U461[机械工程—车辆工程]