面向智能汽车-行人交互的虚拟测试场景构建  

Construction of virtual test scenario for intelligent vehicle and pedestrian interaction

作　　者：郭洪艳[1,2] 张家铭[1,2] 刘俊 胡云峰[1,2] GUO Hong-yan;ZHANG Jia-ming;LIU Jun;HU Yun-feng(National Key Laboratory of Automotive Chassis Integration and Bionics,Jilin University,Changchun 130022,China;College of Communication Engineering,Jilin University,Changchun 130022,China;College of Automotive Engineering,Jilin University,Changchun 130022,China)

机构地区：[1]吉林大学汽车底盘集成与仿生全国重点实验室,长春130022 [2]吉林大学通信工程学院,长春130022 [3]吉林大学汽车工程学院,长春130022

出　　处：《吉林大学学报（工学版）》2024年第9期2511-2519,共9页Journal of Jilin University:Engineering and Technology Edition

基　　金：科学技术部科技创新2030-“新一代人工智能”重大项目(2020AAA0108105)。

摘　　要：针对城市工况下的智能汽车与行人交互测试需求,提出了一种综合考虑场景在真实世界中的出现频率及其对人车交互性能挑战程度的场景生成方法。首先,依据智能汽车与行人交互的关键特征从自然驾驶数据集中提取出行人横穿道路原始场景数据;然后,针对加速测试需求设计了基于重要性采样理论的关键场景提取方法,从原始场景中提取并构建针对智能汽车-行人交互测试的重要场景;最后,通过对重要场景与原始场景的数据分布比较,证明本文方法能够有效筛选出驾驶过程中可能对安全性能带来挑战的场景,从而实现加速测试,同时兼顾测试场景的统计特征。To satisfy the testing requirements for intelligent vehicles and pedestrians interaction under urban conditions,a scenario generation method that comprehensively considers the appearance frequency of scenarios in the real world and their challenges to intelligent vehicles performance is proposed.First,the original scenarios are extracted from the natural driving dataset.Then a critical scenario extraction method based on importance sampling theory is designed to extract essential scenarios from the original scenarios according to the accelerated test requirement,and pedestrian crossing road scenarios based on natural driving data are constructed.Finally,comparing the distribution of essential scenarios and original scenarios,the results show that this method can effectively screen out scenarios that may pose challenges to intelligent vehicles safety and it also realizes accelerated testing while retaining the statistical characteristics of test scenarios.

关 键 词：控制科学与工程 场景生成 智能汽车 自然驾驶数据 重要性采样 行人 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]