Dynamic Testing for Autonomous Vehicles Using Random Quasi Monte Carlo

doi:10.1109/TIV.2024.3358329

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	Dynamic Testing for Autonomous Vehicles Using Random Quasi Monte Carlo
	Ge, Jingwei 1; Zhang, Jiawei 1; Chang, Cheng 1; Zhang, Yi 2,3,4; Yao, Danya 1; Tian, Yonglin 5; Li, Li 6
刊名	IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
	2024-03-01
卷号	9 期号:3 页码:4480-4492
关键词	Autonomous vehicles Automation intelligence testing multi-rounds testing random quasi Monte Carlo
ISSN号	2379-8858
DOI	10.1109/TIV.2024.3358329
通讯作者	Li, Li(li-li@tsinghua.edu.cn)
英文摘要	The substantial resource usage required to create ample scenarios for testing Autonomous Vehicles (AV) presents a bottleneck in their implementation. At present, research relies on sampling the driving behaviour of Surrounding Vehicles (SV) based on naturalistic datasets in simulation. However, these methods still generate huge amounts of scenarios, making it impossible to synthetically evaluate AV intelligence in a very small number of tests (especially in real-world situations). Simultaneously, the unknown distribution of critical scenarios leads to the problem that more critical scenarios cannot be accurately sampled. In this article, a novel optimization problem is described and a dynamic scenario sampling method is proposed to cover more critical scenarios with finite samples. First, the sampling space is constructed by extracting the behavioural model parameters of the SVs. Second, multiple rounds of sampling are carried out successively to learn the distribution of critical scenarios, which in turn gradually improves the coverage of the critical scenarios. To do this, in each round, we divide the sampling space into several subspaces using two-step sampling, sample the scenarios using Random Quasi Monte Carlo (RQMC), evaluate the criticality of the subspace, and then use the evaluation results to guide the selection of the sampling space for the next round. The purpose of RQMC is to uniformly sample in the critical subspace rather than Standard Monte Carlo (SMC). Experimental results show that our method can better narrow the gap with the distribution of critical scenarios and discover more critical scenarios when compared to the baseline method.
资助项目	National Key Research and Development Program of China
WOS关键词	INTELLIGENCE
WOS研究方向	Computer Science ; Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001214544700002
资助机构	National Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58382]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Li, Li
作者单位	1.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China 2.Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol BNRist, Dept Automat, Beijing 100084, Peoples R China 3.Tsinghua Berkeley Shenzhen Inst TBSI, Shenzhen 518055, Peoples R China 4.Jiangsu Prov Collaborat Innovat Ctr Modern Urban T, Nanjing 210096, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 6.Tsinghua Univ, Dept Automat, BNRIST, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Ge, Jingwei,Zhang, Jiawei,Chang, Cheng,et al. Dynamic Testing for Autonomous Vehicles Using Random Quasi Monte Carlo[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(3):4480-4492.
APA	Ge, Jingwei.,Zhang, Jiawei.,Chang, Cheng.,Zhang, Yi.,Yao, Danya.,...&Li, Li.(2024).Dynamic Testing for Autonomous Vehicles Using Random Quasi Monte Carlo.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(3),4480-4492.
MLA	Ge, Jingwei,et al."Dynamic Testing for Autonomous Vehicles Using Random Quasi Monte Carlo".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.3(2024):4480-4492.