An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios

Testing autonomous vehicles (AVs) in hazardous scenarios is a crucial technical approach to ensure their safety. A key aspect of this process is the generation of hazard scenarios. In general, such scenarios are generated through cluster analysis of traffic accident data. However, this approach may...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhengping Tan, Qian Wang, Wenhao Hu, Pingfei Li, Liangliang Shi, Hao Feng
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024171046
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850278606300774400
author Zhengping Tan
Qian Wang
Wenhao Hu
Pingfei Li
Liangliang Shi
Hao Feng
author_facet Zhengping Tan
Qian Wang
Wenhao Hu
Pingfei Li
Liangliang Shi
Hao Feng
author_sort Zhengping Tan
collection DOAJ
description Testing autonomous vehicles (AVs) in hazardous scenarios is a crucial technical approach to ensure their safety. A key aspect of this process is the generation of hazard scenarios. In general, such scenarios are generated through cluster analysis of traffic accident data. However, this approach may not fully capture the criticality of the generated scenarios, as it tends to emphasize the statistical characteristics of the data rather than its real-world applicability. This paper proposes a novel method to enhance scenario adaptation by integrating quantization weights with a new clustering algorithm. These weights, representing the correlation between scenario elements and the AV system, are calculated using fuzzy comprehensive evaluation (FCE). The proposed method is applied to 1044 pedestrian accident cases in China, resulting in the identification of nine categories of typical scenarios and corresponding test schemes for both the perception and decision-making systems of AVs. The results show that the new method increases the proportion of critical scenarios by 17.4 % and 13.6 %, respectively, compared to traditional methods. Overall, the critical scenarios generated in this paper can significantly improve the testing efficiency and safety of AVs.
format Article
id doaj-art-5cfb052d4ea14a16ac52e3eab324a7e8
institution OA Journals
issn 2405-8440
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-5cfb052d4ea14a16ac52e3eab324a7e82025-08-20T01:49:26ZengElsevierHeliyon2405-84402025-01-01111e4107310.1016/j.heliyon.2024.e41073An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenariosZhengping Tan0Qian Wang1Wenhao Hu2Pingfei Li3Liangliang Shi4Hao Feng5School of Automobile &Transportation, Xihua University, Chengdu, 610039, China; Sichuan Xihua Jiaotong Forensic Science Center, Chengdu, 610039, China; Corresponding author. School of Automobile &Transportation, Xihua University, Chengdu, 610039, China; Sichuan Xihua Jiaotong Forensic Science Center, Chengdu, 610039, China.School of Automobile &Transportation, Xihua University, Chengdu, 610039, ChinaState Administration for Market Regulation Defective Product Recall Technical Center (DPRC), Beijing, 100101, ChinaSchool of Automobile &Transportation, Xihua University, Chengdu, 610039, China; Sichuan Xihua Jiaotong Forensic Science Center, Chengdu, 610039, ChinaChina Automotive Engineering Research Institute, Chongqing, 401122, ChinaKey Lab of Forensic Science, Ministry of Justice, China (Academy of Forensic Science), Shanghai, 200063, China; Corresponding author. Key Lab of Forensic Science, Ministry of Justice, China (Academy of Forensic Science), Shanghai, 200063, China.Testing autonomous vehicles (AVs) in hazardous scenarios is a crucial technical approach to ensure their safety. A key aspect of this process is the generation of hazard scenarios. In general, such scenarios are generated through cluster analysis of traffic accident data. However, this approach may not fully capture the criticality of the generated scenarios, as it tends to emphasize the statistical characteristics of the data rather than its real-world applicability. This paper proposes a novel method to enhance scenario adaptation by integrating quantization weights with a new clustering algorithm. These weights, representing the correlation between scenario elements and the AV system, are calculated using fuzzy comprehensive evaluation (FCE). The proposed method is applied to 1044 pedestrian accident cases in China, resulting in the identification of nine categories of typical scenarios and corresponding test schemes for both the perception and decision-making systems of AVs. The results show that the new method increases the proportion of critical scenarios by 17.4 % and 13.6 %, respectively, compared to traditional methods. Overall, the critical scenarios generated in this paper can significantly improve the testing efficiency and safety of AVs.http://www.sciencedirect.com/science/article/pii/S2405844024171046Autonomous vehiclesTest scenarioFuzzy comprehensive evaluationPerception systemDecision-making systemClustering algorithm
spellingShingle Zhengping Tan
Qian Wang
Wenhao Hu
Pingfei Li
Liangliang Shi
Hao Feng
An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
Heliyon
Autonomous vehicles
Test scenario
Fuzzy comprehensive evaluation
Perception system
Decision-making system
Clustering algorithm
title An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
title_full An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
title_fullStr An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
title_full_unstemmed An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
title_short An autonomous vehicles’ test case extraction method: Example of vehicle-to-pedestrian scenarios
title_sort autonomous vehicles test case extraction method example of vehicle to pedestrian scenarios
topic Autonomous vehicles
Test scenario
Fuzzy comprehensive evaluation
Perception system
Decision-making system
Clustering algorithm
url http://www.sciencedirect.com/science/article/pii/S2405844024171046
work_keys_str_mv AT zhengpingtan anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT qianwang anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT wenhaohu anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT pingfeili anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT liangliangshi anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT haofeng anautonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT zhengpingtan autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT qianwang autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT wenhaohu autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT pingfeili autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT liangliangshi autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios
AT haofeng autonomousvehiclestestcaseextractionmethodexampleofvehicletopedestrianscenarios