A Survey of Scenario Generation for Automated Vehicle Testing and Validation

This survey explores the evolution of test scenario generation for autonomous vehicles (AVs), distinguishing between non-adaptive and adaptive scenario approaches. Non-adaptive scenarios, where dynamic objects follow predetermined scripts, provide repeatable and reliable tests but fail to capture th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyu Wang, Jing Ma, Edmund M-K Lai
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/16/12/480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241705224175616
author Ziyu Wang
Jing Ma
Edmund M-K Lai
author_facet Ziyu Wang
Jing Ma
Edmund M-K Lai
author_sort Ziyu Wang
collection DOAJ
description This survey explores the evolution of test scenario generation for autonomous vehicles (AVs), distinguishing between non-adaptive and adaptive scenario approaches. Non-adaptive scenarios, where dynamic objects follow predetermined scripts, provide repeatable and reliable tests but fail to capture the complexity and unpredictability of real-world traffic interactions. In contrast, adaptive scenarios, which adapt in real time to environmental changes, offer a more realistic simulation of traffic conditions, enabling the assessment of an AV system’s adaptability, safety, and robustness. The shift from non-adaptive to adaptive scenarios is increasingly emphasized in AV research, to better evaluate system performance in complex environments. However, generating adaptive scenario is more complex and faces challenges. These include the limited diversity in behaviors, low model interpretability, and high resource requirements. Future research should focus on enhancing the efficiency of adaptive scenario generation and developing comprehensive evaluation metrics to improve the realism and effectiveness of AV testing.
format Article
id doaj-art-58c81209f36a433b9be837fb1300c4cb
institution OA Journals
issn 1999-5903
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-58c81209f36a433b9be837fb1300c4cb2025-08-20T02:00:33ZengMDPI AGFuture Internet1999-59032024-12-01161248010.3390/fi16120480A Survey of Scenario Generation for Automated Vehicle Testing and ValidationZiyu Wang0Jing Ma1Edmund M-K Lai2Department of Data Science and Artificial Intelligence, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandDepartment of Data Science and Artificial Intelligence, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandDepartment of Data Science and Artificial Intelligence, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandThis survey explores the evolution of test scenario generation for autonomous vehicles (AVs), distinguishing between non-adaptive and adaptive scenario approaches. Non-adaptive scenarios, where dynamic objects follow predetermined scripts, provide repeatable and reliable tests but fail to capture the complexity and unpredictability of real-world traffic interactions. In contrast, adaptive scenarios, which adapt in real time to environmental changes, offer a more realistic simulation of traffic conditions, enabling the assessment of an AV system’s adaptability, safety, and robustness. The shift from non-adaptive to adaptive scenarios is increasingly emphasized in AV research, to better evaluate system performance in complex environments. However, generating adaptive scenario is more complex and faces challenges. These include the limited diversity in behaviors, low model interpretability, and high resource requirements. Future research should focus on enhancing the efficiency of adaptive scenario generation and developing comprehensive evaluation metrics to improve the realism and effectiveness of AV testing.https://www.mdpi.com/1999-5903/16/12/480autonomous vehiclesdriving scenariosadaptive testsautomatic scenario generation
spellingShingle Ziyu Wang
Jing Ma
Edmund M-K Lai
A Survey of Scenario Generation for Automated Vehicle Testing and Validation
Future Internet
autonomous vehicles
driving scenarios
adaptive tests
automatic scenario generation
title A Survey of Scenario Generation for Automated Vehicle Testing and Validation
title_full A Survey of Scenario Generation for Automated Vehicle Testing and Validation
title_fullStr A Survey of Scenario Generation for Automated Vehicle Testing and Validation
title_full_unstemmed A Survey of Scenario Generation for Automated Vehicle Testing and Validation
title_short A Survey of Scenario Generation for Automated Vehicle Testing and Validation
title_sort survey of scenario generation for automated vehicle testing and validation
topic autonomous vehicles
driving scenarios
adaptive tests
automatic scenario generation
url https://www.mdpi.com/1999-5903/16/12/480
work_keys_str_mv AT ziyuwang asurveyofscenariogenerationforautomatedvehicletestingandvalidation
AT jingma asurveyofscenariogenerationforautomatedvehicletestingandvalidation
AT edmundmklai asurveyofscenariogenerationforautomatedvehicletestingandvalidation
AT ziyuwang surveyofscenariogenerationforautomatedvehicletestingandvalidation
AT jingma surveyofscenariogenerationforautomatedvehicletestingandvalidation
AT edmundmklai surveyofscenariogenerationforautomatedvehicletestingandvalidation