Critical scenario identification for realistic testing of autonomous driving systems
(2023) In Software Quality Journal 31(2). p.441-469- Abstract
Autonomous driving has become an important research area for road traffic, whereas testing of autonomous driving systems to ensure a safe and reliable operation remains an open challenge. Substantial real-world testing or massive driving data collection does not scale since the potential test scenarios in real-world traffic are infinite, and covering large shares of them in the test is impractical. Thus, critical ones have to be prioritized. We have developed an approach for critical test scenario identification and in this study, we implement the approach and validate it on two real autonomous driving systems from industry by integrating it into their tool-chain. Our main contribution in this work is the demonstration and validation of... (More)
Autonomous driving has become an important research area for road traffic, whereas testing of autonomous driving systems to ensure a safe and reliable operation remains an open challenge. Substantial real-world testing or massive driving data collection does not scale since the potential test scenarios in real-world traffic are infinite, and covering large shares of them in the test is impractical. Thus, critical ones have to be prioritized. We have developed an approach for critical test scenario identification and in this study, we implement the approach and validate it on two real autonomous driving systems from industry by integrating it into their tool-chain. Our main contribution in this work is the demonstration and validation of our approach for critical scenario identification for testing real autonomous driving systems.
(Less)
- author
- Song, Qunying LU ; Tan, Kaige ; Runeson, Per LU and Persson, Stefan LU
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Autonomous driving, Critical scenario identification, Software testing, Test scenario generation
- in
- Software Quality Journal
- volume
- 31
- issue
- 2
- pages
- 441 - 469
- publisher
- Springer
- external identifiers
-
- scopus:85143235313
- ISSN
- 0963-9314
- DOI
- 10.1007/s11219-022-09604-2
- project
- Software testing of autonomous systems
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2022, The Author(s).
- id
- 84f5d57b-4ff6-4e76-9e04-2a5861aeb2e5
- date added to LUP
- 2022-12-12 08:02:45
- date last changed
- 2024-06-13 14:32:00
@article{84f5d57b-4ff6-4e76-9e04-2a5861aeb2e5, abstract = {{<p>Autonomous driving has become an important research area for road traffic, whereas testing of autonomous driving systems to ensure a safe and reliable operation remains an open challenge. Substantial real-world testing or massive driving data collection does not scale since the potential test scenarios in real-world traffic are infinite, and covering large shares of them in the test is impractical. Thus, critical ones have to be prioritized. We have developed an approach for critical test scenario identification and in this study, we implement the approach and validate it on two real autonomous driving systems from industry by integrating it into their tool-chain. Our main contribution in this work is the demonstration and validation of our approach for critical scenario identification for testing real autonomous driving systems.</p>}}, author = {{Song, Qunying and Tan, Kaige and Runeson, Per and Persson, Stefan}}, issn = {{0963-9314}}, keywords = {{Autonomous driving; Critical scenario identification; Software testing; Test scenario generation}}, language = {{eng}}, number = {{2}}, pages = {{441--469}}, publisher = {{Springer}}, series = {{Software Quality Journal}}, title = {{Critical scenario identification for realistic testing of autonomous driving systems}}, url = {{http://dx.doi.org/10.1007/s11219-022-09604-2}}, doi = {{10.1007/s11219-022-09604-2}}, volume = {{31}}, year = {{2023}}, }