Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313154583> ?p ?o ?g. }
- W4313154583 endingPage "1982" @default.
- W4313154583 startingPage "1964" @default.
- W4313154583 abstract "Autonomous driving has gained much attention from both industry and academia. Currently, Deep Neural Networks (DNNs) are widely used for perception and control in autonomous driving. However, several fatal accidents caused by autonomous vehicles have raised serious safety concerns about autonomous driving models. Some recent studies have successfully used the metamorphic testing technique to detect thousands of potential issues in some popularly used autonomous driving models. However, prior study is limited to a small set of metamorphic relations, which do not reflect rich, real-world traffic scenarios and are also not customizable. This paper presents a novel declarative rule-based metamorphic testing framework called <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> . <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> provides a rule template with natural language syntax, allowing users to flexibly specify an enriched set of testing scenarios based on real-world traffic rules and domain knowledge. <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> automatically parses human-written rules to metamorphic relations using an NLP-based rule parser referring to an ontology list and generates test cases with a variety of image transformation engines. We evaluated <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> on three autonomous driving models. With an enriched set of metamorphic relations, <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> detected a significant number of abnormal model predictions that were not detected by prior work. Through a large-scale human study on Amazon Mechanical Turk, we further confirmed the authenticity of test cases generated by <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RMT</small> and the validity of detected abnormal model predictions." @default.
- W4313154583 created "2023-01-06" @default.
- W4313154583 creator A5019279449 @default.
- W4313154583 creator A5033550181 @default.
- W4313154583 creator A5034162107 @default.
- W4313154583 creator A5035107113 @default.
- W4313154583 creator A5068349578 @default.
- W4313154583 creator A5073806117 @default.
- W4313154583 creator A5081182489 @default.
- W4313154583 date "2023-04-01" @default.
- W4313154583 modified "2023-10-17" @default.
- W4313154583 title "A Declarative Metamorphic Testing Framework for Autonomous Driving" @default.
- W4313154583 cites W1104960690 @default.
- W4313154583 cites W2041650849 @default.
- W4313154583 cites W2042037135 @default.
- W4313154583 cites W2112388853 @default.
- W4313154583 cites W2120770606 @default.
- W4313154583 cites W2139903514 @default.
- W4313154583 cites W2142120379 @default.
- W4313154583 cites W2143702316 @default.
- W4313154583 cites W2150443739 @default.
- W4313154583 cites W2160266024 @default.
- W4313154583 cites W2162882947 @default.
- W4313154583 cites W2165073069 @default.
- W4313154583 cites W2170021941 @default.
- W4313154583 cites W218702423 @default.
- W4313154583 cites W2194775991 @default.
- W4313154583 cites W2324595780 @default.
- W4313154583 cites W2340581863 @default.
- W4313154583 cites W2344795941 @default.
- W4313154583 cites W2417764354 @default.
- W4313154583 cites W2495601248 @default.
- W4313154583 cites W2543296129 @default.
- W4313154583 cites W2594877703 @default.
- W4313154583 cites W2616028256 @default.
- W4313154583 cites W2770057444 @default.
- W4313154583 cites W2775678306 @default.
- W4313154583 cites W2799640043 @default.
- W4313154583 cites W2888307014 @default.
- W4313154583 cites W2888824816 @default.
- W4313154583 cites W2898868990 @default.
- W4313154583 cites W2917321477 @default.
- W4313154583 cites W2954629067 @default.
- W4313154583 cites W2957066083 @default.
- W4313154583 cites W2957905354 @default.
- W4313154583 cites W2962762260 @default.
- W4313154583 cites W2963184890 @default.
- W4313154583 cites W2963208512 @default.
- W4313154583 cites W2963327228 @default.
- W4313154583 cites W2963800363 @default.
- W4313154583 cites W2963913218 @default.
- W4313154583 cites W2968940383 @default.
- W4313154583 cites W2969033227 @default.
- W4313154583 cites W2999691867 @default.
- W4313154583 cites W3043716470 @default.
- W4313154583 cites W3088599576 @default.
- W4313154583 cites W3090608524 @default.
- W4313154583 cites W3091501569 @default.
- W4313154583 cites W3096051537 @default.
- W4313154583 cites W3099444373 @default.
- W4313154583 cites W3102458427 @default.
- W4313154583 cites W3103158293 @default.
- W4313154583 cites W3104896058 @default.
- W4313154583 cites W3123477784 @default.
- W4313154583 cites W3125577182 @default.
- W4313154583 cites W3140377724 @default.
- W4313154583 cites W3184041223 @default.
- W4313154583 cites W3193505628 @default.
- W4313154583 cites W3204732539 @default.
- W4313154583 cites W4308643085 @default.
- W4313154583 doi "https://doi.org/10.1109/tse.2022.3206427" @default.
- W4313154583 hasPublicationYear "2023" @default.
- W4313154583 type Work @default.
- W4313154583 citedByCount "1" @default.
- W4313154583 countsByYear W43131545832023 @default.
- W4313154583 crossrefType "journal-article" @default.
- W4313154583 hasAuthorship W4313154583A5019279449 @default.
- W4313154583 hasAuthorship W4313154583A5033550181 @default.
- W4313154583 hasAuthorship W4313154583A5034162107 @default.
- W4313154583 hasAuthorship W4313154583A5035107113 @default.
- W4313154583 hasAuthorship W4313154583A5068349578 @default.
- W4313154583 hasAuthorship W4313154583A5073806117 @default.
- W4313154583 hasAuthorship W4313154583A5081182489 @default.
- W4313154583 hasBestOaLocation W43131545832 @default.
- W4313154583 hasConcept C119857082 @default.
- W4313154583 hasConcept C134306372 @default.
- W4313154583 hasConcept C154945302 @default.
- W4313154583 hasConcept C177264268 @default.
- W4313154583 hasConcept C186644900 @default.
- W4313154583 hasConcept C199360897 @default.
- W4313154583 hasConcept C204321447 @default.
- W4313154583 hasConcept C33923547 @default.
- W4313154583 hasConcept C36503486 @default.
- W4313154583 hasConcept C41008148 @default.
- W4313154583 hasConcept C60048249 @default.
- W4313154583 hasConceptScore W4313154583C119857082 @default.
- W4313154583 hasConceptScore W4313154583C134306372 @default.
- W4313154583 hasConceptScore W4313154583C154945302 @default.