{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:08:00Z","timestamp":1782846480948,"version":"3.54.5"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"FT","award":["240100269"],"award-info":[{"award-number":["240100269"]}]},{"name":"DP","award":["210102447"],"award-info":[{"award-number":["210102447"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Simulation-based testing of autonomous driving systems (ADS) must uncover realistic and diverse failures in dense, heterogeneous traffic. However, existing search-based seeding methods (e.g., genetic algorithms) struggle in high-dimensional spaces, often collapsing to limited modes and missing many failure scenarios. We present PtoP, a framework that combines adaptive random seed generation with Stein Variational Gradient Descent (SVGD) to produce diverse, failure-inducing initial conditions. SVGD balances attraction toward high-risk regions and repulsion among particles, yielding risk-seeking yet well-distributed seeds across multiple failure modes. PtoP is plug-and-play and enhances existing online testing methods (e.g., reinforcement learning--based testers) by providing principled seeds. Evaluation in CARLA on two industry-grade ADS (Apollo, Autoware) and a native end-to-end system shows that PtoP improves safety violation rate (up to 27.68%), scenario diversity (9.6%), and map coverage (16.78%) over baselines.<\/jats:p>","DOI":"10.1145\/3808153","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"3298-3320","source":"Crossref","is-referenced-by-count":0,"title":["From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5442-3656","authenticated-orcid":false,"given":"Linfeng","family":"Liang","sequence":"first","affiliation":[{"name":"Macquarie University, School of Computing, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5456-3827","authenticated-orcid":false,"given":"Xiao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Macquarie University, School of Computing, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3578-0994","authenticated-orcid":false,"given":"Tsong Yueh","family":"Chen","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2572-2355","authenticated-orcid":false,"given":"Xi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Macquarie University, School of Computing, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Apollo: Open Source Autonomous Driving, howpublished = https:\/\/github.com\/ ApolloAuto\/apollo, note = Accessed: 2019-02-11","author":"Baidu Apollo","year":"2017","unstructured":"Baidu Apollo team (2017), Apollo: Open Source Autonomous Driving, howpublished = https:\/\/github.com\/ ApolloAuto\/apollo, note = Accessed: 2019-02-11."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238192"},{"key":"e_1_2_1_3_1","unstructured":"ApolloAuto. 2024. Apollo. https:\/\/github.com\/ApolloAuto\/apollo."},{"key":"e_1_2_1_4_1","unstructured":"Robyn G Attewell and Stephen Ginpil. 1994. Crashes resulting in car occupant fatalities: Frontal impacts. Number CR 138. Australian Government Pub. Service."},{"key":"e_1_2_1_5_1","volume-title":"Communications and the Arts","author":"Australian Government Department of Infrastructure, Transport, Regional Development","year":"2025","unstructured":"Australian Government Department of Infrastructure, Transport, Regional Development, Communications and the Arts. 2025. Monthly Road Deaths -Road Safety Data Hub. https:\/\/datahub.roadsafety.gov.au\/progress-reporting\/monthlyroad-deaths Accessed: 2025-01-27."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2014.2372785"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970311"},{"key":"e_1_2_1_8_1","volume-title":"Ten ways autonomous driving could redefine the automotive world","author":"Bertoncello Michele","year":"2015","unstructured":"Michele Bertoncello and Dominik Wee. 2015. Ten ways autonomous driving could redefine the automotive world. McKinsey & Company 6 (2015)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510466"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1145735.1145745"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660792"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse55347.2025.00114"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2017.7995782"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-"},{"key":"e_1_2_1_16_1","volume-title":"Target: Traffic rule-based test generation for autonomous driving systems. arXiv preprint arXiv:2305.06018","author":"Deng Yao","year":"2023","unstructured":"Yao Deng, Jiaohong Yao, Zhi Tu, Xi Zheng, Mengshi Zhang, and Tianyi Zhang. 2023. Target: Traffic rule-based test generation for autonomous driving systems. arXiv preprint arXiv:2305.06018 (2023)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549152"},{"key":"e_1_2_1_18_1","volume-title":"Conference on robot learning. PMLR, 1-16","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on robot learning. PMLR, 1-16."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/aitest52744.2021.00030"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Shuo Feng Haowei Sun Xintao Yan et al. 2023. Dense reinforcement learning for safety validation of autonomous vehicles. Nature 615 7953 (2023). https:\/\/doi.org\/10.1038\/s41586-023-05732-2 10.1038\/s41586-023-05732-2","DOI":"10.1038\/s41586-023-05732-2"},{"key":"e_1_2_1_21_1","volume-title":"Autoware: Open-Source Software for Autonomous Driving. https:\/\/github.com\/ autowarefoundation\/autoware. Accessed: 2025-02-18.","author":"Foundation Autoware","year":"2025","unstructured":"Autoware Foundation. 2025. Autoware: Open-Source Software for Autonomous Driving. https:\/\/github.com\/ autowarefoundation\/autoware. Accessed: 2025-02-18."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338942"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_20"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/iv47402.2020.9304636"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2023.3309610"},{"key":"e_1_2_1_26_1","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2591-2603","author":"Huai Yuqi","year":"2023","unstructured":"Yuqi Huai, Yuntianyi Chen, Sumaya Almanee, Tuan Ngo, Xiang Liao, Ziwen Wan, Qi Alfred Chen, and Joshua Garcia. 2023. Doppelg\u00e4nger test generation for revealing bugs in autonomous driving software. In 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2591-2603."},{"key":"e_1_2_1_27_1","volume-title":"2018 IEEE International symposium on software reliability engineering workshops (ISSREW). IEEE, 118-123","author":"Kl\u00fcck Florian","year":"2018","unstructured":"Florian Kl\u00fcck, Yihao Li, Mihai Nica, Jianbo Tao, and Franz Wotawa. 2018. Using ontologies for test suites generation for automated and autonomous driving functions. In 2018 IEEE International symposium on software reliability engineering workshops (ISSREW). IEEE, 118-123."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2018.8500400"},{"key":"e_1_2_1_29_1","first-page":"1","article-title":"Understanding the fatal tesla accident on autopilot and the nhtsa probe","volume":"1","author":"Lambert Fred","year":"2016","unstructured":"Fred Lambert. 2016. Understanding the fatal tesla accident on autopilot and the nhtsa probe. Electrek, July 1 (2016), 1.","journal-title":"Electrek"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00025"},{"key":"e_1_2_1_31_1","first-page":"329","article-title":"Exploiting open-endedness to solve problems through the search for novelty","author":"Lehman Joel","year":"2008","unstructured":"Joel Lehman, Kenneth O Stanley, et al. 2008. Exploiting open-endedness to solve problems through the search for novelty.. In ALIFE. 329-336.","journal-title":"ALIFE."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/issre5003"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-68263-4"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.19625701"},{"key":"e_1_2_1_35_1","volume-title":"RLaGA: A Reinforcement Learning Augmented Genetic Algorithm For Searching Real and Diverse Marker-Based Landing Violations. arXiv preprint arXiv:2310.07378","author":"Liang Linfeng","year":"2023","unstructured":"Linfeng Liang, Yao Deng, Kye Morton, Valtteri Kallinen, Alice James, Avishkar Seth, Endrowednes Kuantama, Subhas Mukhopadhyay, Richard Han, and Xi Zheng. 2023. RLaGA: A Reinforcement Learning Augmented Genetic Algorithm For Searching Real and Diverse Marker-Based Landing Violations. arXiv preprint arXiv:2310.07378 (2023)."},{"key":"e_1_2_1_36_1","volume-title":"Stein variational gradient descent: A general purpose bayesian inference algorithm. Advances in neural information processing systems 29","author":"Liu Qiang","year":"2016","unstructured":"Qiang Liu and Dilin Wang. 2016. Stein variational gradient descent: A general purpose bayesian inference algorithm. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2022.3150788"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/dsa56465.2022.00012"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3534064"},{"key":"e_1_2_1_40_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/icst.2015.7102604"},{"key":"e_1_2_1_42_1","volume-title":"General citation guidelines.","year":"2014","unstructured":"Prolific. 2024. General citation guidelines. Available at https:\/\/www.prolific.com. First released in 2014. Copyright 2024. Located in London, UK. Version: Current month(s) and year(s) of use.."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01604"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3416792\/mm1"},{"key":"e_1_2_1_45_1","unstructured":"Inc. Tesla. 2024. Autopilot. https:\/\/www.tesla.com\/en_AU\/autopilot Accessed: 2024-11-13."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549100"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2022"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:19:03Z","timestamp":1782843543000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":47,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808153"],"URL":"https:\/\/doi.org\/10.1145\/3808153","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}