Safety testing and enhancement of urban traffic signals for safe deployment

Safety testing and enhancement of urban traffic signals for safe deployment | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Safety testing and enhancement of urban traffic signals for safe deployment Xiaocai Zhang, Neema Nassir, Zhe Xiao, Wenbin Zhang, Milad Haghani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8336185/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Urban deployments of AI-driven, adaptive traffic signal control (TSC) systems are advancing rapidly, yet systematic pre-deployment safety validation of these "black-box" models remains underexplored. Without rigorous safety validation, these models may pose potential risks when deployed at real-world intersections. We present a model-agnostic framework that adversarially tests any given TSC model within a virtual traffic environment, using deep reinforcement learning to expose their safety-critical "failure points" in travel demand distributions. The expected safety risk of each given model is quantified through a metric that integrates surrogate crash severity with the empirical likelihood of hazardous demand patterns, grounded in over 11 years of real-world traffic signal volume data. Building on these insights, we propose a safety-critical re-training (SCRT) mechanism for safety-underperforming models, which selectively enriches training with the uncovered "failure point" to enhance robustness without altering the model architecture. Across diverse scenarios, this approach consistently reduces expected safety risk following SCRT and significantly outperforms naive re-training that disregards safety-critical demand patterns. Importantly, these safety gains are achieved with only slight to modest impacts on operational efficiency. By operationalizing a "test-before-deploy" safety gate, our framework provides a practical pathway from design-time optimization to deployment-time safety assurance, ultimately advancing safer real-world adoption of AI-driven TSC systems. Physical sciences/Engineering/Civil engineering Physical sciences/Mathematics and computing/Computer science Scientific community and society/Business and industry/Technology Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8336185","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":573225431,"identity":"8431dd9a-7096-4643-9bc2-70c55ef5ae60","order_by":0,"name":"Xiaocai Zhang","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-3783-6560","institution":"The University of Melbourne","correspondingAuthor":true,"prefix":"","firstName":"Xiaocai","middleName":"","lastName":"Zhang","suffix":""},{"id":573225432,"identity":"14e0957b-9f0b-47c0-93ba-8f74a97db612","order_by":1,"name":"Neema Nassir","email":"","orcid":"","institution":"The University of Melbourne","correspondingAuthor":false,"prefix":"","firstName":"Neema","middleName":"","lastName":"Nassir","suffix":""},{"id":573225433,"identity":"4c76e471-46d4-488d-b717-d988ea16731e","order_by":2,"name":"Zhe Xiao","email":"","orcid":"","institution":"https://ror.org/02n0ejh50, https://ror.org/036wvzt09, ASTAR","correspondingAuthor":false,"prefix":"","firstName":"Zhe","middleName":"","lastName":"Xiao","suffix":""},{"id":573225434,"identity":"f50bff30-c5b6-42e3-b8b5-c3f10978c59b","order_by":3,"name":"Wenbin Zhang","email":"","orcid":"","institution":"Florida International University","correspondingAuthor":false,"prefix":"","firstName":"Wenbin","middleName":"","lastName":"Zhang","suffix":""},{"id":573225435,"identity":"a8205764-7bfd-473c-94a7-5bcc11fe8983","order_by":4,"name":"Milad Haghani","email":"","orcid":"","institution":"The University of Melbourne","correspondingAuthor":false,"prefix":"","firstName":"Milad","middleName":"","lastName":"Haghani","suffix":""}],"badges":[],"createdAt":"2025-12-11 11:35:56","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8336185/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8336185/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100130294,"identity":"f19d5132-7b03-456b-b59b-5d46083f0c3d","added_by":"auto","created_at":"2026-01-13 10:07:21","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2981882,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNaturev1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8336185/v1/f5aaf2467b2d524a248e7faf.pdf"},{"id":100130293,"identity":"bfa5a0bd-2ca7-40f2-a79b-b03c8e1a9ff0","added_by":"auto","created_at":"2026-01-13 10:07:21","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6747,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25099588.json","url":"https://assets-eu.researchsquare.com/files/rs-8336185/v1/677b1eb53357514fc4c71716.json"},{"id":104400800,"identity":"a434fcb2-2220-4f86-bb9c-99b794e5514f","added_by":"auto","created_at":"2026-03-11 12:11:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2036914,"visible":true,"origin":"","legend":"Article File","description":"","filename":"SpringerNaturev1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8336185/v1_covered_02464829-ae34-455f-851d-78fc9be33f7b.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Safety testing and enhancement of urban traffic signals for safe deployment","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8336185/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8336185/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Urban deployments of AI-driven, adaptive traffic signal control (TSC) systems are advancing rapidly, yet systematic pre-deployment safety validation of these \"black-box\" models remains underexplored. Without rigorous safety validation, these models may pose potential risks when deployed at real-world intersections. We present a model-agnostic framework that adversarially tests any given TSC model within a virtual traffic environment, using deep reinforcement learning to expose their safety-critical \"failure points\" in travel demand distributions. The expected safety risk of each given model is quantified through a metric that integrates surrogate crash severity with the empirical likelihood of hazardous demand patterns, grounded in over 11 years of real-world traffic signal volume data. Building on these insights, we propose a safety-critical re-training (SCRT) mechanism for safety-underperforming models, which selectively enriches training with the uncovered \"failure point\" to enhance robustness without altering the model architecture. Across diverse scenarios, this approach consistently reduces expected safety risk following SCRT and significantly outperforms naive re-training that disregards safety-critical demand patterns. Importantly, these safety gains are achieved with only slight to modest impacts on operational efficiency. By operationalizing a \"test-before-deploy\" safety gate, our framework provides a practical pathway from design-time optimization to deployment-time safety assurance, ultimately advancing safer real-world adoption of AI-driven TSC systems.","manuscriptTitle":"Safety testing and enhancement of urban traffic signals for safe deployment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-13 10:07:16","doi":"10.21203/rs.3.rs-8336185/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9b21dc68-2a82-46be-a52d-4926df581035","owner":[],"postedDate":"January 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60988553,"name":"Physical sciences/Engineering/Civil engineering"},{"id":60988554,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":60988555,"name":"Scientific community and society/Business and industry/Technology"}],"tags":[],"updatedAt":"2026-03-03T15:45:49+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-13 10:07:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8336185","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8336185","identity":"rs-8336185","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}