Adaptive Platoon Offset Optimization Using Machine Learning for Heterogeneous Traffic Conditions

Adaptive Platoon Offset Optimization Using Machine Learning for Heterogeneous Traffic Conditions | 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 Research Article Adaptive Platoon Offset Optimization Using Machine Learning for Heterogeneous Traffic Conditions Om Shrivastava This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9634292/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 traffic congestion in Indian cities imposes heavy economic and envi-ronmental burdens, with commuters facing significant delays at signalized intersections. This paper presents APOO, a predict-then-optimize framework tai-lored for India’s heterogeneous traffic. Unlike Western models, APOO accounts for high two-wheeler volumes (55–70%), poor lane discipline, and monsoon-driven speed reductions. The framework integrates three key components: a recali-brated Robertson’s dispersion model ( β eff = 0 . 50 – 0 . 80 ), an XGBoost regression model using 20 features for uncertainty-aware predictions, and a dynamic offset optimizer. Evaluated on 5,000 calibrated samples, the system achieved a mean absolute error of 7.62 s ( R 2 = 0 . 85 ) and up to a 77% delay reduction in off-peak simulations. SHAP analysis identifies traffic density and two-wheeler percentage as dominant predictors. Requiring no live sensor infrastructure for initial deploy-ment, APOO offers a scalable solution for Indian urban transportation pilot programs. Traffic signal control Platoon offset optimization Machine learning XGBoost Indian urban mobility Intelligent transportation systems Heterogeneous traffic Full Text Additional Declarations The authors declare no competing interests. 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-9634292","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635715913,"identity":"48877e37-c604-4ffb-a355-b9c0035faaea","order_by":0,"name":"Om Shrivastava","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0004-1747-3629","institution":"VIT Bhopal University","correspondingAuthor":true,"prefix":"","firstName":"Om","middleName":"","lastName":"Shrivastava","suffix":""}],"badges":[],"createdAt":"2026-05-06 18:45:29","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9634292/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9634292/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108959610,"identity":"a64d6e6a-a335-4315-841a-43b020ce19e5","added_by":"auto","created_at":"2026-05-11 08:30:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2527786,"visible":true,"origin":"","legend":"","description":"","filename":"APOOCompiled.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9634292/v1_covered_afdf39d7-01bb-4148-8646-0c69a39aabc5.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAdaptive Platoon Offset Optimization Using Machine Learning for Heterogeneous Traffic Conditions\u003c/p\u003e","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":"Traffic signal control, Platoon offset optimization, Machine learning, XGBoost, Indian urban mobility, Intelligent transportation systems, Heterogeneous traffic","lastPublishedDoi":"10.21203/rs.3.rs-9634292/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9634292/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUrban traffic congestion in Indian cities imposes heavy economic and envi-ronmental burdens, with commuters facing significant delays at signalized intersections. This paper presents APOO, a predict-then-optimize framework tai-lored for India\u0026rsquo;s heterogeneous traffic. Unlike Western models, APOO accounts for high two-wheeler volumes (55\u0026ndash;70%), poor lane discipline, and monsoon-driven speed reductions. The framework integrates three key components: a recali-brated Robertson\u0026rsquo;s dispersion model (\u003cb\u003eβ\u003c/b\u003e\u003csub\u003eeff\u003c/sub\u003e\u0026thinsp;\u003cb\u003e=\u0026thinsp;0\u003c/b\u003e.\u003cb\u003e50\u003c/b\u003e\u0026ndash;\u003cb\u003e0\u003c/b\u003e.\u003cb\u003e80\u003c/b\u003e), an XGBoost regression model using 20 features for uncertainty-aware predictions, and a dynamic offset optimizer. Evaluated on 5,000 calibrated samples, the system achieved a mean absolute error of 7.62 s (\u003cb\u003eR\u003c/b\u003e\u003csup\u003e\u003cb\u003e2\u003c/b\u003e\u003c/sup\u003e\u0026thinsp;\u003cb\u003e=\u0026thinsp;0\u003c/b\u003e.\u003cb\u003e85\u003c/b\u003e) and up to a 77% delay reduction in off-peak simulations. SHAP analysis identifies traffic density and two-wheeler percentage as dominant predictors. Requiring no live sensor infrastructure for initial deploy-ment, APOO offers a scalable solution for Indian urban transportation pilot programs.\u003c/p\u003e","manuscriptTitle":"Adaptive Platoon Offset Optimization Using Machine Learning for Heterogeneous Traffic Conditions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-11 08:27:22","doi":"10.21203/rs.3.rs-9634292/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":"bb6a6ed4-1bdf-4d0d-9fb3-c9d0edc0e2f4","owner":[],"postedDate":"May 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T08:27:26+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-11 08:27:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9634292","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9634292","identity":"rs-9634292","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}