Implicit Semantic Control Manifolds for Learning-Enabled Multi-UAV Coordination

Implicit Semantic Control Manifolds for Learning-Enabled Multi-UAV Coordination | 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 Implicit Semantic Control Manifolds for Learning-Enabled Multi-UAV Coordination Bryan Starbuck, Won Jang, Saee Sholapurkar, Bert Bras This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9182035/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 We present an implicit semantic control representation for learning-enabled autonomous flight in which biologically inspired coordination behaviors are embedded within a large language model (LLM) and constrained by a six parameter motion–LED control manifold derived from nonlinear six-degree-of freedom quadrotor dynamics. The framework encodes behavioral constraints as an implicit generative representation that integrates model-based flight physics with data-driven policy learning, enabling decentralized aerial agents to generate dynamically feasible actions and semantically consistent visual communication under radio-frequency-degraded conditions. A high-capacity teacher LLM is trained within this manifold and distilled and quantized into a compact stu dent model suitable for edge deployment on lightweight aerial platforms. The teacher, student, and classical regression baselines (multilayer perceptron and k nearest neighbor) are evaluated in a closed-loop target search simulation of 200 trials with both nominal on-manifold inputs and corrupted off-manifold pertur bations. LLM-based policies achieve higher semantic robustness (86.0% teacher, 83.2% student) than kNN (71.0%) and MLP (65.0%) and degrade more grace fully under severe corruption. The teacher and student also reduce final position error (8.37 m and 10.46 m) relative to kNN (14.02 m) and MLP (15.54 m), while distillation reduces mean inference latency from 5.24 s to 2.81 s. multi-UAV systems autonomous aerial robotics implicit representations learning-enabled control large language models for robotics knowledge distillation bio-inspired control swarm communication 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-9182035","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":609667748,"identity":"0efa3c18-bac3-41b8-9257-8948e50fc062","order_by":0,"name":"Bryan Starbuck","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYBACAwSTB4gP2ICZzEDM2EBAiwRUSxoDAxuJWg4T1mIufcbwcwFDXR3/7LPHJH6cOW/XP7/5IFDERnbDAexaLPtyjKVnMByWkDiXlybZc+N28oxjbMlAkTRjXFoMzvAYSPMwHJBgOMNjJs3w4XYywzEeM2YehsOJeLQY/+ZhqJOQh2g5lyx/jP8bUMt/fFrMgLYwS4AZDDcO2Bkc42EDajmAU4tlD1uZNY/BYcmNZ/iSLXvOJCcYHkszluYxSDaeiUOLOQ/z5ts8FXX8cmd4D974cczOXu7w4YefeSrsZPtwaGFg4DBASQOJDRAH41IOAuwPULj2+NSOglEwCkbByAQADF1XujF/1gYAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-1977-3225","institution":"Georgia Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Bryan","middleName":"","lastName":"Starbuck","suffix":""},{"id":609667749,"identity":"d3b61650-6f24-4d4c-95cd-8ce1b4b6200c","order_by":1,"name":"Won Jang","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Won","middleName":"","lastName":"Jang","suffix":""},{"id":609667750,"identity":"e121aad1-1ea3-4709-941f-5ad32cf386a0","order_by":2,"name":"Saee Sholapurkar","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Saee","middleName":"","lastName":"Sholapurkar","suffix":""},{"id":609667751,"identity":"cf74824a-8f60-40b6-8d36-bf200fd6b582","order_by":3,"name":"Bert Bras","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bert","middleName":"","lastName":"Bras","suffix":""}],"badges":[],"createdAt":"2026-03-20 21:30:04","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-9182035/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9182035/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105564910,"identity":"e0a2d501-b94b-444c-8971-308a4fdd6f47","added_by":"auto","created_at":"2026-03-27 12:51:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1544124,"visible":true,"origin":"","legend":"","description":"","filename":"ImplicitSemanticControlManifoldsforLearningEnabledMultiUAVCoordination.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9182035/v1_covered_6cdb30e4-a753-4804-a21c-970814e23e72.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eImplicit Semantic Control Manifolds for Learning-Enabled Multi-UAV Coordination\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Georgia Institute of Technology","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":"multi-UAV systems, autonomous aerial robotics, implicit representations, learning-enabled control, large language models for robotics, knowledge distillation, bio-inspired control, swarm communication","lastPublishedDoi":"10.21203/rs.3.rs-9182035/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9182035/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe present an implicit semantic control representation for learning-enabled autonomous flight in which biologically inspired coordination behaviors are embedded within a large language model (LLM) and constrained by a six parameter motion–LED control manifold derived from nonlinear six-degree-of freedom quadrotor dynamics. The framework encodes behavioral constraints as an implicit generative representation that integrates model-based flight physics with data-driven policy learning, enabling decentralized aerial agents to generate dynamically feasible actions and semantically consistent visual communication under radio-frequency-degraded conditions. A high-capacity teacher LLM is trained within this manifold and distilled and quantized into a compact stu dent model suitable for edge deployment on lightweight aerial platforms. The teacher, student, and classical regression baselines (multilayer perceptron and k nearest neighbor) are evaluated in a closed-loop target search simulation of 200 trials with both nominal on-manifold inputs and corrupted off-manifold pertur bations. LLM-based policies achieve higher semantic robustness (86.0% teacher, 83.2% student) than kNN (71.0%) and MLP (65.0%) and degrade more grace fully under severe corruption. The teacher and student also reduce final position error (8.37 m and 10.46 m) relative to kNN (14.02 m) and MLP (15.54 m), while distillation reduces mean inference latency from 5.24 s to 2.81 s.\u003c/p\u003e","manuscriptTitle":"Implicit Semantic Control Manifolds for Learning-Enabled Multi-UAV Coordination","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 04:02:25","doi":"10.21203/rs.3.rs-9182035/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":"3a84b0ff-13be-4a9c-9f77-e5ad15f77cbd","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-24T04:02:25+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 04:02:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9182035","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9182035","identity":"rs-9182035","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}