Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms

Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms | 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 Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms Pingping Qu, Huan Liu, Song Xu, Tengli Yu, Yunhao Chen, Ershen Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6508231/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Collaborative path planning for UAV swarms in dynamic uncertain environments faces dual challenges of partial observability and cooperation mechanism design. The decentralized decision-making nature of multi-agent reinforcement learning (MARL) establishes a novel theoretical framework for autonomous coordination of heterogeneous UAV swarms under partially observable conditions. This paper proposes a reciprocity reward-enhanced multi-agent deep reinforcement learning method (PMI-MADDPG) that optimizes UAV cooperative decision-making through a centralized training with decentralized execution framework. By constructing a partially observable Markov decision process (POMDP) model, we design continuous action spaces considering UAV kinematic constraints, and quantify inter-agent state dependencies using pointwise mutual information. A novel cooperative coefficient estimation network is introduced to dynamically balance individual rewards and swarm-level objectives. Simulation results demonstrate that compared to conventional multi-agent methods, PMI-MADDPG shows significant advantages in task reward acquisition and network convergence efficiency, while revealing the impact of UAV quantity on system stability. The proposed approach provides an innovative solution for cooperative path planning tasks of UAV swarms in complex environments. UAV swarm path planning multi-agent reinforcement learning partially observable Markov decision process reward shaping Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 07 Oct, 2025 Reviewers invited by journal 05 Oct, 2025 Editor assigned by journal 05 Jun, 2025 Submission checks completed at journal 25 Apr, 2025 First submitted to journal 22 Apr, 2025 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-6508231","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":529968479,"identity":"36133631-40b3-434a-8770-c18cacdef296","order_by":0,"name":"Pingping Qu","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Pingping","middleName":"","lastName":"Qu","suffix":""},{"id":529968480,"identity":"1d7b2148-540f-4c2c-8ba3-73c86efd4e28","order_by":1,"name":"Huan Liu","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Huan","middleName":"","lastName":"Liu","suffix":""},{"id":529968481,"identity":"fb43e9af-d48a-47cb-88a1-00e497928f5c","order_by":2,"name":"Song Xu","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Xu","suffix":""},{"id":529968482,"identity":"a029b6fe-9d00-4970-977c-e5ee69cb0181","order_by":3,"name":"Tengli Yu","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Tengli","middleName":"","lastName":"Yu","suffix":""},{"id":529968483,"identity":"6edfc280-5e50-4426-8fa4-28786abe4c9b","order_by":4,"name":"Yunhao Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYFACHgaGDwY2cmzszQeI18I4oyDNmI/nWALxWpg5PhxOnCeRo0CcBv4ZuQeYGQwOp7cx5DAw/KjYRliLxI28BOYCg/TcNoazBxh7ztwmrMVAIseAeYaBdW4bY18CM2MbsVp4DJjT2UAkKVqcE9jYiNUiceaNAeMMgzTDNh62hINE+YW/PceA4cMfG3n5+Y8PPvhRQYQWBoEE9h8w9gEi1IOsIVLdKBgFo2AUjGAAAGWgNiK1Vq2xAAAAAElFTkSuQmCC","orcid":"","institution":"Yunnan Minzu University","correspondingAuthor":true,"prefix":"","firstName":"Yunhao","middleName":"","lastName":"Chen","suffix":""},{"id":529968484,"identity":"892e3e12-6cc6-4dd0-a487-dcdaad060aa1","order_by":5,"name":"Ershen Wang","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Ershen","middleName":"","lastName":"Wang","suffix":""},{"id":529968485,"identity":"e36e6897-d337-46a6-b907-dffb0d1847c1","order_by":6,"name":"La Na","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"La","middleName":"","lastName":"Na","suffix":""}],"badges":[],"createdAt":"2025-04-23 02:53:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6508231/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6508231/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93644233,"identity":"cc8054a8-72b9-40d6-9998-af16829346c9","added_by":"auto","created_at":"2025-10-16 03:50:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5689035,"visible":true,"origin":"","legend":"","description":"","filename":"MultiAgentDeepReinforcementLearningforCooperativePathPlanningofUAVSwarms.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6508231/v1_covered_37a565f4-3d62-4222-81e3-0480eaa7fa81.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"autonomous-agents-and-multi-agent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agnt","sideBox":"Learn more about [Autonomous Agents and Multi-Agent Systems](http://link.springer.com/journal/10458)","snPcode":"10458","submissionUrl":"https://submission.nature.com/new-submission/10458/3","title":"Autonomous Agents and Multi-Agent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"UAV swarm, path planning, multi-agent reinforcement learning, partially observable Markov decision process, reward shaping","lastPublishedDoi":"10.21203/rs.3.rs-6508231/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6508231/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Collaborative path planning for UAV swarms in dynamic uncertain environments faces dual challenges of partial observability and cooperation mechanism design. The decentralized decision-making nature of multi-agent reinforcement learning (MARL) establishes a novel theoretical framework for autonomous coordination of heterogeneous UAV swarms under partially observable conditions. This paper proposes a reciprocity reward-enhanced multi-agent deep reinforcement learning method (PMI-MADDPG) that optimizes UAV cooperative decision-making through a centralized training with decentralized execution framework. By constructing a partially observable Markov decision process (POMDP) model, we design continuous action spaces considering UAV kinematic constraints, and quantify inter-agent state dependencies using pointwise mutual information. A novel cooperative coefficient estimation network is introduced to dynamically balance individual rewards and swarm-level objectives. Simulation results demonstrate that compared to conventional multi-agent methods, PMI-MADDPG shows significant advantages in task reward acquisition and network convergence efficiency, while revealing the impact of UAV quantity on system stability. The proposed approach provides an innovative solution for cooperative path planning tasks of UAV swarms in complex environments.","manuscriptTitle":"Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-16 03:42:11","doi":"10.21203/rs.3.rs-6508231/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"295969849177414446832952261189684304330","date":"2025-10-08T00:22:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-05T09:31:43+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-05T19:43:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-25T13:20:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"Autonomous Agents and Multi-Agent Systems","date":"2025-04-23T02:40:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"autonomous-agents-and-multi-agent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agnt","sideBox":"Learn more about [Autonomous Agents and Multi-Agent Systems](http://link.springer.com/journal/10458)","snPcode":"10458","submissionUrl":"https://submission.nature.com/new-submission/10458/3","title":"Autonomous Agents and Multi-Agent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6d4fa018-eae9-4263-91ba-2b53ea08f81b","owner":[],"postedDate":"October 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-10-16T03:42:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-16 03:42:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6508231","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6508231","identity":"rs-6508231","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}