Hierarchical Learning for Robotic Assembly Leveraging LfD

Hierarchical Learning for Robotic Assembly Leveraging LfD | 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 Hierarchical Learning for Robotic Assembly Leveraging LfD Siddharth Singh, Qing Chang, Tian Yu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4379247/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 Robotic assembly is a long-time horizon problem that has attracted significant attention in the past two decades. The sparsity of the reward and the large state space for planning adds to the complexityof the problem. This paper proposes a Hierarchical Learning (HL) based approach which pivots the multi-level structure to seamlessly integrate task identification and sequencing with motion planning. The higher-level agent emphasizes comprehending tasks and learning task plans. It generates sequences and locations of sub-tasks, while the lower-level agent concentrates on executing the current sub-task. The higher-level agent employs a goal driven reinforcement learning (RL) approach to master the sequencing task, allowing it to adapt to unseen assemblies. Meanwhile, the lower level adopts a Learning from Demonstration (LfD) approach for motion planning, which can learn primitive skills from demonstration and intelligently combine the primitive skill for complicated tasks. The critical contribution of this work lies in the development of a novel method capable of comprehending and executing long horizon goal-driven assembly tasks without relying on expert demonstrations of specific tasks. The proposed approach is validated in a block assembly environment through simulation and physical setup. Project Website: https://sites.google.com/virginia.edu/isl-hllfdra/home Hierarchical Learning Robotic Assembly LfD Full Text Additional Declarations No competing interests reported. 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-4379247","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":339603350,"identity":"f02f66fd-69ce-4319-a030-52e9647a0616","order_by":0,"name":"Siddharth Singh","email":"","orcid":"","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Siddharth","middleName":"","lastName":"Singh","suffix":""},{"id":339603351,"identity":"7b2e53a8-e203-439d-8039-25ecc04e7f21","order_by":1,"name":"Qing Chang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIiWNgGAWjYFAC5gMMDBUMPAwMjA0MCSCBAwS1sAHVnSFNC48BA2MbsgAhLXzHz5g9eDvvsIx5/+K2Bw9qGOT4biTg1yJ5Jq3ccO62wzwyNx62GyQcYzCWJKTF4AbzNmnebWk8EhIH2yQS2BgSNxDWwmAmzTsHpuUfQz0RWliAWhpseCT4G9skEtsYEgyI8Eua5JxjQC0SjEAtfRKGM888wK+F7/jhYxJvaiTsJfiPP5P88c1Gnu84AVvAscADYkiAVUoQUI6ihf8AEapHwSgYBaNgRAIAaARE23pkz3EAAAAASUVORK5CYII=","orcid":"","institution":"University of Virginia","correspondingAuthor":true,"prefix":"","firstName":"Qing","middleName":"","lastName":"Chang","suffix":""},{"id":339603352,"identity":"58e16b67-c486-485a-be6f-f8817bd03385","order_by":2,"name":"Tian Yu","email":"","orcid":"","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Tian","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2024-05-06 23:10:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4379247/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4379247/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68093688,"identity":"b6b57944-7fcd-481d-8144-f1a9dac28d50","added_by":"auto","created_at":"2024-11-02 19:46:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3085860,"visible":true,"origin":"","legend":"","description":"","filename":"HRLLfDSinghChnagYu2024.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4379247/v1_covered_bec929db-8ed7-4f2b-9450-dc34b66d1957.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hierarchical Learning for Robotic Assembly Leveraging LfD","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Hierarchical Learning, Robotic Assembly, LfD","lastPublishedDoi":"10.21203/rs.3.rs-4379247/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4379247/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRobotic assembly is a long-time horizon problem that has attracted significant attention in the past two decades. The sparsity of the reward and the large state space for planning adds to the complexityof the problem. This paper proposes a Hierarchical Learning (HL) based approach which pivots the multi-level structure to seamlessly integrate task identification and sequencing with motion planning. The higher-level agent emphasizes comprehending tasks and learning task plans. It generates sequences and locations of sub-tasks, while the lower-level agent concentrates on executing the current sub-task. The higher-level agent employs a goal driven reinforcement learning (RL) approach to master the sequencing task, allowing it to adapt to unseen assemblies. Meanwhile, the lower level adopts a Learning from Demonstration (LfD) approach for motion planning, which can learn primitive skills from demonstration and intelligently combine the primitive skill for complicated tasks. The critical contribution of this work lies in the development of a novel method capable of comprehending and executing long horizon goal-driven assembly tasks without relying on expert demonstrations of specific tasks. The proposed approach is validated in a block assembly environment through simulation and physical setup. Project Website: https://sites.google.com/virginia.edu/isl-hllfdra/home\u003c/p\u003e","manuscriptTitle":"Hierarchical Learning for Robotic Assembly Leveraging LfD","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-21 05:39:37","doi":"10.21203/rs.3.rs-4379247/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":"939a45cb-3de5-4dcc-b9e8-b41dcb1eb231","owner":[],"postedDate":"August 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-02T19:38:11+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-21 05:39:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4379247","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4379247","identity":"rs-4379247","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}