Enabling Service Robots to Open Self-Closing Doors using Deep RL and Generative Models

Enabling Service Robots to Open Self-Closing Doors using Deep RL and Generative Models | 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 Enabling Service Robots to Open Self-Closing Doors using Deep RL and Generative Models Yufeng Sun, Lin Zhang, Ou Ma This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6115186/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 Various mobile service robots have been applied in human-centered indoor environments such as hospitals, schools, and office buildings for tasks like food or material delivery, surveillance, cleaning, and disinfection. However, they still require human assistance to access rooms with doors, particularly self-closing doors. In this paper, we propose a deep reinforcement learning (DRL)-based solution to enhance existing service robots, enabling them to autonomously open self-closing doors using a simple and inexpensive assistive device. This device is utilized to unlatch doors through the integration of the latest object detection and sensor technologies. Focusing on pulling open self-closing doors, we train an end-to-end control policy in a simplified simulation environment and deploy it to a real-world robot. Additionally, generative models, a variational autoenoder (VAE) and a cycle-consistent adversarial network (CycleGAN), are incorporated into the training and deployment stages to improve the robustness of the door-opening control policy. The proposed solution for opening self-closing doors was validated in both simulation and real-world experiments. Robotics Self-closing door opening door DRL generative models sensor fusion 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-6115186","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":421404571,"identity":"330f9537-2c6c-4b32-9570-cee9c906a99d","order_by":0,"name":"Yufeng Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYLCCigoQydgA4R0gRsuZMyRrOduGzCOkRX5G7jGJg/MOy+u2H25g5qlhkOO7kYBfi8GNvDSJg9sOG247kwjUcozBWJKgFokcM+mP2w4nmB0AauFtYEjcQEiL/IwcM4mDc4Bazj8Ea6knqIXhBkhLA1DLDYgtCQYEHXbmjbHFgWPphttuPGw4OOeYhOHMMw8IOKw9x/DGgRprebPz6Q8fvKmxkec7TshhDAwsEjDWAQYGCTwKEYD5A1HKRsEoGAWjYOQCAFP1SjpNrDzcAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-2508-4207","institution":"University of Cincinnati","correspondingAuthor":true,"prefix":"","firstName":"Yufeng","middleName":"","lastName":"Sun","suffix":""},{"id":421405207,"identity":"d4d1248e-88a1-4ed2-a7cb-fdc1b1d26d00","order_by":1,"name":"Lin Zhang","email":"","orcid":"","institution":"University of Central Arkansas","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Zhang","suffix":""},{"id":421405208,"identity":"aee38ed5-8ee6-460b-8ae3-f93bb5aafee4","order_by":2,"name":"Ou Ma","email":"","orcid":"","institution":"University of Cincinnati","correspondingAuthor":false,"prefix":"","firstName":"Ou","middleName":"","lastName":"Ma","suffix":""}],"badges":[],"createdAt":"2025-02-26 17:21:33","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-6115186/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6115186/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77387134,"identity":"4ceac1ef-c99a-4cab-bfcd-e07839a40e7a","added_by":"auto","created_at":"2025-02-28 05:38:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1208102,"visible":true,"origin":"","legend":"","description":"","filename":"dooropeningusingDRLandgenerativemodels.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6115186/v1_covered_789c1974-3a53-417f-bc5a-5191dd01323e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEnabling Service Robots to Open Self-Closing Doors using Deep RL and Generative Models\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Cincinnati","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":"Self-closing door, opening door, DRL, generative models, sensor fusion","lastPublishedDoi":"10.21203/rs.3.rs-6115186/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6115186/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eVarious mobile service robots have been applied in human-centered indoor environments such as hospitals, schools, and office buildings for tasks like food or material delivery, surveillance, cleaning, and disinfection. However, they still require human assistance to access rooms with doors, particularly self-closing doors. In this paper, we propose a deep reinforcement learning (DRL)-based solution to enhance existing service robots, enabling them to autonomously open self-closing doors using a simple and inexpensive assistive device. This device is utilized to unlatch doors through the integration of the latest object detection and sensor technologies. Focusing on pulling open self-closing doors, we train an end-to-end control policy in a simplified simulation environment and deploy it to a real-world robot. Additionally, generative models, a variational autoenoder (VAE) and a cycle-consistent adversarial network (CycleGAN), are incorporated into the training and deployment stages to improve the robustness of the door-opening control policy. The proposed solution for opening self-closing doors was validated in both simulation and real-world experiments.\u003c/p\u003e","manuscriptTitle":"Enabling Service Robots to Open Self-Closing Doors using Deep RL and Generative Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-28 05:30:28","doi":"10.21203/rs.3.rs-6115186/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":"f1b007ab-aa8e-4c13-ae57-263625afe86b","owner":[],"postedDate":"February 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":44920643,"name":"Robotics"}],"tags":[],"updatedAt":"2025-02-28T05:30:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-28 05:30:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6115186","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6115186","identity":"rs-6115186","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}