Towards Fully Autonomous Valet Parking: A Comprehensive Vision-and-Language Dataset and Benchmark Toolkit

Towards Fully Autonomous Valet Parking: A Comprehensive Vision-and-Language Dataset and Benchmark Toolkit | 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 Towards Fully Autonomous Valet Parking: A Comprehensive Vision-and-Language Dataset and Benchmark Toolkit Pengyu Fu, Jincheng Hu, Jihao Li, Ming Liu, Jingjing Jiang, Yuanjian Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6263001/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 Autonomous Valet Parking (AVP) represents the final stage in autonomous driving applications, where vehicles are expected to navigate complex and dynamic parking environments autonomously without human intervention. However, the progress of AVP research is currently hindered by the lack of task-specific datasets, making it challenging to develop and validate AVP algorithms effectively. By formalizing the static object features of typical parking lots, including locations, obstacles and attributes, this paper introduces the Vision-and-Language Parking (VLP) dataset, featuring 174 onboard panoramic images and 301 commands, marking it as the first dataset for AVP tasks. Additionally, we develop an Agent-oriented Benchmark AI toolkit with 14 baselines from Rule-Based (RB) scripts, Reinforcement Learning (RL), Deep Learning (DL) and Multimodal Large Language Model (MLLM). The results show reinforcement learning faces significant trajectory exploration challenges, deep learning struggles with out-of-distribution data generalization and MLLM shows good language understanding but poor analysis of environmental observation. The dataset and benchmark proposed in this paper provide a foundational basis for the development, sharing, and expansion of AVP algorithms. 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-6263001","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":431140409,"identity":"98e51390-e069-4214-b590-623903ef95e5","order_by":0,"name":"Pengyu Fu","email":"","orcid":"","institution":"Loughborough University","correspondingAuthor":false,"prefix":"","firstName":"Pengyu","middleName":"","lastName":"Fu","suffix":""},{"id":431140410,"identity":"242aef24-6884-4327-9ac9-0fc54a12fb32","order_by":1,"name":"Jincheng Hu","email":"","orcid":"","institution":"Loughborough University","correspondingAuthor":false,"prefix":"","firstName":"Jincheng","middleName":"","lastName":"Hu","suffix":""},{"id":431140411,"identity":"441f41e4-ac07-489c-8058-3641b0d18316","order_by":2,"name":"Jihao Li","email":"","orcid":"","institution":"Loughborough University","correspondingAuthor":false,"prefix":"","firstName":"Jihao","middleName":"","lastName":"Li","suffix":""},{"id":431140412,"identity":"30f2004f-d460-434f-8e9c-8184c138cd36","order_by":3,"name":"Ming Liu","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Ming","middleName":"","lastName":"Liu","suffix":""},{"id":431140413,"identity":"ec23f87f-3997-45e4-b2e0-fe113dfd86d5","order_by":4,"name":"Jingjing Jiang","email":"","orcid":"","institution":"Loughborough University","correspondingAuthor":false,"prefix":"","firstName":"Jingjing","middleName":"","lastName":"Jiang","suffix":""},{"id":431140414,"identity":"57f0bfb4-3496-48db-b87c-b4ad435a8a14","order_by":5,"name":"Yuanjian Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYBACgwM8Bsw/G4As9uY2uChjAwEtDJIgFTwHidQi2cCWANEikUikFn4G5gMMhjvs8uQjH7Y9+LjHhoG//QCb5Aw8WthAJiaeSS42vJ3YbjjjWRqDxJkENskNhLQcbGNO3Dg7sU2a58BhBoYbDGySDwhoYWxsq0/cOPMgRIs8MVqYGdsOJ86XYIRoMQBpweswZsaGw4xtxxM38ID8ciCNx/BMYrMlXu+zNzY+/tlWnTi//fCxBx8O2MjJHT988GYPHi0MzAwMB0C0wQEIn4dArCABeSLVjYJRMApGwQgEAKMBTgfDJEHOAAAAAElFTkSuQmCC","orcid":"","institution":"Loughborough University","correspondingAuthor":true,"prefix":"","firstName":"Yuanjian","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-03-19 15:29:32","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-6263001/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6263001/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78934356,"identity":"e09c9c4a-8ff2-422e-87f8-0f5773adff16","added_by":"auto","created_at":"2025-03-21 04:08:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2205858,"visible":true,"origin":"","legend":"","description":"","filename":"VLPdatasetv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6263001/v1_covered_747b85af-2c20-4992-9570-21d000ee4133.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTowards Fully Autonomous Valet Parking: A Comprehensive Vision-and-Language Dataset and Benchmark Toolkit\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":"","lastPublishedDoi":"10.21203/rs.3.rs-6263001/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6263001/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutonomous Valet Parking (AVP) represents the final stage in autonomous driving applications, where vehicles are expected to navigate complex and dynamic parking environments autonomously without human intervention. However, the progress of AVP research is currently hindered by the lack of task-specific datasets, making it challenging to develop and validate AVP algorithms effectively. By formalizing the static object features of typical parking lots, including locations, obstacles and attributes, this paper introduces the Vision-and-Language Parking (VLP) dataset, featuring 174 onboard panoramic images and 301 commands, marking it as the first dataset for AVP tasks. Additionally, we develop an Agent-oriented Benchmark AI toolkit with 14 baselines from Rule-Based (RB) scripts, Reinforcement Learning (RL), Deep Learning (DL) and Multimodal Large Language Model (MLLM). The results show reinforcement learning faces significant trajectory exploration challenges, deep learning struggles with out-of-distribution data generalization and MLLM shows good language understanding but poor analysis of environmental observation. The dataset and benchmark proposed in this paper provide a foundational basis for the development, sharing, and expansion of AVP algorithms.\u003c/p\u003e","manuscriptTitle":"Towards Fully Autonomous Valet Parking: A Comprehensive Vision-and-Language Dataset and Benchmark Toolkit","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-21 04:00:27","doi":"10.21203/rs.3.rs-6263001/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":"14d8f81c-8e25-4c18-9c75-9a2d12243656","owner":[],"postedDate":"March 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-21T04:00:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-21 04:00:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6263001","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6263001","identity":"rs-6263001","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}