Generative AI for Tactile Accessibility: A Systematic Literature Review of Emerging Methods and Gaps

Generative AI for Tactile Accessibility: A Systematic Literature Review of Emerging Methods and Gaps | 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 Generative AI for Tactile Accessibility: A Systematic Literature Review of Emerging Methods and Gaps Adnan Khan, Abbas Akkasi, Darya Taratynova, Majid Komeili This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8479747/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 Tactile graphics, tactile maps, and vibrotactile cues are essential for supporting access to visual information among blind and low-vision (BLV) users, yet current production workflows remain slow, manual, and highly specialized. Recent advances in generative artificial intelligence (GenAI) offer new possibilities for automating or augmenting these workflows, but the landscape of existing methods is fragmented and difficult to navigate. Research spans several model families, including generative adversarial networks, stable diffusion models, and multimodal language-vision models. These systems vary widely in how they are designed, applied, and evaluated. This systematic review examines GenAI approaches for tactile accessibility published between 2014 and 2025. We include only methods that produce tactile-relevant outputs, such as embossable graphics or vibrotactile signals, or that contribute a generative step within a tactile pipeline. The review maps how these models are instantiated, the stages of the tactile workflow they target, and the evaluation practices they employ. The analysis identifies consistent challenges, including oversmoothing, clutter that reduces haptic legibility, limited generalization, high computational demands, and scarce BLV-centered evaluation. The review concludes by outlining opportunities for tactile-first metrics and practical, low-resource generative pipelines, and provides 1 a curated, publicly available resource that consolidates papers and practitioner tools. blind and low-vision (BLV) tactile graphics tactile accessibility generative AI diffusion models multimodal large language models 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-8479747","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":568930907,"identity":"25b3b6b5-1731-4443-9cad-204785a30d65","order_by":0,"name":"Adnan Khan","email":"data:image/png;base64,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","orcid":"","institution":"Carleton University","correspondingAuthor":true,"prefix":"","firstName":"Adnan","middleName":"","lastName":"Khan","suffix":""},{"id":568930908,"identity":"99d2aa39-fc05-43b3-a550-31fa7a9033e0","order_by":1,"name":"Abbas Akkasi","email":"","orcid":"","institution":"Carleton University","correspondingAuthor":false,"prefix":"","firstName":"Abbas","middleName":"","lastName":"Akkasi","suffix":""},{"id":568930910,"identity":"59792ebc-020f-4a9f-a2c3-9dd1242c5821","order_by":2,"name":"Darya Taratynova","email":"","orcid":"","institution":"Mohamed bin Zayed University of Artificial Intelligence","correspondingAuthor":false,"prefix":"","firstName":"Darya","middleName":"","lastName":"Taratynova","suffix":""},{"id":568930913,"identity":"9c3bf553-5bf4-456a-954e-000f40937da8","order_by":3,"name":"Majid Komeili","email":"","orcid":"","institution":"Carleton University","correspondingAuthor":false,"prefix":"","firstName":"Majid","middleName":"","lastName":"Komeili","suffix":""}],"badges":[],"createdAt":"2025-12-30 09:38:26","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-8479747/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8479747/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99658108,"identity":"b129b6dc-012e-4906-a2db-7085c8c9be2a","added_by":"auto","created_at":"2026-01-07 03:00:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":360768,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerAIReviewShared.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8479747/v1/9c7071632bf5828b05b7ca1d.pdf"},{"id":99794872,"identity":"c43594b0-ae88-4fe6-98a8-ad2bc277484b","added_by":"auto","created_at":"2026-01-08 13:36:32","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5819,"visible":true,"origin":"","legend":"","description":"","filename":"9ed2c9da6fa947f9985f24212fc62446.json","url":"https://assets-eu.researchsquare.com/files/rs-8479747/v1/10f9b51f3cd801cc431c0634.json"},{"id":102469327,"identity":"5e87888a-03ee-48b4-8c81-0b004023357d","added_by":"auto","created_at":"2026-02-12 03:25:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":323396,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerAIReviewShared.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8479747/v1_covered_516eb30f-28f4-47d9-9370-dc46c5d81d7c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Generative AI for Tactile Accessibility: A Systematic Literature Review of Emerging Methods and Gaps","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":true,"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":"blind and low-vision (BLV), tactile graphics, tactile accessibility, generative AI, diffusion models, multimodal large language models","lastPublishedDoi":"10.21203/rs.3.rs-8479747/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8479747/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Tactile graphics, tactile maps, and vibrotactile cues are essential for supporting access to visual information among blind and low-vision (BLV) users, yet current production workflows remain slow, manual, and highly specialized. Recent advances in generative artificial intelligence (GenAI) offer new possibilities for automating or augmenting these workflows, but the landscape of existing methods is fragmented and difficult to navigate. Research spans several model families, including generative adversarial networks, stable diffusion models, and multimodal language-vision models. These systems vary widely in how they are designed, applied, and evaluated. This systematic review examines GenAI approaches for tactile accessibility published between 2014 and 2025. We include only methods that produce tactile-relevant outputs, such as embossable graphics or vibrotactile signals, or that contribute a generative step within a tactile pipeline. The review maps how these models are instantiated, the stages of the tactile workflow they target, and the evaluation practices they employ. The analysis identifies consistent challenges, including oversmoothing, clutter that reduces haptic legibility, limited generalization, high computational demands, and scarce BLV-centered evaluation. The review concludes by outlining opportunities for tactile-first metrics and practical, low-resource generative pipelines, and provides 1 a curated, publicly available resource that consolidates papers and practitioner tools.","manuscriptTitle":"Generative AI for Tactile Accessibility: A Systematic Literature Review of Emerging Methods and Gaps","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-07 03:00:51","doi":"10.21203/rs.3.rs-8479747/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":"b35e2d1a-4eef-47eb-880a-22171a463668","owner":[],"postedDate":"January 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-12T03:25:25+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-07 03:00:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8479747","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8479747","identity":"rs-8479747","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}