Hierarchical Information-guided Robotic Grasp Detection

Hierarchical Information-guided Robotic Grasp Detection | 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 Article Hierarchical Information-guided Robotic Grasp Detection Zeyao Hou, Yueran Zhao, Yutao Jin, Chao Yang, Zongyu he, Xiaoyan Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5674862/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 May, 2025 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract With the advancement of deep learning, robotic grasping has seen widespread application in fields, becoming a critical component in enhancing automation. Accurate and efficient grasping capabilities not only significantly boost productivity but also ensure safety and reliability in complex and dynamic environments. However, current approaches, particularly those based on convolutional neural networks (CNNs), often neglect the hierarchical information inherent in the data and lead to challenges in complex environments with abundant background information. Moreover, these methods struggle to capture long-range dependencies and non-local self-similarity, critical for accurate grasp detection. To address these issues, we propose GraspFormer, a novel method for robotic grasp detection. GraspFormer features a unique Encoder-Decoder framework that incorporates a Grasp Transformer Block designed to model long-range dependencies while avoiding background interference. Our approach also designs hierarchical information-guided self-attention (HIGSA) and an adaptive deep channel modulator (DCM) to enhance feature interactions and competition. Extensive experiments demonstrate that GraspFormer achieves performance comparable to state-of-the-art methods. The code is available at https://github.com/shine793/Hierarchical-Information-guided-Robotic-Grasp-Detection . Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science Deep Learning Robotic Grasp Detection Transformer Attention Mechanism. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 29 May, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 15 Apr, 2025 Reviews received at journal 11 Apr, 2025 Reviews received at journal 11 Apr, 2025 Reviewers agreed at journal 03 Apr, 2025 Reviewers agreed at journal 02 Apr, 2025 Reviewers invited by journal 02 Apr, 2025 Submission checks completed at journal 01 Apr, 2025 First submitted to journal 24 Mar, 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-5674862","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":437315958,"identity":"ed31bce7-d6d2-44c0-8497-bde6688fafe5","order_by":0,"name":"Zeyao Hou","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zeyao","middleName":"","lastName":"Hou","suffix":""},{"id":437315959,"identity":"7abb25ac-d876-4194-8ce8-a2e33463daeb","order_by":1,"name":"Yueran Zhao","email":"","orcid":"","institution":"Tianjin Bonus Robotics Technology Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yueran","middleName":"","lastName":"Zhao","suffix":""},{"id":437315960,"identity":"0f7d0006-f49c-4e12-9dcb-548983b74246","order_by":2,"name":"Yutao Jin","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yutao","middleName":"","lastName":"Jin","suffix":""},{"id":437315961,"identity":"81a363ca-7cbc-4637-8585-0effeefe5b3f","order_by":3,"name":"Chao Yang","email":"","orcid":"","institution":"Tianjin College, University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Yang","suffix":""},{"id":437315962,"identity":"91790546-cd2c-469d-96f0-02dc2c4cd08e","order_by":4,"name":"Zongyu he","email":"","orcid":"","institution":"Tianjin College, University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zongyu","middleName":"","lastName":"he","suffix":""},{"id":437315963,"identity":"cc1a39a9-0a8b-4318-9b66-1dacdae0f62b","order_by":5,"name":"Xiaoyan Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIie3NsQrCMBCA4ZOAOqRmPRF8hoDQRfFZhIAuznUTJycfIOJjuDpcCTiVZg3ooIuzow6CFcXRxk0wP4TLcB8HEAr9br3XrPqTIQKw74j5ggg9jlvRxk6ltQTnxIBYzT4TzLK4qU87lE5BRecGcE+fiawtYnemB2HAorkBiYMSwnjsBpSjtAbYzYs8rxBKUsAqPgSz7eSqSTWXTsl0kY84uhIitFp3OPVFw6bHwyXptoUuIQB1+f5S8XjZflHt4LEUCoVCf90dQvFB2k0DBAIAAAAASUVORK5CYII=","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-12-19 08:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5674862/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5674862/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-03313-z","type":"published","date":"2025-05-29T15:57:30+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":83783031,"identity":"67b317b0-7536-4760-8a5b-8b8970c7e604","added_by":"auto","created_at":"2025-06-02 16:10:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1283258,"visible":true,"origin":"","legend":"","description":"","filename":"HierarchicalInformationguidedRoboticGraspDetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5674862/v1_covered_7ad9724e-3a07-430f-9413-835dd8493bed.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hierarchical Information-guided Robotic Grasp Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Deep Learning, Robotic Grasp Detection, Transformer, Attention Mechanism.","lastPublishedDoi":"10.21203/rs.3.rs-5674862/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5674862/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the advancement of deep learning, robotic grasping has seen widespread application in fields, becoming a critical component in enhancing automation. Accurate and efficient grasping capabilities not only significantly boost productivity but also ensure safety and reliability in complex and dynamic environments. However, current approaches, particularly those based on convolutional neural networks (CNNs), often neglect the hierarchical information inherent in the data and lead to challenges in complex environments with abundant background information. Moreover, these methods struggle to capture long-range dependencies and non-local self-similarity, critical for accurate grasp detection. To address these issues, we propose GraspFormer, a novel method for robotic grasp detection. GraspFormer features a unique Encoder-Decoder framework that incorporates a Grasp Transformer Block designed to model long-range dependencies while avoiding background interference. Our approach also designs hierarchical information-guided self-attention (HIGSA) and an adaptive deep channel modulator (DCM) to enhance feature interactions and competition. Extensive experiments demonstrate that GraspFormer achieves performance comparable to state-of-the-art methods. The code is available at https://github.com/shine793/Hierarchical-Information-guided-Robotic-Grasp-Detection.","manuscriptTitle":"Hierarchical Information-guided Robotic Grasp Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-03 04:57:04","doi":"10.21203/rs.3.rs-5674862/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-15T04:03:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-11T17:12:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-11T06:48:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"63224944114283765945282430813441773166","date":"2025-04-03T21:25:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"31838922804409615945351961420143505578","date":"2025-04-02T08:52:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-02T08:45:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-01T09:45:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-24T07:33:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"66a1319b-fe00-4393-8463-52b0cb82c62d","owner":[],"postedDate":"April 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":46564058,"name":"Physical sciences/Mathematics and computing"},{"id":46564059,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-06-02T16:05:20+00:00","versionOfRecord":{"articleIdentity":"rs-5674862","link":"https://doi.org/10.1038/s41598-025-03313-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-05-29 15:57:30","publishedOnDateReadable":"May 29th, 2025"},"versionCreatedAt":"2025-04-03 04:57:04","video":"","vorDoi":"10.1038/s41598-025-03313-z","vorDoiUrl":"https://doi.org/10.1038/s41598-025-03313-z","workflowStages":[]},"version":"v1","identity":"rs-5674862","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5674862","identity":"rs-5674862","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}