{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:38:21Z","timestamp":1781714301433,"version":"3.54.5"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangxi Key Technologies R&D Program","award":["No.AB241484046"],"award-info":[{"award-number":["No.AB241484046"]}]},{"name":"Guangxi Science and Technology Program","award":["No. GUIKEAB23075177"],"award-info":[{"award-number":["No. GUIKEAB23075177"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Robotic grasping is crucial in manufacturing, logistics, and service robotics, but existing methods struggle with object occlusion and complex arrangements in cluttered scenes. We propose the Generative Residual Attention Network (GR-AttNet), based on the Generative Residual Convolutional Neural Network (GR-CNN). The spatial attention mechanism enhances its adaptability to clutter, and architectural optimization maintains high accuracy while reducing parameters and boosting efficiency. Experiments show GR-AttNet achieves 98.1% accuracy on the Cornell Grasping Dataset, 94.9% on the Jacquard Dataset, with processing speeds of 148\u2009ms and 163\u2009ms respectively, outperforming several state-of-the-art methods. With only 2.8 million parameters, it surpasses various existing models. Simulations further validate over 50% success rates across different scenario complexities. However, challenges remain in handling small object missed detection and severe occlusion cases. GR-AttNet offers a novel, highly practical solution for robotic grasping tasks.<\/jats:p>","DOI":"10.1371\/journal.pone.0337599","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:52:09Z","timestamp":1764874329000},"page":"e0337599","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["GR-AttNet: Robotic grasping with lightweight spatial attention mechanism"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7625-1935","authenticated-orcid":true,"given":"Shengbang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3082-0488","authenticated-orcid":true,"given":"Zhongsheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shutian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yadong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"pone.0337599.ref001","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.actaastro.2024.04.012","article-title":"Review of machine learning in robotic grasping control in space application","volume":"220","author":"H Jahanshahi","year":"2024","journal-title":"Acta Astronautica"},{"key":"pone.0337599.ref002","author":"S Jauhri","year":"2024"},{"issue":"2","key":"pone.0337599.ref003","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","article-title":"Data-Driven Grasp Synthesis\u2014A Survey","volume":"30","author":"J Bohg","year":"2014","journal-title":"IEEE Trans Robot"},{"issue":"4","key":"pone.0337599.ref004","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s43154-020-00021-6","article-title":"A survey on learning-based robotic grasping","volume":"1","author":"K Kleeberger","year":"2020","journal-title":"Curr Robot Rep"},{"key":"pone.0337599.ref005","doi-asserted-by":"crossref","unstructured":"Morales A, Asfour T, Azad P, Knoop S, Dillmann R. Integrated Grasp Planning and Visual Object Localization For a Humanoid Robot with Five-Fingered Hands. In: 2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems. 2006. 5663\u20138. https:\/\/doi.org\/10.1109\/iros.2006.282367","DOI":"10.1109\/IROS.2006.282367"},{"key":"pone.0337599.ref006","doi-asserted-by":"crossref","unstructured":"Miller AT, Knoop S, Christensen HI, Allen PK. Automatic grasp planning using shape primitives. In: 2003 IEEE International Conference in Robotics and Automation. 2003. 1824\u20139.","DOI":"10.1109\/ROBOT.2003.1241860"},{"key":"pone.0337599.ref007","doi-asserted-by":"crossref","unstructured":"Fu Z, Zhao TZ, Finn C. Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation. In: Conference on Robot Learning. 2024.","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"pone.0337599.ref008","article-title":"The grasp generation convolutional neural network","author":"D Morrison","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0337599.ref009","doi-asserted-by":"crossref","unstructured":"Kumra S, Joshi S, Sahin F. Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. https:\/\/doi.org\/10.1109\/iros45743.2020.9340777","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"pone.0337599.ref010","unstructured":"Saxena A. Learning grasps for objects. In: Proceedings of the IEEE International Conference on Robotics and Automation. 2008."},{"key":"pone.0337599.ref011","doi-asserted-by":"crossref","unstructured":"Yun Jiang, Moseson S, Saxena A. Efficient grasping from RGBD images: Learning using a new rectangle representation. In: 2011 IEEE International Conference on Robotics and Automation. 2011. https:\/\/doi.org\/10.1109\/icra.2011.5980145","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"pone.0337599.ref012","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1177\/0278364914549607","article-title":"Deep learning for detecting robotic grasps","volume":"34","author":"I Lenz","year":"2015","journal-title":"Int J Robot Res"},{"issue":"6","key":"pone.0337599.ref013","first-page":"794","article-title":"Fast detection of planar grasp pose for robots based on cascaded convolutional neural network","volume":"40","author":"J Xia","year":"2018","journal-title":"Robot"},{"issue":"2","key":"pone.0337599.ref014","first-page":"3142","article-title":"Robotic grasp detection using deep convolutional neural networks","volume":"5","author":"S Kumra","year":"2020","journal-title":"IEEE Robot Autom Lett"},{"issue":"10","key":"pone.0337599.ref015","first-page":"2867","article-title":"Densely occluded grasping objects detection based on RGB-D fusion","volume":"38","author":"M Li","year":"2023","journal-title":"Control and Decision"},{"key":"pone.0337599.ref016","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Advances in Neural Information Processing Systems, 2017."},{"key":"pone.0337599.ref017","first-page":"1","article-title":"Real-time detection method for robotic target grasping regions","author":"ZL Lu","year":"2019","journal-title":"Comput Eng Appl"},{"issue":"11","key":"pone.0337599.ref018","first-page":"3607","article-title":"Cross-modal interaction fusion grasping detection based on Transformer-CNN hybrid architecture","volume":"39","author":"Y Wang","year":"2024","journal-title":"Control and Decision"},{"key":"pone.0337599.ref019","first-page":"3","author":"S Woo","year":"2018"},{"key":"pone.0337599.ref020","author":"S Xiong","year":"2024"},{"key":"pone.0337599.ref021","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1177\/0278364919859066","article-title":"Learning robust, real-time, reactive robotic grasping","volume":"39","author":"D Morrison","year":"2019","journal-title":"The International Journal of Robotics Research"},{"key":"pone.0337599.ref022","doi-asserted-by":"crossref","unstructured":"Ainetter S, Fraundorfer F. End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB. In: 2021 IEEE International Conference on Robotics and Automation (ICRA). 2021. 13452\u20138. https:\/\/doi.org\/10.1109\/icra48506.2021.9561398","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"pone.0337599.ref023","doi-asserted-by":"crossref","unstructured":"Zhou X, Lan X, Zhang H, Tian Z, Zhang Y, Zheng N. Fully Convolutional Grasp Detection Network with Oriented Anchor Box. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2018;7223\u201330. https:\/\/doi.org\/10.1109\/iros.2018.8594116","DOI":"10.1109\/IROS.2018.8594116"},{"key":"pone.0337599.ref024","first-page":"21","author":"E Ogas","year":"2019"},{"key":"pone.0337599.ref025","article-title":"Concurrent spatial and channel \u2018squeeze & excitation\u2019 in fully convolutional networks. arXiv preprint","author":"AG Roy","year":"2018"},{"key":"pone.0337599.ref026","article-title":"Object detection and pose estimation from RGB and depth data for real-time, adaptive robotic grasping. arXiv preprint","author":"SK Paul","year":"2021"},{"issue":"4","key":"pone.0337599.ref027","article-title":"Visual\u2013tactile fusion object classification method based on adaptive feature weighting","volume":"20","author":"P Zhang","year":"2023","journal-title":"Int J Advanced Robotic Syst"},{"key":"pone.0337599.ref028","doi-asserted-by":"crossref","first-page":"109300","DOI":"10.1016\/j.compbiomed.2024.109300","article-title":"CK-ATTnet: Medical image segmentation network based on convolutional kernel attention","volume":"183","author":"B Cai","year":"2024","journal-title":"Comput Biol Med"},{"key":"pone.0337599.ref029","doi-asserted-by":"crossref","unstructured":"Depierre A, Dellandrea E, Chen L. Jacquard: A Large Scale Dataset for Robotic Grasp Detection. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2018;3511\u20136. https:\/\/doi.org\/10.1109\/iros.2018.8593950","DOI":"10.1109\/IROS.2018.8593950"},{"issue":"2","key":"pone.0337599.ref030","first-page":"1535","article-title":"GraspNet-1Billion: A large-scale benchmark for general object grasping","volume":"5","author":"B Fang","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"4","key":"pone.0337599.ref031","first-page":"3355","article-title":"Dex-Net 3.0: Computing robust robot grasps with a generative model","volume":"3","author":"J Mahler","year":"2018","journal-title":"IEEE Robotics and Automation Letters"},{"key":"pone.0337599.ref032","doi-asserted-by":"crossref","unstructured":"Yan X, Khansari M, Bai Y, Hsu J, Pathak A, Gupta A, et al. Learning to predict grasping interaction with geometry-aware 3D representations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). 2018. 1\u20138.","DOI":"10.1109\/ICRA.2018.8460609"},{"issue":"4","key":"pone.0337599.ref033","doi-asserted-by":"crossref","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","article-title":"Real-World Multiobject, Multigrasp Detection","volume":"3","author":"F-J Chu","year":"2018","journal-title":"IEEE Robot Autom Lett"},{"issue":"1","key":"pone.0337599.ref034","article-title":"DSN-BR-Based Online Inspection Method and Application for Surface Defects of Pharmaceutical Products in Aluminum-Plastic Blister Packages","volume":"37","author":"M Liu","year":"2024","journal-title":"Chin J Mech Eng"},{"key":"pone.0337599.ref035","author":"A Zeng","year":"2018"},{"issue":"1","key":"pone.0337599.ref036","doi-asserted-by":"crossref","first-page":"90","DOI":"10.2478\/jlst-2020-0006","article-title":"Analysing picking errors in vision picking systems","volume":"11","author":"E Vidovi\u010d","year":"2020","journal-title":"Logistics & Sustainable Transport"},{"issue":"3","key":"pone.0337599.ref037","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1561\/1100000005","article-title":"Human-Robot Interaction: A Survey","volume":"1","author":"MA Goodrich","year":"2007","journal-title":"FNT in Human-Computer Interaction"},{"key":"pone.0337599.ref038","doi-asserted-by":"crossref","unstructured":"Redmon J, Angelova A. Real-Time Grasp Detection Using Convolutional Neural Networks. In: 2015 IEEE International Conference on Robotics and Automation. 2015;1316\u201322.","DOI":"10.1109\/ICRA.2015.7139361"},{"issue":"06","key":"pone.0337599.ref039","doi-asserted-by":"crossref","first-page":"5196","DOI":"10.12677\/MOS.2023.126473","article-title":"Improved Grasping Detection Algorithm and Simulation Based on GR-CNN","volume":"12","author":"XH Lou","year":"2023","journal-title":"MOS"},{"issue":"2","key":"pone.0337599.ref040","first-page":"238","article-title":"Transformer-based pixel-level robotic grasp pose detection","volume":"31","author":"QS Yu","year":"2024","journal-title":"J Eng Des"},{"key":"pone.0337599.ref041","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s44199-023-00054-8","article-title":"Continuity corrected Wilson interval for the difference of two independent proportions","volume":"22","author":"G Shan","year":"2023","journal-title":"J Stat Theory Appl"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0337599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:52:16Z","timestamp":1764874336000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0337599"}},"subtitle":[],"editor":[{"given":"Longhui","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":41,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0337599","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}