{"id":3276,"date":"2025-08-04T13:38:06","date_gmt":"2025-08-04T13:38:06","guid":{"rendered":"http:\/\/www.labren.org\/mm\/?p=3276"},"modified":"2025-08-05T13:00:03","modified_gmt":"2025-08-05T13:00:03","slug":"we-are-happy-to-share-our-journal-paper-titled-amagposenet-real-time-6-dof-magnet-pose-estimation-by-dual-domain-few-shot-learning-from-prior-model-published-in-ieee-transactions-on","status":"publish","type":"post","link":"http:\/\/www.labren.org\/mm\/news\/we-are-happy-to-share-our-journal-paper-titled-amagposenet-real-time-6-dof-magnet-pose-estimation-by-dual-domain-few-shot-learning-from-prior-model-published-in-ieee-transactions-on\/","title":{"rendered":"We are happy to share our journal paper titled \u201cAMagPoseNet: Real-Time 6-DoF Magnet Pose Estimation by Dual-Domain Few-Shot Learning from Prior Model\u201d published in IEEE Transactions on Industrial Informatics!"},"content":{"rendered":"\n<p>Impact: Traditional magnetic tracking approaches based on mathematical models and optimization algorithms are computationally intensive, depend on initial guesses, and do not guarantee convergence to a global optimum. Here we propose an annular magnet pose estimation network (called AMagPoseNet) based on dual-domain few-shot learning from a prior mathematical model, featuring the following advantages:<\/p>\n\n\n\n<p>1) Higher localization accuracy (1.87\u00b11.14 mm, 1.89\u00b10.81\u00b0), especially in the near field;<\/p>\n\n\n\n<p>2) Enhanced robustness, as AMagPoseNet is just a single feed-forward neural network that does not rely on initial guesses and avoids the risk of falling into local optima;<\/p>\n\n\n\n<p>3) Lower computational latency (2.08\u00b10.02 ms) since the magnet pose is directly regressed from a single feed-forward network rather than iterative optimization;<\/p>\n\n\n\n<p>4) Real-time estimation of 6-DoF pose if discriminative magnetic field features are provided.<\/p>\n\n\n\n<p>Paper: https:\/\/lnkd.in\/gXBSQ-hG<\/p>\n\n\n\n<p>Dataset: https:\/\/lnkd.in\/gXEFfwfA<\/p>\n\n\n\n<p>Authors: Shijian Su; <a href=\"https:\/\/www.linkedin.com\/company\/103371608\/admin\/page-posts\/published\/#\">Sishen YUAN<\/a>; <a href=\"https:\/\/www.linkedin.com\/company\/103371608\/admin\/page-posts\/published\/#\">Mengya Xu<\/a>; <a href=\"https:\/\/www.linkedin.com\/company\/103371608\/admin\/page-posts\/published\/#\">Huxin Gao<\/a>; Xiaoxiao Yang; and Prof <a href=\"https:\/\/www.linkedin.com\/company\/103371608\/admin\/page-posts\/published\/#\">Hongliang Ren<\/a><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D5622AQEANkv5UGIxAQ\/feedshare-shrink_800\/feedshare-shrink_800\/0\/1724656931728?e=1756944000&amp;v=beta&amp;t=ZMGoflL-tZ_k2ecMdRORRP4xvmQvxpnr4pEJisD9b7s\" alt=\"No alternative text description for this image\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D5622AQEx9emXCY61mw\/feedshare-shrink_800\/feedshare-shrink_800\/0\/1724656925833?e=1756944000&amp;v=beta&amp;t=YMIlidgYTK6Qo40QxOCjD2Z-N0MMA0UNSWqXbYwBw0w\" alt=\"No alternative text description for this image\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Impact: Traditional magnetic tracking approaches based on mathematical models and optimization algorithms are computationally intensive, depend on initial guesses, and do not guarantee convergence to a global optimum. Here we propose an annular magnet pose estimation network (called AMagPoseNet) based on dual-domain few-shot learning from a prior mathematical model, featuring\u2026 <a class=\"continue-reading-link\" href=\"http:\/\/www.labren.org\/mm\/news\/we-are-happy-to-share-our-journal-paper-titled-amagposenet-real-time-6-dof-magnet-pose-estimation-by-dual-domain-few-shot-learning-from-prior-model-published-in-ieee-transactions-on\/\">Continue reading<\/a><\/p>\n","protected":false},"author":17,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[4],"tags":[126,175,128,174],"class_list":["post-3276","post","type-post","status-publish","format-standard","hentry","category-news","tag-cuhk","tag-fewshotlearning","tag-labren","tag-magnetposeestimation"],"_links":{"self":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3276","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/comments?post=3276"}],"version-history":[{"count":1,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3276\/revisions"}],"predecessor-version":[{"id":3277,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3276\/revisions\/3277"}],"wp:attachment":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/media?parent=3276"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/categories?post=3276"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/tags?post=3276"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}