{"id":1428,"date":"2020-05-19T16:59:31","date_gmt":"2020-05-19T16:59:31","guid":{"rendered":"https:\/\/beta.research.ece.ncsu.edu\/aros\/?page_id=1428"},"modified":"2020-06-12T14:06:33","modified_gmt":"2020-06-12T14:06:33","slug":"paper-tcyb2020-upperlimb","status":"publish","type":"page","link":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/","title":{"rendered":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses"},"content":{"rendered":"<p>[et_pb_section fb_built=&#8221;1&#8243; admin_label=&#8221;section&#8221; _builder_version=&#8221;3.22&#8243;][et_pb_row admin_label=&#8221;row&#8221; _builder_version=&#8221;3.25&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;3.25&#8243; custom_padding=&#8221;|||&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_image src=&#8221;https:\/\/research.ece.ncsu.edu\/wp-content\/uploads\/sites\/7\/2020\/05\/pipeline_final.jpg&#8221; _builder_version=&#8221;4.4.0&#8243;][\/et_pb_image][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=&#8221;4.4.0&#8243;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.4.0&#8243;][et_pb_text admin_label=&#8221;Title&#8221; _builder_version=&#8221;4.4.0&#8243;]<\/p>\n<h1>Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses<\/h1>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=&#8221;3_5,2_5&#8243; _builder_version=&#8221;4.4.0&#8243;][et_pb_column type=&#8221;3_5&#8243; _builder_version=&#8221;4.4.0&#8243;][et_pb_text admin_label=&#8221;Abstract&#8221; _builder_version=&#8221;4.4.0&#8243;]<\/p>\n<p>Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging <em>Bayesian Deep Learning<\/em> (BDL), we have developed a novel, reliable vision-based framework to assist upper-limb prosthesis grasping during arm reaching. This framework can measure different types of uncertainties from the model and data for grasping target recognition in realistic and challenging scenarios. A probability calibration network was developed to fuse the uncertainty measures into one calibrated probability for online decision-making. We formulated the problem as the prediction of grasping target while arm reaching. Specifically, we developed a 3D simulation platform to simulate and analyze the performance of vision algorithms under several common challenging scenarios in practice. In addition, we integrated our approach into a shared control framework of a prosthetic arm and demonstrated its potential at assisting human participants with fluent target reaching and grasping tasks.<\/p>\n<p>[\/et_pb_text][\/et_pb_column][et_pb_column type=&#8221;2_5&#8243; _builder_version=&#8221;4.4.0&#8243;][et_pb_text admin_label=&#8221;Resources&#8221; _builder_version=&#8221;4.4.0&#8243; hover_enabled=&#8221;0&#8243;]<\/p>\n<h2 style=\"text-align: left;\">Resources:<\/h2>\n<p>&nbsp;<\/p>\n<ul>\n<li><a href=\"https:\/\/ieeexplore.ieee.org\/document\/9113325\">IEEE <span class=\"il\">Transactions<\/span> on Cybernetics 2020 Article<\/a><\/li>\n<li><a href=\"https:\/\/research.ece.ncsu.edu\/wp-content\/uploads\/sites\/7\/2020\/06\/tcyb2020-upperlimb-appendix.pdf\">Appendix<\/a><\/li>\n<li><a href=\"https:\/\/youtu.be\/fFZdTbNutFc\">Video<\/a><\/li>\n<\/ul>\n<p>This work was a collaboration between the ARoS Lab and the <a href=\"https:\/\/nrel.web.unc.edu\/\">Neuromuscular Rehabilitation Engineering Laboratory (NREL)<\/a> at UNC Chapel Hill \/ NC State. This work was supported by the National Science Foundation (NSF) under Award CNS-1552828, NRI-1527202, DOD W81XWH-15-C-0125 and W81XWH-15-1-0407.<\/p>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Reliable Vision-Based Grasping Target Recognition for Upper-limb ProsthesesComputer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance [&hellip;]<\/p>\n","protected":false},"author":45,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":"","_members_access_role":[],"_members_access_error":""},"class_list":["post-1428","page","type-page","status-publish","hentry"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 4.9.10 - aioseo.com -->\n\t<meta name=\"description\" content=\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<link rel=\"canonical\" href=\"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 4.9.10\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ARoS Lab | Active Robotic Sensing Lab\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab\" \/>\n\t\t<meta property=\"og:description\" content=\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2020-05-19T16:59:31+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-06-12T14:06:33+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary\" \/>\n\t\t<meta name=\"twitter:title\" content=\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/#listItem\",\"name\":\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/#listItem\",\"position\":2,\"name\":\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros#listItem\",\"name\":\"Home\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/#organization\",\"name\":\"ARoS Lab\",\"description\":\"Active Robotic Sensing Lab\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/#webpage\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/\",\"name\":\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab\",\"description\":\"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/paper-tcyb2020-upperlimb\\\/#breadcrumblist\"},\"datePublished\":\"2020-05-19T16:59:31+00:00\",\"dateModified\":\"2020-06-12T14:06:33+00:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/#website\",\"url\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/\",\"name\":\"ARoS Lab\",\"description\":\"Active Robotic Sensing Lab\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/research.ece.ncsu.edu\\\/aros\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab","description":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have","canonical_url":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BreadcrumbList","@id":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/aros#listItem","position":1,"name":"Home","item":"https:\/\/research.ece.ncsu.edu\/aros","nextItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/#listItem","name":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses"}},{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/#listItem","position":2,"name":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses","previousItem":{"@type":"ListItem","@id":"https:\/\/research.ece.ncsu.edu\/aros#listItem","name":"Home"}}]},{"@type":"Organization","@id":"https:\/\/research.ece.ncsu.edu\/aros\/#organization","name":"ARoS Lab","description":"Active Robotic Sensing Lab","url":"https:\/\/research.ece.ncsu.edu\/aros\/"},{"@type":"WebPage","@id":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/#webpage","url":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/","name":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab","description":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/research.ece.ncsu.edu\/aros\/#website"},"breadcrumb":{"@id":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/#breadcrumblist"},"datePublished":"2020-05-19T16:59:31+00:00","dateModified":"2020-06-12T14:06:33+00:00"},{"@type":"WebSite","@id":"https:\/\/research.ece.ncsu.edu\/aros\/#website","url":"https:\/\/research.ece.ncsu.edu\/aros\/","name":"ARoS Lab","description":"Active Robotic Sensing Lab","inLanguage":"en-US","publisher":{"@id":"https:\/\/research.ece.ncsu.edu\/aros\/#organization"}}]},"og:locale":"en_US","og:site_name":"ARoS Lab | Active Robotic Sensing Lab","og:type":"article","og:title":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab","og:description":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have","og:url":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/","article:published_time":"2020-05-19T16:59:31+00:00","article:modified_time":"2020-06-12T14:06:33+00:00","twitter:card":"summary","twitter:title":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses | ARoS Lab","twitter:description":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses Computer vision has shown promising potential in wearable robotics applications (e.g. human grasping target prediction and context understanding). However, in practice, the performance of computer vision algorithms is challenged by insufficient or biased training, observation noise, cluttered background, etc. By leveraging Bayesian Deep Learning (BDL), we have"},"aioseo_meta_data":{"post_id":"1428","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"location":null,"local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2020-12-21 09:45:22","updated":"2025-07-01 13:06:09","seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/research.ece.ncsu.edu\/aros\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tReliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/research.ece.ncsu.edu\/aros"},{"label":"Reliable Vision-Based Grasping Target Recognition for Upper-limb Prostheses","link":"https:\/\/research.ece.ncsu.edu\/aros\/paper-tcyb2020-upperlimb\/"}],"_links":{"self":[{"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/pages\/1428","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/users\/45"}],"replies":[{"embeddable":true,"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/comments?post=1428"}],"version-history":[{"count":9,"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/pages\/1428\/revisions"}],"predecessor-version":[{"id":1511,"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/pages\/1428\/revisions\/1511"}],"wp:attachment":[{"href":"https:\/\/research.ece.ncsu.edu\/aros\/wp-json\/wp\/v2\/media?parent=1428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}