{"id":149,"date":"2015-04-24T11:26:19","date_gmt":"2015-04-24T10:26:19","guid":{"rendered":"http:\/\/babel.isa.uma.es\/kipr\/?p=149"},"modified":"2015-07-16T15:28:57","modified_gmt":"2015-07-16T14:28:57","slug":"reinforcement-learning-used-for-an-adaptive-attention-mechanism-and-integrated-in-an-architecture-with-both-top-down-and-bottom-up-vision-processing","status":"publish","type":"post","link":"https:\/\/babel.isa.uma.es\/kipr\/?p=149","title":{"rendered":"Reinforcement learning used for an adaptive attention mechanism, and integrated in an architecture with both top-down and bottom-up vision processing"},"content":{"rendered":"<h4>Ognibene, D.; Baldassare, G., <strong>Ecological Active Vision: Four Bioinspired Principles to Integrate Bottom\u2013Up and Adaptive Top\u2013Down Attention Tested With a Simple Camera-Arm Robot,<\/strong> Autonomous Mental Development, IEEE Transactions on , vol.7, no.1, pp.3,25, March 2015. <a href=\"http:\/\/doi.org\/10.1109\/TAMD.2014.2341351\" target=\"_blank\">DOI: 10.1109\/TAMD.2014.2341351<\/a>.<\/h4>\n<blockquote><p>Vision gives primates a wealth of information useful to manipulate the environment, but at the same time it can easily overwhelm their computational resources. Active vision is a key solution found by nature to solve this problem: a limited fovea actively displaced in space to collect only relevant information. Here we highlight that in ecological conditions this solution encounters four problems: 1) the agent needs to learn where to look based on its goals; 2) manipulation causes learning feedback in areas of space possibly outside the attention focus; 3) good visual actions are needed to guide manipulation actions, but only these can generate learning feedback; and 4) a limited fovea causes aliasing problems. We then propose a computational architecture (\u201cBITPIC\u201d) to overcome the four problems, integrating four bioinspired key ingredients: 1) reinforcement-learning fovea-based top-down attention; 2) a strong vision-manipulation coupling; 3) bottom-up periphery-based attention; and 4) a novel action-oriented memory. The system is tested with a simple simulated camera-arm robot solving a class of search-and-reach tasks involving color-blob \u201cobjects.\u201d The results show that the architecture solves the problems, and hence the tasks, very efficiently, and highlight how the architecture principles can contribute to a full exploitation of the advantages of active vision in ecological conditions.<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Ognibene, D.; Baldassare, G., Ecological Active Vision: Four Bioinspired Principles to Integrate Bottom\u2013Up and Adaptive Top\u2013Down Attention Tested With a <span class=\"ellipsis\">&hellip;<\/span> <span class=\"more-link-wrap\"><a href=\"https:\/\/babel.isa.uma.es\/kipr\/?p=149\" class=\"more-link\"><span>Read More &rarr;<\/span><\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14,64,35],"tags":[36,33,65,13,15],"class_list":["post-149","post","type-post","status-publish","format-standard","hentry","category-applications-of-reinforcement-learning-to-robots","category-computer-vision","category-psycho-physiological-bases-of-engineering","tag-decision-making","tag-directly-bioinspired","tag-manipulation","tag-q-learning","tag-reinforcement-learning"],"_links":{"self":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/149"}],"collection":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=149"}],"version-history":[{"count":2,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/149\/revisions"}],"predecessor-version":[{"id":151,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/149\/revisions\/151"}],"wp:attachment":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=149"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=149"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=149"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}