{"id":30560,"date":"2016-09-27T13:47:34","date_gmt":"2016-09-27T20:47:34","guid":{"rendered":"http:\/\/lifeboat.com\/blog\/2016\/09\/ai-lab-pepper-robot-learning-ball-in-a-cup"},"modified":"2017-06-04T09:25:19","modified_gmt":"2017-06-04T16:25:19","slug":"ai-lab-pepper-robot-learning-ball-in-a-cup","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2016\/09\/ai-lab-pepper-robot-learning-ball-in-a-cup","title":{"rendered":"[AI Lab] Pepper robot learning \u201cball in a cup\u201d"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/jkaRO8J_1XI?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>This video realized by the AI Lab of SoftBank Robotics shows how Pepper robot learns to play the ball-in-a-cup game (\u201cbilboquet\u201d in French). The movement is first demonstrated to the robot by guiding its arm.<\/p>\n<p>From there, Pepper has to improve its performance through trial-and-error learning. Even though the initial demonstration does not land the ball in the cup, Pepper can still learn to play the game successfully.<\/p>\n<p>The movement is represented as a so-called dynamic movement primitive and optimized using an evolutionary algorithm. Our implementation uses the freely available software library dmpbbo: <a href=\"https:\/\/github.com\/stulp\/dmpbbo\" class=\"\" data-url=\"https:\/\/github.com\/stulp\/dmpbbo\" data-servicelink=\"CDEQ6TgiEwif09zOtbDPAhXKm64KHZElAToo-B0\" rel=\"nofollow\" target=\"_blank\"><a href=\"https:\/\/github.com\/stulp\/dmpbbo\">https:\/\/github.com\/stulp\/dmpbbo<\/a><\/a>.<\/p>\n<p>After 100 trials, Pepper has successfully optimized its behavior and is able to repeatedly land the ball in the cup.<\/p>\n<p><!-- Link: <a href=\"https:\/\/www.youtube.com\/watch?v=jkaRO8J_1XI\">https:\/\/www.youtube.com\/watch?v=jkaRO8J_1XI<\/a> --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This video realized by the AI Lab of SoftBank Robotics shows how Pepper robot learns to play the ball-in-a-cup game (\u201cbilboquet\u201d in French). The movement is first demonstrated to the robot by guiding its arm. From there, Pepper has to improve its performance through trial-and-error learning. Even though the initial demonstration does not land the [\u2026]<\/p>\n","protected":false},"author":359,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1509,41,6],"tags":[],"class_list":["post-30560","post","type-post","status-publish","format-standard","hentry","category-entertainment","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/30560","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=30560"}],"version-history":[{"count":2,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/30560\/revisions"}],"predecessor-version":[{"id":60255,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/30560\/revisions\/60255"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=30560"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=30560"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=30560"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}