{"id":103975,"date":"2020-03-19T11:12:01","date_gmt":"2020-03-19T18:12:01","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/03\/microsoft-researchers-train-ai-in-simulation-to-control-a-real-world-drone"},"modified":"2020-03-19T11:12:01","modified_gmt":"2020-03-19T18:12:01","slug":"microsoft-researchers-train-ai-in-simulation-to-control-a-real-world-drone","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/03\/microsoft-researchers-train-ai-in-simulation-to-control-a-real-world-drone","title":{"rendered":"Microsoft researchers train AI in simulation to control a real-world drone"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/microsoft-researchers-train-ai-in-simulation-to-control-a-real-world-drone2.jpg\"><\/a><\/p>\n<p>In a preprint <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/learning-visuomotor-policies-for-aerial-navigation-using-cross-modal-representations\/\">paper<\/a>, Microsoft researchers describe a machine learning system that reasons out the correct actions to take directly from camera images. It\u2019s trained via simulation and learns to independently navigate environments and conditions in the real world, including unseen situations, which makes it a fit for robots deployed in search and rescue missions. Someday, it could help those robots more quickly identify people in need of help.<\/p>\n<p>\u201cWe wanted to push current technology to get closer to a human\u2019s ability to interpret environmental cues, adapt to difficult conditions and operate autonomously,\u201d wrote the researchers in a <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/training-deep-control-policies-for-the-real-world\/\">blog post<\/a> published this week. \u201cWe were interested in exploring the question of what it would take to build autonomous systems that achieve similar performance levels.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In a preprint paper, Microsoft researchers describe a machine learning system that reasons out the correct actions to take directly from camera images. It\u2019s trained via simulation and learns to independently navigate environments and conditions in the real world, including unseen situations, which makes it a fit for robots deployed in search and rescue missions. [\u2026]<\/p>\n","protected":false},"author":513,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1488,6],"tags":[],"class_list":["post-103975","post","type-post","status-publish","format-standard","hentry","category-drones","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/103975","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\/513"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=103975"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/103975\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=103975"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=103975"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=103975"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}