{"id":111367,"date":"2020-08-15T02:22:19","date_gmt":"2020-08-15T09:22:19","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/08\/soldiers-could-teach-future-robots-how-to-outperform-humans"},"modified":"2020-08-15T02:22:19","modified_gmt":"2020-08-15T09:22:19","slug":"soldiers-could-teach-future-robots-how-to-outperform-humans","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/08\/soldiers-could-teach-future-robots-how-to-outperform-humans","title":{"rendered":"Soldiers could teach future robots how to outperform humans"},"content":{"rendered":"

<\/a><\/p>\n

The researchers fused machine learning from demonstration algorithms and more classical autonomous navigation systems. Rather than replacing a classical system altogether, APPLD learns how to tune the existing system to behave more like the human demonstration. This paradigm allows for the deployed system to retain all the benefits of classical navigation systems\u2014such as optimality, explainability and safety\u2014while also allowing the system to be flexible and adaptable to new environments, Warnell said.<\/p>\n

\n

In the future, a soldier and a game controller may be all that\u2019s needed to teach robots how to outdrive humans.<\/p>\n

At the U.S. Army Combat Capabilities Development Command\u2019s Army Research Laboratory and the University of Texas at Austin, researchers designed an algorithm that allows an autonomous ground vehicle<\/a> to improve its existing navigation<\/a> systems by watching a human drive. The team tested its approach\u2014called adaptive planner parameter learning from demonstration, or APPLD\u2014on one of the Army\u2019s experimental autonomous ground vehicles.<\/p>\n

\u201cUsing approaches like APPLD, current soldiers in existing training facilities will be able to contribute to improvements in autonomous systems<\/a> simply by operating their vehicles as normal,\u201d said Army researcher Dr. Garrett Warnell. \u201cTechniques like these will be an important contribution to the Army\u2019s plans to design and field next-generation combat vehicles that are equipped to navigate autonomously in off-road deployment environments.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

The researchers fused machine learning from demonstration algorithms and more classical autonomous navigation systems. Rather than replacing a classical system altogether, APPLD learns how to tune the existing system to behave more like the human demonstration. This paradigm allows for the deployed system to retain all the benefits of classical navigation systems\u2014such as optimality, explainability [\u2026]<\/p>\n","protected":false},"author":534,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,9,6],"tags":[],"class_list":["post-111367","post","type-post","status-publish","format-standard","hentry","category-information-science","category-military","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/111367","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\/534"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=111367"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/111367\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=111367"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=111367"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=111367"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}