{"458541":{"#nid":"458541","#data":{"type":"news","title":"How to Fall Gracefully If You\u2019re a Robot","body":[{"value":"\u003Cp\u003EMiss Georgia tripped in the final round of the 2015 Miss America Pageant. Jennifer Lawrence stumbled on her way to accept an Oscar. Even \u003Ca href=\u0022https:\/\/www.youtube.com\/watch?v=RQ-3vgLruNI\u0022\u003Erock stars, world leaders and presidential candidates\u003C\/a\u003E have fallen in front of the crowd or completely off stage.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.youtube.com\/watch?v=ASoCJTYgYB0\u0022\u003EAnd robots can too\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EResearchers at Georgia Tech have identified a way to teach robots how to fall with grace and without serious damage. The work is important as costly robots become more common in manufacturing alongside humans. The skill becomes especially important, too, as robots are sought for health care or domestic tasks \u2013 working near the elderly, injured, children or pets.\u003C\/p\u003E\u003Cp\u003EPh.D. graduate Sehoon Ha and Professor Karen Liu developed a new algorithm that tells a robot how to react to a wide variety of falls \u2013 from a single step to recover from a gentle nudge, to a rolling motion that breaks a high-speed fall. As a result, robots can minimize the damage or injury they might cause to themselves or others while falling by learning the best sequence of movements to slow their momentum. The planning algorithm was validated in \u003Ca href=\u0022https:\/\/youtu.be\/cQ1c_N9ejk8\u0022\u003Ephysics simulation and experimentally tested\u003C\/a\u003E on a BioloidGP humanoid.\u003C\/p\u003E\u003Cp\u003E\u201cA fall can potentially cause detrimental damage to the robot and enormous cost to repair,\u201d said Ha, who graduated in summer 2015 and is now a postdoctoral associate at Disney Research Pittsburgh in Pennsylvania. \u201cWe believe robots can learn how to fall safely. Our work unified existing research about how to teach robots to fall by giving them a tool to automatically determine the total number of contacts (how many hands shoved it, for example), the order of contacts, and the position and timing of those contacts. All of that impacts the potential of a fall and changes the robot\u2019s response.\u201d\u003C\/p\u003E\u003Cp\u003EWith the latest finding, Ha builds upon Liu\u2019s previous research that studied \u003Ca href=\u0022http:\/\/www.cc.gatech.edu\/news\/cats-and-athletes-teach-robots-to-fall\u0022\u003Ehow cats modify their bodies\u003C\/a\u003E in the midst of a fall. Liu knew from that work that one of the most important factors in a fall is the angle of the landing. She also knew that a well-designed robot has the \u201cbrain\u201d to compute a softer landing, but hadn\u2019t yet optimized the sequence of motions that take place during a fall, like she and Ha were able to do in their latest research.\u003C\/p\u003E\u003Cp\u003E\u201cFrom previous work, we knew a robot had the computational know-how to achieve a softer landing, but it didn\u2019t have the hardware to move quickly enough like a cat,\u201d Liu said. \u201cOur new planning algorithm takes into account the hardware constraints and the capabilities of the robot, and suggests a sequence of contacts so the robot gradually can slow itself down.\u201d\u003C\/p\u003E\u003Cp\u003ENow the robots may fall more gracefully than people and possibly cats, too. Imagine that.\u003C\/p\u003E\u003Cp\u003EThe research, entitled \u201cMultiple Contact Planning for Minimizing Damage of Humanoid Falls,\u201d was presented this month at the IEEE\/RSJ International Conference on Intelligent Robots and Systems in Hamburg, Germany.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EResearchers have identified a way to teach robots how to fall with grace and without serious damage. The new algorithm tells a robot how to react to a wide variety of falls \u2013 from a single step to recover from a gentle nudge, to a rolling motion that breaks a high-speed fall. As a result, robots can minimize the damage or injury they might cause to themselves or others while falling by learning the best sequence of movements to slow their momentum.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"New algorithm teaches how to react to a variety of falls to minimize damage."}],"uid":"27560","created_gmt":"2015-10-13 15:17:03","changed_gmt":"2016-10-08 03:19:43","author":"Jason Maderer","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2015-10-13T00:00:00-04:00","iso_date":"2015-10-13T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"458561":{"id":"458561","type":"image","title":"Falling Robot","body":null,"created":"1449256347","gmt_created":"2015-12-04 19:12:27","changed":"1475895204","gmt_changed":"2016-10-08 02:53:24","alt":"Falling Robot","file":{"fid":"203545","name":"screen_shot_2015-10-13_at_3.19.42_pm.png","image_path":"\/sites\/default\/files\/images\/screen_shot_2015-10-13_at_3.19.42_pm_0.png","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/screen_shot_2015-10-13_at_3.19.42_pm_0.png","mime":"image\/png","size":114364,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/screen_shot_2015-10-13_at_3.19.42_pm_0.png?itok=7XrWj0qi"}},"50388":{"id":"50388","type":"image","title":"Karen Liu","body":null,"created":"1449175392","gmt_created":"2015-12-03 20:43:12","changed":"1475894458","gmt_changed":"2016-10-08 02:40:58","alt":"Karen Liu","file":{"fid":"128684","name":"liu.jpg","image_path":"\/sites\/default\/files\/images\/liu_0.jpg","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/liu_0.jpg","mime":"image\/jpeg","size":8680,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/liu_0.jpg?itok=OAzajdvP"}}},"media_ids":["458561","50388"],"groups":[{"id":"1183","name":"Home"}],"categories":[{"id":"135","name":"Research"},{"id":"152","name":"Robotics"}],"keywords":[{"id":"654","name":"College of Computing"},{"id":"11477","name":"Fall"},{"id":"1356","name":"robot"},{"id":"667","name":"robotics"}],"core_research_areas":[{"id":"39521","name":"Robotics"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ETara La Bouff\u003Cbr \/\u003ECollege of Computing\u003Cbr \/\u003E404-894-7253 \u003C\/p\u003E","format":"limited_html"}],"email":["tlabouff@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}