{"id":136467,"date":"2025-09-11T15:49:07","date_gmt":"2025-09-11T15:49:07","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/136467\/"},"modified":"2025-09-11T15:49:07","modified_gmt":"2025-09-11T15:49:07","slug":"the-robot-can-bunnyhop-front-flip-now","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/136467\/","title":{"rendered":"The robot can bunnyhop front flip now"},"content":{"rendered":"<p>It started with a track stand. Then a bunnyhop. Now? It\u2019s a full front flip bunnyhop. The <a href=\"https:\/\/cyclingmagazine.ca\/mtb\/bike-riding-robot-pops-wheelies-bunnyhops-and-rides-backwards\/\" rel=\"nofollow noopener\" target=\"_blank\">Ultra Mobility Vehicle<\/a> (UMV) from the RAI Institute just landed one of the most absurd feats in freestyle bike history. And it doesn\u2019t even have a rider.<br \/>Using Reinforcement Learning (RL), the AI-powered UMV has officially taught itself how to front flip bunnyhop.<\/p>\n<p>\u201cThat\u2019s exactly how I\u2019d do it,\u201d BMX and freestyle icon Ryan \u201cR-Willy\u201d Williams commented on the viral clip.<\/p>\n<p>Reinforcement learning: trial, error and send<\/p>\n<p>The RAI Institute still hasn\u2019t responded to interview requests (likely too busy watching their own highlight reel), but their mission is crystal clear: build smarter, more agile robots.<\/p>\n<p>The UMV uses RL: a kind of AI that learns by doing. No pre-programmed moves, no joystick in the background. Just a continuous loop of \u201ctry this,\u201d \u201ccrash,\u201d \u201cadjust,\u201d and \u201ctry again.\u201d It\u2019s basically a toddler with a carbon frame and infinite patience.<\/p>\n<p>\u201cWe\u2019re training all the policies in simulation,\u201d one RAI engineer explains. \u201cWe try an action, evaluate the outcome, then reward or penalize that decision in future runs. The goal is 15 successful landings in a row. No flukes.\u201d<\/p>\n<p>They\u2019ve now got a robot that can balance dynamically, react in real time and launch itself into tricks like a foam-pit rat at Woodward. Not bad for a machine riding what still appears to be a <a href=\"https:\/\/www.specialized.com\/ca\/en\/hotwalk-carbon\/p\/188009?color=303781-188009&amp;searchText=94021-0005\" rel=\"nofollow noopener\" target=\"_blank\">Specialized Hotwalk<\/a> carbon balance bike.<\/p>\n<\/p>\n<p>More Crankworx than warehouse bot<\/p>\n<p>Executive Director Marc Raibert says their broader goal is to build robots that \u201ccare for the disabled, free people from dangerous work and help people live better lives.\u201d<\/p>\n<p>That\u2019s a noble goal. But this one looks like it\u2019s training for Red Bull Joyride.<\/p>\n<p>In their latest research video, RAI engineers describe the challenges: designing lightweight frames that survive repeated crashes, modeling real-world battery behavior to match simulation and teaching a robot to recognize curbs, tables or handrails.<\/p>\n<p>\u201cWe want the robot to operate at human cadence,\u201d they say. \u201cOr superhuman.\u201d<\/p>\n<p>They\u2019re not kidding.<\/p>\n<p>The UMV is now hopping, flipping and navigating obstacles with balance and aggression most riders would envy. It even tracks its own center of mass in mid-air and adapts its body position for stable landings. Backwards manuals anyone? Yep. Robot\u2019s got them on lock.<\/p>\n<p>What\u2019s next: bike flip or backflip?<\/p>\n<p>This isn\u2019t just a sideshow. The lab claims the technology powering UMV could have major implications for search and rescue, off-grid delivery or military recon. Basically anywhere balance, movement and autonomous adaptation matter.<\/p>\n<p>But for now? It\u2019s launching front flips and stacking views online.<\/p>\n<p>You want to impress us, robo-ripper? Let\u2019s see a nac-nac. A suicide no-hander. Or heck, just pull a clean 360.<\/p><\/p>\n","protected":false},"excerpt":{"rendered":"It started with a track stand. Then a bunnyhop. Now? It\u2019s a full front flip bunnyhop. The Ultra&hellip;\n","protected":false},"author":2,"featured_media":136468,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[445],"tags":[49,48,635,1700,82],"class_list":["post-136467","post","type-post","status-publish","format-standard","has-post-thumbnail","category-cycling","tag-ca","tag-canada","tag-cycling","tag-mtb-features","tag-sports"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/136467","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=136467"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/136467\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/136468"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=136467"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=136467"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=136467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}