{"id":6133,"date":"2023-10-05T12:53:51","date_gmt":"2023-10-05T12:53:51","guid":{"rendered":"https:\/\/dailyai.com\/?p=6133"},"modified":"2023-10-05T12:53:51","modified_gmt":"2023-10-05T12:53:51","slug":"open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/","title":{"rendered":"Open X-Embodiment-datas\u00e6t, RT-X-model et spring for AI-robotter"},"content":{"rendered":"<p><strong>Googles DeepMind arbejdede sammen med 33 forskellige akademiske laboratorier for at skabe et AI-tr\u00e6ningsdatas\u00e6t baseret p\u00e5 22 forskellige robottyper.<\/strong><\/p>\n<p>Robotter er virkelig gode til at g\u00f8re \u00e9n bestemt ting. Hvis du vil have den til at g\u00f8re noget bare lidt anderledes, skal robotten tr\u00e6nes helt fra bunden. Det ultimative m\u00e5l for robotteknologi er at have en robot, der er god til en lang r\u00e6kke handlinger, og som selv kan l\u00e6re nye f\u00e6rdigheder.<\/p>\n<p>For at tr\u00e6ne en AI-model har du brug for et stort datas\u00e6t med data, der er relateret til modellens form\u00e5l. Sprogmodeller som <a href=\"https:\/\/dailyai.com\/da\/2023\/09\/openai-reveals-new-voice-and-image-features-for-chatgpt\/\">GPT-4<\/a> er tr\u00e6net p\u00e5 store m\u00e6ngder skriftlige data. Billedgeneratorer som <a href=\"https:\/\/dailyai.com\/da\/2023\/10\/dall-e-3-ai-image-generator-available-free-on-bing-chat\/\">DALL-E 3<\/a> er tr\u00e6net p\u00e5 store m\u00e6ngder billeder.<\/p>\n<p>Med X-Embodiment har DeepMind skabt et datas\u00e6t med robothandlinger baseret p\u00e5 22 forskellige typer robotter. Derefter brugte de datas\u00e6ttet til at tr\u00e6ne nye modeller baseret p\u00e5 deres RT-1- og RT-2-robotmodeller.<\/p>\n<p>Dataene for X-Embodiment stammer fra \"22 robotudf\u00f8relsesformer, der demonstrerer mere end 500 f\u00e6rdigheder og 150.000 opgaver p\u00e5 tv\u00e6rs af mere end 1 million episoder\", if\u00f8lge <a href=\"https:\/\/www.deepmind.com\/blog\/scaling-up-learning-across-many-different-robot-types\" target=\"_blank\" rel=\"noopener\">DeepMinds indl\u00e6g<\/a>.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\" style=\"text-align: center;\">Vi pr\u00e6senterer \ud835\udde5\ud835\udde7-\ud835\uddeb: en generalistisk AI-model, der hj\u00e6lper med at fremme, hvordan robotter kan l\u00e6re nye f\u00e6rdigheder. \ud83e\udd16<\/p>\n<p>For at tr\u00e6ne den samarbejdede vi med 33 akademiske laboratorier over hele verden for at opbygge et nyt datas\u00e6t med erfaringer fra 22 forskellige robottyper.<\/p>\n<p>Find ud af mere: <a href=\"https:\/\/t.co\/k6tE62gQGP\">https:\/\/t.co\/k6tE62gQGP<\/a> <a href=\"https:\/\/t.co\/IXTy2g4Lty\">pic.twitter.com\/IXTy2g4Lty<\/a><\/p>\n<p style=\"text-align: center;\">- Google DeepMind (@GoogleDeepMind) <a href=\"https:\/\/twitter.com\/GoogleDeepMind\/status\/1709207886943965648?ref_src=twsrc%5Etfw\">3. oktober 2023<\/a><\/p>\n<\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>De tidligere testresultater af RT-1 og <a href=\"https:\/\/dailyai.com\/da\/2023\/07\/googles-ai-turns-vision-language-into-robotic-actions\/\">RT-2 modeller<\/a> var allerede imponerende, men DeepMind fandt ud af, at RT-X-versionerne klarede sig betydeligt bedre p\u00e5 grund af det nye datas\u00e6ts generelle karakter.<\/p>\n<p>Testen bestod i at sammenligne en robot styret af en model, der var tr\u00e6net til en bestemt opgave, med den samme robot styret af RT-1-X-modellen. RT-1-X klarede sig i gennemsnit 50% bedre end de modeller, der var designet specifikt til opgaver som at \u00e5bne en d\u00f8r eller tr\u00e6kke et kabel.<\/p>\n<p>RT-2, Googles VLA-robotmodel (vision-language-action), g\u00f8r det muligt for robotter at l\u00e6re af web-, verbale og visuelle data og derefter handle uden at blive tr\u00e6net. Da ingeni\u00f8rerne tr\u00e6nede RT-2-X med X-Embodiment-datas\u00e6ttet, fandt de ud af, at RT-2-X var tre gange s\u00e5 succesfuld som RT-2, n\u00e5r det gjaldt nye f\u00e6rdigheder.<\/p>\n<figure id=\"attachment_6135\" aria-describedby=\"caption-attachment-6135\" style=\"width: 640px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6135 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/RT-2-X-demonstration.gif\" alt=\"\" width=\"640\" height=\"360\" \/><figcaption id=\"caption-attachment-6135\" class=\"wp-caption-text\">RT-2-X demonstrerer en forst\u00e5else af rumlige forhold mellem objekter. Kilde: <a href=\"https:\/\/www.deepmind.com\/blog\/scaling-up-learning-across-many-different-robot-types\" target=\"_blank\" rel=\"noopener\">DeepMind<\/a><\/figcaption><\/figure>\n<p>Med andre ord l\u00e6rte robotten nye f\u00e6rdigheder, som den ikke havde f\u00f8r, baseret p\u00e5 evner, som andre robotter havde bidraget med til datas\u00e6ttet. Overf\u00f8rsel af f\u00e6rdigheder mellem forskellige typer robotter kan v\u00e6re en gamechanger for hurtig udvikling af robotteknologi.<\/p>\n<p>Disse resultater giver anledning til optimisme om, at vi snart vil se robotter med mere generelle f\u00e6rdigheder samt evnen til at l\u00e6re nye uden at v\u00e6re specifikt tr\u00e6net til dem.<\/p>\n<p>DeepMind siger, at denne forskning kan anvendes p\u00e5 selvforbedringsegenskaberne i <a href=\"https:\/\/www.deepmind.com\/blog\/robocat-a-self-improving-robotic-agent\" target=\"_blank\" rel=\"noopener\">RoboCat<\/a>, dens selvforbedrende AI-agent til robotteknologi.<\/p>\n<p>Udsigten til at have en robot, der bliver ved med at forbedre sig og l\u00e6re nye f\u00e6rdigheder, ville v\u00e6re en stor fordel inden for omr\u00e5der som produktion, landbrug eller sundhedspleje. Disse nye f\u00e6rdigheder kunne ogs\u00e5 anvendes i <a href=\"https:\/\/dailyai.com\/da\/2023\/10\/darpa-wants-to-use-ai-to-make-better-battlefield-decisions\/\">Forsvarsindustrien<\/a> hvilket m\u00e5ske er et mindre tiltalende, men uundg\u00e5eligt perspektiv.<\/p>","protected":false},"excerpt":{"rendered":"<p>Googles DeepMind arbejdede sammen med 33 forskellige akademiske laboratorier for at skabe et AI-tr\u00e6ningsdatas\u00e6t baseret p\u00e5 22 forskellige robottyper. Robotter er virkelig gode til at g\u00f8re \u00e9n bestemt ting. Hvis du vil have den til at g\u00f8re noget bare lidt anderledes, skal robotten tr\u00e6nes helt fra bunden. Det ultimative m\u00e5l for robotteknologi er at have en robot, der er god til en lang r\u00e6kke handlinger og har evnen til selv at l\u00e6re nye f\u00e6rdigheder. For at tr\u00e6ne en AI-model har man brug for et stort datas\u00e6t med data, der er relateret til modellens form\u00e5l. Sprogmodeller som GPT-4 tr\u00e6nes<\/p>","protected":false},"author":6,"featured_media":6136,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,102,105,169],"class_list":["post-6133","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-google","tag-machine-learning","tag-robotics"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Open X-Embodiment dataset, RT-X model a leap for AI robots | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/da\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Open X-Embodiment dataset, RT-X model a leap for AI robots | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Google\u2019s DeepMind worked with 33 different academic labs to create an AI training dataset based on 22 different robot types. Robots are really good at doing one specific thing. If you want it to do something even slightly different, the robot needs to be trained from scratch. The ultimate goal for robotics is to have a robot that is good at a general range of actions with the ability to learn new skills by itself. To train an AI model you need a large dataset of data related to the purpose of the model. Language models like GPT-4 are trained\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-05T12:53:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"563\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skrevet af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Open X-Embodiment dataset, RT-X model a leap for AI robots\",\"datePublished\":\"2023-10-05T12:53:51+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/\"},\"wordCount\":521,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/testing-AI-robotics.jpg\",\"keywords\":[\"DeepMind\",\"Google\",\"machine learning\",\"Robotics\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/\",\"name\":\"Open X-Embodiment dataset, RT-X model a leap for AI robots | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/testing-AI-robotics.jpg\",\"datePublished\":\"2023-10-05T12:53:51+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/testing-AI-robotics.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/testing-AI-robotics.jpg\",\"width\":1000,\"height\":563},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Open X-Embodiment dataset, RT-X model a leap for AI robots\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/da\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Open X-Embodiment-datas\u00e6t, RT-X-model er et spring for AI-robotter | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/da\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/","og_locale":"da_DK","og_type":"article","og_title":"Open X-Embodiment dataset, RT-X model a leap for AI robots | DailyAI","og_description":"Google\u2019s DeepMind worked with 33 different academic labs to create an AI training dataset based on 22 different robot types. Robots are really good at doing one specific thing. If you want it to do something even slightly different, the robot needs to be trained from scratch. The ultimate goal for robotics is to have a robot that is good at a general range of actions with the ability to learn new skills by itself. To train an AI model you need a large dataset of data related to the purpose of the model. Language models like GPT-4 are trained","og_url":"https:\/\/dailyai.com\/da\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/","og_site_name":"DailyAI","article_published_time":"2023-10-05T12:53:51+00:00","og_image":[{"width":1000,"height":563,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet af":"Eugene van der Watt","Estimeret l\u00e6setid":"3 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Open X-Embodiment dataset, RT-X model a leap for AI robots","datePublished":"2023-10-05T12:53:51+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/"},"wordCount":521,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg","keywords":["DeepMind","Google","machine learning","Robotics"],"articleSection":["Industry"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/","url":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/","name":"Open X-Embodiment-datas\u00e6t, RT-X-model er et spring for AI-robotter | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg","datePublished":"2023-10-05T12:53:51+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/testing-AI-robotics.jpg","width":1000,"height":563},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/10\/open-x-embodiment-dataset-rt-x-model-a-leap-for-ai-robots\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Open X-Embodiment dataset, RT-X model a leap for AI robots"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Din daglige dosis af AI-nyheder","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene har en baggrund som elektronikingeni\u00f8r og elsker alt, hvad der har med teknologi at g\u00f8re. N\u00e5r han tager en pause fra at l\u00e6se AI-nyheder, kan du finde ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/da\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6133","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/comments?post=6133"}],"version-history":[{"count":4,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6133\/revisions"}],"predecessor-version":[{"id":6139,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6133\/revisions\/6139"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/6136"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=6133"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=6133"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=6133"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}