{"id":311878,"date":"2023-10-25T19:53:27","date_gmt":"2023-10-25T17:53:27","guid":{"rendered":"http:\/\/sftarticles.wpenginepowered.com\/es\/?p=311878"},"modified":"2025-06-12T18:42:48","modified_gmt":"2025-06-12T16:42:48","slug":"nvidia-tiene-un-nuevo-trabajo-entrenar-a-los-robots-del-futuro","status":"publish","type":"post","link":"https:\/\/cms-articles.softonic.io\/es\/nvidia-tiene-un-nuevo-trabajo-entrenar-a-los-robots-del-futuro\/","title":{"rendered":"NVIDIA tiene un nuevo trabajo: entrenar a los robots del futuro"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Cient\u00edficos de <strong>NVIDIA<\/strong> procedentes de la Universidad de Pensilvania han desarrollado un nuevo <a href=\"https:\/\/www.softonic.com\/articulos\/ha-llegado-la-inteligencia-artificial-al-mundo-del-cine-adulto-si-pero-de-una-forma-que-no-imaginas\" title=\"agente de IA\">agente de IA<\/a> destinado a entrenar robots. El algoritmo, bautizado como Eureka, utiliza el famoso modelo de lenguaje <strong>GPT-4<\/strong>, el cual tambi\u00e9n potencia a <strong>ChatGPT<\/strong>. Dicho algoritmo servir\u00eda para mejorar el funcionamiento de los robots tanto a nivel de razonamiento como motriz. <\/p>\n\n\n<div class=\"sc-card-program\">\r\n  <div class=\"sc-card-program__body\">\r\n    <div class=\"sc-card-program__row clearfix\">\r\n      <div class=\"sc-card-program__col-logo\">\r\n        <img decoding=\"async\" class=\"sc-card-program__img\" src=\"https:\/\/images.sftcdn.net\/images\/t_app-icon-m\/p\/47ef1772-2a82-4750-b97a-354b13dbd112\/1330587929\/chatgpt-Download-ChatGPT.jpg\" alt=\"ChatGPT\" width=\"100px\" height=\"100px\">\r\n      <\/div>\r\n      <div class=\"sc-card-program__col-title\">\r\n        <span class=\"sc-card-program__title\">ChatGPT<\/span>\r\n        <a class=\"sc-card-program__button sc-card-program-internal\" href=\"https:\/\/chatgpt.softonic.com\/aplicaciones-web\" target=\"_self\" rel=\"noopener noreferrer\">DESCARGAR<\/a>\r\n      <\/div>\r\n      <div class=\"sc-card-program__col-rating\">\r\n        <svg class=\"rating-score__content\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" version=\"1.1\" x=\"0\" y=\"0\" viewbox=\"0 0 50 50\" enable-background=\"new 0 0 50 50\" xml:space=\"preserve\"><path class=\"rating-score__background rating-score--good\" fill=\"none\" stroke-width=\"6\" stroke-miterlimit=\"10\" d=\"M40 40c8.3-8.3 8.3-21.7 0-30s-21.7-8.3-30 0 -8.3 21.7 0 30\"><\/path><path class=\"rating-score__value rating-score__value--0\" fill=\"none\" stroke-width=\"6\" stroke-dashoffset=\"0\" stroke-miterlimit=\"10\" d=\"M40 40c8.3-8.3 8.3-21.7 0-30s-21.7-8.3-30 0 -8.3 21.7 0 30\"><\/path><text class=\"rating-score__number\" content=\"\" text-anchor=\"middle\" transform=\"matrix(1 0 0 1 25 31.0837)\" data-auto=\"app-user-score\"><\/text><\/svg>\r\n      <\/div>\r\n    <\/div>\r\n    <div class=\"sc-card-program__row\">\r\n      <span class=\"sc-card-program__description\"><\/span>\r\n    <\/div>\r\n    <div class=\"sc-card-program__row\">\r\n      <img decoding=\"async\" class=\"sc-card-program__bigpic\" src=\"\" onerror=\"this.style.display='none'\">\r\n    <\/div>\r\n    <a class=\"sc-card-program__link track-link sc-card-program-internal\" href=\"https:\/\/chatgpt.softonic.com\/aplicaciones-web\" target=\"_self\" rel=\"noopener noreferrer\"><\/a>\r\n  <\/div>\r\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/eureka-research.github.io\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Eureka<\/a> genera <strong>programas de recompensa<\/strong> que sirven para mejorar la destreza de los robots y que sepan realizar tareas complejas. Esto es esencial para que los robots puedan ser \u00fatiles en el d\u00eda a d\u00eda, ya que deben mover sus cuerpos en entornos dif\u00edciles y de forma eficiente. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Para mostrarlo, NVIDIA ha presentado un v\u00eddeo que recoge las casi <strong>30 habilidades<\/strong> que los robots han desarrollado gracias a Eureka. Una de ellas se trata de una mano rob\u00f3tica que realiza <strong>trucos con un bol\u00edgrafo<\/strong>. Y es que siendo sinceros, la agilidad de dicha mano no tiene nada que envidiarle a la de un humano. Otras de las habilidades que ha podido ense\u00f1ar Eureka a los robots incluyen abrir cajones, lanzar pelotas, atraparlas y mucho m\u00e1s. <\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Eureka! Extreme Robot Dexterity with LLMs | NVIDIA Research Paper\" width=\"840\" height=\"473\" src=\"https:\/\/www.youtube.com\/embed\/sDFAWnrCqKc?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u00bfC\u00f3mo entrena Eureka a los robots?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Uno de los procesos utilizados para entrenar a un robot pasa por hacer que ejecuten tareas como desplazarse o agarrar objetos dentro de un entorno f\u00edsico. Cada vez que falla una de estas tareas, el robot &#8220;aprende&#8221; de sus errores para no cometerlos en el futuro. Sin embargo, los investigadores de NVIDIA han probado otra v\u00eda mucho m\u00e1s &#8220;digital&#8221;.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Para ello, se han empleado entornos virtuales similares a los de los videojuegos. Gracias a la plataforma <strong>Isaac Gym<\/strong>, se puede simular la f\u00edsica del mundo real y de esta forma, que los robots entrenen sus capacidades dentro de mundos virtuales. Isaac Gym se basa en <strong>NVIDIA Omniverse<\/strong>, una plataforma de colaboraci\u00f3n de gr\u00e1ficos 3D en tiempo real.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Seg\u00fan podemos leer en el <a href=\"https:\/\/blogs.nvidia.com\/blog\/2023\/10\/20\/eureka-robotics-research\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"blog oficial de NVIDIA\">blog oficial de NVIDIA<\/a>, &#8220;el agente de IA utiliza GPT-4 y la IA generativa para escribir c\u00f3digo que recompensa a los robots y les refuerza el aprendizaje&#8221;. Por si fuer poco, <strong>la IA es capaz de mejorarse a si misma<\/strong> con los resultados de las pruebas. <\/p>\n\n\n<div class=\"sc-card-program\">\r\n  <div class=\"sc-card-program__body\">\r\n    <div class=\"sc-card-program__row clearfix\">\r\n      <div class=\"sc-card-program__col-logo\">\r\n        <img decoding=\"async\" class=\"sc-card-program__img\" src=\"https:\/\/images.sftcdn.net\/images\/t_app-icon-m\/p\/47ef1772-2a82-4750-b97a-354b13dbd112\/1330587929\/chatgpt-Download-ChatGPT.jpg\" alt=\"ChatGPT\" width=\"100px\" height=\"100px\">\r\n      <\/div>\r\n      <div class=\"sc-card-program__col-title\">\r\n        <span class=\"sc-card-program__title\">ChatGPT<\/span>\r\n        <a class=\"sc-card-program__button sc-card-program-internal\" href=\"https:\/\/chatgpt.softonic.com\/aplicaciones-web\" target=\"_self\" rel=\"noopener noreferrer\">DESCARGAR<\/a>\r\n      <\/div>\r\n      <div class=\"sc-card-program__col-rating\">\r\n        <svg class=\"rating-score__content\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" version=\"1.1\" x=\"0\" y=\"0\" viewbox=\"0 0 50 50\" enable-background=\"new 0 0 50 50\" xml:space=\"preserve\"><path class=\"rating-score__background rating-score--good\" fill=\"none\" stroke-width=\"6\" stroke-miterlimit=\"10\" d=\"M40 40c8.3-8.3 8.3-21.7 0-30s-21.7-8.3-30 0 -8.3 21.7 0 30\"><\/path><path class=\"rating-score__value rating-score__value--0\" fill=\"none\" stroke-width=\"6\" stroke-dashoffset=\"0\" stroke-miterlimit=\"10\" d=\"M40 40c8.3-8.3 8.3-21.7 0-30s-21.7-8.3-30 0 -8.3 21.7 0 30\"><\/path><text class=\"rating-score__number\" content=\"\" text-anchor=\"middle\" transform=\"matrix(1 0 0 1 25 31.0837)\" data-auto=\"app-user-score\"><\/text><\/svg>\r\n      <\/div>\r\n    <\/div>\r\n    <div class=\"sc-card-program__row\">\r\n      <span class=\"sc-card-program__description\"><\/span>\r\n    <\/div>\r\n    <div class=\"sc-card-program__row\">\r\n      <img decoding=\"async\" class=\"sc-card-program__bigpic\" src=\"\" onerror=\"this.style.display='none'\">\r\n    <\/div>\r\n    <a class=\"sc-card-program__link track-link sc-card-program-internal\" href=\"https:\/\/chatgpt.softonic.com\/aplicaciones-web\" target=\"_self\" rel=\"noopener noreferrer\"><\/a>\r\n  <\/div>\r\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Cient\u00edficos de NVIDIA procedentes de la Universidad de Pensilvania han desarrollado un nuevo agente de IA destinado a entrenar robots.<\/p>\n","protected":false},"author":9211,"featured_media":311998,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","wpcf-pageviews":1},"categories":[9317],"tags":[10529],"usertag":[],"vertical":[],"content-category":[],"class_list":["post-311878","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-chatgpt"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/posts\/311878","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/users\/9211"}],"replies":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/comments?post=311878"}],"version-history":[{"count":1,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/posts\/311878\/revisions"}],"predecessor-version":[{"id":360594,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/posts\/311878\/revisions\/360594"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/media\/311998"}],"wp:attachment":[{"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/media?parent=311878"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/categories?post=311878"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/tags?post=311878"},{"taxonomy":"usertag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/usertag?post=311878"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/vertical?post=311878"},{"taxonomy":"content-category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/es\/wp-json\/wp\/v2\/content-category?post=311878"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}