{"id":537248,"date":"2026-07-07T09:44:11","date_gmt":"2026-07-07T09:44:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/537248\/"},"modified":"2026-07-07T09:44:11","modified_gmt":"2026-07-07T09:44:11","slug":"nvidia-and-hugging-face-bring-new-models-and-frameworks-to-lerobot-for-the-open-robotics-community","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/537248\/","title":{"rendered":"NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community"},"content":{"rendered":"<p>Open source AI has shown how quickly developers can innovate when models, data and tools are shared. <a target=\"_blank\" href=\"https:\/\/www.nvidia.com\/en-us\/industries\/robotics\/\" rel=\"nofollow noopener\">Robotics<\/a> has the same opportunity, but advancements in <a target=\"_blank\" href=\"https:\/\/www.nvidia.com\/en-us\/glossary\/generative-physical-ai\/\" rel=\"nofollow noopener\">physical AI<\/a> development can still be gated by costly and fragmented resources, from large datasets and robot foundation models to simulation, compute and validation tools.<\/p>\n<p>NVIDIA and <a target=\"_blank\" href=\"https:\/\/huggingface.co\/blog\/lerobot-release-v060\" rel=\"nofollow noopener\">Hugging Face<\/a> are collaborating to bring the <a target=\"_blank\" href=\"https:\/\/developer.nvidia.com\/isaac\/gr00t\" rel=\"nofollow noopener\">NVIDIA Isaac GR00T 1.7<\/a> open, reasoning vision language action (VLA) model for <a target=\"_blank\" href=\"https:\/\/www.nvidia.com\/en-us\/use-cases\/humanoid-robots\/\" rel=\"nofollow noopener\">humanoid robots<\/a> and the <a target=\"_blank\" href=\"https:\/\/nvidia.github.io\/IsaacTeleop\/\" rel=\"nofollow noopener\">NVIDIA Isaac Teleop<\/a> framework to LeRobot \u2014 Hugging Face\u2019s open source library for robotics \u2014 with <a target=\"_blank\" href=\"https:\/\/www.nvidia.com\/en-us\/ai\/cosmos\/\" rel=\"nofollow noopener\">NVIDIA Cosmos 3<\/a>, a frontier model for physical AI, planned soon. Together, these integrations give developers a more accessible and standardized path for end-to-end robot development while driving innovation and collaboration across the open robotics community.<\/p>\n<p>\u201cOpen source is how a field turns advanced research into something people can study, adapt and build on,\u201d said Thomas Wolf, cofounder and chief science officer at Hugging Face. \u201cWith NVIDIA Isaac GR00T 1.7 and Isaac TeleOp in LeRobot today, robotics developers can use shared models, data and workflows to train and evaluate robots in the open. And with NVIDIA Cosmos 3 planned next, the community will have a path to bring frontier world models into that same collaborative loop.\u201d\u00a0<\/p>\n<p>An Open Pipeline for Robot Foundation Models<\/p>\n<p>Hugging Face LeRobot is an open source robotics library for training, running and sharing robot datasets, models, policies and workflows. NVIDIA\u2019s continued partnership with Hugging Face connects NVIDIA\u2019s 3 million robotics developers with Hugging Face\u2019s 16 million AI builders, expanding access to frontier physical AI tools through open workflows.<\/p>\n<p>Bringing NVIDIA physical AI capabilities into LeRobot gives developers a common way to collect and standardize data, train and fine-tune robot foundation models, evaluate performance and deploy models through open workflows. The integrations include:<\/p>\n<p>NVIDIA Isaac Teleop, an open source framework for robot data collection, helps developers capture high-quality human demonstrations from external devices using standardized, interoperable formats, then expand and share datasets with the community, all directly in LeRobot.\u00a0<br \/>\nNVIDIA Isaac GR00T 1.7, the first open and commercially viable robot foundation model, makes it easier to post-train and deploy models through LeRobot workflows, helping developers adapt GR00T to new robot embodiments and tasks with benchmarked performance.<br \/>\nNVIDIA Cosmos 3, a frontier world foundation model for physical AI coming soon to LeRobot, will help developers generate and augment robotics data, simulate scenarios and support policy development when real-world data is limited or too expensive to collect.<\/p>\n<p>These integrations build on a broader set of NVIDIA resources already connected to LeRobot to support the full robotics development loop, including:\u00a0<\/p>\n<p>The largest <a target=\"_blank\" href=\"https:\/\/huggingface.co\/collections\/nvidia\/physical-ai\" rel=\"nofollow noopener\">open source physical AI dataset<\/a>, downloaded more than 15 million times, which includes more than 350,000 real and simulated trajectories and 57 million grasps to help developers kickstart their robotics workflows.<br \/>\n<a target=\"_blank\" href=\"https:\/\/developer.nvidia.com\/isaac\/sim\" rel=\"nofollow noopener\">NVIDIA Isaac Sim<\/a>\u2013 and <a target=\"_blank\" href=\"https:\/\/developer.nvidia.com\/isaac\/lab\" rel=\"nofollow noopener\">Isaac Lab<\/a>-based simulation frameworks to help developers set up environments, generate robot data, test policies and validate behaviors before moving to physical robots.<br \/>\n<a target=\"_blank\" href=\"https:\/\/developer.nvidia.com\/isaac\/lab-arena\" rel=\"nofollow noopener\">NVIDIA Isaac Lab-Arena<\/a> in LeRobot Environment Hub to enable developers to quickly prototype complex simulation environments, register them in LeRobot EnvHub and seamlessly use them within the LeRobot ecosystem to train and evaluate generalist robot policies such as GR00T, Pi and SmolVLA.<br \/>\nNVIDIA Jetson Thor integration with LeRobot\u2019s Reachy 2 to support deployment of VLA models on open source humanoid robots.<\/p>\n<p>Learn more about how to use Isaac Teleop, Isaac GR00T 1.7 and Isaac Lab-Arena with LeRobot for end-to-end humanoid development and <a target=\"_blank\" href=\"https:\/\/huggingface.co\/blog\/nvidia\/nvidia-isaac-teleop-and-gr00t17-in-lerobot\" rel=\"nofollow noopener\">explore detailed LeRobot integration workflows<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"Open source AI has shown how quickly developers can innovate when models, data and tools are shared. Robotics&hellip;\n","protected":false},"author":2,"featured_media":537249,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,31266,61,60,200206,209791,11632,72804,10116,135374,228321,80],"class_list":["post-537248","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-cosmos","tag-ie","tag-ireland","tag-isaac","tag-jetson","tag-open-source","tag-physical-ai","tag-robotics","tag-simulation-and-design","tag-synthetic-data-generation","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/537248","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=537248"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/537248\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/537249"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=537248"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=537248"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=537248"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}