{"id":126389,"date":"2026-07-31T23:47:22","date_gmt":"2026-07-31T23:47:22","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/126389\/"},"modified":"2026-07-31T23:47:22","modified_gmt":"2026-07-31T23:47:22","slug":"google-deepmind-unveils-enhanced-ai-model-for-robotics","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/126389\/","title":{"rendered":"Google DeepMind Unveils Enhanced AI Model for Robotics"},"content":{"rendered":"<p>                         <img class=\"attachment-full size-full wp-post-image\" alt=\"Google DeepMind Unveils Enhanced AI Model for Robotics\" decoding=\"async\"  src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/05\/II-agenty-AI-agents.webp\"\/><\/p>\n<p class=\"short_excerpt\">Google DeepMind unveils Gemini Robotics 2 for full-body robot control.<\/p>\n<p class=\"wp-block-paragraph\">Google DeepMind has <a href=\"https:\/\/deepmind.google\/blog\/gemini-robotics-2-brings-whole-body-intelligence-to-robots\/\" rel=\"nofollow noopener\" target=\"_blank\">introduced<\/a> Gemini Robotics 2, a Vision-Language-Action (VLA) model for full-body robot control, along with the ER 2 solution for comprehensive planning and coordination of multiple devices.<\/p>\n<p class=\"wp-block-paragraph\">Gemini Robotics 2 translates text and visual data into motor actions. The model is designed for robots of various form factors, from desktop manipulators to full-sized humanoids.<\/p>\n<p class=\"wp-block-paragraph\">Unlike the previous version, the AI now controls the entire body. This enables robots to walk, squat, bend, reach, and lift objects in confined spaces.<\/p>\n<p class=\"wp-block-paragraph\">In demonstrations, the humanoid Apptronik Apollo 2, powered by Gemini Robotics 2, picked up a watering can, removed a baseball glove from a shelf, and located specific items.<\/p>\n<p><img decoding=\"async\" src=\"data:image\/svg+xml,%3Csvg%20xmlns=\" http:=\"\" alt=\"image\" class=\"wp-image-285298\" data-lazy-src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/07\/img-70897c18de1448be-1138648571510742.webp\"\/>Apollo 2\u2019s agility metrics. Source: Google DeepMind.<\/p>\n<p class=\"wp-block-paragraph\">Google DeepMind also announced improved motor skills: the model supports complex hands with 22 degrees of freedom and can perform tasks like tying knots, sealing packages, or unscrewing light bulbs.<\/p>\n<p class=\"wp-block-paragraph\">The update also affects the ER 2 model, which DeepMind describes as a \u201chigh-level brain\u201d for robots. The solution plans multi-step tasks, monitors whether actions are completed or need repetition, and allocates work among multiple robots.<\/p>\n<p class=\"wp-block-paragraph\">In one video, Apollo 2 instructs a two-armed Google robot to organize tools into a container while cleaning a garage.<\/p>\n<p class=\"wp-block-paragraph\">The company also showcased the local Gemini Robotics On-Device 2 model. It operates without internet connectivity and adapts to new robots with fewer than 200 examples in just a few hours of training.<\/p>\n<p class=\"wp-block-paragraph\">Currently, Gemini Robotics 2 is available in private preview, while ER 2 is accessible via the Gemini API and Google AI Studio. On-Device 2 is being tested by trusted partners.<\/p>\n<p class=\"wp-block-paragraph\">Earlier, in July, the company Humanoid <a href=\"https:\/\/forklog.com\/en\/news\/humanoid-unveils-kinetiq-ascend-to-train-humanoid-robots-on-real-manufacturing-tasks\" rel=\"nofollow noopener\" target=\"_blank\">introduced<\/a> an approach for training robots on real-world production tasks.<\/p>\n<p>Follow ForkLog on social media<\/p>\n<p>Found a mistake in the text? Select it and press CTRL+ENTER<\/p>\n","protected":false},"excerpt":{"rendered":"Google DeepMind unveils Gemini Robotics 2 for full-body robot control. Google DeepMind has introduced Gemini Robotics 2, a&hellip;\n","protected":false},"author":2,"featured_media":24343,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9],"tags":[25,5044,132,7543,3045],"class_list":["post-126389","post","type-post","status-publish","format-standard","has-post-thumbnail","category-google","tag-artificial-intelligence","tag-deepmind","tag-google","tag-google-deepmind","tag-robots"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/126389","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=126389"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/126389\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/24343"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=126389"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=126389"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=126389"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}