{"data":{"id":2105,"lang":"en","title":"Google DeepMind Unveils Gemini Robotics 2, Giving Humanoid Robots Whole-Body Intelligence","summary":"Google DeepMind's new Gemini Robotics 2 model suite gives humanoid robots full-body control and multi-robot teamwork, demoed on Apptronik's Apollo.","category":"ai","category_label":"AI","published_at":"2026-07-31T10:01:36Z","updated_at":"2026-07-31T10:01:36Z","url":"https://techtools.cz/tools/news/article/2105-google-deepmind-unveils-gemini-robotics-2-giving-humanoid-robots-whole-body","api_url":"https://techtools.cz/news-api/v1/articles/2105?lang=en","markdown_url":"https://techtools.cz/news-api/v1/articles/2105.md?lang=en","image_url":"https://d15shllkswkct0.cloudfront.net/wp-content/blogs.dir/1/files/2026/07/Google-1.png","word_count":158,"reading_time_minutes":1,"sources":[{"url":"https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/","domain":"deepmind.google"},{"url":"https://siliconangle.com/2026/07/30/google-deepmind-debuts-gemini-robotics-2-model-series-humanoid-robots/","domain":"siliconangle.com"}],"translation":{"lang":"cs","id":2178,"title":"Google DeepMind představil Gemini Robotics 2 — humanoidní roboti nyní ovládají celé tělo","url":"https://techtools.cz/tools/news/clanek/2178-google-deepmind-predstavil-gemini-robotics-2-humanoidni-roboti-nyni-ovladaji","api_url":"https://techtools.cz/news-api/v1/articles/2178?lang=cs"},"content":"Google DeepMind announced Gemini Robotics 2 on July 30, a new model suite that lets humanoid robots control their entire bodies, from walking and crouching to fine dual-hand manipulation, instead of just the upper body handled by the original Gemini Robotics model.\n\nThe release includes three parts: the core vision-language-action model driving full-body movement, Gemini Robotics ER 2, a reasoning \"brain\" that plans multi-step tasks lasting several minutes and coordinates teams of robots, and an On-Device 2 variant that runs locally without network latency and adapts to new robot bodies in just a few hours using fewer than 200 examples.\n\nIn a demonstration with Apptronik's Apollo robot, the system walked across a room, picked up a watering can while avoiding obstacles, and placed it on a shelf. DeepMind reported task success rates ranging from about 46% for floor pickups to 90% for precise insertion tasks with a separate gripper arm, and showed multi-finger dexterity using a 22-degree-of-freedom hand."}}