{"rewrite":{"id":"r_8b4ec831808643fb7ed2106d","clusterId":"c_eb5cba5c8320fa3afc2315a3","slug":"google-deepmind-unveils-gemini-robotics-2-for-whole-body-robot-control","model":"deepseek-v4-flash:free","headline":"Google DeepMind Unveils Gemini Robotics 2 for Whole-Body Robot Control","summary":"Google DeepMind announced Gemini Robotics 2 on July 30, 2026, a suite of Vision-Language-Action models that control robots from walking to fine two-handed tasks. The models handle posture, object manipulation, and multi-robot collaboration, adapting to different robot bodies. A higher-level model, Gemini Robotics ER 2, manages long task sequences and outperformed its predecessor in evaluations.","whyItMatters":"The suite moves beyond pre-programmed industrial actions by letting a single model control different robot shapes, from tabletop arms to full humanoids, while a separate model handles multi-step task planning.","webCardHtml":"\u003cp\u003eGoogle DeepMind\u0026#39;s Gemini Robotics 2 is a Vision-Language-Action model that turns camera images and language instructions into robot actions. The same model can drive tabletop arms and full-body humanoids, combining arm movements with walking, crouching, and shifting the center of gravity.\u003c/p\u003e\u003cp\u003eEvaluations with the Apollo and Inspire hands showed success rates of 68.4 percent lifting objects from a table, 45.7 percent from the floor, and 76.3 percent from a shelf. Fine manipulation with two-finger grippers on the Franka Duo hit 74.2 percent for object transfer, 78.9 percent for packing tools, and 89.6 percent for part insertion. A five-fingered Sharpa hand with 22 degrees of freedom reached 92 percent removing a light bulb, though complex tasks like tying a garbage bag (44 percent) and closing a zippered bag (40 percent) remain difficult.\u003c/p\u003e\u003cp\u003eThe companion Gemini Robotics ER 2 model plans long task sequences, making hundreds of decisions over several minutes. It outperformed the prior ER 1.6 across real-world VLA, simulated VLA, and human teleoperation control methods.\u003c/p\u003e","blueskyPost":"Google DeepMind's Gemini Robotics 2 controls robots from walking to fine finger work with one VLA model. Evaluations show strong table and shelf lifting, while multi-finger tasks like tying bags still lag. A separate ER 2 model handles long task sequences.","twitterPost":"Google DeepMind announced Gemini Robotics 2, a VLA model suite controlling whole-body robots from walking to two-handed fine tasks. ER 2 handles long task sequences and outperformed its predecessor across control methods.","threadsPost":null,"newsletterBlurb":"Google DeepMind announced Gemini Robotics 2, a Vision-Language-Action model suite that controls robots from walking to fine two-handed manipulation. Evaluations show strong performance on lifting and insertion tasks, while complex multi-finger actions still struggle. A companion ER 2 model plans long task sequences and outperformed its predecessor.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260731-google-deepmind-gemini-robotics-2/\",\"title\":\"Google DeepMind announces 'Gemini Robotics 2,' an AI model for robots that can control the entire body from walking to fine two-handed tasks\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4676,"outputTokens":692,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1786278110,"createdAt":"2026-08-09T12:09:43.000Z","publishedAt":"2026-08-09T12:11:44.000Z","updatedAt":"2026-08-09T12:09:43.000Z"},"cluster":{"id":"c_eb5cba5c8320fa3afc2315a3","canonicalTitle":"Google DeepMindがロボット向けAIモデル「Gemini Robotics 2」を発表、歩行から両手の細かな作業まで全身を制御可能に","representativeArticleId":"a_13c0dd1f3ac9a3b2af730f79","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"Gemini Robotics 2\"],\"studios\":[\"Google DeepMind\"],\"people\":[],\"type\":\"announcement\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-07-31T01:37:00.000Z","lastSeenAt":"2026-07-31T01:37:00.000Z","updatedAt":"2026-08-09T12:11:44.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260731-google-deepmind-gemini-robotics-2/","title":"Google DeepMindがロボット向けAIモデル「Gemini Robotics 2」を発表、歩行から両手の細かな作業まで全身を制御可能に"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["Gemini Robotics 2"],"studios":["Google DeepMind"],"people":[],"type":"announcement","domain":"other","is_roundup":false},"keyFacts":null}