# Google DeepMind Releases Gemini Robotics 2 for Humanoid Control

> Google DeepMind has released Gemini Robotics 2, a family of three models aimed at giving robots something closer to whole-body intelligence. The lineup splits the work: a vision-language-action model for motor control, an embodied-reasoning model called ER 2, and an On-Device 2 version that runs locally without a cloud connection. The demos are the interesting part. On a collaborative Franka arm, the system hit 74 to 90 percent success on delicate gripper tasks, and a humanoid platform called Apollo managed 45 to 76 percent on full-body manipulation. In practice that means chores people rarely associate with robots: watering plants, inserting tape, tying garbage bags, and screwing in lightbulbs. Those success rates are still far from the reliability you would want at home, but the trajectory matters. By packaging perception, reasoning, and control into models that generalize across different robot bodies, DeepMind is betting that the same foundation-model approach that transformed text and images can finally make general-purpose robots practical. Early access is opening through a Trusted Tester program.

_Section: [Daily AI Updates](https://www.wortins.com/daily-ai) · Source: Google DeepMind · Published Wednesday, August 5, 2026_

## Wortins' read

Google DeepMind has released Gemini Robotics 2, a family of three models aimed at giving robots something closer to whole-body intelligence. The lineup splits the work: a vision-language-action model for motor control, an embodied-reasoning model called ER 2, and an On-Device 2 version that runs locally without a cloud connection. The demos are the interesting part. On a collaborative Franka arm, the system hit 74 to 90 percent success on delicate gripper tasks, and a humanoid platform called Apollo managed 45 to 76 percent on full-body manipulation. In practice that means chores people rarely associate with robots: watering plants, inserting tape, tying garbage bags, and screwing in lightbulbs. Those success rates are still far from the reliability you would want at home, but the trajectory matters. By packaging perception, reasoning, and control into models that generalize across different robot bodies, DeepMind is betting that the same foundation-model approach that transformed text and images can finally make general-purpose robots practical. Early access is opening through a Trusted Tester program.

## Source

[Read the full story at Google DeepMind](https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/)

## Related coverage

- [Researchers used AI to build a WeChat worm that spreads through phone calls](https://www.wortins.com/story/researchers-used-ai-to-build-a-wechat-worm-that-spreads-thro-8bf3f469) — [The Next Web](https://thenextweb.com/news/wechat-worm-ai-calif-tencent-zero-click)
- [A look at why the oft-discussed predictions that AI will deliver double-digit GDP growth in advanced economies are extremely unlikely over the next 10-15 years (Ghosts of Electricity)](https://www.wortins.com/story/a-look-at-why-the-oft-discussed-predictions-that-ai-will-del-6241fa38) — [Techmeme](https://www.techmeme.com/260910/p10#a260910p10)
- [Suno launches v6 music models built with Warner, BMG, and Believe](https://www.wortins.com/story/suno-launches-v6-music-models-built-with-warner-bmg-and-beli-9ba43843) — [The Decoder](https://the-decoder.com/suno-launches-v6-music-models-built-with-warner-bmg-and-believe/)
- [Inception launches Mercury 2.5 at 1,107 tokens per second](https://www.wortins.com/story/inception-launches-mercury-2-5-at-1-107-tokens-per-second-7999ed1b) — [TestingCatalog](https://www.testingcatalog.com/inception-launches-mercury-2-5-at-1-107-tokens-per-second/)
- [Trump officials say AI will help save rural health care. Some leaders in the field don’t believe it](https://www.wortins.com/story/trump-officials-say-ai-will-help-save-rural-health-care-some-bf0e7d83) — [STAT](https://www.statnews.com/2026/09/10/rural-health-care-ai-adoption-challenges-part-4-unraveled-series/?utm_campaign=rss)
- [IBM and NASA release an open-source lunar foundation model](https://www.wortins.com/story/ibm-and-nasa-release-an-open-source-lunar-foundation-model-0522b9e8) — [The Next Web](https://thenextweb.com/news/nasa-ibm-lunar-foundation-model-open-source)

---

_Curated and written by [Wortins](https://www.wortins.com) — The daily AI briefing. Every story links to its original source; the "Wortins read" on each is our own original analysis. [About Wortins & our editorial approach](https://www.wortins.com/about)._
