Google DeepMind Launches Gemini Robotics 2 for Whole-Body Robot Intelligence
heiga_zen · x · 2026-07-31
Google DeepMind has officially launched the Gemini Robotics 2 model, designed to power the next generation of adaptable robots. This major advance introduces intelligent whole-body control, advanced dexterity, and multi-robot collaboration.
Key highlights include:
- Whole-body control & dexterity: Enables humanoids to reason through movements, allowing them to walk, crouch, stretch, and manipulate objects to clean up cluttered rooms. The model can control 22 DOF hands for complex tasks and works with grippers for tight packing.
- Multi-robot collaboration: Allows multiple robots to team up and finish jobs faster.
- On-device deployment & adaptability: The profound intelligence can run locally on-device while seamlessly adapting to entirely new robotic bodies in just a few hours.
Positioned as DeepMind's most advanced vision-language-action model (VLA), it represents a leap from traditional pre-programmed and teleoperated robots towards truly autonomous learning and adaptation in unpredictable environments.
Related event: Google Unveils Gemini Robotics 2 and ER 2 for Full-Body Robot Intelligence(71 posts)→
More from Embodied
- iPhone Duo foldable appears on South African retailer iStore at R47,999 in apparent leak — shauntrennery · 2026-10-16
- New paper: game-theoretic motion planning shows it can be legal to break the rules — GioeleZardini · 2026-10-16
- Autonomous vehicle demo shows car reversing to break narrow-road deadlock, with a robotic arm to shift gears — sanjeevs_iitr · 2026-10-16
- Surface Laptop Ultra review: a beautiful $2,599 laptop for an AI future that hasn't arrived — tomwarren · 2026-10-16
- Waymo brings robotaxis to Toronto, targeting rider service in 2028 — CSProfKGD · 2026-10-16
- Musk shows Cybertruck hovering on jets, delivering on 'flying cars' promise — XFreeze · 2026-10-16