Google DeepMind Launches Gemini Robotics 2: Single Model Controls Whole-Body Movement of Humanoids
DynamicWebPaige · x · 2026-07-31
Google DeepMind has launched Gemini Robotics 2, a next-generation physical AI system designed to bring full-body intelligence, advanced dexterity, and multi-robot teamwork to humanoids.
The system combines three models:
- Gemini Robotics 2: Converts vision and instructions into movement.
- ER 2: Plans tasks lasting several minutes, tracks hundreds of decisions, and coordinates multiple robots.
- On-Device 2: Runs locally and can adapt to a completely new two-arm robot with fewer than 200 examples collected over a few hours.
The same Robotics 2 checkpoint successfully controlled different versions of Apptronik’s Apollo humanoid and a Franka Duo robot. However, performance remains uneven: success rates ranged from 45.7% to 76.3% on whole-body tasks. Five-finger manipulation success varied significantly by task, from 32% for using a dustpan to 92% for unscrewing a bulb.
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