DeepMind Details Gemini Robotics 2: Whole-Body Intelligence and Multi-Robot Collaboration
GoogleDeepMind · x · 2026-07-30
Google DeepMind officially launched Gemini Robotics 2, the intelligence layer powering the next generation of adaptable robots. Unlike traditional pre-programmed robots, the new model breaks through previous limitations to deliver genuine intelligent whole-body control.
Key capabilities include:
- Advanced Dexterity: Capable of controlling a five-fingered hand for intricate tasks like tying knots or screwing in lightbulbs, as well as managing complex packing.
- Multi-Robot Collaboration: Completely different types of robots can communicate and work together to solve problems a single robot couldn't.
- Local On-Device Execution: The model runs locally and seamlessly adapts to entirely new robotic bodies in just a few hours.
This ecosystem is driven by three core models: Gemini Robotics 2 (an advanced VLA model), Gemini Robotics ER 2 (for video understanding and multi-step planning), and On-Device 2 (for local adaptation).
Related event: Google Unveils Gemini Robotics 2 and ER 2 for Full-Body Robot Intelligence(71 posts)→
More from Embodied
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Tesla's hover car isn't a flying car — compressed air can't sustain flight — tinyfool · 2026-10-16
- Scobleizer relays claim that Optimus demo will be even more mind-blowing than the road-flipping Roadster — Scobleizer · 2026-10-16
- Indie dev's AI PASSPORT wearable firmware hits 1,200+ downloads in days — ezshine · 2026-10-16
- 1X Opens California Factory for Mass Production of NEO Humanoid Robots — emmanuelvivier · 2026-10-16