Google DeepMind Unveils Gemini Robotics 2 for Whole-Body Robot Intelligence
fofrAI · x · 2026-07-30
Google DeepMind has introduced three new robotics models designed to power the next generation of highly adaptable robots.
- Gemini Robotics 2: The most advanced vision-language-action (VLA) model that converts vision and language into whole-body robot actions, enabling walking, crouching, fine manipulation, and multi-robot collaboration.
- Gemini Robotics ER 2: An embodied reasoning model that helps robots better understand the world, communicate with humans, and plan multi-step tasks.
- Gemini Robotics On-Device 2: Optimized for local execution, capable of rapidly adapting to entirely new robotic embodiments with just a few hours of data.
Related event: Google DeepMind Unveils Gemini Robotics 2(20 posts)→
More from Embodied
- Google DeepMind Launches Gemini Robotics 2 for Whole-Body Control and Multi-Robot Collaboration — CyberRobooo · 2026-07-31
- DeepMind's Gemini Robotics 2 Enables Multi-Robot Collaboration — CyberRobooo · 2026-07-31
- YC-Backed WaveSight: A New Camera That Sees Through Walls — ycombinator · 2026-07-31
- AI Pendant Friend Relaunches with a Speaker, Doubles in Price — The Verge AI · 2026-07-31
- New MT3 Paradigm Enables Robots to Learn 1000 Tasks in Under 24 Hours — chris_j_paxton · 2026-07-31
- Simulated LiDAR Needs Real-World Noise for Better Robustness — Sentdex · 2026-07-31