DeepMind Launches Gemini Robotics 2 for Humanoid Whole-Body Control
GoogleDeepMind · x · 2026-07-30
Google DeepMind introduced Gemini Robotics 2, advancing physical AI beyond tabletop tasks to intelligent whole-body control. This vision-language-action (VLA) model equips humanoid robots with high dexterity for intricate actions like tying knots or screwing in lightbulbs, and enables multi-robot collaboration.
Two additional models were also announced:
- Gemini Robotics ER 2: Capable of real-world video understanding and complex, multi-step planning.
- On-Device 2: Runs locally and adapts to entirely new robot bodies in just a few hours.
More from Embodied
- Viam Robotics Hackathon: Chess-Playing and Lab Robots Built in a Day — ditzikow · 2026-07-30
- Gemini Robotics Model Accurately Splits 9-Minute Excavator Video into 40+ Clips — DynamicWebPaige · 2026-07-30
- Walden Robotics Bets on Real-World Deployment Over Flashy Demos — adnothing · 2026-07-30
- Economics of Automation: ROI Must Outperform Human Labor by at Least 50% — MatthewChang · 2026-07-30
- DeepMind Launches Gemini Robotics 2 for Whole Body Intelligence — ai2027 · 2026-07-30
- Google Launches Gemini Robotics ER 2 for Embodied Reasoning — OfficialLoganK · 2026-07-30