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:

Related event: Google DeepMind Unveils Gemini Robotics 2 for Full-Body Robot Intelligence and Multi-Robot Collaboration(10 posts)→

Original post →

More from Embodied

Embodied channel →