Google DeepMind Launches Gemini Robotics 2 for Intelligent Whole-Body Robot Control

jason_mayes · x · 2026-07-31

Google DeepMind has introduced Gemini Robotics 2, a new embodied AI model designed to serve as the intelligence layer for the next generation of adaptable robots.

As their most advanced vision-language-action (VLA) model, it equips robots with intelligent whole-body control, advanced dexterity, and multi-robot collaboration. For instance, a humanoid can autonomously walk, crouch, stretch, and clean up a cluttered room, or team up with other robots to finish tasks faster. Furthermore, this intelligence can run locally on-device while seamlessly adapting to entirely new robotic bodies in just a few hours.

Related event: Google DeepMind Unveils Gemini Robotics 2(69 posts)→

Original post →

More from Embodied

Embodied channel →