Knowledge / Gemini Robotics 2 Signal

Gemini Robotics 2 Signal

Google DeepMind's July 2026 update introduced Gemini Robotics 2 as a VLA intelligence layer for different robot embodiments.

What changed

Google DeepMind describes Gemini Robotics 2 as a VLA model that converts vision and language input into motor control. The same release describes whole-body humanoid control, advanced dexterity and multi-robot collaboration.

Why it matters for embodiment

The significance is architectural: intelligence is presented as a layer that can adapt across different physical platforms rather than being tied to one robot body.

Related layer

Gemini Robotics ER 2 is described as the higher-level embodied reasoning model, while On-Device 2 targets local execution on robotic hardware.

Primary source

Read the primary source →

Editorial guide · Reviewed September 2026