Gemini Robotics 2

All projects

Agents / Skills

An intelligence layer for whole-body robot control and embodied reasoning.

byGoogle DeepMind

Playable

Gemini Robotics 2 media is blocked

Allow external media to connect to the provider and play this content.

Description

A suite of models designed to power the next generation of adaptable robots, enabling whole-body coordination, advanced dexterity, and multi-robot collaboration. It includes a Vision-Language-Action (VLA) model for motor control and a specialized reasoning model (ER 2) that allows robots to plan multi-step tasks and communicate with humans.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: It demonstrates a significant leap in physical AI, enabling foundation-model-driven whole-body control for humanoids…
Attributed to: @GoogleDeepMind
Built with: North Mini Code Gemini Robotics 2 Gemini Robotics ER 2 Gemini Robotics On-Device 2
Links: deepmind.google
View tweet
Tags: #robotics #embodied-ai #vla #humanoid

Discovered: X
First posted: X · Jul 30, 2026
Listed: Added 2h ago
Build: Strong
Models: Strong