Gemini Robotics ER 2: Powering Robotics With Video Understanding, Task Orchestration, and Multi-Robot Collaboration
Google, Thursday, July 30th, 2026
Google DeepMind launches Gemini Robotics ER 2 as a high-level reasoning brain for robots.
Google DeepMind launched Gemini Robotics ER 2, a model designed to act as a high-level brain for robots rather than a low-level controller.
It enables real-time spatial reasoning, multi-step task planning, and coordination between different robots working on the same task. The model represents a step change in video understanding and tool orchestration for robotic applications.
Developers can access it through the Gemini API, Google AI Studio, or the Gemini Enterprise Agent Platform to build physical AI agents. It is released alongside Gemini Robotics 2, which handles whole body control.