Google brings Gemini Robotics ER 2, DeepMind's embodied reasoning model, to Google Cloud in public preview so enterprises can orchestrate VLA models and multi-robot teams
On Oct 27 Google Cloud announced that Gemini Robotics ER 2, Google DeepMind's embodied reasoning model, is in public preview on the Gemini platform via Model Garden, under the model ID gemini-robotics-er-2-preview and built on Gemini 3.5 Flash. It acts as a robot's high-level brain: it reasons over space and time in video, plans multi-step tasks, checks whether an action succeeded, and calls VLA models and navigation APIs as tools, including across teams of different robots. Google says it pinpoints key video frames with 91.3% accuracy.
Key Takeaways
- Model ID gemini-robotics-er-2-preview, built on Gemini 3.5 Flash, takes text, image, video and audio input, with a 131,072-token input and 65,536-token output limit
- The core pattern is declaring VLA models, navigation APIs or custom functions as tools, with ER 2 planning and orchestrating them while explaining itself and accepting redirection in natural language
- It classifies task progress as binary, discrete or continuous scores; Google cites 91.3% accuracy and a 0.96-second mean frame distance for finding key moments in video
- It reads values from more than 10 instrument types, including dials, sight glasses, digital displays and rulers
- The enterprise version adds IAM, security controls and function calling; the Cloud preview supports GenerateContent but not the Live API, and Boston Dynamics and Arm are among early users
Linked Models & Agents:
