Google's Gemini robotics models help robots think, see, act
Google DeepMind just rolled out two fresh AI models—Gemini Robotics-ER 1.5 and Gemini Robotics 1.5—to help robots think, see, and act more like us.
ER 1.5 is the brains of the operation, planning steps and using tools (even Google Search), while Robotics 1.5 turns what it sees into real-world actions.
Gemini Robotics-ER 1.5 and Gemini Robotics 1.5
Gemini Robotics-ER 1.5 handles complex spatial tasks, breaks down big jobs into smaller steps, and taps digital tools for help.
Gemini Robotics 1.5 takes those plans and actually moves the robot—plus, it can explain what it's doing in plain language.
By splitting up planning and action, robots get better at making decisions on the fly.
How to access the new models
You can now access Gemini Robotics-ER 1.5 through the Gemini API in Google AI Studio if you want to experiment or build something cool with it this year.
The action-focused model is rolling out to select partners first.