Google has found a new way to demonstrate what its Gemini AI model can do, with the help of a robot.
It was a robot from Google’s Everybody Robots division, which was closed last year. But apparently the robots are still around, so Google put a yellow bow tie on one of them, then used Gemini to teach the robot how to respond to commands and navigate DeepMind’s office space.
To achieve this, Google uses visual language models (VLMs) that are trained on images and videos as well as text, allowing them to answer questions and perform tasks requiring perception.
For example, in one video, a Google employee asks the robot to take him somewhere to draw things. The robot says it needs a minute to think, then takes the employee to a whiteboard. In another video, the robot is asked to follow instructions on the whiteboard, where a map shows directions to what’s called the Blue Zone. The robot follows the instructions to a robotic testing area and then announces, “I have successfully followed the instructions on the whiteboard.”
Press play to see the robot in action, then let us know what you think in the comments!
