Google launches Gemini Robotics model capable of running locally on robots

Google DeepMind rolled out a Gemini model to control robots without an internet connection. The vision language action (VLA) model, Gemini Robotics On-Device, has been optimised to run on the robot itself, Google stated.

Based on the cloud-based Gemini Robotics, the new VLA model shows strong general-purpose dexterity and task generalisation, the company said. Since Gemini Robotics On-Device can be used to execute tasks without a data network, it can be helpful for activities that need quick responses to a command or in environments with intermittent or zero internet connectivity.