Google's Gemini AI empowers robots to act independently

Google has launched a new AI model, Gemini Robotics On-Device, enabling robots to understand instructions and handle objects without an internet connection. This advancement allows robots to operate more independently and respond faster to commands. The new model, developed by Google's DeepMind, runs directly on robots, building upon the earlier Gemini Robotics model. It uses natural language processing, similar to ChatGPT, and is designed for latency-sensitive applications or areas with limited connectivity. The Gemini Robotics On-Device model demonstrates strong dexterity and task generalization, allowing robots to adapt to new situations. This offline capability enhances the robots' utility in various environments.