Google DeepMind’s new AI models help robots perform physical tasks, even without training

Google DeepMind is launching two new AI models, Gemini Robotics and Gemini Robotics-ER, designed to help robots perform a wider range of real-world tasks. Gemini Robotics, built on Gemini 2.0, focuses on generality, interactivity, and dexterity, enabling robots to understand new situations and interact with people and their environment. Gemini Robotics-ER is an advanced visual language model that allows robots to reason and make decisions based on their environment, with a focus on safety and collaboration with companies like Boston Dynamics and Agility Robotics.

Full Article