Google DeepMind has introduced two new AI models, Gemini Robotics and Gemini Robotics-ER, based on its Gemini 2.0 large language model. These models are designed to bring AI into the physical world by enabling robots to perform complex tasks with greater generality, interactivity, and dexterity. Gemini Robotics focuses on combining vision, language, and action to control robots, while Gemini Robotics-ER adds advanced spatial understanding for more adaptable and autonomous operations. These advancements aim to make robots more capable of handling real-world scenarios and tasks without extensive training.