Google DeepMind unveiled two new artificial intelligence (AI) models on Thursday, which can control robots to make them perform a wide range of tasks in real-world environments. Dubbed Gemini Robotics...
Google DeepMind introduced Gemini Robotics and Gemini Robotics-ER, AI models for controlling robots in real-world tasks. Gemini Robotics, based on Gemini 2.0, provides generality, interactivity, and dexterity, enabling robots to perform complex manipulations. Gemini Robotics-ER focuses on spatial reasoning. Google is partnering with Apptronik to build humanoid robots powered by Gemini 2.0. The models were trained using data from the robotic platform Aloha 2.
