Google DeepMind Introduces Gemini Robotics for Advanced Robotics

Google (NASDAQ:GOOGL) DeepMind has announced two new artificial intelligence models based on the Gemini 2.0 technology: Gemini Robotics and Gemini Robotics-ER. These models aim to lay the foundation for next-generation practical robots.

Gemini Robotics is an advanced visual-language-action (VLA) model that expands Gemini 2.0 to encompass physical actions and provides direct control over robots. The Gemini Robotics-ER model enhances Gemini's embodied reasoning (ER) capabilities, enabling robotic experts to run their programs. Designed to allow various robots to perform a wider range of real-world tasks, Google DeepMind is collaborating with Apptronik to create humanoid robots using Gemini 2.0, while also working with a trusted test group to guide the development of Gemini Robotics-ER. This innovative approach brings us closer to versatile robots capable of complex tasks.