Google DeepMind Introduces Gemini Robotics for Real-World Applications

Image: Sora

Google DeepMind has unveiled Gemini Robotics, a suite of AI models designed to enable robots to understand and interact with the physical world. Built upon the Gemini 2.0 architecture, these models incorporate vision-language-action capabilities, allowing robots to perform complex tasks such as folding origami or packing items. Gemini Robotics-ER, an advanced variant, enhances spatial reasoning and adaptability across various robotic platforms, including humanoid robots developed in partnership with Apptronik. This development marks a significant step toward integrating AI into real-world environments.

Source: https://deepmind.google/discover/blog/gemini-robotics-brings-ai-into-the-physical-world/?utm_source=chatgpt.com