<ul><li>Google DeepMind has introduced two new AI models, Gemini Robotics and Gemini Robotics-ER, to enhance robotic capabilities in the physical world by enabling robots to perform a broader range of real-world tasks.</li><li>Gemini Robotics is a vision-language-action (VLA) model that allows robots to comprehend new situations and execute physical actions without specific training.</li><li>Gemini Robotics-ER is designed for roboticists to develop their own models, offering advanced spatial understanding and improved object detection and pointing capabilities.</li><li>Google is partnering with Apptronik to develop humanoid robots using these models, indicating its future focus on expanding partnerships and exploring the capabilities of the technology.</li></ul>

Google DeepMind’s Gemini Robotics to Build AI for Robots of all Shapes and Sizes

Discover more