Gemini Robotics from Google Deepmind, is the Gemini 2.0-based AI models for robots. Multimodal, general, interactive, and dexterous. Powers ALOHA 2, Apptronik Apollo, and more.
Hi everyone！
Sharing Gemini Robotics, a new project from Google DeepMind that brings Gemini 2.0 to the world of robotics. This is a big step towards robots that can understand and interact with the physical world in a general and adaptable way.
Key capabilities:
🤖 Embodied AI: Designed for robots to act in the real world, not just process information.
🧠 Powered by Gemini 2.0: Leverages Gemini's multimodal reasoning and world understanding.
👁️🗨️ Multimodal Input: Responds to text, images, audio, and video.
✨ General Purpose: Adapts to new situations, objects, and instructions.
🗣️ Interactive: Understands everyday commands and reacts to changes.
🖐️ Dexterous: Can perform tasks requiring fine motor skills.
🦾 Works with different robots platforms like ALOHA 2 (bi-arm) and Apptronik Apollo (humanoid).
🤝 Collaborating with Apptronik, Agile Robots, Agility Robotics, Boston Dynamics, and Enchanted Tools.
It will be interesting to see how the research community builds upon this work.
