Gemini Robotics

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.

Gemini Robotics, powered by Google DeepMind's Gemini 2.0 AI models, bridges AI and physical robotics, enabling robots to perform real-world tasks with advanced reasoning and adaptability. Designed for versatility, it supports multimodal inputs like text, images, audio, and video, while excelling in physical space reasoning. Key features include generalization to novel scenarios, interactive responsiveness, and fine motor dexterity for complex tasks like origami folding or meal preparation. Compatible with diverse robot forms, from bi-arm platforms like ALOHA 2 to humanoid robots like Apptronik’s Apollo, Gemini Robotics is shaping the future of embodied AI. Collaborations and testing opportunities are paving the way for its broader application.