Models · The Decoder ·

Google Deepmind unveils Gemini Robotics 2 to power robots of all shapes from tabletop arms to humanoids

Google Deepmind unveils Gemini Robotics 2 to power robots of all shapes from tabletop arms to humanoids

Google DeepMind introduced Gemini Robotics 2, a vision-language-action model designed to control robots ranging from tabletop arms to humanoids. Gemini Robotics ER 2 adds a higher-level reasoning layer for robotics tasks.

Read the full story at The Decoder →