Google DeepMind's Gemini Robotics 2 Controls Full Humanoid Robots

Google DeepMind unveiled Gemini Robotics 2, a vision-language-action model that translates visual and language input into motor commands for full humanoid and bi-arm robots. The system handles whole-body control, dexterity, and multi-robot collaboration. Demos showed a humanoid walking, crouching, and cleaning a cluttered room by manipulating objects.