Google DeepMind's Gemini Robotics 2 Drives Full Humanoids From Feet to Fingertips

Google DeepMind announced Gemini Robotics 2, a vision-language-action model that converts vision and language input into motor control for full humanoid robots — from feet to fingertips — and bi-arm platforms. The system enables whole-body control, advanced dexterity, and multi-robot collaboration. Demonstrated scenarios include a humanoid walking, crouching, and manipulating objects to clean a cluttered room.