Google DeepMind Unveils Gemini Robotics 2 with Full Humanoid Body Control and Enhanced Dexterity

Google DeepMind has released Gemini Robotics 2, the latest version of its vision-language-action (VLA) model, enabling full-body control for humanoid robots. The updated model significantly improves physical dexterity, allowing robots to perform delicate tasks like tying knots and sealing ziplock bags. It also introduces intelligent whole-body control, multi-robot collaboration, and enhanced safety features for human interaction.