The Gemini AI model that allows humanoids to screw in light bulbs and tie bin bags

Google DeepMind has unveiled Gemini Robotics 2, an AI model that can control entire humanoid robots, enabling them to perform tasks such as screwing in light bulbs and tying bin bags. The system combines a vision language model with two vision language action models, and the company describes it as a milestone toward physical artificial general intelligence. Carolina Parada, head of robotics at Google DeepMind, said: 'For the first time, our model can now control entire humanoid robots, translating intent into intelligent whole-body control.'