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

GoogleDeepMind has unveiled a version of Gemini that can control humanoidrobotsfor the first time.- The Gemini Robotics 2 system brings “intelligent whole-body control”, allowing humanoids to perform tasks autonomously, with a video showing robots screwing in light bulbs and typing up bin bags.

• Gemini Robotics 2 combines a vision language model (VLM) with two vision language action (VLA) models, facilitating communication with humans and environmental understanding. GoogleDeepMind described its release as a “milestone” towards achieving physical AGI (artificial general intelligence), whereby robots have human-level abilities.- Carolina Parada, head of robotics at Google DeepMind, wrote in a blog post detailing the new AImodel: “For the first time, our model can now control entire humanoid robots, translating intent into intelligent whole-body control.”