Google DeepMind has unveiled a new generation of AI models capable of fully controlling humanoid robots. Unlike previous systems that managed individual mechanisms, the latest architecture (including Gemini Robotics 2, Gemini Robotics ER 2, and Gemini Robotics On-Device 2) can coordinate complex, whole-body movements — from limbs to fine motor skills like grasping small objects. The system converts visual input and verbal commands into cohesive actions, enabling robots to adapt to dynamic environments, plan tasks, and correct errors autonomously. In demonstrations, a robot named Apollo successfully performed tasks such as placing objects, tying knots, and fastening zippers. This advancement could significantly expand the practical applications of robotics in industries like manufacturing, healthcare, and logistics.
About the Author
