Google DeepMind’s new AI model can control a robot’s entire body

Google DeepMind has unveiled an updated iteration of its Gemini Robotics system, specifically Gemini Robotics 2. This new model is designed to manage complete humanoid robot kinematics, covering movements from the ground up to the hands.

This capability represents a shift from prior versions that primarily handled upper-body manipulation. Coordinating full-body motion is essential for robots to maintain balance while performing tasks in unstructured environments.

Advancements in this area could streamline the development of general-purpose agents. By improving physical coordination through AI policies, developers may reduce the time required to train robots for diverse real-world applications.

This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.