Google DeepMind has launched the Gemini Robotics 2 model.

According to the introduction, Gemini Robotics 2 enables robots to reason through every action, thereby unlocking a wide range of tasks.

For example, it can enable a humanoid robot to walk, squat, stretch, and manipulate objects to clean up a messy room. It can even collaborate with other robots to complete work faster.

This deep intelligence can also run locally on devices, while seamlessly adapting to entirely new robot bodies in just a few hours.

At the same time, Google DeepMind also released two other robot AI models—Gemini Robotics ER 2 and On-Device 2. Gemini Robotics ER 2 is the most powerful Embodied Reasoning (ER) model, a Vision-Language Model (VLM), which will enable robots to communicate with humans, understand the physical world, and plan multi-step tasks lasting several minutes.

On-Device 2 is the most efficient Vision-Language-Action (VLA) model, optimized to run locally on robot devices. The model can now rapidly adapt to entirely new robot entities through hours of data.

$Alphabet(GOOGL.US)