Introducing Gemini Robotics 2
Google DeepMind launches Gemini Robotics 2 with whole-body intelligence, dexterity, and multi-robot collaboration.
“What we're building here is the intelligence layer to power any robot to do a broad range of useful tasks.”
Google DeepMind announced Gemini Robotics 2, a suite of embodied reasoning models that bring whole-body spatial intelligence, advanced dexterity, and multi-robot coordination to physical robots including humanoids and non-humanoid arms like Franka Duo. The release adds actions as a native modality in Gemini, enabling robots to understand natural language commands and reason about complex real-world tasks such as cleaning a garage from a single high-level prompt. This marks a significant maturation of the Vision Language Action (VLA) paradigm that DeepMind claims to have pioneered, now deployed at general-purpose scale.