Google’s new robotics AI can run without the cloud and still tie your shoes

Google DeepMind's new on-device vision language action (VLA) model enables autonomous robot control without cloud connectivity. This system, drawing from Gemini's multimodal understanding, generates robot actions for new tasks. It allows for more reliable operation in challenging situations, can be customized by developers, and may lead to more versatile and responsive robots capable of adapting quickly to various environments and tasks.