Gemini Robotics 2 combines several different AI models into a single system. A vision language model (VLM), which understands images and video, can communicate with humans and reason how to perform different tasks. In video demonstrations shared ahead of the release, the company showed several different robots performing complex tasks autonomously using the amalgamated model. Giving frontier AI models access to robots so that they can wander around workplaces or homes and manipulate objects does, however, come with risks. It’s also introducing ASIMOV-Agentic, a new benchmark for measuring the safety of various AI systems collaborating to control a robot.