AI Summary

Google DeepMind released Gemini Robotics 2, a new AI system that can control various robots, including humanoids that perform dexterous tasks such as screwing in lightbulbs and tying trash bags. The system merges several AI models into one framework. A vision‑language model interprets images and video, enabling the robot to understand its surroundings and communicate with humans. Two vision‑language‑action models, trained to navigate physical space, manage the robot’s full‑body movements and the precise motions of grippers or hands. Together, these models allow the robot to perceive its environment and decide how to act.

AI summaries can be wrong sometimes—always verify important details using the source article.