Translating vision and language into robotic actions.

At some point we’ll certainly want to tell robots what we want done in the real world. Google’s AI researchers are now one big step closer. “Unlike chatbots, robots need “grounding” in the real world and their abilities. Their training isn’t just about, say, learning everything there is to know about an apple: how it grows, its physical properties, or even that one purportedly landed on Sir Isaac Newton’s head. A robot needs to be able to recognize an apple in context, distinguish it from a red ball, understand what it looks like, and most importantly, know how to pick it up.” ~ learn more