More relevance for robots with Relevance
Let’s face it, it’s not easy to be a robot! Especially not when you are trying to understand a human being!
Scientists from MIT developed an approach that can help learn robots to understand what humans want. If they order a coffee, the robot should hand over milk and sugar, if I’m cutting bread the housebot should get cleaning materials for the bread crums etc.
The approach (not a language) is called Relevance and, simply explained, it mimics the Reticular Activating System (RAS). RAS is the part of the humans brain that can filter out distractions and focus on what’s important. It helps us focusing on the task we perform.
The team developed a robotic system that (source: MIT); …’broadly mimics the RAS’s ability to selectively process and filter information. The approach consists of four main phases. The first is a watch-and-learn “perception” stage, during which a robot takes in audio and visual cues, for instance from a microphone and camera, that are continuously fed into an AI “toolkit.” This toolkit can include a large language model (LLM) that processes audio conversations to identify keywords and phrases, and various algorithms that detect and classify objects, humans, physical actions, and task objectives. The AI toolkit is designed to run continuously in the background, similarly to the subconscious filtering that the brain’s RAS performs.’
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
