New Deep Learning Method Helps Robots Become Jacks-of-all-Trades
One of the biggest things standing in the way of the robot revolution is their inability to adapt. That may be about to change though, thanks to a new approach that blends pre-learned skills on the fly to tackle new challenges.
The reason robots tend to be so fragile is that the algorithms that control them are often manually designed. If they encounter a situation the designer didn’t think of, which is almost inevitable in the chaotic real world, then they simply don’t have the tools to react.
Building off this research, though, scientists have now created a new AI system that can blend together expert sub-systems specialized for a specific task. In a paper in Science Robotics, they explain how this allows a four-legged robot to improvise new skills and adapt to unfamiliar challenges in real time.
The technique, dubbed multi-expert learning architecture (MELA), relies on a two-stage training approach.