Sharing knowledge with robots

Intelligent robots need to share knowledge with human beings for flexible interaction. However, the gap between low-level sensory data and abstract human knowledge makes it difficult to preencode robot behavior against human's various complex demands. This article presents a way of enabling robots to learn abstract concepts from sensory and perceptual data. In order to overcome the gap between the low-level sensory data and higher level concept description, a method called feature abstraction is used. Feature abstraction dynamically defines abstract sensors from primitive sensory devices and makes it possible to learn appropriate sensory-motor constraints. This method has been implemented on a real mobile robot as a learning system called Acorn-II. Acorn-II was evaluated with some empirical results and it was shown that the system can learn some abstract concepts more accurately than other existing systems.