ABSTRACT
This paper presents a way that enables robots to learn abstract concepts from sensory/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 shown that the system can learn some abstract concepts more accurately than other existing systems.
