Implications of embodiment for robot learning

Abstract

The work is based on that of Brooks (1986), who argued that intelligence requires a body and therefore suggested that robots be used to study principles of intelligence. We show in more detail why some of the problems in intelligent behavior like category learning are simplified if the embodiment is exploited appropriately. We will also demonstrate that embodied systems can learn in an unstructured and "unlabelled" environment. Moreover, the seemingly intractable problems of behaving and learning in the real world become manageable. We will substantiate our argument with an information theoretic analysis. The work presented in this paper is theoretically motivated. It has been derived from a number of design principles of autonomous agents. They will be briefly outlined to provide the general context in which this research is situated.