Shared challenges in object perception for robots and infants

Robots and humans receive partial, fragmentary hints about the world's state through their respective sensors. These hints—tiny patches of light intensity, frequency components of sound, etc.—are far removed from the world of objects which we feel and perceive so effortlessly around us. The study of infant development and the construction of robots are both deeply concerned with how this apparent gap between the world and our experience of it is bridged. In this paper, we focus on some fundamental problems in perception which have attracted the attention of researchers in both robotics and infant development. Our goal was to identify points of contact already existing between the two fields, and also important questions identified in one field that could fruitfully be addressed in the other. We start with the problem of object segregation: how do infants and robots determine visually where one object ends and another begins? For object segregation, both the fields have examined the idea of using ‘key events’ where perception is in some way simplified and the infant or robot acquires knowledge that can be exploited at other times. We propose that the identification of the key events themselves constitutes a point of contact between the fields. Although the specific algorithms used in robots do not necessarily map directly to infant strategies, the overall ‘algorithmic skeleton’ formed by the set of algorithms needed to identify and exploit key events may in fact form the basis for mutual dialogue. We then look more broadly at the role of embodiment in humans and robots, and see the opportunities it affords for development. Copyright © 2008 John Wiley & Sons, Ltd.