A framework for attention and object categorization using a stereo head robot

Abstract

Describes a framework for dealing with attention and categorization using a robot platform consisting of an articulated stereo head with four degrees of freedom (pan, tilt, left verge and right verge). As a practical result of this development, the system can select a region of interest, perform shifts of attention involving saccadic movements, perform efficient feature extraction and object identification/recognition, incrementally construct a world map, and keep this map consistent with the current perception of the world. Another important result for the attentional mechanism is that the system is capable of visiting all regions of its restricted world, selecting one region at a time according to a salience map. For identification, the system starts without any knowledge of the environment and increases its knowledge base (associative memory) as necessary in order to deal with the current set of objects.