Context-Dependent Attention System for a Social Robot

摘要

This paper presents part of an ongoing project to integrate perception, attention, drives, emotions, behavior arbitration, and expressive acts for a robot designed to interact socially with humans. The authors present the design of a visual attention system based on a model of human visual search behavior from Wolfe (1994). The attention system integrates perceptions (e.g., motion detection, color saliency, and face pop-outs) with habituation effects and influences from the robot's motivational and behavioral state to create a context-dependent attention activation map. This activation map is used to direct eye movements and to satiate the drives of the motivational system.