An intelligent human-robot interaction framework to control the human attention

Abstract

Attention control can be defined as shifting someone's attention from his/her existing attentional focus to another. However, it is not an easy task for the robot to control a human's attention toward its intended direction, especially when the robot and the human are not facing each other, or the human is intensely attending his/her task. The robot should convey some communicative intention through appropriate actions according to the human's situation. In this paper, we propose a robotic framework to control the human attention in terms of three phases: attracting attention, making eye contact, and shifting attention. Results show that the robot can attract a person's attention by three actions: head turning, head shaking, and uttering reference terms corresponding to three viewing situations in which the human vision senses the robot (near peripheral filed of view, far peripheral field of view, and out of field of view). After gaining attention, the robot makes eye contact through showing gaze awareness by blinking its eyes, and directs the human attention by the combination of eye and head turning behavior to share an object. Experiments using sixteen participants confirm the effectiveness of the propose framework to control human attention.