A Robotic Framework for Making Eye Contact with Humans

TL;DR

This paper presents a computational model enabling robots to proactively establish eye contact with humans, even when initial conditions are not ideal, enhancing human-robot interaction.

Contribution

It introduces a novel proactive eye contact model for robots, addressing challenges of initial orientation and attention capture in human-robot interaction.

Findings

The model effectively captures human attention in various scenarios.

Robotic head experiments confirm improved eye contact success.

The approach enhances naturalness in human-robot communication.

Abstract

Meeting eye contact is the essential prerequisite skill of a human to initiate any conversation with others. However, it is not an easy task for a robot to meet eye contact with a human if they are not facing each other initially or the human is intensely engaged his or her task. If the robot would like to start communication with a particular person, it should turn its gaze to that person first. However, only such a turning action alone is not always enough to set up eye contact. Sometimes, the robot should perform some strong actions so that it can capture the human's attention toward it. In this paper, we proposed a computational model for robots that can proactively capture human attention and makes eye contact with him or her. Evaluation experiments by using a robotic head reveal the effectiveness of the proposed model in different viewing situations.