Utilization of Non-verbal Behaviour and Social Gaze in Classroom Human-Robot Interaction Communications

TL;DR

The paper addresses the challenge of sustaining natural and robust classroom human-robot interaction (HRI) by incorporating social gaze into robot cognitive architecture. It reports two studies: the first uses the iCub robot in language-learning scenarios with extrovert/introvert personalities across teacher, student, and collaborator roles to examine nonverbal cues and teaching efficacy; the second proposes integrating the Social Gaze Space (SGS) model into the robot's attentional system, implemented with onboard vision and a 5×5 state-space for gaze state transitions. The key contributions include a novel onboard-vision SGS implementation on iCub, a structured exploration of personality and role effects on interaction quality, and a planned evaluation framework using perception and interaction-quality questionnaires. The work holds practical significance for designing more natural, explainable, and failure-resilient classroom robots that can ground conversation through joint attention and nonverbal signaling.

Abstract

This abstract explores classroom Human-Robot Interaction (HRI) scenarios with an emphasis on the adaptation of human-inspired social gaze models in robot cognitive architecture to facilitate a more seamless social interaction. First, we detail the HRI scenarios explored by us in our studies followed by a description of the social gaze model utilized for our research. We highlight the advantages of utilizing such an attentional model in classroom HRI scenarios. We also detail the intended goals of our upcoming study involving this social gaze model.