Adaptive Social Robot for Sustaining Social Engagement during Long-Term Children–Robot Interaction

ABSTRACT

One of the known challenges in Children–Robot Interaction (cHRI) is to sustain children’s engagement during long-term interactions with robots. Researchers have hypothesized that robots that can adapt to children’s affective states and can also learn from the environment can result in sustaining engagement during cHRI. Recently, researchers have conducted a range of studies where robots portray different social capabilities and have shown that it has positively influenced children’s engagement. However, despite an immense body of research on implementation of different adaptive social robots, a pivotal question remains unanswered: Which adaptations portrayed by a robot can result in maintaining long-term social engagement during cHRI? In other words, what are the appropriate and effective adaptations portrayed by a robot that will sustain social engagement for an extended number of interactions? In this article, we report on a study conducted with three groups of children who played a snakes and ladders game with the NAO robot to address the aforementioned question. The NAO performed 1) game-based adaptations, 2) emotion-based adaptations, and 3) memory-based adaptation. Our results showed that emotion-based adaptations were found out to be most effective, followed by memory-based adaptations. Game adaptation didn’t result in sustaining long-term social engagement.

Acknowledgments

We would like to thank all the children who participated in our study. We would also like to thank Michele Balogh-Caristo, a teacher at the St Margaret Mary’s School, who coordinated the study.

Additional information

Notes on contributors

Muneeb Imtiaz Ahmad

Muneeb Imtiaz Ahmad is a PhD Candidate in Social Robotics, at the Human–Machine Interaction Group, The MARCS Institute at the Western Sydney University, Australia. He holds a Masters of Science in Computer Science from the university of Paderborn, Germany. His main research interests are: Social Robotics, Human–Robot Interaction, and evaluation of various social robots’ roles in education.

Omar Mubin

Omar Mubin is a senior lecturer at the School of Computing, Engineering and Mathematics at Western Sydney University, Australia. His research interests comprise of human–computer interaction, social robotics (and the perception of humans of them thereof), exploring the role of robots in education, empirical research in human–computer interaction and user-centred design.

Joanne Orlando

Joanne Orlando’s research focuses on how technology impacts established practices for teaching and learning. She has published extensively in this area, and her publications focus on pedagogical innovations in educational technology and how change develops in curriculum and teaching practice. Joanne is based at the Centre for Educational Research, Western Sydney University Australia.