A humanoid robot’s effortful adaptation boosts partners’ commitment to an interactive teaching task

Vignolo, A., Powell, H., Rea, F., Sciutti, A., Mcellin, L. and Michael, J. (2022) A humanoid robot’s effortful adaptation boosts partners’ commitment to an interactive teaching task. ACM Transactions on Human-Robot Interaction, 11(1), pp. 1-17. (doi: 10.1145/3481586)

Abstract

We tested the hypothesis that, if a robot apparently invests effort in teaching a new skill to a human participant, the human participant will reciprocate by investing more effort in teaching the robot a new skill, too. To this end, we devised a scenario in which the iCub and a human participant alternated in teaching each other new skills. In the Adaptive condition of the robot teaching phase , the iCub slowed down its movements when repeating a demonstration for the human learner, whereas in the Unadaptive condition it sped the movements up when repeating the demonstration. In a subsequent participant teaching phase , human participants were asked to give the iCub a demonstration, and then to repeat it if the iCub had not understood. We predicted that in the Adaptive condition , participants would reciprocate the iCub’s adaptivity by investing more effort to slow down their movements and to increase segmentation when repeating their demonstration. The results showed that this was true when participants experienced the Adaptive condition after the Unadaptive condition and not when the order was inverted, indicating that participants were particularly sensitive to the changes in the iCub’s level of commitment over the course of the experiment.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Powell, Mr Henry
• Authors: Vignolo, A., Powell, H., Rea, F., Sciutti, A., Mcellin, L., and Michael, J.
• College/School: College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience
• Journal Name: ACM Transactions on Human-Robot Interaction
• Publisher: Association for Computing Machinery (ACM)
• ISSN: 2573-9522
• ISSN (Online): 2573-9522
• Published Online: 18 October 2021
• Copyright Holders: Copyright © 2021 The Authors
• First Published: First published in ACM Transactions on Human-Robot Interaction 11(1):1-17
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher