Designing Evaluation Metrics for Quality of Human-Robot Interaction in Guiding Human Behavior

Tetsunari Inamura, Yoshiaki Mizuchi

Abstract: To build and improve the interaction capabilities of robots, the quality of interaction should be evaluated based on human subjectivity, not only on the time required or the degree of accomplishment. However, it remains unclear which evaluation metrics humans prioritize when robots guide their behavior. To investigate the factors that humans prioritize when evaluating the quality of human-robot interaction in guiding human behavior, we asked the evaluators to answer what they based their evaluation of the quality of interaction on in an open-ended form and listed the evaluation items. In addition, based on the scoring results of the collected evaluation items, we conducted a factor analysis to uncover the underlying evaluation metrics. The study revealed four evaluation metrics including not just the appropriateness of attribute explanation and instruction conciseness, but also the ability to guide human users based on their behavior.