Modeling of Bowing Behaviors in Apology Based on Severity

With the expansion of social robots’ working environments, developing strategies to mitigate their mistakes has become crucial, especially given the difficulty of entirely avoiding errors. Previous studies have explored effective strategies for robot apologies, including conversational content, yet have paid less attention to nonverbal behaviors like bowing. In this study, we focused on the modeling of bowing behaviors. A distinctive aspect of our study is its consideration of failure severity, since we hypothesized that apology behaviors vary with the situation. For instance, a minor delay might prompt a rather mechanical apology, whereas a serious failure would undoubtedly elicit a more sincere response. We elucidated the relationship in apologies between failure severity and bowing behaviors, based on data collected from participants. Then we implemented the modeled bowing behavior in a robot and conducted a web-based survey to assess its effectiveness. Our findings highlighted the significance of taking into account the severity of bowing behaviors.