Interactive Human-Robot Teaching Recovers and Builds Trust, Even With Imperfect Learners

Building and maintaining trust is critical for continued human-robot teaching and the prospect of robot learning social skills from natural environments. Whereas previous work often explored strategies to reduce system errors, mitigate trust loss, or using enhanced interactivity to induce learning success, few studies have investigated the possible benefits of fully engaged, interactive teaching on human trust. Motivated by the discrepancy discovered from a pair of previous investigations, the studies presented in this paper for the first time directly tested the causal impact of interactivity on the loss and recovery of trust in a human-robot social skills training context. Using a novel paradigm, we experimentally manipulated the mode of interaction that participants were able to engage in (robot supervisor or active teacher) and measured the teachers' changing trust in a 15-trial robot training session, centering on the critical social skills of norm-appropriate behavior. Our results demonstrate that interactive teachers were more resilient to initial trust loss, showed increased reliance from baseline to post-training, and attributed more of the robot's improvement to themselves than did supervisors, even when their robots were imperfectly slower learners.