Emotion recognition and expression are essential components of human-agent interaction, particularly for users with limited verbal communication abilities. This pilot study explores the potential of personalized color-based emotion visualization to support emotional understanding and interpersonal communication among students with developmental and communication-related disorders. Eight students from a special needs school participated in a dyadic task, watching short animation clips and explaining them to a peer under two conditions: with and without projected color cues. Color-emotion mappings were co-constructed through a preliminary survey based on each pair’s associations. While the small sample size limited statistical significance, trends suggested that color visualization may enhance emotional valence, interpersonal physiological synchronization, and affective interpretation. These findings offer preliminary insights into how adaptive, user-defined visual cues can inform the design of emotionally supportive agents. To address the limitations of this study, future work will recruit a larger cohort across specific diagnostic groups and evaluate the integration of these mechanisms into embodied agents, examining their effects on user engagement and emotional alignment in real-world interactions.

This study investigates the impact of active listening and mirroring behaviors on intimacy and trust in human-robot interaction. Based on the principles of effective human communication, active listening and mirroring were adapted for robotic systems to enhance relationship dynamics like intimacy, negative attitudes, and trust. The experimental setup involved a social robot to exhibit non-verbal cues that aligned with active listening and mirroring during interactions in the cooking scenario. The participants experienced two conditions: active listening and active listening with mirroring. The results indicated that the combination of active listening with mirroring significantly enhances intimacy and perceived trust compared to active listening only, while there is no significant difference in reducing negative attitudes. These findings suggest that incorporating non-verbal cues can substantially improve engagement in human-robot interactions, making robots more relatable and trustworthy companions.

This study explored how a table-top robot as a recipient of explanations can be applied to the education of students with autism spectrum disorder and intellectual disability. Four 17-year-old participants were recruited from a special needs school. We observed their engagement in assigned tasks and any significant interactions with the robot during the three personalized learning sessions in the school environment. During sessions without a robot, each student was asked to solve arithmetic questions related to purchasing items. During sessions with a robot, each student was required to not only solve questions but also explain the processes or results of simple calculations to the robot. We examined the behavioral, affective, and cognitive engagement of each participant during personalized learning sessions. The results showed that participants solved problems faster, more accurately, or with fewer distractions in the with-robot conditions compared to the task-only conditions. It suggests that this approach, where students explain what they know to a robot, might be effectively adopted for students in special needs schools. Future research should examine the role of robots more comprehensively, acknowledging the limitations of this study, such as the measurement of only three sessions.

As the operation of robots is becoming easier, adopting a robot as a companion for families is increasing. When considering that family playtime has a positive influence on all family members, it is important to provide various activities for families to play together. Robots might mediate fun activities to increase family playtime. Therefore, this research was designed to compare play activities between dyadic child-robot interactions and family-robot interactions. We explored the possible activities for family playtime with a NAO robot. The results from three family groups showed that verbal activities, such as giving an instruction to a robot and talking to a robot, increased when family members are playing together with the robot. Also, increased physical activities were involving all family members, such as giving and receiving balls. Therefore, it will be necessary for a robot to recognize the voices of multiple family members and respond to each member appropriately. More importantly, a robot's time allocation for each family member and encouraging the participation of all members will be necessary to maintain or Increase the family playtime.