Allison Langer

The field of child-robot interaction (CRI) is growing rapidly, in part due to demand to provide sustained, personalized support for children in educational contexts. The present study uses a within-subject design to compare how children between 5 and 8 years of age (n=32) interact with a robot and human instructor during a tangram learning task. To assess how the children’s characteristics may influence their behaviors with the instructors, we correlated interaction metrics, such as eye gaze, social referencing, and vocalizations, with parent-reported scales of children’s temperament, social skills, and prior technology exposure. We found that children gazed more at the robot instructor and had more instances of social referencing toward a research assistant in the room while interacting with the robot. Age was related to task time completion, but few other individual characteristics were related to behavioral characteristics with the human and robot instructors. When asked about preferences and perceptions of the instructors after completing the tangram tasks, children showed a strong preference for interacting with the robot. These findings have implications for the integration of social technologies into educational contexts and suggest individual differences play a key role in understanding how children will uniquely respond to robots.

Socially assistive robots (SARs) have the potential to revolutionize educational experiences by providing safe, non-judgmental, and emotionally supportive environments for children's social development. The success of SARs relies on the synergy of different modalities, such as speech, gestures, and gaze, to maximize interactive experiences. This paper presents an approach for generating SAR behaviors that extend an upper ontology. The ontology may enable flexibility and scalability for adaptive behavior generation by defining key assistive intents, turn-taking, and input properties. We compare the generated behaviors with hand-coded behaviors that are validated through an experiment with young children. The results demonstrate that the automated approach covers the majority of manually developed behaviors while allowing for significant adaptations to specific circumstances. The technical framework holds the potential for broader interoperability in other assistive domains and facilitates the generation of context-dependent and socially appropriate robot behaviors.