Parle: A Curious Robot

This project aimed to test whether children can “catch” curiosity from a social robot. In other words, does playing with a robot that behaves like a curious child make children more curious. So we invited children to play a tablet game with Parle, the DragonBot. Parle, a Personalized Assistive Robot that Learns English, behaved like a curious child, expressing enthusiasm of learning and exploration. We found that indeed, Parle’s curiosity was “contagious”: children playing with it were more curious after the interaction, compared to children playing with a non-curious robot.

Parle the DragonBot personalized the interaction to each specific child. It assessed the children’s reading skills in an optimal manner using state-of-the-art machine learning algorithms. The results show that the assessment was very good (see figure below). The personalization algorithm then selected which words to present to each child in order to optimize each child’s learning gains. The algorithm thus resulted in a personalized tutoring system.

Parle the DragonBot exhibited three types of curiosity behavior. It was excited about learning new things; it wondered about new exploration possibilities and it challenged the child. Children’s curiosity was assess using three measures: uncertainty seeking, free exploration and question generation. Children playing with the curious robot had higher uncertainty seeking and free exploration than children playing with a non-curious robot. However, question generation was not altered by the interaction. We hypothesize that this is due to the fact that Parle exhibited free-exploration and uncertainty seeking behaviors, but did not ask any questions, thus did not promote children to ask questions.