Facial expressiveness is a key factor in a robot's ability to engage and interact with children. Prior work has shown that a robot's expressiveness can enhance child engagement in interaction. Many current implementations of robots in therapy spaces can have non-personalized, static faces that are designed following traditional considerations for facial features, limiting the depth of interactions and emotional connections. Despite the potential for personalization in digital faces, the current landscape of robot faces fails to utilize a user-centered design process. There is a significant research gap on child preference informed design. Currently, robots used in child-focused therapy spaces are designed through the lens of what adults prefer.

In this work, we present a novel study investigating the influence of a personalized digital face in human-robot interaction with children. The study focuses on the benefits of a design activity where children were instructed to draw their own custom robot faces. We compared two faces: one utilizing a default digital face; the other utilizing a robot face personalized using their own drawn robot faces. We compared the perceived social intelligence of each face in order to evaluate the design implications of personalization. The results of this study show a significant difference in the perceived social intelligence of a customized agent compared to a non-personalized face, where a customized agent was rated higher than a non-personalized agent.

AI Institute for Transforming Education for Children with Speech and Language Processing Challenges, National Science Foundation PI: Venugopal Govindaraju, co-PI: David Feil-Seifer, Amount: $20,000,000, Jan. 15, 2023 - Dec. 31, 2027

REU Site: Collaborative Human-Robot Interaction for Robots in the Field, National Science Foundation PI: David Feil-Seifer, co-PI: Emily Hand, Amount: $405,000, March 1, 2022 - Feb. 28, 2025