Design Activity for Robot Faces: Evaluating Child Responses To Expressive Faces

TL;DR

The study addresses the lack of child-centered personalization in socially assistive robot faces by engaging children in a design activity to create their own digital robot faces. Using a within-subject design, it compares child-drawn faces to a generic face on perceived social intelligence (PSI) as measured by a PSI instrument, with animations generated from the drawings. The results show significantly higher PSI for child-drawn faces across multiple subscales, suggesting that user-driven personalization can enhance trust, sociability, and perceived competence in therapeutic and educational contexts. The work highlights the practical potential of incorporating child co-design to improve engagement and acceptance of social robots in real-world SAR deployments.

Abstract

Facial expressiveness plays a crucial role in a robot's ability to engage and interact with children. Prior research has shown that expressive robots can enhance child engagement during human-robot interactions. However, many robots used in therapy settings feature non-personalized, static faces designed with traditional facial feature considerations, which can limit the depth of interactions and emotional connections. Digital faces offer opportunities for personalization, yet the current landscape of robot face design lacks a dynamic, user-centered approach. Specifically, there is a significant research gap in designing robot faces based on child preferences. Instead, most robots in child-focused therapy spaces are developed from an adult-centric perspective. We present a novel study investigating the influence of child-drawn digital faces in child-robot interactions. This approach focuses on a design activity with children instructed to draw their own custom robot faces. We compare the perceptions of social intelligence (PSI) of two implementations: a generic digital face and a robot face, personalized using the user's drawn robot faces. The results of this study show the perceived social intelligence of a child-drawn robot was significantly higher compared to a generic face.

Figures (7)

• Figure 1: The study setup includes a Kinova Gen3 robot arm with a mounted digital screen. Participants were asked to observe the robot embodiment and answer questions after an introductory behavior.
• Figure 2: The generic face was designed with features that are traditionally included in existing assistive robots.kalegina2018
• Figure 3: Participants served three different roles for the duration of the study. Each child was a design partner, tester, and evaluator of the system.
• Figure 4: Participants drew faces in varying styles. Many stylistic choices were unique to each participant which indicated to each participant's personality reflected somewhat into the drawings. Some common features in the drawings include: circle eyes, pupils of different sizes, and smiling mouths.
• Figure 5: Drawn faces were fixed with facial landmarks relating to features including eyebrows, eyes, nose, mouth, and chin. A generated animation space would then take the placed landmarks and use it to animate the drawings.