Elena Malnatsky

The increased presence of social robots geared toward children necessitate those who design and develop these technologies to understand and prepare for addressing emerging ethical and practical questions throughout phases of interaction design, technical development, and real-world use while maintaining a child-friendly and playful approach. Even more importantly, it is crucial to understand how we can address various tensions between the ethical and practical use of social robots with children, that may emerge between designers, developers, and users. In this full-day workshop, we will introduce the "playful by design" toolkit to promote hands-on and rights-based design experiences for researchers and practitioners to (1) identify and discuss tensions that arise in child-robot interaction research and (2) co-create a working-draft and collaboration plan for designing a "roboticist's guide to working with children". This workshop builds on the authors' past workshop and work-in-progress report at IDC 2025 where our key goal is to co-develop a community-driven resource through collecting and analyzing testimonials from child-robot interaction researchers.

Dialogic learning fosters motivation and deeper understanding in education through purposeful and structured dialogues. Foundational models offer a transformative potential for child-robot interactions, enabling the design of personalized, engaging, and scalable interactions. However, their integration into educational contexts presents challenges in terms of ensuring age-appropriate and safe content and alignment with pedagogical goals. We introduce a hybrid approach to designing personalized educational dialogues in child-robot interactions. By combining rule-based systems with LLMs for selective offline content generation and human validation, the framework ensures educational quality and developmental appropriateness. We illustrate this approach through a project aimed at enhancing reading motivation, in which a robot facilitated book-related dialogues.

Dialogic learning fosters motivation and deeper understanding in education through purposeful and structured dialogues. Foundational models offer a transformative potential for child-robot interactions, enabling the design of personalized, engaging, and scalable interactions. However, their integration into educational contexts presents challenges in terms of ensuring age-appropriate and safe content and alignment with pedagogical goals. We introduce a hybrid approach to designing personalized educational dialogues in child-robot interactions. By combining rule-based systems with LLMs for selective offline content generation and human validation, the framework ensures educational quality and developmental appropriateness. We illustrate this approach through a project aimed at enhancing reading motivation, in which a robot facilitated book-related dialogues.

In this paper, we present a participatory design approach to age-based personalization for child-robot interaction. This is an important step towards social robots being effective across age groups. As a testbed for our approach, we used humor. Personalized humor is a powerful social motivator and is uniquely suited to build relatable and sustained child-robot interactions. Through a series of co-design workshops (n = 102 children), we identified humor concepts that fit the specific sense of humor for each of the four age groups (8–9, 9–10, 10–11, 11–12 y.o.), as well as humor concepts that resonated across these age groups. A user study showed that, overall, children found the interaction more amusing and a better fit for both their own sense of humor and that of their peer group when the robot used age-personalized humor compared to age-agnostic humor. The strength of the effects varied by age group, with the oldest group consistently scoring lower on the outcome measures, indicating that the design was not equally effective for all groups.

While social robots hold significant potential in education, not all children find their interaction with a robot relatable. We present a child-centered research approach that actively involves children in shaping personalized interaction content. We applied this method in a user study (n=102, 8-13 y.o) where we designed robot humor that was tailored to different age groups. Results indicated that children found age-personalized humor more amusing and felt a stronger affinity with it, both personally and at the group level. Our forthcoming longitudinal study will focus on enhancing children's relatedness to the robot and a book, aiming to stimulate reading motivation. We plan to investigate how generative AI can efficiently scale up both co-design and content creation steps.