ELLA: Generative AI-Powered Social Robots for Early Language Development at Home

TL;DR

This paper introduces ELLA, a generative AI-powered social robot designed to support early language development at home through interactive storytelling and scaffolded dialogue, with insights from iterative design and deployment with children.

Contribution

It presents the design, development, and deployment of ELLA, a novel AI-powered social robot tailored for preschoolers' language learning in home environments.

Findings

Children engaged actively with ELLA during deployment.

Design insights improved robot interaction quality.

Generative AI enables adaptive, personalized interactions.

Abstract

Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond scripted interactions and engage children in adaptive, conversational activities, but it remains unclear how to design such systems for pre-schoolers and how children engage with them over time in the home. We present ELLA (Early Language Learning Agent), an autonomous, generative AI-powered social robot that supports early language development through interactive storytelling, parent-selected language targets, and scaffolded dialogue. Using a multi-phased, human-centered process, we interviewed parents (n=7) and educators (n=5) and iteratively refined ELLA through twelve in-home design workshops. We then deployed ELLA with ten children for eight days. We report design insights from in-home workshops, characterize children's engagement and behaviors during deployment, and distill design implications for generative AI-powered social robots supporting early language learning at home.