A multi-modal embodied robot framework for English as a second language learning in preschoolers: design and evaluation

Abstract

A multi-modal embodied robot framework was developed and evaluated to support English as a Second Language (ESL) learning in preschoolers through physical interaction and adaptive engagement. The system integrates a 4-DOF OpenManipulator-X robot with a tablet-based educational application, forming a unified instructional platform that delivers synchronized auditory, visual, and kinesthetic stimuli. Designed to improve lexical retention and motivation in early learners, the framework enables task-based interaction through pick-and-place vocabulary reinforcement, collaborative drawing, and tablet-mediated language tasks, coupled with a real-time emotion recognition module to adjust instructional cues. An experimental design within the subject was used with 21 Korean preschool children (ages 4-8), comparing robot-assisted language learning (RALL) with traditional teacher-led language learning (TLLL) in matched tasks involving vocabulary learning, math reasoning, color categorization, and spelling recall. Each session was conducted under controlled classroom conditions and analyzed using both quantitative and qualitative metrics, including engagement frequency, task precision, and structured post-session surveys. The results demonstrate significantly higher participation and task completion rates in the RALL condition, with vocabulary acquisition outcomes comparable to TLLL (p > 0.05). Children exhibited increased motivation and sustained interaction when guided by the robot and the application, suggesting that embodied adaptive systems can effectively support early second language learning. The study contributes validated design principles for integrating physical embodiment, affective responsiveness, and multi-modal instructional delivery in educational robotics. Implications are discussed for the scalable deployment of robot-assisted systems in preschool contexts, emphasizing child-centered interaction and developmental appropriateness within RALL environments.