From Keyboard to Chatbot: An AI-powered Integration Platform with Large-Language Models for Teaching Computational Thinking for Young Children
Changjae Lee, Jinjun Xiong
TL;DR
Spark proposes an AI-powered platform that teaches computational thinking to 4–9 year-olds by replacing keyboards with natural language interaction, a domain-specific Spark Programming Language (SPL), and a tangible robot course. The system combines a VUI chatbot, an LLM-driven task decomposition module, and a Unitree Go1 robot to execute decomposed programs in real time, with SPL translating to Python for execution. Key contributions include the SPL design, the end-to-end four-flow interaction model, and the integration of STT/TTS with a tangible robotic interface to demonstrate outcomes. The approach aims to reduce keyboard reliance, improve mapping from intent to action, and offer a developmentally appropriate, engaging learning experience with real-world demonstrations for early childhood education in computational thinking.
Abstract
Teaching programming in early childhood (4-9) to enhance computational thinking has gained popularity in the recent movement of computer science for all. However, current practices ignore some fundamental issues resulting from young children's developmental readiness, such as the sustained capability to keyboarding, the decomposition of complex tasks to small tasks, the need for intuitive mapping from abstract programming to tangible outcomes, and the limited amount of screen time exposure. To address these issues in this paper, we present a novel methodology with an AI-powered integration platform to effectively teach computational thinking for young children. The system features a hybrid pedagogy that supports both the top-down and bottom-up approach for teaching computational thinking. Young children can describe their desired task in natural language, while the system can respond with an easy-to-understand program consisting of the right level of decomposed sub-tasks. A tangible robot can immediately execute the decomposed program and demonstrate the program's outcomes to young children. The system is equipped with an intelligent chatbot that can interact with young children through natural languages, and children can speak to the chatbot to complete all the needed programming tasks, while the chatbot orchestrates the execution of the program onto the robot. This would completely eliminates the need of keyboards for young children to program. By developing such a system, we aim to make the concept of computational thinking more accessible to young children, fostering a natural understanding of programming concepts without the need of explicit programming skills. Through the interactive experience provided by the robotic agent, our system seeks to engage children in an effective manner, contributing to the field of educational technology for early childhood computer science education.