This paper presents Earthquaker-AI, a hybrid educational framework that integrates a conversational AI assistant based on Retrieval-Augmented Generation (RAG) into the existing Earthquaker robotics project. The system aims to enhance earthquake preparedness and conscious action among primary-school students by combining hands-on engagement with cognitive processing.
- The robotics component uses Lego WeDo2 automation to simulate seismic response, allowing students to interact with sensors and actuators as tangible representations of protective actions.
- The AI assistant provides rubric-based verbal feedback aligned with safety guidelines to support self-regulated learning and calmness under emergency conditions.
- Learning follows a progressive trajectory: early grades use two-dimensional rubrics for basic recognition, middle grades use three-axis rubrics for action sequences, and upper grades use four-dimensional rubrics for written responses.
- The dialogic module uses RAG to semantically match student queries with official guidelines, ensuring safe and accurate responses.
The framework combines robotics, rubrics, and AI to promote technological literacy, self-regulation, and responsible use of digital systems, contributing to early crisis-management skills.