Back to AI Research

AI Research

Earthquaker-AI: A Retrieval-Augmented Generation Fr... | AI Research

Key Takeaways

  • Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education is a research project that en...
  • This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a conversational AI assistant based on Retrieval-Augmented Generation.
  • It aims to enhance earthquake preparedness and conscious action among primary-school students.
  • The system extends the award-winning STEM project Earthquaker moving from mechanical simulation with Lego WeDo2 to cognitive and metacognitive processing.
  • The robotics component uses Lego WeDo2 automation to simulate seismic response, letting students interact with sensors and actuators as tangible representations of protective actions.
Paper AbstractExpand

This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a conversational AI assistant based on Retrieval-Augmented Generation. It aims to enhance earthquake preparedness and conscious action among primary-school students. The system extends the award-winning STEM project Earthquaker moving from mechanical simulation with Lego WeDo2 to cognitive and metacognitive processing. The robotics component uses Lego WeDo2 automation to simulate seismic response, letting students interact with sensors and actuators as tangible representations of protective actions. The assistant operates as a guided learning mechanism aligning student responses with safety guidelines, while providing rubric-based verbal feedback that supports self-regulated learning and calmness under emergency conditions. Earthquaker-AI follows a progressive learning trajectory aligned with cognitive development. In early grades, the focus is on basic recognition of safety actions through multiple-choice questions, assessed via a two-dimensional rubric. In middle grades, students identify correct action sequences through multiple-choice questions, evaluated via a three-axis rubric. In upper grades, the approach shifts to verbal production, requiring short written responses assessed via a four-dimensional rubric that includes clarity of expression. The dialogic module uses RAG to match student queries semantically with official guidelines, generating safe, accurate responses. Experimental evaluation shows high groundedness and accuracy, with a low hallucination rate. Overall, Earthquaker-AI combines hands-on engagement, information processing, and reflective practice. Combining robotics, rubrics, and AI promotes technological literacy, self-regulation, and responsible use of digital systems, contributing to early crisis-management skills.

Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education is a research project that enhances earthquake preparedness for primary school students by combining physical robotics with an intelligent conversational assistant. The framework evolves the existing "Earthquaker" STEM project—which uses Lego WeDo2 robotics to simulate seismic events—by adding a cognitive layer that helps students process safety information and practice calm, informed decision-making during emergencies.

Bridging Robotics and Cognitive Learning

The system integrates hands-on mechanical simulation with a digital AI assistant. While students use Lego WeDo2 sensors and actuators to physically model how to react to an earthquake, the AI assistant provides a guided learning environment. This dual approach ensures that students are not just learning the mechanics of safety, but are also developing the cognitive and metacognitive skills necessary to remain calm and act correctly when a real emergency occurs.

A Progressive AI-Driven Curriculum

To ensure the system is appropriate for different developmental stages, Earthquaker-AI uses a tiered learning trajectory:

  • Early Grades: Focuses on basic recognition of safety actions through multiple-choice questions, evaluated by a two-dimensional rubric.

  • Middle Grades: Requires students to identify the correct sequence of safety actions, assessed via a three-axis rubric.

  • Upper Grades: Shifts to verbal production, where students provide short written responses that are evaluated using a four-dimensional rubric, which also accounts for the clarity of their expression.

Technology and Performance

The core of the system’s intelligence is a Retrieval-Augmented Generation (RAG) module. This allows the AI to match student queries against official safety guidelines, ensuring that the information provided is accurate and reliable. According to the experimental evaluation, the system demonstrates high groundedness and accuracy, with a notably low rate of hallucinations. By combining these technologies, the framework promotes technological literacy and helps students build essential crisis-management skills through reflective practice and structured feedback.

Comments (0)

No comments yet

Be the first to share your thoughts!