Research map / Large language models / AI and society

A Versatile Low-Cost Kit for Teaching Novice Learners AI Using Robotics Components and a No-Code Development Playground

AAAI 2025 · Large language models › AI and society · approach: Classroom tools and student perceptions · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Presents a low-cost (under 50 EUR) Raspberry Pi Zero-based robotics kit with a no-code, offline, Teachable Machine-style development studio that lets K-12 learners train image classifiers and map classification results to physical actions.

Problem

K-12 AI education needs accessible, low-cost, hands-on tools that teach modern ML concepts without programming, while remaining adaptable to classroom materials and privacy-compliant.

Approach

A physical robotics kit built around a Raspberry Pi Zero with camera, combined with a no-code, offline development studio where children define image classes, collect and curate data, train a classifier locally, and configure physical actions via sliders, grounded in maker pedagogy and customizable to cardboard, wood, metal, and plastic construction kits.

Key results

• Complete robotics kit (Raspberry Pi Zero, camera, motor, power bank, PCB, connectors, filament, screws) costs about 48.50 EUR per Table 2.
• The same one-motor desk-cleaning robot was built from cardboard, a wooden builder kit, and a metal builder kit, showing material versatility.
• The system is self-contained and runs without Internet access, with classifier training performed locally on the user's device.

Limitations

• No formal evaluation with learners; the kit is a prototype and its effectiveness is not yet empirically tested.
• Requires 3D printing and manual assembly, which may challenge novice learners or educators.
• Limited to a single camera input and no-code approach may not challenge advanced learners.

Experimental setup

Baselines: LEGO Mindstorms NAO Pepper Pope et al. 2024 no-code AI education tool

Builds on: Teachable Machine constructionism AI4K12 Five Big Ideas in AI meta-design

Closest papers by meaning

• Build Your Own Robot Friend: An Open-Source Learning Module for Accessible and Engaging AI Education (AAAI 2024 · similarity 0.86)
• “AlphAI”: Teaching AI Algorithms to K12 by Training Learning Robots and Visualizing How It Works (AAAI 2025 · similarity 0.84)
• Smart Motor: A Low-Cost Hardware and Software Toolkit for Introducing Supervised Machine Learning to Elementary School Students (AAAI 2025 · similarity 0.83)
• Foundations of Autonomous Vehicles: A Curriculum Model for Developing Competencies in Artificial Intelligence and the Internet of Things for Grades 7–10 (AAAI 2024 · similarity 0.83)
• “From Unseen Needs to Classroom Solutions”: Exploring AI Literacy Challenges & Opportunities with Project-Based Learning Toolkit in K-12 Education (AAAI 2025 · similarity 0.83)
• Using Explainable AI and Hierarchical Planning for Outreach with Robots (AAAI 2025 · similarity 0.81)