[Paper Review] Build Your Own Robot Friend: An Open-Source Learning Module for Accessible and Engaging AI Education

Zhonghao Shi, Allison O'Connell+6 more|arXiv (Cornell University)|Jan 6, 2024

Online Learning and Analytics4 citations

TL;DR

This paper presents an open-source, low-cost learning module enabling college and high school students to build a social robot companion from scratch, integrating hands-on education in AI, robotics, machine learning, and human-centered design. Evaluated with 15 students, the module proved highly effective, easy to follow, and significantly increased interest in pursuing AI and robotics, with 100% of participants expressing future interest in the field.

ABSTRACT

As artificial intelligence (AI) is playing an increasingly important role in our society and global economy, AI education and literacy have become necessary components in college and K-12 education to prepare students for an AI-powered society. However, current AI curricula have not yet been made accessible and engaging enough for students and schools from all socio-economic backgrounds with different educational goals. In this work, we developed an open-source learning module for college and high school students, which allows students to build their own robot companion from the ground up. This open platform can be used to provide hands-on experience and introductory knowledge about various aspects of AI, including robotics, machine learning (ML), software engineering, and mechanical engineering. Because of the social and personal nature of a socially assistive robot companion, this module also puts a special emphasis on human-centered AI, enabling students to develop a better understanding of human-AI interaction and AI ethics through hands-on learning activities. With open-source documentation, assembling manuals and affordable materials, students from different socio-economic backgrounds can personalize their learning experience based on their individual educational goals. To evaluate the student-perceived quality of our module, we conducted a usability testing workshop with 15 college students recruited from a minority-serving institution. Our results indicate that our AI module is effective, easy-to-follow, and engaging, and it increases student interest in studying AI/ML and robotics in the future. We hope that this work will contribute toward accessible and engaging AI education in human-AI interaction for college and high school students.

Motivation & Objective

• To address the lack of accessible and engaging AI education for students from all socio-economic backgrounds, especially in K-12 and undergraduate settings.
• To develop a low-cost, open-source learning module that enables hands-on experience in AI, robotics, machine learning, and human-centered design.
• To integrate human-centered AI topics—such as human-robot interaction, affective computing, and AI ethics—into a practical, project-based curriculum.
• To ensure affordability and accessibility by reducing the robot’s component count from 63 to 20 and keeping total cost under $250 when printed at scale.
• To evaluate the module’s usability, engagement, and educational impact through a two-day workshop with students from a minority-serving institution.

Proposed method

• The authors redesigned the Blossom robot platform, simplifying its open-source hardware to reduce the number of fabricated parts from 63 to 20, focusing on 3D-printed components to lower cost and assembly complexity.
• They developed comprehensive open-source documentation, step-by-step assembling manuals, and video tutorials to support self-paced, customizable learning across diverse educational goals.
• The learning module integrates core AI/ML concepts through a social robot application, emphasizing human-robot interaction, perception, and ethical considerations in AI design.
• The module was evaluated via a two-day usability workshop with 15 college students from a minority-serving institution, using a post-workshop survey with 5-point Likert scale questions.
• Quantitative analysis used one-sample Wilcoxon signed-rank tests to assess whether median responses were significantly above neutral (3) on the Likert scale for usability, learning effectiveness, and future interest.
• Qualitative feedback was collected to inform future improvements and validate student engagement and cross-disciplinary learning outcomes.

Experimental results

Research questions

• RQ1 How can an open-source, low-cost robot learning module be designed to be accessible and engaging for students from diverse socio-economic and academic backgrounds?
• RQ2 To what extent does a hands-on, social robot-based curriculum improve student engagement and perceived learning in AI, robotics, and machine learning?
• RQ3 Can integrating human-centered AI topics—such as human-robot interaction and AI ethics—into a project-based module enhance student interest and understanding?
• RQ4 How effective is the module in increasing students’ intention to pursue further study in AI and robotics?
• RQ5 What is the usability and perceived effectiveness of the module when implemented in a real-world educational setting with minimal instructor support?

Key findings

• 92% of participants reported that the workshop significantly enhanced their understanding of robotics/electronic engineering, with a median response of 'Strongly Agree' (p = .0004).
• 92% of participants reported strong learning gains in computer science/software engineering (median = Strongly Agree, p = .0008).
• 92% of participants reported significant learning in AI/ML (median = Strongly Agree, p = .0014).
• 92% of participants reported strong learning in mechanical engineering (median = Strongly Agree, p = .0018).
• 85% of participants found the learning process easy-to-follow, with a median response of 'Strongly Agree' (p = .0009).
• 100% of participants expressed a strong intention to study more about robotics and AI in the future, with a median response of 'Strongly Agree' (p = .0001).