Corobolab successfully integrates software and hardware components to create a comprehensive collaborative learning environment that enhances AI education for K-12 students.

Objective: The main goal of this study was to develop and evaluate Corobolab, a purpose-built collaborative learning tool specifically designed to facilitate the harmonious integration of AI education and collaborative learning for both educators and learners in K-12 settings.

Methods: The researchers designed an integrated software-hardware platform that establishes a two-tiered collaborative ecosystem. The software component includes a graphical programming interface based on Blockly and the Electron framework, enabling multiple students to engage in real-time collaborative programming simultaneously. The hardware component consists of a wheeled robot with various attachments including a Raspberry Pi 4B main control board, motor driver board, LCD display, stepper motor, Mecanum wheels, and detachable sensors such as cameras, ultrasonic, and infrared sensors. The researchers created 32 AI cases covering motion control, computer vision, machine speech, model training, and mathematical integration, and conducted an 8-week collaborative project-based AI course in several primary and secondary schools. Data was collected through interviews with randomly selected students and teachers, which were then coded into three different dimensions: satisfaction, user experience, and possible challenges.

Key Findings:

• The two-tiered collaborative structure (software and hardware) enabled effective teamwork where students could each develop different functional modules and then integrate them into a complete project.
• Students reported increased engagement and immersion when working collaboratively, noting that the tangible hardware component provided concrete understanding of abstract AI concepts.
• The shared programming workspace successfully supported real-time collaboration among multiple students.
• The modular hardware design allowed for customization according to specific project requirements, enhancing flexibility for different educational objectives.
• Teachers appreciated the tool's ability to support rich course content and its suitability for group activities.
• Students with no prior programming experience found the block-based programming interface accessible and easier to use than traditional code.
• Some challenges were identified, including unclear hardware construction prompts, network or hardware failures, and slow response times.

Implications:

• Corobolab provides an efficient software-hardware collaborative environment for AI education classrooms, enhancing the quality of AI education in K-12 settings.
• The tool offers distinct benefits in fostering student engagement, enhancing knowledge retention, and promoting collaboration.
• The integration of hardware-based instant feedback provides students with tangible connections between theoretical algorithmic concepts and real-world applications.
• From an educational design perspective, Corobolab introduces a unique framework for two-tier collaboration that expands curricular diversity.
• Teachers can focus more on teaching content innovation and student ability development while students enjoy a richer and more dynamic collaborative learning environment.
• The approach enables educators to adapt tasks to students' varying abilities by structuring assignments around different roles or competencies within student group projects.

Limitations:

• Both students and educators would benefit from brief training sessions prior to formal courses to ensure effective utilization of Corobolab.
• The system requires some maintenance during operation, highlighting the need for robust technical support infrastructure.
• Some students reported confusion during the hardware platform construction process due to insufficient prompts or guidance.
• Network issues during usage can result in delays, while pronunciation or speech inaccuracies may produce significant biases in algorithmic recognition.
• The current tools are primarily designed for foundational AI education targeting K-12 students and may need adaptation for more advanced AI curricula.

Future Directions:

• Develop more comprehensive guidance for hardware construction to address user experience issues.
• Create robust technical support infrastructure to minimize disruptions during operation.
• Adapt the platform for more advanced AI curricula to extend its utility beyond foundational education.
• Implement training sessions for both educators and students prior to course implementation.
• Further refine the system to reduce network-related delays and improve speech recognition accuracy.

Title and Authors: "The Development of a Collaborative Learning Tool for AI Education: Corobolab" by Haibin Lai, Peng Peng, Yuhui Lv, Peiwei Cai, Qiongxiong Ma, and Zhun Zhang.

Published On: 2025 (according to the copyright notice in the paper)

Published By: 2025 14th International Conference on Educational and Information Technology (ICEIT), IEEE.