Curio: A Cost-Effective Solution for Robotics Education

TL;DR

The paper addresses the high cost and limited capabilities of educational robotics platforms that hinder scalable AI education. It introduces Curio, a smartphone-integrated robot priced under $50 that offloads processing to the user’s phone while supporting web-based and Python development for AI tasks. A case study with 20 participants demonstrates high engagement (SUS ~88) and learning gains, with 95% reporting improved robotics understanding and 75% increased confidence in AI applications. The work suggests Curio can democratize robotics education, with future plans to integrate it into university courses and use it as a cost-effective research testbed.

Abstract

Student engagement is one of the key challenges in robotics and artificial intelligence (AI) education. Tangible learning approaches, such as educational robots, provide an effective way to enhance engagement and learning by offering real-world applications to bridge the gap between theory and practice. However, existing platforms often face barriers such as high cost or limited capabilities. In this paper, we present Curio, a cost-effective, smartphone-integrated robotics platform designed to lower the entry barrier to robotics and AI education. With a retail price below $50, Curio is more affordable than similar platforms. By leveraging smartphones, Curio eliminates the need for onboard processing units, dedicated cameras, and additional sensors while maintaining the ability to perform AI-based tasks. To evaluate the impact of Curio on student engagement, we conducted a case study with 20 participants, where we examined usability, engagement, and potential for integrating into AI and robotics education. The results indicate high engagement and motivation levels across all participants. Additionally, 95% of participants reported an improvement in their understanding of robotics. Findings suggest that using a robotic system such as Curio can enhance engagement and hands-on learning in robotics and AI education. All resources and projects with Curio are available at trycurio.com.

Figures (7)

• Figure 1: The Curio robot. Left: Back view with a smartphone. Right: Curio in a self-driving scenario going around a track.
• Figure 2: Components of the Curio robot and the communication process between Bluetooth devices (5). MDBT42Q module (1) handles the received command and controls the stepper motors (2) connected to wheels.
• Figure 3: Overview of the case study environment. The laptop (1) is running a Jupyter Notebook, which runs a face-tracking algorithm. The Curio robot (2). The smartphone (3) is mounted on the robot and functions as a camera.
• Figure 4: The flowchart of the face-tracking activity. The process begins with the Jupyter Notebook establishing a connection (1). The smartphone, acting as an IP camera, captures and transmits images to the notebook (2). The received image undergoes pre-processing (3) before a face detection algorithm is applied (4). Based on the detected face's position, the system makes a movement decision (5). Finally, a command is sent via Bluetooth (6) to the Curio robot, which adjusts its movement accordingly. The red dashed box highlights the computational process performed in the Jupyter Notebook.
• Figure 5: Mean scores of engagement-related questions with standard deviation error bars. The red dashed line represents the overall mean score (4.63).