With the rise of Artificial Intelligence (AI) systems in society, our children have routine interactions with these technologies. It has become increasingly important for them to understand how these technologies are trained, what their limitations are and how they work. To introduce children to AI and Machine Learning (ML) concepts, recent efforts introduce tools that integrate ML concepts with physical computing and robotics. However, some of these tools cannot be easily integrated into building projects and the high price of robotics kits can be a limiting factor to many schools. We address these limitations by offering a low-cost hardware and software toolkit that we call the Smart Motor to introduce supervised machine learning to elementary school students. Our Smart Motor uses the nearest neighbor algorithm and utilizes visualizations to highlight the underlying decision-making of the model. We conducted a one week long study using Smart Motors with 9- to 12- year old students and measured their learning through observation, questioning and examining what they built. We found that students were able to integrate the Smart Motors into their building projects but some students struggled with understanding how the underlying model functioned. In this paper we discuss these findings and insights for future directions for the Smart Motor.

In this innovative practice paper, we present case studies of participants using a trainable robotics tool called Smart Motors from two workshops: one with participants from elementary schools in a robotics camp and the second with students from a high school. We designed the workshops to help us observe two key aspects: how students engage with the tool as new users from different age groups and the variability in levels of enjoyment and iterative thinking with an engineering design task while using the tool. Learning robotics can be complex as it can involve learning programming, mechanical design, and electrical circuits simultaneously. Some existing robotics kits support beginners with mechanical design tasks via easy-to-integrate sensor kits, motors, and control hubs, and some support beginners with alternative programming methods like web-based block coding languages and QR codes. However, cost, availability, and ease of use make integrating robotics into the curriculum difficult for some classes. Smart Motors are easy-to-use, low-cost alternatives to lower those barriers to bringing robotics into the classroom. Smart Motors simplifies mechanical “set-up” by packaging the user interface, motor, and sensor in one unit. They use training and a machine learning algorithm called the nearest neighbor to make decisions. Since they do not require coding to generate desired outcomes, students can use them in classrooms without computers or internet access. We allowed first-time Smart Motor users to learn the tool while participating in a play-based design activity with three sessions. The first session of the workshop was a discussion of Artificial Intelligence and Machine Learning. The second session was an introduction to Smart Motors, in which the participants built a “hello-world” waving contraption using Smart Motors and LEGO® pieces. The third session consisted of an activity derived from Tufts University's Novel Engineering curriculum, where the participants listened to a story, chose a character, and designed solutions for them. We analyzed their work with the help of field notes and video data. Using the Learning through Play Experience Tool, we looked for evidence of two of the five characteristics of playful learning: Joyful and Iterative. We transcribed the video data in detail and coded for the states of play in two-minute chunks, where we looked at and analyzed the play trends. We found that Smart Motors supports playful learning in engineering design workshops, allowing participants from different ages and experience levels to engage creatively to design products of various complexity.

Smart Motors is a low-cost, low-barrier-to-entry trainable robotic system enabling playful learning with technology in various classroom types. Many kits and online tools have been developed as educational resources for children to learn about robotics, enabling an increasingly widespread integration of engineering and robotics into classrooms. Despite the positive features of many existing technologies, however, issues of equitable access for students in under-resourced classrooms have emerged: the high costs of many of the kits and the need for internet connectivity, computers, and technical expertise on the part of teachers all limit their adoption. Smart Motors offers a low-cost solution based on readily available materials, enabling students in diverse educational contexts and ages to gain exposure to robotics and artificial intelligence. Users can train this type of motor to run to various positions corresponding to different sensor inputs, enabling students to bring their engineering projects to life. The underlying shift from coding to training robots eliminates the need for access to computers and the internet for students to engage in hands-on robotics activities. Furthermore, the system can be developed with locally available materials, enabling its adoption in diverse and international settings. In this paper, we describe the international collaboration in developing Smart Motors, detail various prototypes built with locally on-hand materials, describe the issues we have faced in this endeavor, and outline future plans. We are creating an international community of engineers and educators developing new designs and testing various materials available in local settings. This global network enables a wide range of educational contexts to be at the core of the development process. Studying students' engagement with the system at workshops further ensures that the product is accessible and contributes to students' and teachers' learning in various settings.