Abstract

In this study we will investigate whether we can reduce the barriers to entry for high school robotics through the use of code generation models derived from large language models (LLMs). As such, we aim to raise the abstraction barrier for the development of artificial intelligence algorithms needed to program and control the Romi Robot used in the FIRST Robotics Competition (FRC). To do so we develop a web interface that helps automate the prompt-engineer step and allows students to easily incorporate OpenAI Codex into their workflows. To evaluate the impact of our approach, we will survey students to understand their overall experience and their satisfaction with, and perceived usefulness of, this technology. Additionally we will survey FRC community members to understand the community perception of the importance and equity of programming education within the context of high school robotics. We hope this study helps chart a path towards reduced coding prerequisites for high school robotics.