Presentation

· Contributors · Organizations · Search Program

Evaluating Generative AI as a Human Factors Requirements-based Review System of Spaceflight Ground Displays

DescriptionSpaceflight launch control displays provide monitoring, control, and commanding capabilities during critical prelaunch preparations and the final launch countdown. During development, launch control displays are often evaluated against a set of standards or style guidelines. This can often be a time-consuming process. Image recognition-capable Generative Artificial Intelligence systems offer an alternative to human-only display evaluations, allowing for a quick assessment of requirements compliance against internal guidelines or industry-accepted standards. The present research evaluates the capabilities of commercially available GenAI systems for assessing launch control displays against a set of usability and design standards. A custom GenAI implementation was developed and provided with few-shot learning of adequate design requirements. Additionally, the custom implementation was provided with a custom display user guide, NASA and FAA display design standards, custom UI design standards to serve as design requirements, and a list of acronyms typically found in displays and their meaning. Variations of 3 displays were evaluated by the AI system. Results show that while custom launch control display usability requirements evaluator varied in its capabilities dependent on the display shown, overall accuracy was adequate. The findings suggest that GenAI systems may be viable as first-pass evaluators in requirements-based human factors review workflows.

Contributors