Effect of Explanations in AI-Assisted Anomaly Treatment for Human Spaceflight Missions
Event Type
TimeWednesday, October 12th3:30pm - 4:30pm EDT
LocationPoster Gallery
DescriptionArtificial Intelligence (AI) agents have the potential to play a critical role in human spaceflight by being the first point of contact for astronauts. In a long duration spaceflight mission, when communication delays with the Mission Control Crew (MCC) become longer and more frequent, replacing the MCC with an on-board AI gives the crew more autonomy and allows them to respond faster and more safely to emergencies. For AI to succeed in this role, providing accurate diagnoses is important. However, providing explanations for those recommendations is critical to help establish trust between humans and AI. This study evaluates the effects of types of explanations on crew performance metrics and trust in the context of anomaly resolution. The subjects work with the AI on various anomaly scenarios in which the accuracy of the AI's predictions varies. We discuss our findings and provide design recommendations for future AI agents in human spaceflight.