Piloting Planetarium Visualizations with LLMs during Live Events in Science Centers

TL;DR

This study explores integrating AI as a co-pilot in planetarium shows, aiming to assist human guides by interpreting verbal commands to control visualizations, thereby reducing workload and enhancing live event experiences.

Contribution

We developed and evaluated an AI pilot system for planetarium visualization shows, demonstrating its potential to support human guides and outlining future research directions.

Findings

AI pilots can interpret verbal commands for visualization control.

AI pilots currently lack some critical skills for live shows.

Potential for AI to reduce human workload and support multitasking.

Abstract

We designed and evaluated an AI pilot in a planetarium visualization software, OpenSpace, for public shows in science centers. The piloting role is usually given to a human working in close collaboration with the guide on stage. We recruited 7 professional guides with extensive experience in giving shows to the public to study the impact of the AI-piloting on the overall experience. The AI-pilot is a conversational AI-agent listening to the guide and interpreting the verbal statements as commands to execute camera motions, change simulation time, or toggle visual assets. Our results show that, while AI pilots lack several critical skills for live shows, they could become useful as co-pilots to reduce workload of human pilots and allow multitasking. We propose research directions toward implementing visualization pilots and co-pilots in live settings.