Piloting Planetarium Visualizations with LLMs during Live Events in Science Centers
Authors:
- Mathis BrossierMBMathis Brossier
- Mujtaba Fadhil JawadMJMujtaba Fadhil Jawad
- Emma BromanEBEmma Broman
- Ylva SellingYSYlva Selling
- Julia HallstenJHJulia Hallsten
- Alexander BockABAlexander Bock
- Johanna BjörklundJBJohanna Björklund
- Tobias IsenbergTITobias Isenberg
- Anders YnnermanAYAnders Ynnerman
- Mario RomeroMRMario Romero
- Lonni BesançonLBLonni Besançon
Preprint
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Enhancing Visual Reasoning With LLM-Powered Knowledge Graphs for Visual Question Localized-Answering in Robotic SurgeryIEEE Journal of Biomedical and Health Informatics, 2025
- Lessons Learnt from Expert-Centred Studies Exploring Opportunities and Challenges for Immersive Forensic Investigation2025
- Next-Generation Database Interfaces: A Survey of LLM-Based Text-to-SQLIEEE Transactions on Knowledge and Data Engineering, 2025
- How should the advancement of large language models affect the practice of science?Proceedings of the National Academy of Sciences, 2025
- Societal guardrails for AI? Perspectives on what we know about public opinion on artificial intelligenceScience and Public Policy, 2024
- Moliverse: Contextually embedding the microcosm into the universeComputers & Graphics, 2023
- Insights From Experiments With Rigor in an EvoBio Design StudyIEEE Transactions on Visualization and Computer Graphics, 2020
- Chart Mining: A Survey of Methods for Automated Chart AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- OpenSpace: A System for AstrographicsIEEE Transactions on Visualization and Computer Graphics, 2019
- Design Study Methodology: Reflections from the Trenches and the StacksIEEE Transactions on Visualization and Computer Graphics, 2012