Human Factors and AI in UAV Systems: Enhancing Operational Efficiency Through AHP and Real-Time Physiological Monitoring

Abstract

Integrating Artificial Intelligence (AI) into Unmanned Aerial Vehicle (UAV) operations has advanced efficiency, safety, and decision-making. This study addresses critical gaps in UAV methods, including insufficient integration of human factors, operator variability, and the lack of systematic error analysis. To overcome these challenges, a novel approach combines the Analytic Hierarchy Process (AHP) with three core human factors models: the Observe-Orient-Decide-Act (OODA) loop, the Human Factors Analysis and Classification System (HFACS), and the SHELL model. An online survey was conducted across diverse UAV operator groups to prioritize critical factors within each model. Additionally, real-time monitoring of heart rate (HR), heart rate variability (HRV), and respiratory rate (RR) was conducted during UAV operations at various automation levels with different experience levels. Visualization through boxplots and percentage change matrices provided insights into operator stress and workload across automation levels. Integrating AHP findings and physiological data revealed significant differences in operator prioritization, highlighting the need for tailored AI-UAV strategies. This research combines survey data with real-time physiological monitoring, offering visions into optimizing human-AI interaction in UAV operations and providing a foundation for improving AI integration and operator strategies.