Artificial Intelligence as an Enabler of Operational Resilience in Autonomous UAV-AutoID Systems Operating in Dynamic Indoor Environments

The increasing deployment of autonomous UAV-AutoID systems in warehouses, production halls, and other industrial facilities has created a growing need to ensure their operational resilience under dynamic indoor conditions. These environments are characterized by spatial constraints, changing lighting, electromagnetic interference, sensor degradation, communication limitations, and variable mission requirements. While existing research on artificial intelligence in unmanned aerial vehicles primarily focuses on navigation, localization, computer vision, obstacle avoidance, and autonomous flight control, the role of AI as a mechanism for enhancing the resilience of the complete UAV-based system remains insufficiently explored. This paper proposes a system-level framework for integrating artificial intelligence into the operational resilience of autonomous UAV-AutoID systems operating in dynamic indoor environments. Building upon the M-UAV resilience assessment method, the proposed approach incorporates AI-based mechanisms for disturbance detection, operational risk prediction, adaptive mission planning, intelligent decision support, and real-time mission reconfiguration. The framework considers interactions among the UAV platform, AutoID technologies, onboard perception and control software, communication infrastructure, data-processing components, and the operational environment. It explains how machine learning, computer vision, Edge AI, and adaptive decision-making can support early identification of adverse conditions, selection of corrective actions, and maintenance of acceptable system performance despite disturbances. The proposed concept extends conventional resilience assessment by introducing AI as a proactive resilience-building mechanism rather than only a tool for flight automation. It therefore enables a transition from retrospective evaluation toward predictive and adaptive resilience management. The study provides a foundation for further research on intelligent, reliable, and self-adaptive UAV systems for Industry 4.0, Logistics 4.0, automated inventory, and industrial inspection applications.