This research investigates the efficacy of utilizing unmanned aerial vehicles (UAVs) for foreign object debris (FOD) detection on airport runways, aiming to surpass traditional methods such as radar, infrared technologies, and stationary cameras. FOD poses a significant risk to aircraft during landing and takeoff, encompassing a diverse range of materials including loose hardware, pavement fragments, wildlife, and more. The potential damage caused by FOD incidents, estimated at $4 billion annually in the aerospace industry, underscores the critical need for effective detection and mitigation strategies. Drawing attention to notable instances such as the Air France Concorde tragedy in 2000, where FOD on the runway led to catastrophic consequences, the paper highlights contributory factors such as poor maintenance practices, inadequate staff training, and adverse weather conditions. Current detection methods, while effective to varying degrees, exhibit limitations such as radar technology’s susceptibility to inaccuracies with small debris and high costs. In examining historical incidents related to runway Foreign Object Debris (FOD), notable events underscore the critical importance of effective detection and mitigation strategies. For instance, the tragic loss of the Air France Concorde in 2000, attributed to runway FOD causing a catastrophic fuel-fed fire, highlights the dire consequences of overlooking debris during takeoff. Similarly, incidents such as the engine failure of an Embraer 190 in Oslo in 2010, caused by ingestion of broken edge light fittings, emphasize the need for comprehensive inspection protocols to prevent damage to aircraft systems. These incidents serve as poignant reminders of the potential hazards posed by runway debris and reinforce the imperative for advanced detection technologies to ensure the safety of air travel operations. Proposing innovative solutions, this study introduces two novel approaches for FOD detection on airport runways. Firstly, an autonomous UAV equipped with LiDAR technology offers rapid and comprehensive scanning capabilities, enabling efficient identification of foreign objects. Secondly, employing a UAV with an RGB camera and an AI detector trained via deep learning methods presents a promising alternative, facilitating real-time detection of FOD at low altitudes. Preliminary evaluations demonstrate the effectiveness of both proposed systems in detecting objects of varying sizes and distances from the UAV. These solutions represent significant advancements towards enhancing runway safety and operational efficiency in the context of modern smart airports.