Access at the vast majority of busy airports located outside the United States is subject to schedule coordination. These airports declare a value of capacity and allocate a corresponding number of slots to the airlines. Slot allocation follows rules and priorities established by the International Air Transport Association (IATA), which introduce coupling constraints across the allocation of slots at multiple times of the day and on multiple days of the year. As a result, slot allocation is a highly complex combinatorial problem, which carries enormous weight for airlines, airports, and passengers. Integer programming models have been proposed to support slot allocation by minimizing deviations from the airlines’ requests. Because of the problem’s complexity, these models have been only successfully implemented at small- and medium-sized airports. This paper develops an original algorithm based on large-scale neighborhood search to solve the slot allocation problem at the largest schedule-coordinated airports. The proposed algorithm combines a constructive heuristic, which provides an initial feasible solution in short computational times, and an improvement heuristic, which iteratively reoptimizes slot allocation by subdividing the slot requests into smaller subsets. The algorithm is implemented at Lisbon’s Airport (LIS), one of the top-20 busiest airports in Europe. Results suggest that it can provide optimal or near-optimal solutions in a few hours of computation, while direct implementation of existing optimization models with commercial solvers does not terminate after several days of computation. Ultimately, the proposed approach considerably enhances the capabilities of slot allocation models and algorithms.

Aircraft skin surface defect detection is critical for aviation safety but is currently mostly reliant on manual or visual inspections. Recent advancements in computer vision offer opportunities for automation. This paper reviews the current state of computer vision algorithms and their application in aircraft defect detection, synthesizing insights from academic research (21 publications) and industry projects (18 initiatives). Beyond a detailed review, we experimentally evaluate the accuracy and feasibility of existing low-cost, easily deployable hardware (drone) and software solutions (computer vision algorithms). Specifically, real-world data were collected from an abandoned aircraft with visible defects using a drone to capture video footage, which was then processed with state-of-the-art computer vision models—YOLOv9 and RT-DETR. Both models achieved mAP50 scores of 0.70–0.75, with YOLOv9 demonstrating slightly better accuracy and inference speed, while RT-DETR exhibited faster training convergence. Additionally, a comparison between YOLOv5 and YOLOv9 revealed a 10% improvement in mAP50, highlighting the rapid advancements in computer vision in recent years. Lastly, we identify and discuss various alternative hardware solutions for data collection—in addition to drones, these include robotic platforms, climbing robots, and smart hangars—and discuss key challenges for their deployment, such as regulatory constraints, human–robot integration, and weather resilience. The fundamental contribution of this paper is to underscore the potential of computer vision for aircraft skin defect detection while emphasizing that further research is still required to address existing limitations.

Aircraft skin surface defect detection is critical for aviation safety but is currently mostly reliant on manual or visual inspections. Recent advancements in computer vision offer opportunities for automation. This paper reviews the current state of computer vision algorithms and their application in aircraft defect detection, synthesizing insights from academic research (21 publications) and industry projects (18 initiatives). Beyond a detailed review, we experimentally evaluate the accuracy and feasibility of existing low-cost, easily deployable hardware (drone) and software solutions (computer vision algorithms). Specifically, real-world data were collected from an abandoned aircraft with visible defects using a drone to capture video footage, which was then processed with state-of-the-art computer vision models — YOLOv9 and RT-DETR. Both models achieved mAP50 scores of 0.70–0.75, with YOLOv9 demonstrating slightly better accuracy and inference speed, while RT-DETR exhibited faster training convergence. Additionally, a comparison between YOLOv5 and YOLOv9 revealed a 10% improvement in mAP50, highlighting the rapid advancements in computer vision in recent years. Lastly, we identify and discuss various alternative hardware solutions for data collection — in addition to drones, these include robotic platforms, climbing robots, and smart hangars — and discuss key challenges for their deployment, such as regulatory constraints, human-robot integration, and weather resilience. The fundamental contribution of this paper is to underscore the potential of computer vision for aircraft skin defect detection while emphasizing that further research is still required to address existing limitations.