Angelos Plastropoulos

Hangar-based maintenance, repair and overhaul (MRO) operations expose aircraft to close-proximity interactions with ground support equipment (GSE), where operator errors can cause structural damage and disruption. This study presents a monocular vision framework for collision-risk monitoring in a smart hangar, coupling instance segmentation, domain-adapted monocular depth inference and deterministic clearance reasoning. A paired dataset comprises synthetic top-down hangar renderings with pixel-aligned red-green-blue (RGB)-depth supervision and a matched miniature testbed containing scaled aircraft/GSE models and 3D-printed calibration objects, imaged by custom-mounted RGB cameras. The dual-head pipeline comprises YOLOv8-seg for six-class instance masks and DepthAnything-V2 for metric depth under the trained model convention. On the scene-disjoint synthetic test split, the custom-trained depth model achieves 0.135 m MAE, compared with 8.385m for pretrained weights, without materially increasing depth-inference time. WIthout dense RBG-camera depth ground truth, testbed-image transfer is reported as an ordinal/structural calibration-object proxy: relative step ordering is often preserved, whereas inter-step metric spacing is compressed and deemed inadequate for direct clearance-threshold decisions. Custom YOLOv8-seg variants achieve mean Intersection over Union (IoU) of 0.88–0.92 across synthetic and testbed splits, while the off-the-shelf baseline yields near-zero overlap in transfer tests. Collision inference is evaluated on deterministic 30-image samples per synthetic/testbed scenario, combining depth-derived height envelopes and boundary-only ground-plane distances to produce clear/warning/alert states and overlays. Median no-render compute latency is 0.736–1.037 s; profiling identifies post-processing, particularly GSE clustering and geometry construction, as the dominant runtime component. The study provides an auditable perception-to-geometry pipeline and highlights the need for uncertainty-aware threshold calibration before deployment.

Search-and-rescue (SAR) missions following earthquakes and other disasters require aerial video perception systems that do more than detect objects in isolated frames. Operators must maintain the identities of access points, vehicles, responders, hazards, and other mission-relevant targets despite UAV ego-motion, dust, debris, occlusion, scale variation, and abrupt scene transitions. This paper presents E’CHIT (Edge-Oriented Colour Histogram Instance-Guided Tracking), a deployment-oriented, operator-centric UAV tracking framework for real-world disaster-response applications. Its primary scientific contribution is an identity-stabilised, detector-assisted tracking methodology. YOLOv8-seg proposals trained on D’RespNeT initialise and refresh tracks; a Custom-RE3 recurrent module propagates target states through short detector dropouts; and a lightweight EOMC verifier, based on edge orientation, mean colour, and shape consistency, determines whether tracks should be accepted, refreshed, or reacquired. A scene-cut watchdog that combines luminance mean absolute difference (MAD) with HSV histogram divergence prevents stale identities from carrying over after hard edits or sudden feed changes. Custom-RE3 is the continuation module implemented and evaluated in this study. The surrounding E’CHIT wrapper follows an initialise–reseed–verify–reset cycle and is tracker-adaptable at the software-interface level: another compatible SOT or MOT continuation module can be integrated through adapter modifications, state and bounding-box conversion, and method-specific retuning, followed by independent validation. All reported quantitative results therefore apply to the Custom-RE3 implementation. D’RespNeT, the optional reinforcement learning (RL) warm start, the HUD, and the deployment stack support this central tracking contribution. D’RespNeT provides 28 polygon-annotated SAR classes. An author-developed PPO/SAC script is used only during offline detector training. In the reported runs, it produces different early optimisation trajectories for selected difficult or under-represented classes, while the default supervised schedule remains the strongest final global mAP reference. No RL policy runs during deployment; the detector architecture, parameter count, and inference graph remain unchanged. Evaluation on D’RespNeT and authentic disaster-response UAV footage shows that E’CHIT increases Success@IoU ≥ 0.5 from 0.62 to 0.79, reduces identity switches by approximately 71%, and maintains real-time 1080p performance, achieving 164–330 FPS for single-target tracking and 24–100+ FPS for end-to-end multi-target operation on an RTX-class GPU using FP16. The VOT2014, NT-VOT211, and VOTS2024 figures reproduce historical result spaces reported in the literature and include a clearly labelled, non-official E’CHIT operating-point marker solely for context. This marker was not produced using the corresponding official datasets, toolkits, reset rules, or submission routes; it is excluded from the primary quantitative claims and must not be interpreted as a leaderboard rank or a protocol-identical comparison. Overall, the system demonstrates how identity-stable UAV tracks can provide actionable operator cues for target monitoring, entry-point assessment, and UAV–UGV/ground-team coordination in cluttered disaster scenes.

The accuracy, robustness and affordability of localisation are fundamental to autonomous robotic inspection within aircraft maintenance, repair and overhaul (MRO) hangars. Hangars typically have high ceilings and are predominantly steel-framed structures with metal cladding. Because of this, they are regarded as GPS-denied environments, characterised by significant multipath effects and strict operational constraints, which together form a unique challenging setting. The lack of comparative techno-economic benchmarks for localisation technologies in such environments remains a critical gap. Addressing this, the paper presents the first techno-economic analysis that benchmarks motion capture (MoCap), ultra-wideband (UWB) and a ceiling-mounted camera (CMC) system across three operational scenarios: robot localisation, asset monitoring and surface defect detection within a single-bay hangar. A two-stage optimisation framework for camera selection and placement is introduced, which couples market-based camera-lens selection with an optimisation solver, producing camera layouts that minimise hardware while meeting accuracy and coverage targets. The consolidated blueprints provide quantification of the required equipment and its performance: 15 global-shutter GigE cameras are adequate for drone localisation, 9 cameras meet the requirements for on-bay monitoring and 49 high-resolution cameras facilitate defect mapping of the upper airframe surfaces for midsize defects. Across these scenarios, the study reports indicative performance and cost envelopes: a MoCap installation delivers submillimeter localisation at an estimated £190k per bay, UWB delivers centimetre-level tracking for around £49k and the proposed CMC system layouts achieve task-specific coverage with costs in the £9k–£77k range. The analysis equips MRO planners with an actionable method to balance accuracy, coverage and budget, demonstrating that an optimised CMC system can deliver robust and cost-effective sensing for next-generation smart hangars.

The accuracy, resilience, and affordability of localisation are fundamental to autonomous robotic inspection within aircraft maintenance and overhaul (MRO) hangars. Hangars typically feature tall ceilings and are often made of materials such as metal. Due to its nature, it is considered a GPS-denied environment, with extensive multipath effects and stringent operational constraints that collectively create a uniquely challenging environment. This persistent gap highlights the need for domain-specific comparative studies, including rigorous cost, accuracy, and integration assessments, to inform a reliable and scalable deployment of a localisation system in the Smart Hangar. This paper presents the first techno-economic roadmap that benchmarks motion capture (MoCap), ultra-wideband (UWB), and a ceiling-mounted camera network across three operational scenarios: robot localisation, asset tracking, and surface defect detection within a 40x50 m hangar bay. A dual-layer optimisation for camera selection and positioning framework is introduced, which couples market-based camera-lens selection with an optimisation solver, producing camera layouts that minimise hardware while meeting accuracy targets. The roadmap equips MRO planners with an actionable method to balance accuracy, coverage, and budget, demonstrating that an optimised vision architecture has the potential to unlock robust and cost-effective sensing for next-generation Smart Hangars.

Aircraft maintenance is a multifaceted process that requires highly skilled, qualified and experienced personnel. Effective maintenance processes optimise aircraft operational lifespan, minimise lifecycle costs and improve reliability by reducing the probability of unexpected maintenance events. The initial diagnostic phase relies on detailed visual inspections conducted by certified technicians. Following inspections, data assessment leads to the development of a comprehensive maintenance plan, along with the sourcing of necessary resources and spare parts. As the maintenance, repair and overhaul (MRO) sector transitions into the era of Industry 4.0, there is a growing emphasis on integrating data analytics and cyber-physical systems into maintenance practices. A key objective in this evolution is the adoption of robotic systems for inspection tasks. This shift requires the reconfiguration of formal inspection procedures to ensure compatibility with robotic operations. Moreover, it is critical to address the specific requirements of robotics and to incorporate smart hangar technologies that take advantage of real-time data to improve both efficiency and effectiveness in maintenance operations. This study provides a comprehensive review of the MRO landscape and maintenance checks, with a particular focus on robotic aircraft inspection systems, navigation and smart hangar infrastructure. The discussion concludes with an examination of defect detection methods using machine vision along with relevant metrics to compare with human performance.

Accurate forecasting of the remaining useful life (RUL) of aviation equipment is crucial for enhancing safety and reducing maintenance costs. This study presents a novel hybrid prognostic methodology that integrates physics-based and data-driven models to improve RUL estimations for critical aircraft components. The physics-based approach simulates long-term degradation patterns using fundamental principles such as mass conservation and Bernoulli’s equation, while the data-driven model employs a hyper tangent boosted neural network (HTBNN) to detect short-term anomalies and deviations in real-time sensor data. The integration of various models enhances accuracy, adaptability, and reliability in prognostics. The proposed methodology is assessed using NASA’s N-CMAPSS dataset for gas turbines and a fuel system test rig, demonstrating a 15% improvement in prediction accuracy and a 20% reduction in uncertainty compared to traditional methods. These findings highlight the potential for widespread application of this hybrid methodology in predictive maintenance and prognostic and health management (PHM) of aircraft systems.

Sustainability is becoming a major strategic driver within the aviation industry, which has moved from providing primarily economic benefits to delivering the ‘triple bottom line’, including social and environmental impact as well as financial performance. Sustainable aviation is also being tracked by the International Civil Aviation Organisation (ICAO) Global Collation for Sustainable Aviation. Operations and Infrastructure is an important near-term opportunity to deliver sustainability benefits. Digital Technologies, Integrated Vehicle Health Management (IVHM) and Maintenance Repair and Overhaul (MRO) play a prominent role in implementing these benefits, with a particular focus on operational efficiencies. As part of this, the sustainable smart hangar of the future is a concept that is becoming more and more important in forming the future of the aviation industry. The Hangar of the Future is an excellent opportunity for innovation, combining the progress in manufacturing, materials, robotics and artificial intelligence technologies. Succeeding in developing a hangar with these characteristics will provide us with potential benefits ranging from reduced downtime and costs to improved safety and environmental impact. This work explores some of the key features related to the sustainable smart hangar of the future by discussing research that takes place in DARTeC’s (Digital Aviation Research and Technology Centre) hangar led by the IVHM Centre in Cranfield. Additionally, the paper touches on some longer-term aspirations.

Aircraft maintenance is a complex process that requires a highly trained, qualified, and experienced team. The most frequent task in this process is the visual inspection of the airframe structure and engine for surface and sub-surface cracks, impact damage, corrosion, and other irregularities. Automated defect detection is a valuable tool for maintenance engineers to ensure safety and condition monitoring. The proposed approach is to process the captured feedback using various deep learning architectures to achieve the highest performance defect detections. Additionally, an algorithm is proposed to estimate the size of the detected defect. The team collaborated with TUI’s Airline Maintenance Team at Luton Airport, allowing us to fly a drone inside the hangar and use handheld cameras to collect representative data from their aircraft fleet. After a comprehensive dataset was constructed, multiple deep-learning architectures were developed and evaluated. The models were optimized for detecting various aircraft skin defects, with a focus on the challenging task of dent detection. The size estimation approach was evaluated in both controlled laboratory conditions and real-world hangar environments, providing insights into practical implementation challenges.