Kritik Görevler İçin Akıllı İnsansız Hava Aracı: Gerçek Zamanlı Görsel Zekâya Sahip Bir VTOL İHA’nın Geliştirilmesi

Öz

Bu çalışma, arama-kurtarma, gözetleme ve hassas tarım gibi kritik görevler için optimize edilmiş, yerleşik gerçek zamanlı görsel zekâ sistemine sahip sabit kanatlı bir Dikey Kalkış ve İniş (VTOL) insansız hava aracının (İHA) tasarımını, üretimini ve değerlendirmesini sunmaktadır. İHA, hafif ve düşük maliyetli malzemeler ile 3B baskı bileşenleri kullanılarak üretilmiş, bu sayede geliştirme maliyetleri önemli ölçüde azaltılmış ve sistemin hem akademik araştırmalarda hem de saha uygulamalarında erişilebilirliği artırılmıştır. Bu çalışmanın temel katkısı, tamamen açık kaynaklı bir mimari içerisinde VTOL işlevselliğinin, gömülü donanım üzerinde gerçek zamanlı derin öğrenme çıkarımıyla bütünleştirilmesidir. Mevcut İHA’ların çoğu hacimli veya pahalı donanımlara bağımlı iken, önerilen sistem nesne tespitini (YOLOv5s) doğrudan Raspberry Pi 4B üzerinde gerçekleştirerek harici hesaplamaya gerek duymadan verimli yerleşik işlem yapabilmektedir. Üç farklı algılama modeli — YOLOv5s, Tiny-YOLOv4 ve MobileNet-SSD — özel olarak oluşturulmuş bir hava veri kümesi üzerinde eğitilmiş ve gerçek zamanlı performans açısından değerlendirilmiştir. YOLOv5s modeli, %82,4 ortalama hassasiyet (mAP@0.5) ve 4,2 FPS değerleriyle en yüksek doğruluğu elde etmiştir. Modüler ve ölçeklenebilir tasarımı sayesinde, önerilen İHA platformu, gerçek dünya koşullarında akıllı hava sistemlerinin uygulanması için pratik ve ekonomik bir çözüm sunmaktadır.

Anahtar Kelimeler

• Sabit kanatlı insansız hava aracı
• Döner kanatlı hava aracı
• Gerçek zamanlı hava gözetimi
• Gömülü yapay zekâ
• VTOL İHA

Smart Drone for Critical Missions: Development of a VTOL UAV with Real-Time Visual Intelligence

Öz

This study presents the design, construction, and evaluation of a fixed-wing Vertical Take-Off and Landing (VTOL) unmanned aerial vehicle (UAV) equipped with an onboard real-time visual-intelligence system optimized for critical missions such as search and rescue, surveillance, and precision agriculture. The UAV was built using lightweight, cost-effective materials and 3D-printed components, which considerably reduced development costs and improved accessibility for both academic research and field applications. A central contribution of this work is the integration of VTOL functionality with real-time deep-learning inference on embedded hardware within a fully open-source architecture. Unlike most existing UAVs that depend on bulky or expensive hardware, the proposed system performs efficient object detection (YOLOv5s) directly on a Raspberry Pi 4B, enabling onboard processing without external computation. Three detection models—YOLOv5s, Tiny-YOLOv4, and MobileNet-SSD—were trained on a custom aerial dataset and evaluated for real-time performance. YOLOv5s achieved the highest accuracy, with a mean Average Precision (mAP@0.5) of 82.4 % at 4.2 FPS. Owing to its modular and scalable design, the proposed UAV platform offers a practical and affordable solution for implementing intelligent aerial systems in real-world critical-mission environments.

Anahtar Kelimeler

• Fixed-wing drone
• Rotating-wing aircraft
• Real-time aerial surveillance
• Embedded AI
• VTOL UAV

Kaynakça

1. G. Cai, K. Y. Lum, B. M. Chen, and T. H. Lee, “A brief overview on miniature fixed-wing unmanned aerial vehicles,” in Proc. IEEE Int. Conf. Control Autom. (ICCA), 2010, pp. 285–290.
2. F. Ahmed, J. C. Mohanta, A. Keshari, and P. S. Yadav, “Recent advances in unmanned aerial vehicles: A review,” Arab. J. Sci. Eng., vol. 47, no. 7, pp. 7963–7984, 2022.
3. K. Buchholz, “Commercial drones projected growth,” Statista, Mar. 3, 2019. [Online]. Available: https://www.statista.com/chart/17201/commercial-drones-projected-growth/.
4. T. Baca, R. Penicka, P. Stepan, M. Petrlik, V. Spurny, D. Hert, and M. Saska, “Autonomous cooperative wall building by a team of unmanned aerial vehicles in the MBZIRC 2020 competition,” Robot. Auton. Syst., vol. 166, p. 104482, 2023.
5. A. Puri, “A survey of unmanned aerial vehicles (UAV) for traffic surveillance,” Dept. Comput. Sci. Eng., Univ. South Florida, pp. 1–29, 2005.
6. E. J. V. Rozo, “Medición de contaminación mediante UAV (Vehículo Aéreo no Tripulado),” Mundo Fesc, vol. 6, no. 11, pp. 16–26, 2016.
7. R. D. B. Ruiz, A. C. Lordsleem Júnior, and J. H. A. Rocha, “Inspeção de fachadas com veículos aéreos não tripulados (VANT): estudo exploratório,” Rev. ALCONPAT, vol. 11, no. 1, pp. 88–104, 2021.
8. A. Aabid, B. Parveez, N. Parveen, S. A. Khan, J. M. Zayan, and O. Shabbir, “Reviews on design and development of unmanned aerial vehicle (drone) for different applications,” J. Mech. Eng. Res. Dev., vol. 45, no. 2, pp. 53–69, 2022.

9. A. J. Torija and C. Clark, “A psychoacoustic approach to building knowledge about human response to UAV noise,” Int. J. Environ. Res. Public Health, vol. 18, no. 2, p. 682, 2021.
10. Titan Dynamics, “Cobra VTOL: Build & User Manual,” Rev. 1.1, 2024. [Online]. Available: https://www.titandynamics.org/s/Titan-Cobra-User-Manual.pdf.
11. C. Davenport, J. Jonas, J. Martin, H. Mazur, S. Vinson, and B. Wirtz, “Aircraft design for AIAA Design Build Fly Competition,” Worcester Polytechnic Institute, 2022.
12. M. Y. Narkevich, O. S. Logunova, P. I. Kalandarov, A. N. Kalitaev, G. V. Tokmazov, P. Y. Romanov, and O. Alimov, “Results of a pilot experiment on monitoring the condition of buildings and structures using UAVs,” IOP Conf. Ser.: Earth Environ. Sci., vol. 939, no. 1, p. 012030, 2021.
13. Y. O. Aktaş et al., “A low-cost prototyping approach for design analysis and flight testing of the Turac VTOL UAV,” in Proc. Int. Conf. Unmanned Aircr. Syst. (ICUAS), 2014, pp. 1029–1039.
14. C. Chen, Z. Zheng, T. Xu, S. Guo, S. Feng, W. Yao, and Y. Lan, “YOLO-based UAV technology: A review of research and applications,” Drones, vol. 7, no. 3, p. 190, 2023.
15. A. Gupta and X. Fernando, “Simultaneous localization and mapping (SLAM) and data fusion in unmanned aerial vehicles: Recent advances and challenges,” Drones, vol. 6, no. 4, p. 85, 2022.
16. J. Łęcki, M. Hering, M. Jabłoński, and A. Karpus, “An analysis of the performance of lightweight CNNs for object detection on mobile devices,” Sensors, vol. 24, no. 6, p. 1234, 2024.
17. A. Telikani et al., “Unmanned aerial vehicle–aided intelligent transportation systems: Vision, challenges, and opportunities,” IEEE Commun. Surveys Tuts., vol. 27, no. 1, pp. 45–78, 2025.
18. S. Boddu and A. Mukherjee, “Efficient edge deployment of quantized YOLOv4-Tiny for aerial emergency object detection on Raspberry Pi 5,” arXiv preprint arXiv:2506.09300, 2025.
19. K. Niu, C. Wang, J. Xu, J. Liang, X. Zhou, K. Wen, and C. Yang, “Early forest fire detection with UAV image fusion: A deep learning method using visible and infrared sensors,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 18, no. 5, pp. 1234–1245, 2025.
20. Feiyu Technology, “FY-41AP AutoPilot & OSD System Installation and Operation Manual,” 2024. [Online]. Available: https://cdn1.feiyu-tech.com/download/20190926/58574a74bea0d.pdf
21. N. Nithyavathy, S. Pavithra, M. Naveen, B. Logesh, and T. James, “Design and development of a drone for healthcare,” Int. J. Sci. Technol. Res., vol. 9, no. 1, pp. 2676–2680, 2020.
22. A. Üzel, D. C. Zuidervliet, and P. J. van Duijsen, “Educational setup for brushless motor drives,” in Proc. 17th Conf. Electr. Mach., Drives Power Syst. (ELMA), 2021, pp. 1–6.
23. S. Sripad, A. Bills, and V. Viswanathan, “A review of safety considerations for batteries in electric aircraft,” MRS Bull., vol. 46, no. 5, pp. 435–442, 2021.
24. T. Placke, R. Kloepsch, S. Dühnen, and M. Winter, “Lithium-ion, lithium-metal, and alternative rechargeable battery technologies: The odyssey for high energy density,” J. Solid State Electrochem., vol. 21, pp. 1939–1964, 2017.
25. H. A. Gabbar, A. M. Othman, and M. R. Abdussami, “Review of battery management systems (BMS) development and industrial standards,” Technologies, vol. 9, no. 2, p. 28, 2021.
26. CFRP-Tstar, “Carbon fiber rods – the best choice for your projects,” 2024. [Online]. Available: https://www.cfrp-tstar.com/high-quality-carbon-fiber-rods/.
27. C. J. Swinney and J. C. Woods, “Low-cost Raspberry Pi–based UAS detection and classification system using machine learning,” Aerospace, vol. 9, no. 12, p. 738, 2022.
28. M. Pagnutti, R. E. Ryan, G. Cazenavette, M. Gold, R. Harlan, E. Leggett, and J. Pagnutti, “Laying the foundation to use Raspberry Pi 3 V2 camera module imagery for scientific and engineering purposes,” J. Electron. Imag., vol. 26, no. 1, p. 013014, 2017.
29. M. H. Hamzenejadi and H. Mohseni, “Fine-tuned YOLOv5 for real-time vehicle detection in UAV imagery: Architectural improvements and performance boost,” Expert Syst. Appl., vol. 231, p. 120845, 2023.
30. Roboflow, “Roboflow: Annotate and preprocess tool.” [Online]. Available: https://roboflow.com
31. Z. Chen, L. Cao, and Q. Wang, “YOLOv5-based vehicle detection method for high-resolution UAV images,” Mobile Inf. Syst., vol. 2022, Art. no. 1828848, 2022.
32. Electronoobs, “6S & BMS Battery Pack,” 2024. [Online]. Available: https://electronoobs.com/eng_circuitos_tut27.php.
33. Feiyu Technology, “FY-40A Flight Stabilization System Installation & Operation Manual,” 2024. [Online]. Available: http://www.feiyu-uav.net/data/upload/admin/20181124/5bf915baf02ff.pdf.
34. T. Y. Lin et al., “Microsoft COCO: Common objects in context,” in Comput. Vis. – ECCV 2014, Cham, Switzerland: Springer, 2014, pp. 740–755.
35. Made-in-China, “Fixed Wing Drone,” 2024. [Online]. Available: https://www.made-in-china.com/products-search/hot-china-products/Fixed_Wing_Drone.html.