Automated Landing of an Unmanned Aerial Vehicleon a Mobile Platform Using Neural Networks

Cover Page

Cite item

Full Text

Abstract

The development of unmanned aerial vehicles is one of the promising directions for civil aviation with a wide range of applications. Neural networks can be trained for real-time decision making, adapting to changing battlefield conditions and ensuring optimal task execution. Among many UAV navigation and control tasks, the challenge of automatic landing of an unmanned aerial vehicle on a mobile landing platform (ships, vehicles, specialized platforms) remains relevant. Automated landing of an unmanned aerial vehicle on a mobile carrier is particularly significant.The article examines the system of automatic landing of an unmanned aerial vehicle (UAV) on a mobile platform using neural network technologies. The research method is based on the application of artificial neural networks for developing an adaptive control system capable of real-time decision-making during landing maneuvers.As a result of the research, a control algorithm was developed that ensures precise landing of UAVs on various types of moving platforms (ships, vehicles, specialized platforms), which significantly expands the operational range of unmanned vehicles and increases their efficiency in various operating conditions.

About the authors

Vladislav A. Suslov

Baltic State Technical University “Voenmeh” named after D.F. Ustinov

Author for correspondence.
Email: vlarsu@mail.ru
ORCID iD: 0009-0007-1028-5993
SPIN-code: 2143-8843

Post-graduate student of the Department of Launch and Technical Complexes of Rockets and Spacecraft

Saint Petersburg, Russia

Sergey V. Gagarsky

Baltic State Technical University “Voenmeh” named after D.F. Ustinov

Email: svgagarski@mail.ru
Candidate of Technical Sciences, Associate Professor of the Department of Launch and Technical Complexes of Rockets and Spacecraft Saint Petersburg, Russia

References

  1. Tokarev YuP. Methods of Controlling Unmanned Aerial Vehicles in Common Airspace Using Flight Information with Automatic Dependent Surveillance: Ph.D. thesis in Technical Sciences: 05.22.13. Moscow; 2022. (In Russ.)
  2. Platunova AV, Klishin AN, Ilyukhin SN. Features of Forming Adaptive Control Laws for High-Precision Aircraft. Engineering Bulletin. 2016;(10):5. (In Russ.) EDN: XCMPBB
  3. Nikanorova MD, Zabolotskaya EV. Numerical cal-culation of aerodynamic characteristics unmanned aerial vehicle. Politechnical student journal. 2019;4(33):1–14. https://doi.org/10.18698/2541-8009-2019-4-464
  4. Korevanov S, Kazin VV. Application of artificial neural networks in problems of general and comparative navigation methods of UAV. Civil aviation high tech-nologies. 2014;(201):46–49. (In Russ.) EDN: RYFUSP
  5. Dolgov EN. Artificial Intelligence for Aircraft Control. Young Scientist. 2021;16(358):81–86. (In Russ.) EDN: DDXGPE
  6. Scherbinin VV, Vasil’eva YS, Chizhevskaya OM, Shevtsova EV. Functioning methods and algorithms of color vision-based correlation-extremal aircraft navigation system. Gyroscopy and Navigation. 2013;4(1):39–49. https://doi.org/10.1134/S2075108713010082
  7. Smolsky AG, Kovalenko SN, Mikhuta MV. Neural network algorithm for processing geospatial information from an unmanned aerial vehicle. In: Geoinformation systems for military purposes: theory and practice of application. Minsk; 2023. p. 12–16. (In Russ.) EDN: ZVCQOK
  8. Makarov IM, Lokhin VM, Manko SV. Artificial Intelligence and Intelligent Control Systems. Moscow: Nauka Publ.; 2006. (In Russ.)
  9. Gafarov FM, Galimyanov AF. Artificial Neural Networks and Applications: Textbook. Kazan: Kazan Federal University; 2018. (In Russ.)
  10. Sizov AV, Ippolitov SV, Savchenko AYu, Maly-shev VA. Method of autonomous correction of inertial navigation system of unmanned aircraft on the basis of modern geoinformation technologies. Modeling, Optimization and Information Technologies. 2019;7(1):183–195. (In Russ.) https://doi.org/10.26102/2310-6018/2019.24.1.030
  11. Ivanova IA, Nikonov VV, Tsareva AA. Methods of Organizing Control of Unmanned Aerial Vehicles. Actual problems of the humanities and natural sciences. 2014;(11–1):56–63. (In Russ.) EDN: TCIQMH
  12. Korotin PS, Alekseev EG. The experience of using Keras as a Front end for tensorflow. In: XXIII scientific and practical conference of National Research Mordovian State University. Saransk; 2019. p. 301–306. EDN: KVNYOF
  13. Tkachev N, Fedyaev O. Parametric description of deep neural network models in the Keras library. In: Soft-ware Engineering: Methods and Technologies. Donetsk; 2018. p. 112–118. EDN: ZVPZTL
  14. Gagarsky SV, Suslov VA. Helicopter Deck Landing System. Saint Petersburg: Autonomous Systems LLC; 2022. (In Russ.)
  15. Fedoseeva NA, Zagvozdkin MV. Promising Areas of Application of Unmanned Aerial Vehicles. Scientific Journal. 2017;22(9):26–29. (In Russ.) EDN: ZSUMLX
  16. Popov AN. Planning methods of movement tra-jectory of unmanned aerial vehicle. Izvestia of Samara Scientific Center RAS. 2017;19(1–2):364–370. (In Russ.) EDN: ZTPOIN
  17. Mammadov AZ. Model inertial navigation for unmanned aerial vehicles. Universum: Technical Sciences. 2021;5(86):5–9. (In Russ.) https://doi.org/10.32743/UniTech.2021.86.5.11683
  18. Keras Library. Available from: https://keras.io/ (accessed: 17.05.2024).
  19. Autonomous Navigation System. Available from: https://info.wikireading.ru/84077 (accessed: 27.04.2024).
  20. UAV Sensors. Available from: https://www.energovector.com/energoznanie-kak-roboty-orientiruyutsya-v-prostranstve.html (accessed: 27.04.2024).

Copyright (c) 2024 Suslov V.A., Gagarsky S.V.

License URL: https://creativecommons.org/licenses/by-nc/4.0/legalcode

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies