Multi-rotor unmanned aerial vehicle emergency landing algorithm based on underlying surface image analysis


Аuthors

Koshkarov A. S.*, Guliy D. D.**, Baryaksheva V. P.***

Saint Petersburg State University of Aerospace Instrumentation, 67, Bolshaya Morskaya str., Saint Petersburg, 190000, Russia

*e-mail: koshkarof@gmail.com
**e-mail: guliy1999@inbox.ru
***e-mail: vsvally@mail.ru

Abstract

The imminent expansion of application areas of high-tech products has also affected the field of unmanned aircraft systems. The use of unmanned aerial vehicles is finding increasing application in various sectors of the national economy, aviation, automotive, and the use of lightweight light unmanned aerial vehicles already covers up to 100 different sectors of the modern economy. The trend towards the use of unmanned aerial vehicles remains stable and is presumed to continue to grow in the digital economy. However, despite all the benefits, the use of drones also carries certain risks associated with the possibility of an accident that could result in the loss of the drone or damage to the environment.

Implementing emergency standards and regulations is an important aspect of unmanned aerial vehicles to ensure the safety of people, the environment, and property. In the case of multirotors, this critical capability takes the form of forced landing site selection. Common examples of events requiring an emergency landing are low battery, loss of ground contact, and deterioration in performance of satellite navigation systems. Since these emergency situations require an immediate landing, it is important to be able to have safe landing in a dense urban environment and complex transportation infrastructure. Therefore, the realization of emergency landing of a multirotor type unmanned aerial vehicle is an actual research area in the field of unmanned aviation. The use of analysis of underlying surface combined with machine learning methods and neural networks, will can significantly improve the efficiency of emergency landing methods, providing a more accurate assessment of the surface condition.

The paper presents the procedure for developing an algorithm for emergency landing of a multi-rotor unmanned aerial vehicle based on the analysis of the underlying surface image. The realization of the algorithm is carried out in two stages: image segmentation using the UNetFormer neural network and detection of a safe landing zone with the allocation of safe classes of objects observed in the frame, calculation of the occupied area of the unmanned aerial vehicle on the emergency frame and the range to the emergency landing zone selected by the algorithm.

Keywords:

drone, emergency landing, semantic image segmentation

References

  1. Analiz sushchestvuyushchego sostoyaniya mezhdunarodnogo rynka primenenii bespilotnykh aviatsionnykh sistem grazhdanskogo naznacheniya. Russian Drone. URL: https://russiandrone.ru/publications/1-analiz-sushchestvuyushchego-sostoyaniya-mezhdunarodnogo-rynka-primeneniy-bespilotnykh-aviatsionnykh

  2. Gosudarstvo. Biznes. Tekhnologii. Bespilotnye letatel'nye apparaty v Rossii. URL: https://www.tadviser.ru/

  3. Niemiec R., Gandhi F. Multi-rotor Coordinate Transforms for Orthogonal Primary and Redundant Control Modes for Regular Hexacopters and Octocopters, Conference: 42nd Annual European Rotorcraft Forum, Lille, France, 2016, pp. 646-664.

  4. Apollonov D.V., Bibikova K.I., Shibaev V.M., Efimova I.E. Trudy MAI, 2022, no. 122. URL: https://trudymai.ru/eng/published.php?ID=164299. DOI: 10.34759/trd2022-122-23

  5. Dzhavadov N.G., Agaev F.G., Guseinov G.A., Zul'fugarly P.R. Trudy MAI, 2022, no. 127. URL: https://trudymai.ru/eng/published.php?ID=170350. DOI: 10.34759/trd-2022-127- 20

  6. Fedorenko R.V., Abdullin I.N., Klimchik A.S. Trudy tsentra kompetentsii NTI «Tekhnologii komponentov robototekhniki i mekhatroniki» (Proceedings of the center of competence NTI "Technologies of components of robotics and mechatronics"): sbornik statei. Izhevsk, Izhevskii institut komp'yuternykh issledovanii, 2019, pp. 129–166.

  7. Joris Guérin, Kevin Delmas, Jérémie Guiochet. Certifying Emergency Landing for Safe Urban UAV, 51st Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2021. DOI: 10.1109/DSN-W52860.2021.00020

  8. W.-Y. Shin, M.H. Kabir, M.R. Hoque, S.-H. Yang Development of an Edge-Based Algorithm for Moving-Object Detection Using Background Modeling, Journal of Information and Communication Convergence Engineering, 2014, vol. 3, no. 12, pp. 193-197. DOI: 10.6109/jicce.2014.12.3.193

  9. M. Bahr, M. McKay, R. Niemiec, F. Gandhi. Handling Qualities Assessment of Large Variable-RPM Multi-Rotor Aircraft for Urban Air Mobility, 76th Vertical Flight Society Annual Forum, 2020, pp. 646-664. DOI: 10.4050/f-0076-2020-16479

  10. Benedikt Kolbeinsson, Krystian Mikolajczyk. Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion. URL: https://doi.org/10.48550/arXiv.2212.00787

  11. V'yugin V.V. Matematicheskie osnovy teorii mashinnogo obucheniya i prognozirovaniya (Mathematical foundations of the theory of machine learning and prediction), Moscow, MTsNMO, 2014, 304 p.

  12. Libo Wang, Rui Li, Ce Zhang, Shenghui Fang, et al. UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery, 2023. URL: https://doi.org/10.48550/arXiv.2109.08937

  13. Ali Hatamizadeh, Ziyue Xu, Dong Yang, Wenqi Li, Holger Roth, Daguang Xu. UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation, 2022. DOI: 10.13140/RG.2.2.17557.19687

  14. Trusfus M.V., Abdullin I.N. Trudy MAI, 2021, no. 116. URL: https://trudymai.ru/eng/published.php?ID=121099. DOI: 10.34759/trd-2021-116-13

  15. Dey Nilanjan, Dutta Saurab, Dey Goutami, Chakraborty Sayan, Ray Ruben, Roy Payel. Adaptive thresholding: A comparative study, 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies, ICCICCT 2014. DOI: 10.1109/ICCICCT.2014.6993140

  16. Razmer pikselya na mestnosti gsd. TOPoGIS. URL: https://topogis.ru/razmer-pikselya-na-mestnosti-gsd.php

  17. Dmitriev V.I., Zvonarev V.V., Lisitsyn Yu.E. Trudy MAI, 2020, no. 112. URL: http://trudymai.ru/published.php?ID=116566. DOI: 10.34759/trd-2020-112-16

  18. Sergeev A.A., Filimonov A.B., Filimonov N.B. Mekhatronika, avtomatizatsiya, upravlenie, 2021, no. 22 (3), pp. 156-167. DOI: 10.17587/mau.22.156-167

  19. Moiseev V.S. Osnovy teorii effektivnogo primeneniya bespilotnykh letatel'nykh apparatov (Fundamentals of the theory of effective application of unmanned aerial vehicles), Moscow, Kazan', Redaktsionno-izdatel'skii tsentr «Shkola», 2015, 444 p.

  20. Solomatin M.S., Mitrofanov D.V. Model' intellektual'nogo detektora sistemy zashchity avtomatizirovannoi sistemy upravleniya, Trudy MAI, 2020, no. 110. URL: https://trudymai.ru/eng/published.php?ID=112926. DOI: 10.34759/trd-2020-110-16

  21. ADAMW. URL: https://pytorch.org/docs/stable/generated/torch.optim.AdamW.html

  22. T-drones. URL: https://www.t-drones.com/goods.php?id=1148

  23. Kvadrokopter T-DRONES M1200. URL: https://mydrone.ru/kvadrokopter-t-drones-m1200/


Download

mai.ru — informational site MAI

Copyright © 2000-2024 by MAI

 Вход