MODELS OF THE SYSTEM OF COLLECTIVE SELF-ORGANISATION OF UNMANNED AERIAL VEHICLES USING ARTIFICIAL INTELLIGENCE

A. Trystan; D. Zhukov; A. Bеrеzhnyi

doi:10.26906/SUNZ.2024.2.047

A. Trystan
D. Zhukov
A. Bеrеzhnyi

DOI: https://doi.org/10.26906/SUNZ.2024.2.047

Keywords: agents, algorithms, artificial intelligence, aviation complex, division of roles, collective, coordination, control, information technology, multi-agent systems, routing, self-organisation, self-training, swarm, unmanned aerial vehicle

Abstract

The article examines the current state and trends in the development of unmanned aerial vehicles (hereinafter - UAVs), methods and means of their control, self-organisation, flight routing, as well as the involvement of artificial intelligence technologies in the UAV teams system. The main trends in the use of UAVs in the defence sector are analysed. The key problems in this area are highlighted, as well as the shortcomings of existing methods and systems. The article analyses scientific works of domestic and foreign scholars, studies problematic issues and suggests ways of their solution. The introduction of artificial intelligence into the UAV control system has significant potential and makes the development of these technologies urgent. The development of UAV collective control systems, including those using artificial intelligence, allows for the effective use of technology in various fields, ensuring increased coordination, functionality and overall efficiency. At the same time, despite active research in this area, a number of problems related to the development of methods and algorithms for group work still remain unresolved. The issue of integrating information technologies created on their basis and the specifics of their implementation in collective intelligence systems in order to increase the efficiency of solving complex formalised tasks is not sufficiently studied. A method of self-organisation of the UAV team with decentralised control is proposed, in which a number of functions (route planning, distribution of roles, determination of optimal actions, obtaining and processing information) assigned to the onboard control system of the robotic air complex can be performed by each element of the UAV team system due to their self-organisation. The practicality of this method lies in the fact that the UAV's artificial intelligence will constantly self-learn and improve, and if necessary, can be reprogrammed to meet the required conditions of the task. As a consequence, the results and time required to complete missions will improve significantly, while the number of control operators will decrease. It solves a number of problems and shortcomings related to the organisation of the management system, route planning, distribution of roles, speed and completeness of receiving, processing and transmitting information, which in turn improves the security and performance of the system.

Downloads

Download data is not yet available.

References

1. Military Drone Market Size to Hit USD 23.78 Billion by 2027; Rapid Advancements in Drone Techn. to Open New Avenues of Expansion for the Market. URL: https://www.globenewswire.com/en/news-release/2020/11/11/2124835/0/en/Military.html
2. Holembo V. A. Orhanizatsiia roboty hrupy bezpilotnykh litalnykh aparativ / V. A. Holembo, R. H. Melnikov // Visnyk Natsionalnoho universytetu "Lvivska politekhnika". Kompiuterni systemy ta merezhi. Lviv. 2018. № 905. P. 56-63.
3. Berezhnyi A. O., Soroka M.Iu., Salo N.A. Metody rishennia zavdan planuvannia povedinky ahentiv v intelektualnykh systemakh pidtrymky pryiniattia rishen. Zbirnyk naukovykh prats, KhNUPS, Kharkiv. 2019. № 4(62). P. 18-24. DOI:10.30748/zhups.2019.62.02.
4. Berezhnyi A.O. Metody ta informatsiina tekhnolohiia avtomatyzovanoho planuvannia marshrutiv polotiv bezpilotnykh litalnykh aparativ dlia pidvyshchennia efektyvnosti poshuku obiektiv: Dysertatsiia. ChDTU, Kharkiv. 2020. 192 p.
5. Pohudina O. K. Metodolohiia formuvannia intelektualnoi skladovoi ahentnoi systemy roiu bezpilotnykh litalnykh aparativ : monohrafiia, NAU "Kharkivskyi aviatsiinyi instytut". Drukarnia Madryd. Kharkiv. 2021. 211 p. ISBN 978-617-7988-32-7.
6. Demidov B.O., Borysenko M.V., Kucherenko Yu.F., Zadorozhna A.Iu. Perspektyvni napriamky rozvytku i vykorystannia metodiv i tekhnolohii shtuchnoho intelektu dlia ZSU v ramkakh vprovadzhennia suchasnykh innovatsii u viiskovii sferi. Nauka i tekhnika Povitrianykh Syl Zbroinykh Syl Ukrainy. Kharkiv. 2021. № 3(44). P. 7-17. DOI:10.30748/nitps.2021.44.01.
7. Sarkar N. I. Artificial Intelligence-Based Autonomous UAV Networks: A Survey. Advances of Unmanned Aerial Vehicle Communication. New Zealand. Drones. 2023, 7. DOI:10.3390/drones7050322.
8. Mandloi Y. S., Inada Y. Machine Learning Approach for DronePerception and Control. Tokai University. Pädiatrie. Tokyo. 2019. P. 424-431. DOI:10.1007/978-3-030-20257-6_36.
9. Kamate S., Yilmazer N. Application of Object Detectionand Tracking Techniques for Unmanned Aerial Vehicles. Procedia Computer Science. USA. 2015. Vol. 61. P. 436–441. DOI:10.1016/j.procs.2015.09.183.
10. Bekhti M., Abdennebi M., Achir N., Boussetta K. Path Planning of Unmanned Aerial Vehicles with Terrestrial Wireless Network Tracking. Wireless Days (WD), Toulouse. 2016. P. 1–6. DOI:10.1109/WD.2016.7461521.
11. Zain A. A., Zhangang H., Rana J. M. Collective Motion and Self-Organization of a Swarm of UAVs: A Cluster-Based Architecture. Time-Sensitive Networks for Unmanned Aircraft Systems. Sensors 3820. China. 2022. DOI:10.3390/s21113820.
12. Feifei Z., Yi Z., Bing H., Hongjian F., Zhuoya Z. Nature-іnspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network. Patterns 3, 100611. China. 2022. DOI:10.1016/j.patter.2022.100611.
13. Kozhushko Ya. M., Hrychaniuk O. M., Samorok M. H., Balabukha O. S. Analiz mozhlyvoho bortovoho osnashchennia radiotekhnichnymy ta televiziinymy systemamy bezpilotnoho litalnoho aparatu. Zbirnyk naukovykh prats Kharkivskoho natsionalnoho universytetu Povitrianykh Syl. Kharkiv. 2018. № 4(58). P. 37-42. DOI:10.30748/zhups.2018.58.05.
14. Riazanov V. V. Zarodzhennia y rozvytok bezpilotnykh litalnykh aparativ u ХХ-ХХІ stolittiakh. Osnovni periody, tendentsii. Voienno-istorychnyi visnyk 4 (34). 2019. P. 172-190.
15. Shlokyn V.N., Malakhov S.V., Hostev A.L., Kozhushko Ya.N. Osobennosty postroenyia radyosety hruppи BPLA. Naukovyi zhurnal // Systemy ozbroiennia i viiskova tekhnika. KhNU PS, Kharkiv. 2013. Vyp. 1 (33). P. 49-57.
16. Kozhushko Ya.M. ta inshi. Analiz ta osoblyvosti pobudovy barazhuiuchoho boieprypasu “lantset”. Vyprobuvannia ta sertyfikatsiia. Cherkasy. 2023. (1(1), P. 61-69. DOI:10.37701/ts.01.2023.08.