IAES International Journal of Artificial Intelligence (IJ-AI)

Vol. 13, No. 3, September 2024, pp. 3576~3587

ISSN: 2252-8938, DOI: 10.11591/ ijai.v 13.i3.pp3576-3587  3576

Improved unmanned aerial vehicle control for efficient obstacle

detection and data protection

Khuralay Moldamurat1 , Sabyrzhan Atanov2 , Kairat Akhmetov1 , Makhabbat Bakyt2 , Niyaz

Belgibekov3 , Assel Zhumabayeva1 , Yuriy Shabayev4
1
Department of Space T echnique and Technology, L. N. Gumilyov Eurasian National University, Astana, Republic of Kazakhstan
2
Department of Information Security, Faculty of Information T echnology, L.N. Gumily ov Eurasian National University, Astana,
Republic of Kazakhstan
3
Center for Military-Strategic Research, Joint -Stock Company, Astana, Republic of Kazakhstan
4
Department Weapons and Military Equipment, National Defense University, Astana, Republic of Kazakhstan

Article Info ABSTRACT

Article history: The article centers on the research objectives and tasks associated with
developing a swarm control system for unmanned aerial vehicles (UAVs)
Received Oct 20, 2023 utilizing artificial intelligence (AI). A comprehensive literature review was
Revised Jan 24, 2024 undertaken to assess the effectiveness of the "swarm" method in UAV
Accepted Mar 11, 2024 management and identify key challenges in this domain. Swarm algorithms
were implemented in the M ATLAB/Simulink environment for modeling and
simulation purposes. The study successfully instantiated and simulated a UAV
Keywords: swarm control system adhering to fundamental principles and laws. Each
UAV operates autonomously, following target-swarm principles inspired by
Control systems the collective behavior of bees and ants. The collective movement and
Local radio communication behavior of the swarm are controlled by an AI-based program. The system
Machine learning demonstrated effective obstacle detection and avoidance through computer
Modeled management simulations. Results obtained highlight key features contributing to success,
Unmanned aerial vehicles including decentralized autonomy, collective intelligence, UAV coordination,
scalability, and flexibility. The deployment of a local radio communication
system in UAV swarm control and remote object monitoring is also discussed.
The research findings hold practical significance as they enable the effective
execution of complex tasks and have potential applications in various fields.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Makhabbat Bakyt
Department of Information Security, Faculty of Information Technology
L.N. Gumilyov Eurasian National University
Satpayev str. 2, Astana, Republic of Kazakhstan
Email: [email protected]

1. INTRODUCTION
In recent years, research in the field of group aviation control systems integrating artificial intelligence
and swarm behavior algorithms has become an important and relevant scientific topic. Traditional
methodologies based on individual control of each unmanned aerial vehicle (UAV) face limitations in
effectively controlling large groups of UAVs [1][5]. The principles of swarm intelligence allow each UAV
to operate autonomously, interacting seamlessly with other swarm members, which promises revolutionary
discoveries in various fields. From advanced analysis of the earth's surface for environmental and geological
studies to improved surveillance of fire zones, swarm management systems are opening up new perspectives.
Moreover, precise coordination between drones paves the way for breathtaking cinematic effects and
facilitates effective search and rescue operations. These systems also promote automation by reducing human

Journal homepage: http://ijai.iaescore.com

Int J Artif Intell ISSN: 2252-8938  3577

intervention in UAV operations [6][10]. However, addressing obstacle detection and avoidance challenges is
key to unlocking the full potential of swarm-controlled UAVs (Figure 1).

Figure 1. Structure of information-measuring and control systems of UAV

Recent research has focused on developing intelligent automatic control systems for obstacle
detection and avoidance to improve the safety and reliability of UAV operation. Although some studies have
proposed real-time obstacle detection algorithms [11], adaptive evasion strategies [12], and integration of
control systems with sensors [13], challenges remain in achieving optimal obstacle detectio n and avoidance
due to the complexity of the real environment and high costs [14][16]. The goal of this work is to develop a
swarm control system for UAVs using artificial intelligence and swarm behavior algorithms, improving the
performance of UAVs for various applications such as terrain analysis and surveillance. Challenges include
developing obstacle detection algorithms, adaptive evasion strategies, sensor integration, and conducting
computer simulations to validate algorithms. Successful completion o f these missions will significantly
improve the safety, reliability and effectiveness of UAV missions in a variety of real-world situations.

2. METHOD
The method for developing a control system for group aviation complexes was based on the theoretical
foundations of swarming intelligence, artificial intelligence and control theory. Concepts of swarming intelligence,
inspired by collective behavior in nature, have been used to develop algorithms that allow swarms of drones to
work in concert. Artificial intelligence techniques, including reinforcement learning and deep learning, have been
seamlessly integrated to control swarm behavior and decision making. Control theory principles have been
important to ensure stability and optimal control of individual drones and collective swarms [17]–[22].

2.1. Implementation of software and hardware

The proposed control system was implemented in the MATLAB/Simulink environment, which
provides modeling and analysis of the behavior of the swarm. Special software modules were created to
simulate the behavior of individual UAVs, their communication protocols and a centralized artificial
intelligence program. The UAVs have been designed with realistic flight physics and dynamics, carefully
considering factors such as thrust, drag and aerodynamics. For hardware, a fleet of commercially available
UAVs was used for testing and validation in real-world conditions. These UAVs were equipped with on-board
processors, sensors and communication modules that ensure the coordina tion of the swarm and the execution
of commands from the artificial intelligence program.

Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)
3578  ISSN: 2252-8938

2.2. Experimental conditions

Simulations were conducted under different climate conditions to evaluate system performance and
stability. Variables including changing weather conditions, obstacles in the flight path, and simulated
communication disruptions were introduced to evaluate the swarm's adaptability and response to dynamic
scenarios. The actual experiments were conducted in controlled open spaces that provide d sufficient space for
the drones to fly safely. The swarm was assigned predetermined missions and evaluation was made based on
mission completion time, efficiency, and overall behavior of the swarm [23][27].

2.3. Checking the proposed solutions

Thoroughly tested swarm algorithms and artificial intelligence techniques were subjected to
comparative analysis. The performance of the swarm-based control system was compared with traditional
methods for controlling individual drones, evaluating the improvement s achieved in efficiency and scalability.
The adequacy of the proposed models was assessed by comparing the simulation results with real experimental
data. The swarm behavior in both environments was analyzed for consistency, ensuring smooth translation of
theoretical models into practical applications. In addition, the system's response to disturbances and unexpected
scenarios during experiments was analyzed to evaluate the reliability of the proposed solutions [28][33].
Specific materials and methods in research on UAV control. As part of the study, specific methods
were implemented that corresponded to the objectives of the study: i) UAVs were combined with a requirement
of at least four for the study, with an emphasis on the selection and effective mode ling of specific UAV models;
ii) information and measurement technologies, including GPS devices, cameras , and sensors, were carefully
selected and configured for real-time data exchange within the swarm; iii) various machine learning algorithms,
such as enhanced learning, have been applied to optimize the performance and decision making of UAVs, with
the choice of algorithm depending on the research objectives and available data ; iv) UAV swarm simulation
software facilitated virtual testing of the proposed control system, evaluating performance in different
scenarios; v) virtual experiments were conducted under real-life conditions, deploying the UAV and
performing various tasks to test the proposed system, including creating a prototype model; and vi) collected
data from experiments, whether through data mining and analysis or simulation, was studied to evaluate system
performance, taking into account metrics such as task completion time, coordination efficiency, and resource
utilization. It is important to note that the materials and methods implemented in the work were adapted to
achieve the specific objectives of the study, and mathematical calculations and images of computer simulations
were presented in tables and graphs in the article. To ensure clarity and completeness of the description of the
research methodology presented in this section, an image of a simulation of the experimental setup is provided,
as well as an accompanying description.
The Figure 2 shows a diagram of the experimental setup for testing the control system for UAVs. The
installation consists of a set of platforms on which UAV models and obstacles are located, as well as visualization
and data collection tools. UAV models are equipped with sensors and communications to enable rea l-time
interaction and synchronization. The experimental setup provides the opportunity for virtual and real testing of
the UAV control system in various conditions, which allows us to evaluate its performance and reliability.

Figure 2. Schematic representation of the experimental setup simulation

3. RESULTS AND DISCUSSION

3.1. Algorithm for detecting obstacles in the operations of group unmanned aerial vehicles
A simulation study showed that the integration of advanced encryption techniques successfully
improved data security in a swarm of UAVs. Encrypted communication channels ensure confidentiality and
data integrity, which confirms the effectiveness of the system in conditions of instant adaptation in real time.
This highlights the potential of advanced encryption for strong data protection in practical UAV applications

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3576-3587

Int J Artif Intell ISSN: 2252-8938  3579

[34][39]. However, there are certain problems and limitations: High demands on on -board computing
resources, the need for specialized control software, integration difficulties, and the need to avoid mutual
interference between UAVs pose obstacles to UAV-based swarm operations.
Conclusions and prospects for future research: The review shows significant overlap in UAV
operations involving multifunctional integrated avionics s ystems (IIAS) for both military and civilian
applications. The urgent task is to create multifunctional UAVs capable of effectively solving various
problems. Research efforts should be focused on refining multifunctional UAV development methodologies,
including evaluation methods, models, and development algorithms.

3.2. Improving multispectral imaging of UAV using RF classification and RF spectral characterization
UAV equipped with multispectral cameras offer tunable image resolution based on flight altitude, but
interpreting high-resolution images requires machine learning algorithms. Random forest (RF) method using
linking or bootstrap aggregation shows superiority in image classification and obtaining spectral estimates
through RF method. Simulation results demonstrate improved performance of RF compared to artificial neural
networks and support vector machines, especially in quantitative remote sensing data analysis tasks as shown
in Figure 3.

Figure 3. Communication with the UAV group

The integration of machine learning algorithms, advanced sensors and information technology
technologies has expanded the applications of UAVs in various sectors, including computers, wireless
networks, smart cities, military, communications, agriculture, and mining. One significant application is the
creation of local radio communications with intelligent UAV systems . Which is critical for complex
communications needs and military operations in closed radio conditions or local communications while
moving in difficult terrain as shown in Figure 4.

Figure 4. Example of UAV operation for local radio communication

Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)
3580  ISSN: 2252-8938

UAVs, also known as drones, come in different types designed for specific purposes, such as light
unmanned aerial vehicles with a flight range of up to 25-40 km and a take-off weight of up to 5 kg and heavy
UAVs with long flight and a take-off weight of up to 1500 kg and flight range up to 1500 km (see Table 1).
UAVs launched in swarms with intelligent control systems are proving highly effective in c reating local
radio communications. Swarm reconfiguration aims to find trajectories, optimize fuel consumption, avoid
collisions, achieve desired shapes, provide optimal control sequences, prevent overthrust, and determine
destinations for homogeneous UAVs while minimizing fuel consumption along the resulting trajectories.

Table 1. Types of UAV

UAV type T ake-off weight Range
Light UAV Up to 5 kg 25-40 km
Light medium-range UAV Up to 5-50 kg 10-70 km
Medium class UAV Up to 50-100 kg 70-150 km
Heavy medium-range UAV Up to 500 kg 70-300 km
Heavy UAV with long flight Up to 1500 kg 1500 km

3.3. Improving drone sensor integration for real-time data processing and positioning
UAV are equipped with a variety of sensors, including optical cameras, thermal sensors, lidar sensors
for light ranging, lightweight portable radiometers (LPRs), and multispectral cameras as shown in Figure 5.
During a group flight, UAVs process information in real time, and to service the system, all devices must
determine their coordinates. The standard error (RMS) of control points is a key criterion for the accuracy of
determining the coordinates of objects based on photographic material, defined as (1):

1
𝛥𝑋𝑌 = √ ∑𝑛𝑖=1(𝑙 𝑖 − 𝑙 𝑖 )2 (1)
𝑛

where ∆XY is the SKO in the plan, n is the number of control points , – the planned coordinates of the control
point measured by the total station, – the planned coordinates of the control point measured in the images.

Figure 5. Tetracam multispectral range camera

The group control system relies on independent trajectory and operational control for each UAV.
UAVs determine their actions during flight, ensuring efficiency and maximum success while minimizing costs
to the team. Artificial intelligence coordinates tasks during group UAV launches. The principles of collective
control of UAVs include: i) each team member independently determines their actions based on shared goals,
the status of the environment, the current state, and the actions of other team members ; ii) optimal actions are
aimed at maximizing the functionality of the goal defined in the near future period ; and iii) compromise
solutions are tolerated and priority is given to actions that benefit the entire team.
This collective control approach is effective in distributed multi-agent systems, providing low
computational complexity for fast decision making in dynamic situations. Swarm intelligence techniques such
as ant colony, bee, and particle swarm algorithms are considered promising solutions. These algorithms are
based on simple rules for the behavior of an individual agent, which ultimately leads to an intelligent
multi-agent system within a colony [40]‒[45].

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3576-3587

Int J Artif Intell ISSN: 2252-8938  3581

3.4. Development of software code for simulating group control of UAVs

In this section, we discuss in detail the development of program code for controlling a group of UAVs
based on programming principles. Control and simulation code was created using MATLAB/Simulink. The
focus group of UAVs includes three objects flying in the formation. With the arguments p, t, c, we create three
UAV objects by setting their initial coordinates. A timeline is added and code is written for their trajectory and
movement during flight.
During the flight of a group of UAVs, collisions with obstacles that arise at random points are
simulated. This is critical to verify the training and adaptability of our UAV swarm control model to changing
trajectories when encountering obstacles in different scenarios. Obstacles in the code are identified by the
wallpoint argument and generated at random coordinates using the MATLAB/Simulink rand() function.
The process of creating a UAV control group begins. MATLAB/Simulink serves as a modeling
environment, providing a high-level language and interactive software space for numerical calculations and
visualization of results. All three UAV objects are added to a list designated uavList. A nested logical for loop
is implemented, where the first level selects an object from uavList, and subsequent levels determine the
coordinates of obstacles on the path of the UAV group. Using logical if statements, parameters are set to change
the flight path when obstacles are detected. The first condition indicates a change in flight along the
X-coordinate, and the second along the Y-coordinate. The n parameter determines the distance by which UAV
objects will change their trajectory. The final program code is presented in Figure 6.

Figure 6. Listing of the program

Execution of the program results in a simulation of the flight of a group of UAVs, as shown in
Figure 7. The program simulates the flight of a group of UAVs, as shown in Figure 7. In the image, the three
red circular objects represent UAVs flying from the lower left corner to the upper right corner. Randomly
placed crosses on the field represent obstacles. The simulation demonstrates the ability of a UAV group to
maintain formation and control characteristics during navigation. This paper presents a softwa re simulation
method [46][49].
In Figure 7, the three red circular objects represent UAVs flying from the lower left corner to the
upper right corner. Randomly placed crosses on the field represent obstacles. The simulation demonstrates the
ability of a UAV group to maintain formation and control characteristics during navigation. This paper presents
a software simulation method [46]‒[49].

Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)
3582  ISSN: 2252-8938

Figure 7. Flight simulation of an UAV system

3.5. Integration of artificial intelligence and swarm algorithms for optimal coordination of groups of
UAVs
When the formation of a UAV formation encounters obstacles, the lead UAV maneuvers to change
its trajectory, avoid the obstacle, and re-enter the formation without any problems. This maneuver is illustrated
in detail in Figure 8, which is a graphical representation of obstacles to an UAV based on their distance, denoted
by “ak.”. The subs of Figures 8(a) to 8(f) are as: (a) ak=0.1: depicts an obstacle close to the UAV; (b) ak=0.5:
shows an obstacle at a distance of 0.5 from the UAV; (c) ak=1.0: illustrates an obstacle located at a distance of
1.0 from the UAV; (d) ak=2.0: displays an obstacle at a distance of 2.0 from the UAV; (e) ak=3.0: shows an
obstacle at a distance of 3.0 from the UAV; and (f) ak=5.0: demonstrates an obstacle at a maximum distance
of 5.0 from the UAV.

(a) (b) (c) (d) (e) (f)

Figure 8. Obstacles to the creation of an UAV, depending on the degree of remoteness ak: (a) ak=0.1;
(b) ak=0.5; (c) ak=1.0; (d) ak=2.0; (e) ak=3.0; and (f) ak=5.0

Figure 8 demonstrates the efficient navigation of UAVs around obstacles at different distances (ak).
When a formation of UAVs encounters obstacles, the lead UAV maneuvers to change its trajectory, avoid the
obstacle, and return to the formation. This maneuver is illustrated step-by-step in Figure 9, which represents a
step-by-step construction of the UAV maneuver to avoid obstacles. The subs of Figure 9 are as: Figure 9(a)
the first stage of the maneuver, showing the initial phase of the trajectory change ; Figures 9(b) to 9(e):
Subsequent intermediate stages of the maneuver, demonstrating the successive steps of changing the UAV's
trajectory to avoid obstacles ; and Figure 9(f) the final result of the maneuver, where the UAV successfully
avoided the obstacle and regained its formation.

(a) (b) (c) (d) (e) (f)

Figure 9. Step-by-step construction of an UAV maneuver for avoiding obstacles: (a) first stage,
(b) second stage, (c) third stage, (d) fourth stage, (e) fifth stage, and (f) final result

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3576-3587

Int J Artif Intell ISSN: 2252-8938  3583

Groups of UAVs skillfully avoid obstacles, reaching their destination without damaging their
formation. The simulation produced successful results , with detailed analyzes presented in Table 2. The results
calculated using (1) and presented in Table 2 indicate a technical level coefficient (KTY) of approximately
1.46, highlighting the development prospects for STS [50]. Flight of groups of UAVs autonomously solves
emerging obstacles, showing success in 9 cases out of 10 in achieving mission goals compared to a simple
automatic control system. This success is attributed to the introduction of advanced technology in the
management system for groups of moving objects. The practical use of the group launch system in modern
aviation consistently provides highly effective results [51].

Table 2. Analysis of estimated parameters in the IIUS information model for DN UAVs
IIUS parameter Existing IIUS analogue New IIUS model (under development) Well-known world analogue
D (km) 200 300 350
Reliability 80 140 220

3.6. Analysis and reflections on the development and research of simulation of UAV swarm control
systems
UAVs equipped with remote control capabilities play a key role in monitoring various locations and
reporting potential hazards. This study, described in [52], [53] for signal propagation analysis, introduces a
method to evaluate the efficiency of signal propagation. The proposed method stands out for its ability to
efficiently estimate distances, which contributes to the reliability of the experimental result s, as shown in
Figures 8 and 9.
Although the algorithm exhibits optimal performance at a distance of 150% of the size of the
unmanned vehicles, the study acknowledges certain limitations that require discussion. Algorithm performance
may degrade over shorter distances, creating the risk of damaging the device. Minor damage to the rear of the
device and increased maneuver time over shorter distances are observed. Addressing these issues may involve
improving the algorithm to improve accuracy and efficiency.
Future research directions could explore advanced mathematical models and methodologies to
enhance control system capabilities. However, implementation in the real world may face challenges due to
the complex nature of UAV operations. Addressing these challenges has the potential to make significant
advances in UAV intelligence, paving the way for safer and more efficient drone applications.

3.7. Description of techniques used

To achieve the set goals, a combination of advanced techniques and methodo logies was used to facilitate
the development and validation of an intelligent UAV control system. The techniques were involved in the work:
 Simulation in MATLAB/Simulink: MATLAB/Simulink was used to simulate the behavior of a group of
UAVs, enabling the development and testing of flight algorithms. This simulation environment facilitated
the analysis of different scenarios and evaluation of system performance under different conditions.
 Obstacle detection algorithms: advanced obstacle detection algorithms have been developed to improve
the UAV's ability to detect obstacles in real time. These algorithms were designed to process data from
multiple sensors, including optical cameras, thermal sensors, lidar sensors, and multispectral cameras, to
accurately identify obstacles in the UAV's flight path.
 Adaptive avoidance strategy: an adaptive avoidance strategy has been developed to allow UAVs to
dynamically adjust their flight paths in response to detected obstacles. This strategy involved calculating
alternative flight paths based on real-time obstacle detection data, allowing the UAV to avoid obstacles
while minimizing the risk of collision.
 Seamless sensor integration: a variety of UAV sensors, including optical cameras, thermal sensors, lidar
sensors, lightweight handheld radiometers and multispectral cameras, have been seamlessly integrated
with the control system. This integration enabled efficient data sharing and communication, providing
accurate and timely information to detect and avoid obstacles.
 Computer simulations: comprehensive computer simulations were carried out to validate the developed
algorithms and evaluate system performance. These simulations included testing the system in controlled
environments with simulated obstacles and complex scenario s, allowing for thorough evaluation and
improvement of the system's capabilities.
By using these techniques and methodologies, the research team was able to develop and validate an intelligent
UAV control system capable of effectively detecting and avoidin g obstacles during flight. These techniques
have contributed to improvements in system accuracy, reliability, and efficiency, paving the way for improved
safety and efficiency of UAV missions in a variety of applications.

Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)
3584  ISSN: 2252-8938

3.7.1. Research review

In this study, a comprehensive work was carried out to develop and validate an intelligent control
system for a group of UAVs. The main goals were to improve real-time obstacle detection and avoidance. As
well as improve the safety and efficiency of UAV missions in various scenarios.

3.7.2. The discussion of the results

The results obtained allow us to draw the following conclusions . i) the developed algorithms for obstacle
detection and adaptive bypass strategy demonstrate high efficiency in solving the assigned tasks. ii) seamless
integration of various sensors has improved the accuracy and timeliness of obstacle detection, thereby increasing
the reliability of the control system. And iii) computer simulations confirmed the performance and effectiveness
of the developed algorithms in various scenarios, which provides further confirmation of the results.

3.7.3. Limitations and prospects for further research

One limitation of this study is the limited set of test scenarios and conditions. Future research should
expand the range of test scenarios to include more complex and realistic conditions to further explore the
capabilities of the control system. Another direction for future research could be to further improve obstacle
detection algorithms and avoidance strategies for more accurate and reliable system operation. The use of new
technologies such as deep learning to improve system performance should also be explored. In general, the results
of the study confirm the effectiveness of the developed intelligent co ntrol system for a group of UAVs in the
conditions of detecting and avoiding obstacles. Further research and development can make significant
contributions to improving the safety, reliability and efficiency of UAV missions in a wide range of applications.

4. CONCLUSION
MATLAB simulation results have played a key role in the development of flight algorithms for
UAV teams, facilitating collaborative efforts to increase mission speed and coverage. These algorithms have
demonstrated high accuracy in detecting obstacles, ensuring system safety with a minimum number of false
positives. An adaptive avoidance strategy was developed to allow the UAV to maneuver in real time around
obstacles, reducing the risk of collisions and increasing operational efficiency. The seamless integration of
the UAV's diverse sensors with the control system enabled efficient data exchange, facilitating accurate
obstacle detection and avoidance. Comprehensive testing through simulation and real-life scenarios
confirmed the reliability and efficiency of the system. This research represents a significant breakthrough in
UAV control systems, contributing to improved safety, reliability and efficiency in a variety of applications.

ACKNOWLEDGEMENTS
This research is funded by the Science Committee of the Ministry of Science and Higher Education
of the Republic of Kazakhstan (Project No. AP195077/0225).

REFERENCES
[1] N. T . Hegde, V. I. George, C. G. Nayak, and K. Kumar, “T ransition flight modeling and robust control of a VTOLunmannedquad
tilt-rotor aerial vehicle,” Indonesian Journal of Electrical Engineering and Computer Science (IJEECS),vol.18,no.3,pp.1252-
1261, Jun. 2020, doi: 10.11591/ijeecs.v18.i3.pp1252 -1261.
[2] M. T hangaraj and R. S. Sangam, “Intelligent UAV path planning framework using artificial neural network and artificialpotential
field,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 29, no. 2, pp. 1192-1200, Feb. 2023, doi:
10.11591/ijeecs.v29.i2.pp1192-1200.
[3] M. F. A.-Baghdadi and M. E. Manaa, “Unmanned aerial vehicles and machine learning for detecting objects in realtime,” Bulletin
of Electrical Engineering and Informatics, vol. 11, no. 6, pp. 3490–3497, Dec. 2022, doi: 10.11591/eei.v11i6.4185.
[4] K. K. Hasan, S. Saat, Y. Yusop, and M. R. Awal, “Development of self -charging unmanned aerial vehicle system usinginductive
approach,” International Journal of Power Electronics and Drive Systems (IJPEDS), vol. 13, no. 3,pp.1635-1644,Sep.2022,doi:
10.11591/ijpeds.v13.i3.pp1635-1644.
[5] S. K. Debnath et al., “Flight cost calculation for unmanned air vehiclebasedon path length andheadinganglechange,” InternationalJournal
of Power Electronics and Drive Systems (IJPEDS), vol. 11, no. 1, pp. 382-389, Mar. 2020, doi: 10.11591/ijpeds.v11.i1.pp382 -389.
[6] T .-L. Nguyen, D.-H. Ha, P. T . T in, and H. D. Cong, “Unmanned aerial vehicle-aided cooperative regenerative relayingnetwork
under various environments,” International Journal of Electrical and Computer Engineering (IJECE) , vol. 11, no.6, pp.5153-
5159, Dec. 2021, doi: 10.11591/ijece.v11i6.pp5153 -5159.
[7] A. N and U. S V, “Obstacle avoidance and distance measurement for un manned aerial vehicles usingmonocular vision,” International
Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 5, pp. 3504-3511, Oct. 2019, doi: 10.11591/ijece.v9i5.pp3504-3511.
[8] M. A. Massad, B. A. Alsaify, and A. Y. Alma’aitah, “Innovative unmanned aerial vehicle self -backhauling hybrid solution using
RF/FSO system for 5G network,” International Journal of Electrical and Computer Engineering (IJECE),vol.12,no.4,pp.4483-
4506, Aug. 2022, doi: 10.11591/ijece.v12i4.pp4483 -4506.
[9] A. M. Hasan and S. M. Raafat, “Optimized formation control of multi-agent system using PSO algorithm,” Indonesian Journalof

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3576-3587

Int J Artif Intell ISSN: 2252-8938  3585

Electrical Engineering and Computer Science, vol. 20, no. 3, pp. 1591-1600, Dec. 2020, doi:10.11591/ijeecs.v20.i3.pp1591-1600.
[10] M. A. A.-Shareeda, M. A. Saare, and S. Manickam, “Unmanned aerial vehicle: a review and future directions,” Indonesian Journal
of Electrical Engineering and Computer Science, vol. 30, no. 2, pp. 778-786, May 2023, doi: 10.11591/ijeecs.v30.i2.pp778-786.
[11] I. Jomaa, W. M. Saleh, R. R. Ismail, and S. H. Hussien, “Secured drone communication based on Esalsa20 algorithm,” International
Journal of Circuits, Systems and Signal Processing , vol. 17, pp. 67–75, Mar. 2023, doi: 10.46300/9106.2023.17.8.
[12] W. Shafik, S. M. Matinkhah, S. S. Afolabi, and M. N. Sanda, “A 3 -dimensional fast machine learning algorithm for mobile
unmanned aerial vehicle base stations,” International Journal of Advances in Applied Sciences, vol.10,no.1,pp.28-38,Mar.2021,
doi: 10.11591/ijaas.v10.i1.pp28-38.
[13] R. I. Boby, K. Abdullah, A. Z. Jusoh, N. Parveen, and M. Mahmud, “Adaptive control of nonlinear system basedon QFT application
to 3-DOF flight control system,” TELKOMNIKA (Telecommunication Computing Electronics and Control), vol.17,no.5,Oct.
2019, doi: 10.12928/telkomnika.v17i5.12810.
[14] A.-A. A. Boulogeorgos and A. Alexiou, “How much do hardware imperfections affect the performance of reconfigurableintelligent
surface-assisted systems?,” IEEE Open Journal of the Communications Society, vol. 1, pp. 1185–1195, 2020, doi:
10.1109/OJCOMS.2020.3014331.
[15] T . S. Gunawan, W. A. Yahya, E. Sulaemen, M. Kartiwi, and Z. Janin, “Development of control system for quadroto r unmanned
aerial vehicle using LoRa wireless and GPS tracking,” TELKOMNIKA (Telecommunication Computing Electronicsand Control),
vol. 18, no. 5, Oct. 2020, doi: 10.12928/telkomnika.v18i5.16716.
[16] A. Elbatal, A. M. Youssef, and M. M. Elkhatib, “Smart aerosonde UAV longitudinal flight control system based on genetic
algorithm,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 5, pp. 2433–2441, Oct. 2021, doi:
10.11591/eei.v10i5.2342.
[17] C. H. Van, H.-N. Nguyen, S.-P. Le, and M. Voznak, “Secrecy performance analysis on spatial modelingof wirelesscommunications
with unmanned aerial vehicle and ground devices,” International Journal of Electrical and Computer Engineering (IJECE),vol.
13, no. 6, pp. 6410-6418, Dec. 2023, doi: 10.11591/ijece.v13i6.pp6410-6418.
[18] A. H. Ali, M. A. M. A. -Ja’afari, and S. H. Abdulwahed, “Performance assessment of antenna array for an unmannedair vehicle,”
International Journal of Electrical and Computer Engineering (IJECE) , vol. 10, no. 3, pp. 2579-2588, Jun. 2020, doi:
10.11591/ijece.v10i3.pp2579-2588.
[19] P. F. -Lamas, L. Ramos, V. M. -Guerra, and T . M. F. -Caramés, “A review on IoT deep learning UAV systems for autonomous
obstacle detection and collision avoidance,” Remote Sensing, vol. 11, no. 18, Sep. 2019, doi: 10.3390/rs11182144.
[20] M. Y. Arafat, M. M. Alam, and S. Moh, “Vision-based navigation techniques for unmanned aerial vehicles:reviewandchallenges,”
Drones, vol. 7, no. 2, Jan. 2023, doi: 10.3390/drones7020089.
[21] A. T . Isikveren, “Method of quadrant-based algorithmic nomographs for hybrid/electric aircraft predesign,” JournalofAircraft,
vol. 55, no. 1, pp. 396–405, Jan. 2018, doi: 10.2514/1.c034355.
[22] W. Pebrianto, P. Mudjirahardjo, and S. H. Pramono, “Partial half fine-tuning for object detection with unmannedaerialvehicles,” IAES
International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 1, pp. 399-407, Mar. 2024, doi: 10.11591/ijai.v13.i1.pp399-407.
[23] K. Moldamurat, Y. Seitkulov, S. Atanov, M. Bakyt, and B. Yergaliyeva, “Enhancing cryptographic protection,authentication,and
authorization in cellular networks: a comprehensive research study,” International Journal ofElectricaland ComputerEngineering,
vol. 14, no. 1, pp. 479–479, Feb. 2024, doi: 10.11591/ijece.v14i1.pp479-487.
[24] C. An, S. Jia, J. Zhou, and C. Wang, “Fast model-free learning for controlling a quadrotor UAV with designed error trajectory,”
IEEE Access, vol. 10, pp. 79669–79680, 2022, doi: 10.1109/ACCESS.2022.3194276.
[25] K. Wang, Q. Gu, B. Huang, Q. Wei, and T . Zhou, “Adaptive event -triggered near-optimal trackingcontrolfor unknown continuous-
time nonlinear systems,” IEEE Access, vol. 10, pp. 9506–9518, 2022, doi: 10.1109/ACCESS.2021.3140076.
[26] S. A. Ahmed, H. Desa, A.-S. T . Hussain, and T . A. T aha, “Implementation of deep neural networks learning on unmannedaerial
vehicle based remote-sensing,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13,no.1, pp.941-947,Mar.2024,
doi: 10.11591/ijai.v13.i1.pp941-947.
[27] M. M. M. Islam and J.-M. Kim, “ vision-based autonomous crack detection of concrete structures using a fully convolutional
encoder–decoder network,” Sensors, vol. 19, no. 19, Sep. 2019, doi: 10.3390/s19194251.
[28] L. Quan, L. Han, B. Zhou, S. Shen, and F. Gao, “Survey of UAV motion planning,” IET Cyber-Systems and Robotics,vol.2,no.1,
pp. 14–21, Mar. 2020, doi: 10.1049/iet -csr.2020.0004.
[29] N. Li et al., “Indoor and outdoor low-cost seamless integrated navigation system based on the integration of INS/GNSS/LIDAR
System,” Remote Sensing, vol. 12, no. 19, Oct. 2020, doi: 10.3390/rs12193271.
[30] M. H. Harun, S. S. Abdullah, M. S. M. Aras, and M. B. Bahar, “Sensor fusion technology for unmanned autonomous vehic les
(UAV): a review of methods and applications,” in 2022 IEEE 9th International Conference on Underwater System Technology:
Theory and Applications (USYS), Dec. 2022, pp. 1–8, doi: 10.1109/USYS56283.2022.10072667.
[31] S. -H. Lo and Y. Yin,“ A novel approach to adopt explainable artificial intelligence in x-ray image classification,”in Advancesin
Machine Learning & Artificial Intelligence, vol. 3, no. 1, Jan. 2022, doi: 10.33140/amlai.03.01.01.
[32] B. Li, Z. Yang, D. Chen, S. Liang, and H. Ma, “Maneuvering target tracking of UAV based on MN-DDPG and transfer learning,”
Defence Technology, vol. 17, no. 2, pp. 457–466, Apr. 2021, doi: 10.1016/j.dt.2020.11.014.
[33] H. Kaplan, K. T ehrani, and M. Jamshidi, “ A fault diagnosis design based on deep learning approach for electric vehicle
applications,” Energies, vol. 14, no. 20, Oct. 2021, doi: 10.3390/en14206599.
[34] C. Blum and A. Roli, “Metaheuristics in combinatorial optimization,” ACM Computing Surveys, vol. 35, no.3,pp.268–308,Sep.
2003, doi: 10.1145/937503.937505.
[35] Z. Sui, Z. Pu, J. Yi, and S. Wu, “Formation control with collision avoidance through deep reinforcement learning using model-
guided demonstration,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 6, pp. 2358–2372,Jun.2021,
doi: 10.1109/tnnls.2020.3004893.
[36] M. Bakyt, K. Moldamurat, D.Z. Satybaldina, and N. K. Yurkov, “ Modeling information security threatsfor theterrestrialsegment of space
communications,” 7th International Conference on Digital Technologies in Education, Science and Industry, DTESI 2022, pp. 1-8, 2022.
[37] Y. Shen, Z. Pan, N. Liu, and X. You, “Joint design and performance analysis of a full-duplex UAV legitimate surveillancesystem,”
Electronics, vol. 9, no. 3, Feb. 2020, doi: 10.3390/electronics9030407.
[38] Y.-S. Ong and A. Gupta, “AIR5: five pillars of artificial intelligence research,” IEEE Transactions on Emerging Topics in
Computational Intelligence, vol. 3, no. 5, pp. 411–415, Oct. 2019, doi: 10.1109/T ET CI.2019.2928344.
[39] A. E. Ashurov, “On the probability of stellar encounters in globular clusters,” The Astronomical Journal,vol.127,no.4,pp.2154–
2161, Apr. 2004, doi: 10.1086/382840.
[40] M. M. Alam, M. Y. Arafat, S. Moh, and J. Shen, “T opology control algorithms in multi-unmanned aerial vehicle networks:An
extensive survey,” Journal of Network and Computer Applications, vol. 207, Nov. 2022, doi: 10.1016/j.jnca.2022.103495.
[41] A. Akbar and P. R. Lewis, “Self-adaptive and self-aware mobile-cloud hybrid robotics,” in 2018 Fifth InternationalConferenceon
Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)
3586  ISSN: 2252-8938

Internet of Things: Systems, Management and Security, Oct. 2018, pp. 262–267, doi: 10.1109/IoT SMS.2018.8554735.
[42] I. Foster, C. Kesselman, and S. T uecke, “T he anatomy of the grid: enabling scalable virtual organizations,” The International
Journal of High Performance Computing Applications, vol. 15, no. 3, pp. 200–222,Aug.2021,doi:10.1177/109434200101500302.
[43] H. Freimuth and M. König, “A framework for automated acquisition and processing of as-built data with autonomousunmanned
aerial vehicles,” Sensors, vol. 19, no. 20, Oct. 2019, doi: 10.3390/s19204513.
[44] P. S. Bithas, E. T . Michailidis, N. Nomikos, D. Vouyioukas, and A. G. Kanatas, “A survey on machine-learning techniques for
UAV-based communications,” Sensors, vol. 19, no. 23, Nov. 2019, doi: 10.3390/s19235170.
[45] T . Amorim and T . P. Nascimento, “Self-organized UAV flocking based only on relative range and bearing,” Comunicaçõesem
Informática, vol. 5, no. 1, pp. 14–17, Jul. 2021, doi: 10.22478/ufpb.2595-0622.2021v5n1.57248.
[46] Y. Endailalu, “Integration of radio over fiber (RoF) with fiber to the home (FT T H) schemes,” M.E.Thesis,Department of Electrical
and Computer Engineering, Ryerson Universit y and Karlsruhe University of Applied Science, Karlsruhe, Germany, 2021, doi:
10.32920/ryerson.14653506.
[47] W. Li and D. Kim, “Autonomous shepherding behaviors of multiple target steering robots,” Sensors, vol. 17, no.12,Nov.2017,
doi: 10.3390/s17122729.
[48] J. L. Leevy and T . M. Khoshgoftaar, “A survey and analysis of intrusion detection models based on CSE -CIC-IDS2018 bigdata,”
Journal of Big Data, vol. 7, no. 1, Dec. 2020, doi: 10.1186/s40537 -020-00382-x.
[49] W. Hu, C.-H. Chang, A. Sengupta, S. Bhunia, R. Kastner, and H. Li, “An overview of hardware security and trust: threats,
countermeasures, and design tools,” IEEE Transactions on Computer-Aided Design of Integrated Circuitsand Systems, vol.40,no.
6, pp. 1010–1038, Jun. 2021, doi: 10.1109/tcad.2020.3047976.
[50] S. Hajiaghasi, A. Salemnia, and M. Hamzeh, “Hybrid energy storage system for microgrids applications: a review,” Journal of
Energy Storage, vol. 21, pp. 543–570, Feb. 2019, doi: 10.1016/j.est.2018.12.017.
[51] D. Xu, X. Zhang, Z. Zhu, C. Chen, and P. Yang, “Behavior-based formation control of swarm robots,” MathematicalProblemsin
Engineering, vol. 2014, pp. 1–13, 2014, doi: 10.1155/2014/205759.
[52] I. Staffell et al., “T he role of hydrogen and fuel cells in the global energy system,” Energy & Environmental Science,vol.12,no.
2, pp. 463–491, 2019, doi: 10.1039/c8ee01157e.
[53] A. Madni, C. Madni, and S. Lucero, “Leveraging digital twin technology in model-based systems engineering,”Systems,vol.7,no.
1, Jan. 2019, doi: 10.3390/systems7010007.

BIOGRAPHIES OF AUTHORS

Khuralay Moldamurat was educated at the I. Zhansugurova Zhetysu State

University, specialist physics and informatics. Academy of Economics and Law named after
academician U.A. Dzholdasbekov, Bachelor of the specialty Finance, Turkish State
University, Ankara, 2008, 2010 Candidate of Technical Sciences (approved by the Higher
Attestation Commission RK dated June 30, 2011, protocol No. 6. Diploma No. 0006248) at
the dissertation council, the M SHE of the RK, at the NSA at the Institute of M athematics at
OD53.12. on the topic: Verification and automation of microcontroller programming, the
dissertation is scientifically defended. (050010, Almaty, Pushkin St., house 125, office 306).
Currently, she is Associate Professor of the Department of Space Technique And Technology
at the L.N. Gumilyov ENU, Astana, Kazakhstan. Her research interests include IT
technologies, radio engineering, programming of microcontrollers and automation systems,
and modern technologies for designing space nanosatellites. She can be contacted at email:
[email protected].

S abyrzhan Atanov is a doctor of technical sciences, a professor at the

Department of Computer Science of the L.N. Gumilyov Eurasian National University,
Astana, Kazakhstan, head of a number of projects under the grant of the M inistry of Education
and Science of the Republic of Kazakhstan, including "Design of robotic systems with
artificial intelligence", the international scientific and technical project "Development of a
neural network system for ensuring the stability of spacecraft control". His research is focused
on system design with artificial intelligence and design and programming of microcontroller
embedded systems. He can be contacted at email: [email protected].

Kairat Akhmetov is a Candidate of Technical Sciences and Doctor of

Philosophy, Associate Professor of the Department of Space Engineering and Technology,
L. N. Gumilyov Eurasian National University. Area of scientific interests: robotics, ferrous
metallurgy, non-ferrous and rare metals, technological machines, and equipment. He can be
contacted at email: [email protected].

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3576-3587

Int J Artif Intell ISSN: 2252-8938  3587

Makhabbat Bakyt received her Bachelor of Engineering and Technology and

M aster of Engineering from the L. N. Gumilyov Eurasian National University, Astana,
Kazakhstan. She is currently a Doctoral student of the Department Information Security
Department of the L. N. Gumilyov Eurasian National University. Her research interests
include aircraft data encryption, cryptograp hic protection, and information security. She can
be contacted at email: [email protected].

Niyaz Belgibekov is the Vice President of JSC «Center for military -strategic
research», holds a M aster of Technical Sciences degree. With a background at the National
Defense University named after the First President of the Republic of Kazakhstan - the Leader
of the Nation, he brings a wealth of experience to the forefront. Notably, he has organized
and presided over an international scientific and practical conference on the "Development
of weapons and military equipment at the present stage." His contributions extend bey ond
conferences, with numerous scientific and educational articles published across various
platforms. For further inquiries or collaborations. He can be contacted at email:
[email protected].

Assel Zhumabayeva is Senior Lecturer, M aster of Department of Space

technique and technology of L. N. Gumilyov Eurasian National University. Area of scientific
interests: robotics and mechatronics. She can be contacted at email: [email protected].

Yuriy S habayev is а Ph.D. student Department Weapons and military equipment

National Defense University named after The First President of the Republic of Kazakhstan
– Elbasy. He can be contacted at email: [email protected].

Improved unmanned aerial vehicle control for efficient obstacle detection … (Khuralay Moldamurat)