ON THE OPTIMIZATION OF UAV SWARM ACO-BASED PATH PLANNING

(Received: 26-Jan.-2025, Revised: 13-Apr.-2025 , Accepted: 6-May-2025)

Authors Areej J. Alabbadi, Belal H. Sababha,

Keywords #Ant colony optimization (ACO) #3D dynamic environment #UAV swarm #Hybrid navigation approach #Collision avoidance mechanism

Abstract Unmanned Aerial Vehicles (UAVs) play a crucial role in various operations, especially where human life must be protected. Efficient path planning and autonomous coordination are critical for UAV swarms in dynamic 3D cooperative missions, where real-time adaptability is essential. This work addresses the challenge of optimizing UAV swarm operations by proposing a novel hybrid navigation system based on Ant Colony Optimization (ACO). The system efficiently balances path optimization with dynamic formation control, adapting to mission- specific requirements. A key contribution is the hybrid navigation approach, which prioritizes the desired formation of the swarm or the path length and flight time through a threshold- based mechanism, allowing real- time adaptation to changing environments. The system also introduces a comprehensive cost function that evaluates the quality of the path, time consumption, mission completeness and formation divergence. The experiments show that the system consistently provides high-quality paths, achieving around 97% path quality in most cases and never declines below 90%, even in challenging scenarios. The collision avoidance module ensures the completeness of the 100% mission, successfully navigating drones around obstacles and maintaining an optimal path. Furthermore, the formation conservation mechanism effectively maintained the desired swarm configurations while dynamically adapting to obstacles, with the formation change staying within 30% of the allowable range in most scenarios, highlighting the system’s ability to preserve the desired formation even in dynamic environments. This research advances UAV swarm intelligence, enabling efficient and autonomous operations in complex 3D environments for diverse cooperative missions. The system’s adaptability to formation requirements opens new possibilities for UAV swarm applications, improving navigation efficiency and enhancing formation control.

References

[1] S. Hayat et al., "Survey on Unmanned Aerial Vehicle Networks for Civil Applications: ACommunications Viewpoint," IEEE Comm. Surveys and Tutorials, vol. 18, no. 4, pp. 2624–2661, 2016.

[2] M. Campion et al., "A Review and Future Directions of UAV Swarm Communication Architectures,"Proc. of the 2018 IEEE Int. Conf. on Electro/Information Technology (EIT), pp. 0903–0908, 2018.

[3] R. Arnold, K. Carey, B. Abruzzo and C. Korpela, "What Is a Robot Swarm: A Definition for SwarmingRobotics," Proc. of the 2019 IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conf. (UEMCON), pp. 0074–0081, New York, USA, 2019.

[4] M. Khelifi and I. Butun, "Swarm Unmanned Aerial Vehicles (SUAVs): A Comprehensive Analysis ofLocalization, Recent Aspects and Future Trends," J. of Sensors, vol. 2022, no. 1, p. 8600674, 2022.

[5] Q. Li et al., "A Review of Unmanned Aerial Vehicle Swarm Task Assignment," Proc. of the Int. Conf.on Guidance, Navigation and Control (ICGNC 2022), Springer, pp. 6469–6479, 2022.

[6] Y. Alqudsi, A. Kassem and G. El-Bayoumi, "A Robust Hybrid Control for Autonomous Flying Robots in an Uncertain and Disturbed Environment," INCAS Bulletin, vol. 13, no. 2, pp. 187 – 204, 2021.

[7] S. A. H. Mohsan et al., "Unmanned Aerial Vehicles (UAVs): Practical Aspects, Applications, OpenChallenges, Security Issues and Future Trends," Intelligent Service Robotics, vol. 16, no. 1, pp. 109–137, 2023.

[8] M. Abdelkader, S. Güler, H. Jaleel and J. S. Shamma, "Aerial Swarms: Recent Applications andChallenges," Current Robotics Reports, vol. 2, pp. 309–320, 2021.

[9] M. Cummings, "Operator Interaction with Centralized versus Decentralized UAV Architectures,"Handbook of Unmanned Aerial Vehicles, pp. 977–992, DOI: 10.1007/978-90-481-9707-1_117, 2015.

[10] S. S. Ponda et al., "Cooperative Mission Planning for Multi-UAV Teams," Handbook of UnmannedAerial Vehicles, vol. 2, pp. 1447–1490, DOI: 10.1007/978-90-481-9707-1_16, 2015.

[11] M.-H. Kim, H. Baik and S. Lee, "Response Threshold Model Based UAV Search Planning and TaskAllocation," Journal of Intelligent and Robotic Systems, vol. 75, pp. 625–640, 2014.

[12] P. O. Pettersson and P. Doherty, "Probabilistic Roadmap Based Path Planning for an AutonomousUnmanned Helicopter," Journal of Intelligent and Fuzzy Systems, vol. 17, no. 4, pp. 395–405, 2006.

[13] L. De Filippis, G. Guglieri and F. Quagliotti, "Path Planning Strategies for UAVs in 3D Environments,"Journal of Intelligent and Robotic Systems, vol. 65, pp. 247–264, 2012.

[14] O. Cetin, I. Zagli and G. Yilmaz, "Establishing Obstacle and Collision Free Communication Relay forUAVs with Artificial Potential Fields," J. of Intell. and Robotic Systems, vol. 69, pp. 361–372, 2013.

[15] S. Hacohen, S. Shoval and N. Shvalb, "Applying Probability Navigation Function in DynamicUncertain Environments," Robotics and Autonomous Systems, vol. 87, pp. 237–246, 2017.

[16] K. S. Camilus and V. Govindan, "A Review on Graph Based Segmentation," International Journal ofImage, Graphics and Signal Processing, vol. 4, no. 5, p. 1, 2012.

[17] S. M. Persson and I. Sharf, "Sampling-based A* Algorithm for Robot Path-planning," The InternationalJournal of Robotics Research, vol. 33, no. 13, pp. 1683–1708, 2014.

[18] H. Cartwright, "Swarm Intelligence by James Kennedy and Russell Ceberhart with Yuhui Shi. MorganKaufmann Publishers: San Francisco, 2001. £43.95.xxvii+512pp. ISBN: 1-55860-595-9," The Chemical Educator, vol. 7, pp. 123–124, 2002.

[19] A. Slowik and H. Kwasnicka, "Nature Inspired Methods and Their Industry Applications—SwarmIntelligence Algorithms," IEEE Trans. on Industrial Informatics, vol. 14, no. 3, pp. 1004–1015, 2017.

[20] R. D. Arnold and J. P. Wade, "A Definition of Systems Thinking: A Systems Approach," ProcediaComputer Science, vol. 44, pp. 669–678, 2015.

[21] R. Austin, Unmanned Aircraft Systems: UAVs Design, Development and Deployment, John Wiley &Sons, vol. 54, ISBN: 978-0-470-05819-0, 2011.

[22] M. A. Akhloufi, S. Arola and A. Bonnet, "Drones Chasing Drones: Reinforcement Learning and DeepSearch Area Proposal," Drones, vol. 3, no. 3, p. 58, 2019.

[23] R. J. Bachmann et al., "A biologically Inspired Micro-vehicle Capable of Aerial and TerrestrialLocomotion," Mechanism and Machine Theory, vol. 44, no. 3, pp. 513–526, 2009.

[24] M. Hassanalian et al., "A New Method for Design of Fixed Wing Micro Air Vehicle," Proc. of theInstitution of Mechanical Engineers, Part G: J. of Aerospace Eng., vol. 229, no. 5, pp. 837–850, 2015.

[25] S. Roy, S. Biswas and S. S. Chaudhuri, "Nature-inspired Swarm Intelligence and Its Applications," Int.Journal of Modern Education and Computer Science, vol. 6, no. 12, p. 55, 2014.

[26] F. Glover, "Future Paths for Integer Programming and Links to Artificial Intelligence," Computers &Operations Research, vol. 13, no. 5, pp. 533–549, 1986.

[27] Y. Chen et al., "Delivery Path Planning of Heterogeneous Robot System under Road NetworkConstraints," Computers and Electrical Engineering, vol. 92, p. 107197, 2021.

[28] N. A. Kyriakakis et al., "Moving Peak Drone Search Problem: An Online Multi-Swarm IntelligenceApproach for UAV Search Operations," Swarm and Evolutionary Comput., vol. 66, p. 100956, 2021.

[29] X. Yu, C. Li and J. Zhou, "A Constrained Differential Evolution Algorithm to Solve UAV PathPlanning in Disaster Scenarios," Knowledge-based Systems, vol. 204, p. 106209, 2020.

[30] V. Gonzalez et al., "Coverage Mission for UAVs Using Differential Evolution and Fast MarchingSquare Methods," IEEE Aerospace and Electronic Systems Magazine, vol. 35, no. 2, pp. 18–29, 2020.

[31] C. Wu, X. Huang, Y. Luo and S. Leng, "An Improved Fast Convergent Artificial Bee ColonyAlgorithm for Unmanned Aerial Vehicle Path Planning in Battlefield Environment," Proc. of the 2020 IEEE 16th Int. Conf. on Control & Automation (ICCA), pp. 360–365, Singapore, 2020.

[32] X. Zhen et al., "Rotary Unmanned Aerial Vehicles Path Planning in Rough Terrain Based on Multi-objective Particle Swarm Optimization," J. of Sys. Eng. and Electr., vol. 31, no. 1, pp. 130–141, 2020.

[33] M. D. Phung and Q. P. Ha, "Safety-enhanced UAV Path Planning with Spherical Vector-based ParticleSwarm Optimization," Applied Soft Computing, vol. 107, p. 107376, 2021.

[34] B. Tong et al., "A Path Planning Method for UAVs Based on Multi-objective Pigeon-inspiredOptimisation and Differential Evolution," Int. J. of Bio-inspired Computation, vol. 17, no. 2, pp. 105–112, 2021.

[35] C. Qu et al., "A Novel Hybrid Grey Wolf Optimizer Algorithm for Unmanned Aerial Vehicle (UAV) Path Planning," Knowledge-based Systems, vol. 194, p. 105530, 2020.

[36] Y. Alqudsi and M. Makaraci, "UAV Swarms: Research, Challenges and Future Directions," Journal ofEngineering and Applied Science, vol. 72, no. 1, p. 12, 2025.

[37] Y. Alqudsi and M. Makaraci, "Exploring Advancements and Emerging Trends in Robotic SwarmCoordination and Control of Swarm Flying Robots: A Review," Proc. of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 239, no. 1, pp. 180–204, 2025.

[38] S. Alqefari and M. E. B. Menai, "Multi-UAV Task Assignment in Dynamic Environments: CurrentTrends and Future Directions," Drones, vol. 9, no. 1, p. 75, 2025.

[39] M. Dorigo, G. Di Caro and L. M. Gambardella, "Ant Algorithms for Discrete Optimization," ArtificialLife, vol. 5, no. 2, pp. 137–172, 1999.

[40] D. Corne, M. Dorigo, F. Glover, D. Dasgupta, P. Moscato, R. Poli and K. V. Price, New Ideas inOptimization, ISBN: 0077095065, McGraw-Hill Ltd., UK, 1999.

[41] H.-B. Duan, "Ant Colony Algorithms: Theory and Applications," Chinese Science, 2005.

[42] B. H. Sababha et al., "Sampling-based Unmanned Aerial Vehicle Air Traffic Integration, Path Planningand Collision Avoidance," Int. Journal of Advanced Robotic Systems, vol. 19, no. 2, 2022.

[43] A. Al-Mousa, B. H. Sababha, N. Al-Madi, A. Barghouthi and R. Younisse, "Utsim: A Framework andSimulator for UAV Air Traffic Integration, Control and Communication," Int. Journal of Advanced Robotic Systems, vol. 16, no. 5, p. 1729881419870937, 2019.

Abstract: Unmanned Aerial Vehicles (UAVs) play a crucial role in various operations, especially where human life must be protected. Efficient path planning and autonomous coordination are critical for UAV swarms in dynamic 3D cooperative missions, where real-time adaptability is essential. This work addresses the challenge of optimizing UAV swarm operations by proposing a novel hybrid navigation system based on Ant Colony Optimization (ACO). The system efficiently balances path optimization with dynamic formation control, adapting to mission- specific requirements. A key contribution is the hybrid navigation approach, which prioritizes the desired formation of the swarm or the path length and flight time through a threshold- based mechanism, allowing real- time adaptation to changing environments. The system also introduces a comprehensive cost function that evaluates the quality of the path, time consumption, mission completeness and formation divergence. The experiments show that the system consistently provides high-quality paths, achieving around 97% path quality in most cases and never declines below 90%, even in challenging scenarios. The collision avoidance module ensures the completeness of the 100% mission, successfully navigating drones around obstacles and maintaining an optimal path. Furthermore, the formation conservation mechanism effectively maintained the desired swarm configurations while dynamically adapting to obstacles, with the formation change staying within 30% of the allowable range in most scenarios, highlighting the system’s ability to preserve the desired formation even in dynamic environments. This research advances UAV swarm intelligence, enabling efficient and autonomous operations in complex 3D environments for diverse cooperative missions. The system’s adaptability to formation requirements opens new possibilities for UAV swarm applications, improving navigation efficiency and enhancing formation control.
URL: https://jjcit.org/paper/265

,abstract={Unmanned Aerial Vehicles (UAVs) play a crucial role in various operations, especially where human life must be protected. Efficient path planning and autonomous coordination are critical for UAV swarms in dynamic 3D cooperative missions, where real-time adaptability is essential. This work addresses the challenge of optimizing UAV swarm operations by proposing a novel hybrid navigation system based on Ant Colony Optimization (ACO). The system efficiently balances path optimization with dynamic formation control, adapting to mission- specific requirements. A key contribution is the hybrid navigation approach, which prioritizes the desired formation of the swarm or the path length and flight time through a threshold- based mechanism, allowing real- time adaptation to changing environments. The system also introduces a comprehensive cost function that evaluates the quality of the path, time consumption, mission completeness and formation divergence. The experiments show that the system consistently provides high-quality paths, achieving around 97% path quality in most cases and never declines below 90%, even in challenging scenarios. The collision avoidance module ensures the completeness of the 100% mission, successfully navigating drones around obstacles and maintaining an optimal path. Furthermore, the formation conservation mechanism effectively maintained the desired swarm configurations while dynamically adapting to obstacles, with the formation change staying within 30% of the allowable range in most scenarios, highlighting the system’s ability to preserve the desired formation even in dynamic environments. This research advances UAV swarm intelligence, enabling efficient and autonomous operations in complex 3D environments for diverse cooperative missions. The system’s adaptability to formation requirements opens new possibilities for UAV swarm applications, improving navigation efficiency and enhancing formation control.},
keywords={Ant colony optimization (ACO),3D dynamic environment,UAV swarm,Hybrid navigation approach,Collision avoidance mechanism},
ISSN={2413-9351},
month={}}