A novel formula for micro-UAV swarm systems: architecture, algorithms, and verification^✩

Abstract

During indoor operations, Unmanned Aerial Vehicles (UAVs) are required to embody attributes such as heightened sensitivity, compact design, and robust maneuverability. A high operational advantage is evident when tasks are executed using multiple UAVs in unison. Despite the prevalent focus in current UAV research on enhancing discrete components or modules, a holistic, integrated approach that encompasses the UAV architecture, platform design, algorithms, simulation, and swarm intelligence, is lacking. This study introduces a micro-UAV swarm system designed for efficient perception within partially known indoor environments. We devised the comprehensive architectural blueprint of a micro-UAV swarm system. A communication routing evaluation metric is proposed to improve the quality of intercommunication among UAVs in the micro-UAV swarm. In addressing the localization and perception challenges, this study features the development of a multisensor-based autonomous positioning methodology, complemented by an object detection and tracking framework based on YOLOv5 and DeepSORT technologies. In the realm of decision making, we used the DuelingDQN algorithm to facilitate mission allocation and scheduling within the micro-UAV swarm system. For flight control, we introduced a control strategy that integrated pipeline control and visual servoing mechanisms. We developed a dedicated simulation platform and designed a realistic scenario to rigorously validate the efficacy of the entire micro-UAV swarm system in simulated exercises and actual flight tests.

Keywords

Micro unmanned aerial vehicles / Multisensor localization / Communication routing metric / Visual servoing / Holistic system integration

References

[1] A. Otto, N. Agatz, J. Campbell, B. Golden, E. Pesch, Optimization approaches for civil applications of unmanned aerial vehicles (UAVs) or aerial drones: a survey, Networks 72 (4) (2018) 411-458.

[2] R. Beard, D. Kingston, M. Quigley, D. Snyder, R. Christiansen, W. Johnson, T. McLain, M. Goodrich, Autonomous vehicle technologies for small fixed-wing UAVs, J. Aerosp. Comput. Inf. Commun. 2 (1) (2005) 92-108.

[3] M. Ahmed, A.A. Soofi, S. Raza, F. Khan, S. Ahmad, W.U. Khan, Advancements in RIS- assisted UAV for empowering multiaccess edge computing: a survey, IEEE Internet Things J. 12 (6) (2025) 6325-6346.

[4] A. Telikani, A. Sarkar, B. Du, J. Shen, Machine learning for UAV-aided ITS: a review with comparative study, IEEE Trans. Intell. Transp. Syst. 25 (11) (2024) 15388-15406.

[5] N.I. Vitzilaios, N.C. Tsourveloudis, An experimental test bed for small unmanned helicopters, J. Intell. Robot. Syst. 54 (2009) 769-794.

[6] H. Yang, Y. Lee, S.Y. Jeon, Multi-rotor drone tutorial: systems, mechanics, control and state estimation, Intell. Serv. Robot. 10 (2017) 79-93.

[7] S.P. Madruga, A.H.B.W. Tavares, S.O.D. Luiz, Aerodynamic effects compensation on multi-rotor UAVs based on a neural network control allocation approach, IEEE/CAA J. Autom. Sin. 9 (2) (2021) 295-312.

[8] H. Gong, B. Huang, B. Jia, Modelling power consumptions for multi-rotor UAVs, IEEE Trans. Aerosp. Electron. Syst. 59 (6) (2023) 7409-7422.

[9] K.W. Tong, J. Wu, Y.H. Hou, Robust drogue positioning system based on detection and tracking for autonomous aerial refueling of UAVs, IEEE Trans. Autom. Sci. Eng. 22 (2023) 4737-4747.

[10] V. Turan, E. Avsar, D. Asad, Image processing based autonomous landing zone de- tection for a multi-rotor drone in emergency situations, Turk. J. Eng. 5 (4) (2021) 193-200.

[11] Y. Li, C. Fu, Z. Huang, Keyfilter-aware real-time UAV object tracking, in: 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 193-199.

[12] S. Ouahouah, M. Bagaa, J. Prados-Garzon, Deep-reinforcement-learning-based col- lision avoidance in UAV environment, IEEE Internet Things J. 9 (6) (2021) 4015-4030.

[13] M. Eskandari, A.V. Savkin, SLAPS: simultaneous localization and phase shift for a ris-equipped UAV in 5G/6G wireless communication networks, IEEE Trans. Intell. Veh. 8 (12) (2023) 4722-4733.

[14] C. Bai, P. Yan, H. Piao, W. Pan, J.F. Guo, Learning-based multi-UAV flocking control with limited visual field and instinctive repulsion, IEEE Trans. Cybern. 54 (1) (2023) 462-475.

[15] J. Li, D.H. Ye, M. Kolsch, Fast and robust UAV to UAV detection and tracking from video, IEEE Trans. Emerg. Top. Comput. 10 (3) (2021) 1519-1531.

[16] G. Yang, X. Shi, L. Feng, S.B. He, Z.G. Shi, J.M. Chen, Cedar: a cost-effective crowd- sensing system for detecting and localizing drones, IEEE Trans. Mob. Comput. 19 (9) (2019) 2028-2043.

[17] J. Hu, Y. Li, Y. Lei, Z. Xu, M.W. Lv, J.W. Han, Robust and adaptive calibration of uwb- aided vision navigation system for UAVs, IEEE Robot. Autom. Lett. 8 (12) (2023) 8247-8254.

[18] H. Samaranayake, O. Mudannayake, D. Perera, Detecting water in visual image streams from UAV with flight constraints, J. Vis. Commun. Image Represent. 96 (2023) 103933.

[19] C. Shi, Y. Li, N. Song, B.Y. Wei, Y.B. Zhang, W.Z. Li, Identifying light interfer- ence in event-based vision, IEEE Trans. Circuits Syst. Video Technol. 34 (6) (2024) 4800-4816.

[20] P. Stockel, P. Wallrath, R. Herschel, N. Pohl, Detection and monitoring of people in collapsed buildings using a rotating radar on a UAV, IEEE Trans. Radar Syst. 2 (2023) 13-23.

[21] T. Anzai, M. Zhao, T. Nishio, Fully autonomous brick pick and place in fields by ar- ticulated aerial robot: results in various outdoor environments, IEEE Robot. Autom. Mag. 31 (2) (2024) 39-53.

[22] Y. Ye, H. Chen, C. Zhang, X.L. Hao, Z.X. Zhang,Sarpnet: shape attention regional proposal network for lidar-based 3D object detection, Neurocomputing 379 (2020) 53-63.

[23] J. Huang, Y. Shen, J. Wang, Automatic pylon extraction using color-aided classi- fication from UAV LiDAR point cloud data, IEEE Trans. Instrum. Meas. 72 (2023) 1-11.

[24] A. Feng, J. Zhou, E.D. Vories, K. Sudduth, M. Zhang, Yield estimation in cotton using UAV-based multi-sensor imagery, Biosyst. Eng. 193 (2020) 101-114.

[25] B. Du, R. Mao, N. Kong, Distributed data fusion for on-scene signal sensing with a multi-UAV system, IEEE Trans. Control Netw. 7 (3) (2020) 1330-1341.

[26] W. Wang, Y. Peng, G. Cao, Low-illumination image enhancement for night-time UAV pedestrian detection, IEEE Trans. Ind. Inform. 17 (8) (2020) 5208-5217.

[27] S. Liu, S. Wang, W. Shi, Vehicle tracking by detection in UAV aerial video, Sci. China Inf. Sci. 62 (2019) 1-3.

[28] R. Singh, D.K. Nishad, S. Khalid, A. Chaudhary, A review of the application of fuzzy mathematical algorithm-based approach in autonomous vehicles and drones, Int. J. Intell. Robot 9 (1) (2025) 344-364.

[29] Y. Chen, G. Luo, Y. Mei, J. Yu, X. Sun, UAV path planning using artificial poten- tial field method updated by optimal control theory, Int. J. Syst. Sci. 47 (6) (2016) 1407-1420.

[30] V. Roberge, M. Tarbouchi, G. LabontE, Fast genetic algorithm path planner for fixed- wing military UAV using GPU, IEEE Trans. Aerosp. Electron. Syst. 54 (5) (2018) 2105-2117.

[31] W. Dai, Y. Zhang, P. Li, Z. Feng, Rgb-D slam in dynamic environments using point correlations, IEEE Trans. Pattern. Anal. 44 (1) (2020) 373-389.

[32] P. Schmuck, M. Chli, Multi-uav collaborative monocular slam, in: 2017 IEEE Interna- tional Conference on Robotics and Automation (ICRA), IEEE, 2017, pp. 3863-3870.

[33] Y. Xu, L. Zheng, X. Wu, Y. Tang, W.N. Liu, D.H. Sun, Joint resource allocation for UAV-assisted V2X communication with mean field multi-agent reinforcement learn- ing, IEEE Trans. Veh. Technol. 74 (1) (2025) 1209-1223.

[34] S. Hao, Z. Zhang, M. Huo, C. Wei, Enhancing unmanned ground vehicle evasion through generative adversarial imitation learning in UAV pursuit scenarios, Guid. Navig. Control 5 (1) (2025) 149-154.

[35] R. Amin, L. Aijun, S. Shamshirband, A review of quadrotor UAV: control methodolo- gies and performance evaluation, Int. J. Autom. Control 10 (2) (2016) 87-103.

[36] J.J. Xiong, G.B. Zhang, Global fast dynamic terminal sliding mode control for a quadrotor UAV, ISA Trans. 66 (2017) 233-240.

[37] J. Dong, B. He, Novel fuzzy PID-type iterative learning control for quadrotor UAV, Sensors 19 (1) (2018) 24-28.

[38] S. Dionisio-Ortega, L.O. Rojas-Perez, J. Martinez-Carranza, J.I. Cruz-Vega, A deep learning approach towards autonomous flight in forest environments, in: 2018 In- ternational Conference on Electronics, Communications and Computers (CONIELE- COMP), IEEE, 2018, pp. 139-144.