Robust neural network-driven control for multi-agent formation in the presence of Byzantine attacks and time delays

Asad Khan; Azmat Ullah Khan Niazi; Saadia Rehman; Saba Shaheen; Taoufik Saidani; Adnan Burhan Rajab; Muhammad Awais Javeed; Yubin Zhong; Asad Khan; Azmat Ullah Khan Niazi; Saadia Rehman; Saba Shaheen; Taoufik Saidani; Adnan Burhan Rajab; Muhammad Awais Javeed; Yubin Zhong

doi:10.3934/math.2025583

AIMS Mathematics

2025, Volume 10, Issue 6: 12956-12979. doi: 10.3934/math.2025583

Previous Article Next Article

Research article

Robust neural network-driven control for multi-agent formation in the presence of Byzantine attacks and time delays

1.
Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China
2.
Department of Mathematics and Statistics, The University of Lahore, Sargodha 40100, Pakistan
3.
Center for Scientific Research and Entrepreneurship, Northern Border University, Arar 73213, Saudi Arabia
4.
Department of Computer Engineering, College of Engineering, Knowledge University, Erbil 44001, Iraq
5.
Department of Computer Engineering, Al-Kitab University, Altun Kupri, Iraq
6.
School of Transportation, Southeast University, Nanjing 211189, Jiangsu, China
7.
School of Mathematics and Information Science, Guangzhou University, Guangzhou 510006, China

Received: 18 February 2025 Revised: 24 March 2025 Accepted: 17 April 2025 Published: 05 June 2025
MSC : 34H05, 93C10, 93D09

This paper presents an adaptive leader-follower formation control strategy for second-order nonlinear multi-agent systems with unknown dynamics. To handle system uncertainties, we used neural networks (NNs) to approximate and compensate for nonlinear effects. A key feature of our approach is its ability to deal with Byzantine attacks and time delays, which can disrupt coordination among agents. Unlike existing methods, our control strategy actively accounts for these challenges while ensuring stable formation tracking. Using Lyapunov stability theory, we proved that all system errors remain within a bounded range. Numerical simulations confirmed the effectiveness of our approach, showing that it successfully maintains formation control even in the presence of adversarial attacks and delays.
- Byzantine attack and time delay,
- multi-agent system,
- second-order nonlinear dynamics,
- formation control,
- adaptive neural networks,
- framework for leader-follower,
- Lyapunov stability
Citation: Asad Khan, Azmat Ullah Khan Niazi, Saadia Rehman, Saba Shaheen, Taoufik Saidani, Adnan Burhan Rajab, Muhammad Awais Javeed, Yubin Zhong. Robust neural network-driven control for multi-agent formation in the presence of Byzantine attacks and time delays[J]. AIMS Mathematics, 2025, 10(6): 12956-12979. doi: 10.3934/math.2025583

Related Papers:

Abstract

This paper presents an adaptive leader-follower formation control strategy for second-order nonlinear multi-agent systems with unknown dynamics. To handle system uncertainties, we used neural networks (NNs) to approximate and compensate for nonlinear effects. A key feature of our approach is its ability to deal with Byzantine attacks and time delays, which can disrupt coordination among agents. Unlike existing methods, our control strategy actively accounts for these challenges while ensuring stable formation tracking. Using Lyapunov stability theory, we proved that all system errors remain within a bounded range. Numerical simulations confirmed the effectiveness of our approach, showing that it successfully maintains formation control even in the presence of adversarial attacks and delays.

References

[1]	D. Maldonado, E. Cruz, J. A. Torres, P. J. Cruz, S. del Pilar, S. Gamboa, Multi-agent Systems: A survey about its components, framework and workflo, IEEE Access, 12 (2024), 80950–80975. https://doi.org/10.1109/ACCESS.2024.3409051 doi: 10.1109/ACCESS.2024.3409051
[2]	M. Abbasi, H. J. Marquez, Dynamic event-triggered formation control of multi-agent systems with non-uniform time-varying communication delays, IEEE T. Autom. Sci. Eng., 22 (2025), 8988–9000. https://doi.org/10.1109/TASE.2024.3494658 doi: 10.1109/TASE.2024.3494658
[3]	X. L. Quan, R. J. Du, R. C. Wang, Z. S. Bing, Q. Shi, An efficient closed-loop adaptive controller for a small-sized quadruped robotic rat, Cyborg and Bionic Systems, 5 (2024), 0096. https://doi.org/10.34133/cbsystems.0096 doi: 10.34133/cbsystems.0096
[4]	L. H. Ji, Z. Q. Lin, C. J. Zhang, S. S. Yang, J. Li, H. Q. Li, Data-based optimal consensus control for multiagent systems with time delays: using prioritized experience replay, IEEE T. Syst. Man Cy., 54 (2024), 3244–3256. https://doi.org/10.1109/TSMC.2024.3358293 doi: 10.1109/TSMC.2024.3358293
[5]	Y. H. Sun, Z. N. Peng, J. P. Hu, B. K. Ghosh, Event-triggered critic learning impedance control of lower limb exoskeleton robots in interactive environments, Neurocomputing, 564 (2024), 126963. https://doi.org/10.1016/j.neucom.2023.126963 doi: 10.1016/j.neucom.2023.126963
[6]	B. Ibrahim, H. Noura, Formation flight control of multi-UAV system using neighbor-based trajectory generation topology, Wseas Transactions on Applied and Theoretical Mechanics, 15 (2020), 173–181. https://doi.org/10.37394/232011.2020.15.20 doi: 10.37394/232011.2020.15.20
[7]	J. P. Hu, B. Chen, B. K. Ghosh, Formation-circumnavigation switching control of multiple ODIN systems via finite-time intermittent control strategies, IEEE T. Control Netw., 11 (2024), 1986–1997. https://doi.org/10.1109/TCNS.2024.3371597 doi: 10.1109/TCNS.2024.3371597
[8]	A. Khan, A. U. K. Niazi, W. Abbasi, F. Awan, M. M. A. Khan, F. Imtiaz, Cyber secure consensus of fractional order multi-agent systems with distributed delays: Defense strategy against denial-of-service attacks, Ain Shams Eng. J., 15 (2024), 102609. https://doi.org/10.1016/j.asej.2023.102609 doi: 10.1016/j.asej.2023.102609
[9]	H. T. Reda, A. Anwar, A. Mahmood, Comprehensive survey and taxonomies of false data injection attacks in smart grids: attack models, targets, and impacts, Renew. Sust. Energy Rev., 163 (2022), 112423. https://doi.org/10.1016/j.rser.2022.112423 doi: 10.1016/j.rser.2022.112423
[10]	N. Suryanto, Y. Kim, H. Kang, H. T. Larasati, Y. Yun, T. T. H. Le, et al., DTA: Physical camouflage attacks using differentiable transformation network, In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, 15305–15314. https://islab-ai.github.io/dta-cvpr2022/
[11]	Y. S. Liu, W. X. Li, X. W. Dong, Z. Ren, Resilient formation tracking for networked swarm systems under Malicious data deception attacks, Int. Jo. Robust Nonlin., 35 (2024), 2043–2052. https://doi.org/10.1002/rnc.7777 doi: 10.1002/rnc.7777
[12]	A. Khan, M. A. Javeed, A. U. K. Niazi, S. Rehman, W. U. Hassan, Y. B. Zhong, A robust control framework for multi-agent systems under Byzantine attacks using hybrid event-triggered techniques, Ain Shams Eng. J., 15 (2024), 103149. https://doi.org/10.1016/j.asej.2024.103149 doi: 10.1016/j.asej.2024.103149
[13]	F. Ding, R. Wang, T. D. Zhang, G. Zheng, Z. X. Wu, S. Wang, Real-time trajectory planning and tracking control of bionic underwater robot in dynamic environment, Cyborg and Bionic Systems, 5 (2024), 0112. https://doi.org/10.34133/cbsystems.0112 doi: 10.34133/cbsystems.0112
[14]	J. F. Hao, P. Chen, J. Chen, X. Li, Effectively detecting and diagnosing distributed multivariate time series anomalies via Unsupervised Federated Hypernetwork, Inform. Process. Manag., 62 (2025), 104107. https://doi.org/10.1016/j.ipm.2025.104107 doi: 10.1016/j.ipm.2025.104107
[15]	Z. Wang, M. L. Chen, Y. L. Guo, Z. Li, Q. F. Yu, Bridging the domain gap in satellite pose estimation: A self-training approach based on geometrical constraints, IEEE T. Aero. Elec. Sys., 60 (2023), 2500–2514. https://doi.org/10.1109/TAES.2023.3250385 doi: 10.1109/TAES.2023.3250385
[16]	H. B. Zeng, Z. J. Zhu, T. S. Peng, W. Wang, X. M. Zhang, Robust tracking control design for a class of nonlinear networked control systems considering bounded package dropouts and external disturbance, IEEE T. Fuzzy Syst., 32 (2024), 3608–3617. https://doi.org/10.1109/TFUZZ.2024.3377799 doi: 10.1109/TFUZZ.2024.3377799
[17]	D. B. Tong, B. Ma, Q. Y. Chen, Y. B. Wei, P. Shi, Finite-time synchronization and energy consumption prediction for multilayer fractional-order networks, IEEE T. Circuits-II, 70 (2023), 2176–2180. https://doi.org/10.1109/TCSII.2022.3233420 doi: 10.1109/TCSII.2022.3233420
[18]	J. L. Guo, Y. K. Li, B. Huang, L. Ding, H. B. Gao, M. Zhong, An online optimization escape entrapment strategy for planetary rovers based on Bayesian optimization, J. Field Robot., 41 (2024), 2518–2529. https://doi.org/10.1002/rob.22361 doi: 10.1002/rob.22361
[19]	M. Shi, D. B. Tong, Q. Y. Chen, W. N. Zhou, Pth moment exponential synchronization for delayed multi-agent systems with Lévy noise and Markov switching, IEEE T. Circuits-II, 71 (2023), 697–701. https://doi.org/10.1109/TCSII.2023.3304635 doi: 10.1109/TCSII.2023.3304635
[20]	X. Liu, S. C. Lou, W. Dai, Further results on "System identification of nonlinear state-space models", Automatica, 148 (2023), 110760. https://doi.org/10.1016/j.automatica.2022.110760 doi: 10.1016/j.automatica.2022.110760
[21]	W. M. Wang, H. B. Zeng, J. M. Liang, S. P. Xiao, Sampled-data-based load frequency control for power systems considering time delays, J. Franklin I., 362 (2025), 107477. https://doi.org/10.1016/j.jfranklin.2024.107477 doi: 10.1016/j.jfranklin.2024.107477
[22]	J. X. Lv, X. Z. Ju, C. H. Wang, Neural network prescribed-time observer-based output-feedback control for uncertain pure-feedback nonlinear systems, Expert Syst. Appl., 264 (2025), 125813. https://doi.org/10.1016/j.eswa.2024.125813 doi: 10.1016/j.eswa.2024.125813
[23]	Z. S. Zhou, Y. F. Wang, G. F. Zhou, X. L. Liu, M. Y. Wu, K. P. Dai, Vehicle lateral dynamics-inspired hybrid model using neural network for parameter identification and error characterization, IEEE T. Veh. Technol., 73 (2024), 16173–16186. https://doi.org/10.1109/TVT.2024.3416317 doi: 10.1109/TVT.2024.3416317
[24]	L. Fu, J. Q. Wang, X. W. Fu, G. L. Zhao, Finite-time Pade-based adaptive FNN controller implementation for microbial fuel cell with delay and multi-disturbance, Int. J. Hydrogen Energ., 98 (2025), 1034–1043. https://doi.org/10.1016/j.ijhydene.2024.10.372 doi: 10.1016/j.ijhydene.2024.10.372
[25]	F. Z. Song, Y. Liu, Y. Dong, X. K. Chen, J. B. Tan, Motion control of wafer scanners in lithography systems: From setpoint generation to multi-stage coordination, IEEE T. Instrum. Meas., 73 (2024), 7508040. https://doi.org/10.1109/TIM.2024.3413202 doi: 10.1109/TIM.2024.3413202
[26]	Y. Y. Liu, Q. L. Hu, G. Feng, Navigation functions on 3-manifold with boundary as a disjoint union of Hopf tori, IEEE T. Automat. Contr., 70 (2025), 219–234. https://doi.org/10.1109/TAC.2024.3419817 doi: 10.1109/TAC.2024.3419817
[27]	B. Xu, X. Y. Wang, J. Zhang, Y. Guo, A. A. Razzaqi, A novel adaptive filtering for cooperative localization under compass failure and non-gaussian noise, IEEE T. Veh. Technol., 71 (2022), 3737–3749. https://doi.org/10.1109/TVT.2022.3145095 doi: 10.1109/TVT.2022.3145095
[28]	Z. M. Zou, S. M. Yang, L. Zhao, Dual-loop control and state prediction analysis of QUAV trajectory tracking based on biological swarm intelligent optimization algorithm, Sci. Rep., 14 (2024), 19091. https://doi.org/10.1038/s41598-024-69911-5 doi: 10.1038/s41598-024-69911-5
[29]	Y. F. Yin, Z. T. Wang, L. L. Zheng, Q. R. Su, Y. Guo, Autonomous UAV navigation with adaptive control based on deep reinforcement learning, Electronics, 13 (2024), 2432. https://doi.org/10.3390/electronics13132432 doi: 10.3390/electronics13132432
[30]	G. L. Jing, Y. F. Zou, M. H. Xu, Y. Q. Zhang, D. X. Yu, Z. G. Shan, et al., Nicaea: A Byzantine fault tolerant consensus under unpredictable message delivery failures for parallel and distributed computing, IEEE T. Comput., 74 (2025), 915–928. https://doi.org/10.1109/TC.2024.3506856 doi: 10.1109/TC.2024.3506856
[31]	H. L. Wei, H. Zhang, K. AI-Haddad, Y. Shi, Ensuring secure platooning of constrained intelligent and connected vehicles against Byzantine attacks: A distributed MPC framework, Engineering, 33 (2024), 35–46. https://doi.org/10.1016/j.eng.2023.10.007 doi: 10.1016/j.eng.2023.10.007
[32]	J. A. V. Trejo, M. Adam-Medina, C. D. Garcia-Beltran, G. V. G. Ramírez, B. yolanda lópez Zapata, E. M. Sanchez-Coronado, et al., Robust formation control based on leader-following consensus in multi-agent systems with faults in the information exchange: Application in a fleet of unmanned aerial vehicles, IEEE Access, 9 (2021), 104940–104949. https://doi.org/10.1109/ACCESS.2021.3098303 doi: 10.1109/ACCESS.2021.3098303
[33]	S. Manfredi, Robust consensus design of uncertain multiagent systems with bounded gains and incremental nonlinear interactions, IEEE T. Ind. Inform., 20 (2024), 11844–11853. https://doi.org/10.1109/TII.2024.3413319 doi: 10.1109/TII.2024.3413319
[34]	H. Meng, D. H. Pang, J. D. Cao, Y. C. Guo, A. U. K. Niazi, Optimal bipartite consensus control for heterogeneous unknown multi-agent systems via reinforcement learning, Appl. Math. Comput., 476 (2024), 128785. https://doi.org/10.1016/j.amc.2024.128785 doi: 10.1016/j.amc.2024.128785
[35]	Y. H. Lan, J. Y. Zhao, Improving track performance by combining padé-approximation-based preview repetitive control and equivalent-input-disturbance, J. Electr. Eng. Technol., 19 (2024), 3781–3794. https://doi.org/10.1007/s42835-024-01830-x doi: 10.1007/s42835-024-01830-x
[36]	X. Z. Ju, Y. S. Jiang, L. Jing, P. Liu, Quantized predefined-time control for heavy-lift launch vehicles under actuator faults and rate gyro malfunctions, ISA T., 138 (2023), 133–150. https://doi.org/10.1016/j.isatra.2023.02.022 doi: 10.1016/j.isatra.2023.02.022
[37]	F. Ding, K. C. Zhu, J. Liu, C. Peng, Y. F. Wang, J. G. Lu, Adaptive memory event triggered output feedback finite-time lane keeping control for autonomous heavy truck with roll prevention, IEEE T. Fuzzy Syst., 32 (2024), 6607–6621. https://doi.org/10.1109/TFUZZ.2024.3454344 doi: 10.1109/TFUZZ.2024.3454344
[38]	S. B. Long, W. C. Huang, J. H. Wang, J. R. Liu, Y. X. Gu, Z. A. Wang, A fixed-time consensus control with prescribed performance for multi-agent systems under full-state constraints, IEEE T. Autom. Sci. Eng., 22 (2025), 6398–6407. https://doi.org/10.1109/TASE.2024.3445135 doi: 10.1109/TASE.2024.3445135
[39]	G. X. Wen, C. Y. Zhang, P. Hu, Y. Cui, Adaptive neural network leader-follower formation control for a class of second-order nonlinear multi-agent systems with unknown dynamics, IEEE Access, 8 (2020), 148149–148156. https://doi.org/10.1109/ACCESS.2020.3015957 doi: 10.1109/ACCESS.2020.3015957
[40]	X. Xu, B. Li, Semi-global stabilization of parabolic PDE–ODE systems with input saturation, Automatica, 171 (2025), 111931. https://doi.org/10.1016/j.automatica.2024.111931 doi: 10.1016/j.automatica.2024.111931

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)