A method for detecting anomalous behavior of agents in swarm robotic systems using the local disorganization metric

P.Y. Shamray, T.Y. Melnikov, E.A. Domnitsky, I.Y. Popov, D.A. Zakoldaev

Abstract


In a number of applied problems, it is necessary to preserve a periodic spatial structure within a swarm of robotic agents. This paper introduces a local disorganization metric that enables the detection of anomalies in the spatial configuration of the swarm based on navigation information, in particular data on inter-agent distances. Based on the proposed metric, a method for detecting and localizing an intruder is developed. The method relies on the exchange of information about the metric value and the agent identifier up to the second coordination layer. To separate high-level information from data describing the geometric positions of agents, the concept of a navigation field is introduced. Numerical simulations have confirmed the sensitivity of the proposed detection method for the considered adversary model. A limitation of the method is its vulnerability to Byzantine attacks, which can be addressed by further incorporating reputation and trust metrics and by employing distributed consensus mechanisms. The obtained results may serve as a basis for further research in the field of information security intruder detection in robotic swarms.


Full Text:

PDF (Russian)

References


. Liu, K. Han, and W. Rasdorf, “Assessment and Prediction of Impact of Flight Configuration Factors on UAS-Based Photogrammetric Survey Accuracy,” Remote Sensing, vol. 14, no. 16, p. 4119, Jan. 2022, doi: 10.3390/rs14164119.

M. Zaeri Amirani, N. Bigdeli, and M. Haeri, “Distributed fault detection and isolation in time-varying formation tracking UAV multi-agent systems,” Asian Journal of Control, vol. 25, no. 1, pp. 604–622, 2023, doi: 10.1002/asjc.2821.

M. J. C. S. Reis and A. J. D. Reis, “Edge-Based Real-Time Fault Detection in UAV Systems via B-Spline Telemetry Reconstruction and Lightweight Hybrid AI,” Sensors, vol. 25, no. 16, p. 4944, Jan. 2025, doi: 10.3390/s25164944.

X. Su, M. Hao, R. Yang, K. Yue, and Z. Feng, “Distributed Observer-Based Simultaneous Fault Detection and Formation Control of Multi-UAVs,” in 2023 42nd Chinese Control Conference (CCC), Jul. 2023, pp. 4968–4973. doi: 10.23919/CCC58697.2023.10240561.

H. Ahn and S. Chung, “Deep learning-based anomaly detection for individual drone vehicles performing swarm missions,” Expert Systems with Applications, vol. 244, p. 122869, Jun. 2024, doi: 10.1016/j.eswa.2023.122869.

H. E. Sevil, “Anomaly Detection using Parity Space Approach in Team of UAVs with Entropy based Distributed Behavior,” in AIAA Scitech 2020 Forum, in AIAA SciTech Forum. , American Institute of Aeronautics and Astronautics, 2020. doi: 10.2514/6.2020-1625.

F. Alrefaei, “Machine Learning for Intrusion Detection into Unmanned Aerial System 6G Networks,” Doctoral Dissertations and Master’s Theses, May 2024, [Online]. Available: https://commons.erau.edu/edt/815

V. Lannurien et al., “A retrospective on DISPEED -- Leveraging heterogeneity in a drone swarm for IDS execution,” Jun. 13, 2025, arXiv: arXiv:2506.11800. doi: 10.48550/arXiv.2506.11800.

T. Li, W. Lin, R. Ma, Z. Ma, Y. Shen, and J. Ma, “CoDetect: cooperative anomaly detection with privacy protection towards UAV swarm,” Sci. China Inf. Sci., vol. 67, no. 5, p. 159103, Apr. 2024, doi: 10.1007/s11432-023-3984-7.

A. Boyko and R. Girgidov, “Key features of a swarm assemlby algorythm for autonomous unmanned aerial vehicles (UAVs) in absence of GNSS and stable radio communication,” Rob. and Tech. Cyb. J., vol. 10, no. 1, pp. 25–31, Mar. 2022, doi: 10.31776/RTCJ.10103.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162