Protection System For A Group Of Robots Based On The Detection Of Anomalous Behavior

This article is devoted to the development of a security system for a group of mobile robots. A feature of this system is the combination of various methods of security, such as detecting attacks and establishing trusted devices in one system. Thanks to the developed data analysis method, it is possible to use the same set of parameters for different security purposes. This article describes the modular system architecture. In particular, much attention is paid to the module for detecting anomalous activity. This module conducts an initial assessment of the data and identifies the fact of abnormal behavior. The module converts statistical data into a certain type of probability distribution, which is suitable for the parameter and identifies deviations from standard indicators. If an anomaly is detected, then it gives information for further study to other modules. The network simulation results and the initial parameter estimation confirm the effectiveness of the proposed methods.