Distributed Intrusion Detection for the Security of Industrial Cooperative Robotic Systems

Abstract

This paper addresses the problem of detecting possible intruders in a group of autonomous robots which coexist in a shared environment and interact with each other according to a set of common rules. We consider intruders as robots which misbehave, i.e. do not follow the rules, because of either spontaneous failures or malicious reprogramming. Our goal is to detect intruders by observing the congruence of their behavior with the social rules as applied to the current state of the overall system. Moreover, in accordance with the fully distributed nature of the problem, the detection itself must be performed by individual robots, based only on local information. We present a general formalism that allows to model uniformly a large variety of multi–robot systems and propose an intrusion detection protocol that is based on a local monitor and a suitable set–valued consensus. We apply our method to a system composed of forklifts moving within an industrial scenario setup, and we present performance results of the obtained intrusion detection system by simulation.