Security by Design: Reducing Information Exchange in Multi-Agent Search Tasks

Abstract

Intrinsic to multi-agent systems is the trait of inter-agent dependency on information exchange. During safety-critical tasks, errors in information exchange between agents can lead to vulnerable system behaviour. Consequently, adversarial agents often seek to exploit this vulnerability, rather than exploiting the communicated information itself. Motivated by this problem, the objective of this research is to investigate alternative coordination strategies of multi-agent systems that reduce information exchange and maximize task efficiency.

We consider the task of a multi-agent system of autonomous agents, such as a team of vehicles, performing a reconnaissance mission in an unknown, hostile, and urban environment. We abstract this task by considering a two-agent system exploring an unknown and structured maze. The goal of the agents is to search all states in the maze while minimizing communication and maximizing search efficiency.

Our results demonstrate that through restricting communication to line-of-sight, exploiting the structure of the environment, and employing deterministic decision-making policies, information exchange can be reduced while preserving a high degree of efficiency in the coordination of autonomous agents.