Area Protection in Adversarial Path-Finding Scenarios with Multiple Mobile Agents on Graphs: a theoretical and experimental study of target-allocation strategies for defense coordination

TL;DR

This paper investigates area protection in adversarial graph scenarios with multiple agents, analyzing the complexity and proposing online vertex-allocation strategies, including a simulation-based method, to enhance defense effectiveness.

Contribution

It introduces a theoretical complexity analysis and develops practical online strategies, notably a simulation-based approach, for defending against adversarial agents in graph-based scenarios.

Findings

Decision problem is PSPACE-hard with multiple target allocations.

Simulation-based strategy effectively captures attack bottlenecks.

Proposed strategies outperform baseline methods in various benchmarks.

Abstract

We address a problem of area protection in graph-based scenarios with multiple agents. The problem consists of two adversarial teams of agents that move in an undirected graph shared by both teams. Agents are placed in vertices of the graph; at most one agent can occupy a vertex; and they can move into adjacent vertices in a conflict free way. Teams have asymmetric goals: the aim of one team - attackers - is to invade into given area while the aim of the opponent team - defenders - is to protect the area from being entered by attackers by occupying selected vertices. We study strategies for allocating vertices to be occupied by the team of defenders to block attacking agents. We show that the decision version of the problem of area protection is PSPACE-hard under the assumption that agents can allocate their target vertices multiple times. Further we develop various on-line vertex-allocation strategies for the defender team in a simplified variant of the problem with single stage vertex allocation and evaluated their performance in multiple benchmarks. The success of a strategy is heavily dependent on the type of the instance, and so one of the contributions of this work is that we identify suitable vertex-allocation strategies for diverse instance types. In particular, we introduce a simulation-based method that identifies and tries to capture bottlenecks in the graph, that are frequently used by the attackers. Our experimental evaluation suggests that this method often allows a successful defense even in instances where the attackers significantly outnumber the defenders.