Modeling Communication of Collaborative Multi-Agent System under Epistemic Planning

TL;DR

This paper introduces an epistemic planning-based communication model for multi-agent systems that optimizes cooperation and performance by treating communication as an action affecting the team's knowledge state.

Contribution

It presents a novel epistemic planning framework for agent communication, enabling effective decision-making and cooperation in multi-agent tasks.

Findings

Improved team performance across all simulated scenarios.

Effective communication decisions enhance coordination.

Model reduces communication costs while maintaining high performance.

Abstract

In most multiagent applications, communication is essential among agents to coordinate their actions, and thus achieve their goal. However, communication often has a related cost that affects overall system performance. In this paper, we draw inspiration from studies of epistemic planning to develop a communication model for agents that allows them to cooperate and make communication decisions effectively within a planning task. The proposed model treats a communication process as an action that modifies the epistemic state of the team. In two simulated tasks, we evaluate whether agents can cooperate effectively and achieve higher performance using communication protocol modeled in our epistemic planning framework. Based on an empirical study conducted using search and rescue tasks with different scenarios, our results show that the proposed model improved team performance across all scenarios compared with baseline models.