Optimizing Agent Collaboration through Heuristic Multi-Agent Planning

TL;DR

This paper introduces a new multi-agent planning algorithm that improves collaboration among sensing agents with different capabilities, outperforming existing state-of-the-art algorithms in complex scenarios.

Contribution

The paper proposes a novel algorithm that enables agents to adopt the same plan when sensing capabilities differ, addressing limitations of current QDec-POMDP algorithms.

Findings

The new algorithm outperforms QDec-FP and QDec-FPS in scenarios with diverse sensing agents.

Significant performance improvements are demonstrated in complex multi-agent sensing tasks.

The approach enhances coordination effectiveness among heterogeneous sensing agents.

Abstract

The SOTA algorithms for addressing QDec-POMDP issues, QDec-FP and QDec-FPS, are unable to effectively tackle problems that involve different types of sensing agents. We propose a new algorithm that addresses this issue by requiring agents to adopt the same plan if one agent is unable to take a sensing action but the other can. Our algorithm performs significantly better than both QDec-FP and QDec-FPS in these types of situations.