用图注意力网络指导搜索，提升密集多智能体路径规划效率
Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
- 结合图注意力网络的神经启发式策略融入搜索算法
- 在密集场景下优于纯搜索与纯学习方法，求解成功率更高
- 适合需要实时协调的复杂多智能体系统应用
在实时环境中求解密集多智能体路径规划（MAPF）问题仍具挑战性，即便使用最先进的规划器亦然。为此，我们提出一种混合框架，将基于MAGAT（一种具有图注意力机制的神经MAPF策略）的预训练启发式函数，融合至领先的基于搜索的算法LaCAM中。相较于以往学习引导搜索的方法，本方法在性能上表现更优。通过改进的MAGAT架构、针对目标地图的预训练-微调策略，以及处理神经启发式不完美性的死锁检测机制，所提出的LaGAT方法在密集场景下超越了纯搜索与纯学习方法。结果表明，经过精心设计的混合搜索方案，可有效解决高度耦合的复杂多智能体协同难题。
原文摘要 · Abstract (English)
Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme, into a leading search-based algorithm, LaCAM. While prior work has explored learning-guided search in MAPF, such methods have historically underperformed. In contrast, our approach, termed LaGAT, outperforms both purely search-based and purely learning-based methods in dense scenarios. This is achieved through an enhanced MAGAT architecture, a pre-train-then-fine-tune strategy on maps of interest, and a deadlock detection scheme to account for imperfect neural guidance. Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for tightly coupled, challenging multi-agent coordination problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。