arXiv：cs.LG· Brandon Ho, Nikola Rogers, Seung-Kyum Choi·· 4 小时前AI 评分34
基于异构图神经网络的多智能体路径规划共享路网生成与评估
Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
AI 导读
研究者提出一种可扩展的异构图神经网络（GNN）框架，用于自动生成和评估共享多智能体路网，将路点、智能体位置和任务位置建模为异构图中不同类型的节点。该模型在专家求解器轨迹聚合的占用密度图上训练，学习识别关键兴趣点并剪除冗余节点与边，生成紧凑且对任务排列不变、可复用于多智能体取送任务的路网。实验显示，在稠密路网中运行时和图的规模均减少至少 40%，并可能找到更优解。
正文
Abstract:Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as lattice grids or standard sampling-based approaches, frequently face a trade-off between graph density and the likelihood of finding feasible, high-quality solutions. In this paper, we propose a scalable heterogeneous Graph Neural Network (GNN) framework for the automated generation and evaluation of shared multi-agent roadmaps. Our model covers the representation of waypoints, agent locations, and task locations as distinct nodes in a heterogeneous graph, allowing it to reason over global connectivity and inter-agent interactions. By training on occupation density maps aggregated and collected from expert solver trajectories, the GNN learns to identify critical points of interest and prune redundant nodes and edges. This process produces a compact, coordination-aware roadmap that is invariant to task permutations and is reusable for multi-agent pick and delivery tasks. Experimental results demonstrate that our framework can reduce planning effort and can potentially find better solutions, reaching at least 40% reduction in runtime and in graph size for dense roadmaps.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO) |
| Cite as: | arXiv:2610.09034 [cs.AI] |
| (or arXiv:2610.09034v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09034 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Brandon Ho [view email]
[v1]
Tue, 6 Oct 2026 19:33:51 UTC (5,259 KB)
来源：arXiv：cs.LG · arxiv.org