外观
论文arXiv 2610.0903422 天前
使用异构图神经网络的多智能体路径规划共享路线图生成与评估器
原文链接：Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network（arXiv 2610.09034 · 发布日期：2026-10-06）
Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
针对连续环境MAPP路线图取舍问题，提出异构GNN自动生成与评估共享路线图，并在多智能体取送任务上验证。
核心要点
- 传统网格或采样路线图常在图密度与可行高质量解之间存在权衡。
- 方法将路标、智能体位置和任务位置建为异构图节点，推理全局连通与交互。
- 通过专家轨迹聚合的占用密度图训练，识别关键点并剪除冗余节点和边。
- 实验显示在稠密路线图上可减少规划开销，运行时间和图规模至少降低40%。
验证范围与局限：验证范围为多智能体取送任务中的稠密路线图，摘要未说明仿真或真机。
英文摘要 (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.
作者：Brandon Ho, Nikola Rogers, Seung-Kyum Choi
来源
本页事实对应的公开页面，以原文为准。