跳到正文
arXiv cs.AI· Jongann Lee, Melkior Ornik·· 2 小时前AI 评分19

基于图神经网络与 CAAT 图的异构智能体团队协同规划方法(arXiv 论文)

Coordination of Heterogeneous Teams with Uncertain Task Requirements

AI 导读

一篇 arXiv 论文提出层次化规划器,用图神经网络策略为异构智能体分配动作,再以最短路径算法导航,核心是基于智能体、任务、能力和动作构建的 CAAT 图表示。该方法可同时协调任务需求发现与执行,比分别优化二者的基线用时更短。仅用室外地图训练的策略可零样本迁移到包含更多智能体、任务和能力的室内地图,无需微调。

正文 · 原文

View PDF HTML (experimental)

Abstract:Coordinating a team of heterogeneous agents to complete tasks with unknown requirements is a challenging multi-agent planning problem. Agents differ in their ability to discover task requirements and in their ability to engage tasks, so the planner must coordinate task discovery, execution, and staging. This paper introduces a hierarchical planner that uses a graph neural network policy to assign actions to agents, then finds a path to the action's location using a shortest-path algorithm. The central part of our approach is the CAAT graph, which is a graph representation of the planning context consisting of the agents, tasks, capabilities, and actions. We demonstrate that our learned planner can jointly coordinate a heterogeneous team to simultaneously discover task requirements and complete tasks in a shorter time compared to baselines that optimize task discovery and task engagement independently. Furthermore, we show that our policy can zero-shot plan on out-of-distribution settings by training only on an outdoor map then transferring without finetuning to an indoor map with more agents, tasks, and capabilities than seen during training.
Subjects: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2611.21828 [cs.MA]
  (or arXiv:2611.21828v1 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2611.21828

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jongann Lee [view email]
[v1] Mon, 16 Nov 2026 19:48:17 UTC (1,607 KB)

来源:arXiv cs.AI · arxiv.org