← 研踪 PaperTrailarXiv:2611.21828 · v1
Coordination of Heterogeneous Teams with Uncertain Task Requirements
首次提交 2026-11-17 03:48
版本更新 2026-11-17 03:48
雷达观测 2026-11-18 19:44
摘要
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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 03:48 · 最新观测版本
Coordination of Heterogeneous Teams with Uncertain Task Requirements
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.
查看此版本解读 →查看此版本原文 ↗