COMPASS: Cooperative Multi-Agent Persistent Monitoring using Spatio-Temporal Attention Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xingjian, Wang, Yizhuo, Sartoretti, Guillaume
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914102328164352
author Zhang, Xingjian
Wang, Yizhuo
Sartoretti, Guillaume
author_facet Zhang, Xingjian
Wang, Yizhuo
Sartoretti, Guillaume
contents Persistent monitoring of dynamic targets is essential in real-world applications such as disaster response, environmental sensing, and wildlife conservation, where mobile agents must continuously gather information under uncertainty. We propose COMPASS, a multi-agent reinforcement learning (MARL) framework that enables decentralized agents to persistently monitor multiple moving targets efficiently. We model the environment as a graph, where nodes represent spatial locations and edges capture topological proximity, allowing agents to reason over structured layouts and revisit informative regions as needed. Each agent independently selects actions based on a shared spatio-temporal attention network that we design to integrate historical observations and spatial context. We model target dynamics using Gaussian Processes (GPs), which support principled belief updates and enable uncertainty-aware planning. We train COMPASS using centralized value estimation and decentralized policy execution under an adaptive reward setting. Our extensive experiments demonstrate that COMPASS consistently outperforms strong baselines in uncertainty reduction, target coverage, and coordination efficiency across dynamic multi-target scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle COMPASS: Cooperative Multi-Agent Persistent Monitoring using Spatio-Temporal Attention Network
Zhang, Xingjian
Wang, Yizhuo
Sartoretti, Guillaume
Multiagent Systems
Robotics
Persistent monitoring of dynamic targets is essential in real-world applications such as disaster response, environmental sensing, and wildlife conservation, where mobile agents must continuously gather information under uncertainty. We propose COMPASS, a multi-agent reinforcement learning (MARL) framework that enables decentralized agents to persistently monitor multiple moving targets efficiently. We model the environment as a graph, where nodes represent spatial locations and edges capture topological proximity, allowing agents to reason over structured layouts and revisit informative regions as needed. Each agent independently selects actions based on a shared spatio-temporal attention network that we design to integrate historical observations and spatial context. We model target dynamics using Gaussian Processes (GPs), which support principled belief updates and enable uncertainty-aware planning. We train COMPASS using centralized value estimation and decentralized policy execution under an adaptive reward setting. Our extensive experiments demonstrate that COMPASS consistently outperforms strong baselines in uncertainty reduction, target coverage, and coordination efficiency across dynamic multi-target scenarios.
title COMPASS: Cooperative Multi-Agent Persistent Monitoring using Spatio-Temporal Attention Network
topic Multiagent Systems
Robotics
url https://arxiv.org/abs/2507.16306