Generalizable Collaborative Search-and-Capture in Cluttered Environments via Path-Guided MAPPO and Directional Frontier Allocation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ying, Jialin, Li, Zhihao, Dong, Zicheng, Wu, Guohua, Liao, Yihuan
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Robotics Machine Learning Multiagent Systems I.2.9
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866908703816417280
author	Ying, Jialin Li, Zhihao Dong, Zicheng Wu, Guohua Liao, Yihuan
author_facet	Ying, Jialin Li, Zhihao Dong, Zicheng Wu, Guohua Liao, Yihuan
contents	Collaborative pursuit-evasion in cluttered environments presents significant challenges due to sparse rewards and constrained Fields of View (FOV). Standard Multi-Agent Reinforcement Learning (MARL) often suffers from inefficient exploration and fails to scale to large scenarios. We propose PGF-MAPPO (Path-Guided Frontier MAPPO), a hierarchical framework bridging topological planning with reactive control. To resolve local minima and sparse rewards, we integrate an A*-based potential field for dense reward shaping. Furthermore, we introduce Directional Frontier Allocation, combining Farthest Point Sampling (FPS) with geometric angle suppression to enforce spatial dispersion and accelerate coverage. The architecture employs a parameter-shared decentralized critic, maintaining O(1) model complexity suitable for robotic swarms. Experiments demonstrate that PGF-MAPPO achieves superior capture efficiency against faster evaders. Policies trained on 10x10 maps exhibit robust zero-shot generalization to unseen 20x20 environments, significantly outperforming rule-based and learning-based baselines.
format	Preprint
id	arxiv_https___arxiv_org_abs_2512_09410
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Generalizable Collaborative Search-and-Capture in Cluttered Environments via Path-Guided MAPPO and Directional Frontier Allocation Ying, Jialin Li, Zhihao Dong, Zicheng Wu, Guohua Liao, Yihuan Robotics Machine Learning Multiagent Systems I.2.9 Collaborative pursuit-evasion in cluttered environments presents significant challenges due to sparse rewards and constrained Fields of View (FOV). Standard Multi-Agent Reinforcement Learning (MARL) often suffers from inefficient exploration and fails to scale to large scenarios. We propose PGF-MAPPO (Path-Guided Frontier MAPPO), a hierarchical framework bridging topological planning with reactive control. To resolve local minima and sparse rewards, we integrate an A*-based potential field for dense reward shaping. Furthermore, we introduce Directional Frontier Allocation, combining Farthest Point Sampling (FPS) with geometric angle suppression to enforce spatial dispersion and accelerate coverage. The architecture employs a parameter-shared decentralized critic, maintaining O(1) model complexity suitable for robotic swarms. Experiments demonstrate that PGF-MAPPO achieves superior capture efficiency against faster evaders. Policies trained on 10x10 maps exhibit robust zero-shot generalization to unseen 20x20 environments, significantly outperforming rule-based and learning-based baselines.
title	Generalizable Collaborative Search-and-Capture in Cluttered Environments via Path-Guided MAPPO and Directional Frontier Allocation
topic	Robotics Machine Learning Multiagent Systems I.2.9
url	https://arxiv.org/abs/2512.09410