Multi-USV Coverage Path Planning Using Spatial Graph Multi-Actor-Attention-Critic Reinforcement Learning Framework With Operator Pooling

Multi-uncrewed surface vehicle coverage path planning (MCPP) presents significant challenges in large-scale aquatic environments due to dynamic ocean currents, non-euclidean spatial structures, and task load imbalance. To address these challenges, we propose the spatial graph multi-agent actor-attention-critic (SGMAAC) framework, which integrates a novel spatial graph attention network (SpGAT) for adaptive non-euclidean feature extraction and operator pooling for dynamic path optimization and task load balance. Specifically, SpGAT captures global-local topological dependencies to enhance decision-making under irregular topography, while operator pooling employs multi-step grow, deduplicate, and exchange operations to eliminate redundant paths and balance task loads across USVs. Additionally, SGMAAC introduces a multi-objective reward function that jointly optimizes coverage efficiency, collision avoidance, and energy consumption, enabling coordinated path planning in large-scale aquatic environments. Experimental results demonstrate that SGMAAC outperforms baseline methods across diverse aquatic scenarios, achieving improvements in convergence speed, makespan, task load balance, and path costs.