Unmanned surface vehicle (USV) clusters operating in contested maritime environments face communication degradation from jamming, satellite denial, and partial node loss. Existing countermeasures either react after link failure or rely on a single signal quality indicator. A framework is presented that integrates two complementary mechanisms for resilient USV cluster communication: (1) a multi-indicator communication quality metric $Q_{\mathrm{comm}}$ that fuses signal-to-noise ratio, packet loss rate, latency, and temporal stability into a single scalar; and (2) a multi-modal backup communication chain spanning acoustic modem, optical link, and multi-hop RF(Radio Frequency) relay that provides physical-layer redundancy when primary radio frequency links are degraded. Across five representative failure scenarios simulated on a seven-vehicle cluster with 50 independent runs per configuration, the multi-indicator $Q_{\mathrm{comm}}$ metric achieves a mean of 0.521, outperforming single-indicator baselines on the composite $Q_{\mathrm{comm}}$ metric (Cohen’s d = 8.020, p < 0.0001, n = 250 per method); $Q_{\mathrm{comm}}$ is the framework’s own optimization target; this comparison is, therefore, presented as an internal consistency demonstration rather than an independent validation. The framework reduces recovery time from 113.8 s (single-indicator) to 15.3 s—an 86.6% improvement. With the backup communication chain enabled, delivery rates exceed 94% across all methods and scenarios. A direct Monte Carlo ablation (50 seeds × 5 scenarios) reveals that multi-indicator fusion is the primary driver of assessment accuracy and recovery speed, while the multi-modal backup chain is the dominant delivery driver: without it, delivery falls from 94.6% to 24.2%. A sigmoid-blended topology utility function is included as an architectural design component; its independent validation requires extended-duration threat experiments identified as future work. The contributions of this work are the validated multi-indicator fusion metric and the multi-modal backup chain architecture, which together provide a practical foundation for resilient USV communication.

Safety-critical autonomous systems often require multiple agents to detect, assign, and intercept non-cooperative mobile targets using only partial observations. These subtasks are tightly coupled because the same agents must balance spatial exploration for detection with goal-directed motion for interception, while target maneuvers remain uncertain. This study develops and validates an integrated multi-agent coordination framework for jointly optimizing distributed detection, dynamic task allocation, and path planning under partial observability. The problem is formulated as a coupled Dec-POMDP made computationally tractable through factored decentralized policies, parameter sharing, and centralized training with decentralized execution, and a Weighted Coordinated Multi-Agent Proximal Policy Optimization (W-MAPPO) framework is introduced to adaptively coordinate competing subtasks. W-MAPPO combines an observation-conditioned Policy Ratio Predictor, an LSTM-based history-aware processor for temporal modeling of target maneuvers, and a Voronoi-based collaborative detection module for spatial coverage coordination within a centralized-training decentralized-execution paradigm. Comprehensive simulation experiments across increasing target densities compare W-MAPPO with seven representative MARL baselines and two classical methods, supported by statistical testing, ablation studies, sensitivity analysis, and representative case studies. W-MAPPO achieves a 94% success rate in the 5 vs 5 scenario and maintains stable interception performance as the number of targets increases to 10 and 15. These results demonstrate the technical reliability and practical potential of integrated subtask coordination for partially observable multi-agent systems.

Safety-critical autonomous systems often require multiple agents to detect, assign, and intercept non-cooperative mobile targets using only partial observations. These subtasks are tightly coupled because the same agents must balance spatial exploration for detection with goal-directed motion for interception, while target maneuvers remain uncertain. This study develops and validates an integrated multi-agent coordination framework for jointly optimizing distributed detection, dynamic task allocation, and path planning under partial observability. The problem is formulated as a coupled Dec-POMDP made computationally tractable through factored decentralized policies, parameter sharing, and centralized training with decentralized execution, and a Weighted Coordinated Multi-Agent Proximal Policy Optimization (W-MAPPO) framework is introduced to adaptively coordinate competing subtasks. W-MAPPO combines an observation-conditioned Policy Ratio Predictor, an LSTM-based history-aware processor for temporal modeling of target maneuvers, and a Voronoi-based collaborative detection module for spatial coverage coordination within a centralized-training decentralized-execution paradigm. Comprehensive simulation experiments across increasing target densities compare W-MAPPO with seven representative MARL baselines and two classical methods, supported by statistical testing, ablation studies, sensitivity analysis, and representative case studies. W-MAPPO achieves a 94% success rate in the 5 vs 5 scenario and maintains stable interception performance as the number of targets increases to 10 and 15. These results demonstrate the technical reliability and practical potential of integrated subtask coordination for partially observable multi-agent systems.

Safety-critical autonomous systems often require multiple agents to detect, assign, and intercept non-cooperative mobile targets using only partial observations. These subtasks are tightly coupled because the same agents must balance spatial exploration for detection with goal-directed motion for interception, while target maneuvers remain uncertain. This study develops and validates an integrated multi-agent coordination framework for jointly optimizing distributed detection, dynamic task allocation, and path planning under partial observability. The problem is formulated as a coupled Dec-POMDP made computationally tractable through factored decentralized policies, parameter sharing, and centralized training with decentralized execution, and a Weighted Coordinated Multi-Agent Proximal Policy Optimization (W-MAPPO) framework is introduced to adaptively coordinate competing subtasks. W-MAPPO combines an observation-conditioned Policy Ratio Predictor, an LSTM-based history-aware processor for temporal modeling of target maneuvers, and a Voronoi-based collaborative detection module for spatial coverage coordination within a centralized-training decentralized-execution paradigm. Comprehensive simulation experiments across increasing target densities compare W-MAPPO with seven representative MARL baselines and two classical methods, supported by statistical testing, ablation studies, sensitivity analysis, and representative case studies. W-MAPPO achieves a 94% success rate in the 5 vs 5 scenario and maintains stable interception performance as the number of targets increases to 10 and 15. These results demonstrate the technical reliability and practical potential of integrated subtask coordination for partially observable multi-agent systems.

Safety-critical autonomous systems often require multiple agents to detect, assign, and intercept non-cooperative mobile targets using only partial observations. These subtasks are tightly coupled because the same agents must balance spatial exploration for detection with goal-directed motion for interception, while target maneuvers remain uncertain. This study develops and validates an integrated multi-agent coordination framework for jointly optimizing distributed detection, dynamic task allocation, and path planning under partial observability. The problem is formulated as a coupled Dec-POMDP made computationally tractable through factored decentralized policies, parameter sharing, and centralized training with decentralized execution, and a Weighted Coordinated Multi-Agent Proximal Policy Optimization (W-MAPPO) framework is introduced to adaptively coordinate competing subtasks. W-MAPPO combines an observation-conditioned Policy Ratio Predictor, an LSTM-based history-aware processor for temporal modeling of target maneuvers, and a Voronoi-based collaborative detection module for spatial coverage coordination within a centralized-training decentralized-execution paradigm. Comprehensive simulation experiments across increasing target densities compare W-MAPPO with seven representative MARL baselines and two classical methods, supported by statistical testing, ablation studies, sensitivity analysis, and representative case studies. W-MAPPO achieves a 94% success rate in the 5 vs 5 scenario and maintains stable interception performance as the number of targets increases to 10 and 15. These results demonstrate the technical reliability and practical potential of integrated subtask coordination for partially observable multi-agent systems.

To address the challenges of multi-scale target variation, complex background interference, and insufficient feature fusion quality in maritime remote sensing ship detection, this paper proposes MarShip-DET, a frequency-aware multi-scale fusion detection algorithm based on YOLO11n. Three core modules are introduced: Channel-Decoupled Progressive Feature Extraction Module (CDPFEM), which employs asymmetric channel decoupling with dual-statistic channel attention and image-relative-position-encoded multi-head self-attention to enhance discriminative feature extraction; Edge-Aware Region Context Fusion Module (EARCFusion), which integrates learnable Sobel edge sensing and cross-attention correction to achieve precise foreground refinement; and Wavelet-guided Prototype Attention Module (WavePAM), which combines Haar wavelet frequency decomposition with prototype-guided spatial compression attention to strengthen deep semantic representation. Experiments on HRSC2016 demonstrate that MarShip-DET achieves an mAP50 of 94.9% and an mAP50-95 of 84.4%, improving by 3.7% and 4.3% over the baseline, respectively. Zero-shot experiments on HRSID and SSDD, including comparisons with YOLO11n, D-FINE-N, and YOLOv13n, provide additional evidence of cross-domain transferability under the evaluated protocol.