Real-time object detection on resource-constrained edge devices remains a critical challenge in precision agriculture and autonomous systems, particularly when integrating advanced multi-modal sensors (RGB-D, thermal, hyperspectral). This paper introduces FEGW-YOLO, a lightweight detection framework explicitly designed to bridge the efficiency-accuracy gap for fine-grained visual perception on edge hardware while maintaining compatibility with multiple sensor modalities. The core innovation is a Feature Complexity Descriptor (FCD) metric that enables adaptive, layer-wise compression based on the information-bearing capacity of network features. This compression-guided approach is coupled with (1) Feature Engineering-driven Ghost Convolution (FEG-Conv) for parameter reduction, (2) Efficient Multi-Scale Attention (EMA) for compensating compression-induced information loss, and (3) Wise-IoU loss for improved localization in dense, occluded scenes. The framework follows a principled “Compress, Compensate, and Refine” philosophy that treats compression and compensation as co-designed objectives rather than isolated knobs. Extensive experiments on a custom strawberry dataset (11,752 annotated instances) and cross-crop validation on apples, tomatoes, and grapes demonstrate that FEGW-YOLO achieves 95.1% mAP@0.5 while reducing model parameters by 54.7% and computational cost (GFLOPs) by 53.5% compared to a strong YOLO-Agri baseline. Real-time inference on NVIDIA Jetson Xavier achieves 38 FPS at 12.3 W, enabling 40+ hours of continuous operation on typical agricultural robotic platforms. Multi-modal fusion experiments with RGB-D sensors demonstrate that the lightweight architecture leaves sufficient computational headroom for parallel processing of depth and visual data, a capability essential for practical advanced sensing systems. Field deployment in commercial strawberry greenhouses validates an 87.3% harvesting success rate with a 2.1% fruit damage rate, demonstrating feasibility for autonomous systems. The proposed framework advances the state-of-the-art in efficient agricultural sensing by introducing a principled metric-guided compression strategy, comprehensive multi-modal sensor integration, and empirical validation across diverse crop types and real-world deployment scenarios. This work bridges the gap between laboratory research and practical edge deployment of advanced sensing systems, with direct relevance to autonomous harvesting, precision monitoring, and other resource-constrained agricultural applications.
Coordinating Multi-Unmanned Surface Vehicle (USV) swarms in complex, adversarial maritime environments is a significant challenge, as existing multi-agent reinforcement learning (MARL) methods often fail to capture intricate spatiotemporal dependencies, leading to suboptimal policies. To address this, we propose Adv-TransAC, a novel Spatio-Temporal Meta-Reinforcement Learning framework. Its core innovation is a hybrid GAT-transformer architecture that decouples spatial and temporal reasoning: a Graph Attention Network (GAT) models instantaneous tactical formations, while a transformer analyzes their temporal evolution to infer intent. This is combined with an adversarial meta-learning mechanism to enable rapid adaptation to opponent tactics. In high-fidelity escort and defense simulations, Adv-TransAC significantly outperforms state-of-the-art MARL baselines in task success rate and policy robustness. The learned policies demonstrate the emergence of complex cooperative behaviors, such as intelligent risk-aware coordination and proactive interception maneuvers. The framework’s practicality is further validated by a communication-efficient federated optimization architecture. By effectively modeling spatiotemporal dynamics and enabling rapid adaptation, Adv-TransAC provides a powerful solution that moves beyond reactive decision-making, establishing a strong foundation for next-generation, intelligent maritime platforms.
The fusion of Artificial Intelligence and the Internet of Things (AI-IoT, also widely referred to as AIoT) offers transformative potential for smart cities, yet presents a critical challenge: how to process heterogeneous data streams from intelligent sensing—particularly crowd sensing data derived from citizen interactions like text, voice, and system logs—into reliable intelligence for sustainable urban governance. To address this challenge, we introduce the Intelligent Multimodal Ticket Processing System (IMTPS), a novel AI-IoT smart system. Unlike ad hoc solutions, the novelty of IMTPS resides in its theoretically grounded architecture, which orchestrates Information Theory and Game Theory for efficient, verifiable extraction, and employs Causal Inference and Meta-Learning for robust reasoning, thereby synergistically converting noisy, heterogeneous data streams into reliable governance intelligence. This principled design endows IMTPS with four foundational capabilities essential for modern smart city applications: Sustainable and Efficient AI-IoT Operations: Guided by Information Theory, the IMTPS compression module achieves provably efficient semantic-preserving compression, drastically reducing data storage and energy costs. Trustworthy Data Extraction: A Game Theory-based adversarial verification network ensures high reliability in extracting critical information, mitigating the risk of model hallucination in high-stakes citizen services. Robust Multimodal Fusion: The fusion engine leverages Causal Inference to distinguish true causality from spurious correlations, enabling trustworthy integration of complex, multi-source urban data. Adaptive Intelligent System: A Meta-Learning-based retrieval mechanism allows the system to rapidly adapt to new and evolving query patterns, ensuring long-term effectiveness in dynamic urban environments. We validate IMTPS on a large-scale, publicly released benchmark dataset of 14,230 multimodal records. IMTPS demonstrates state-of-the-art performance, achieving a 96.9% reduction in storage footprint and a 47% decrease in critical data extraction errors. By open-sourcing our implementation, we aim to provide a replicable blueprint for building the next generation of trustworthy and sustainable AI-IoT systems for citizen-centric smart cities.
Coral reefs are facing a catastrophic decline due to climate-induced bleaching, threatening critical marine biodiversity. Automated, large-scale monitoring is essential; however, modern object detectors are hindered by two fundamental limitations in complex underwater scenes: a spatial reasoning deficit in their decoupled heads, which inhibits robust multi-scale feature integration, and a feature robustness deficit, which renders deterministic networks vulnerable to stochastic visual variations. To address these limitations, we propose Coral-YOLO, a novel framework for detection and forecasting. We introduce the Holistic Attention Block Head (HAB-Head), which enables deep cross-scale reasoning through explicit feature interaction, and MCAttention, a randomized training mechanism that enables the network to learn scale-invariant features with inherent robustness. Evaluated on our newly curated, multi-year CR-Mix dataset, Coral-YOLO achieves a state-of-the-art 50.3% AP (average precision at IoU threshold 0.5:0.95, following COCO metrics), representing a +1.8 percentage point improvement over the YOLOv12-m baseline, with particularly pronounced gains on small objects (+2.6 percentage points in ). Crucially, its integrated temporal forecasting module achieves 82.7% accuracy in predicting future coral health, substantially outperforming conventional methods. Coral-YOLO sets a new performance benchmark and enables proactive reef conservation. It provides a powerful tool to identify at-risk corals long before severe bleaching becomes visually apparent.
Deep-sea exploration increasingly relies on Autonomous Underwater Vehicles (AUVs) to enable persistent, wide-area surveying in harsh and uncertain environments. In practice, however, deployments are constrained by tight energy budgets and bandwidth-limited, intermittent acoustic links, which complicate mission-level coordination. Moreover, many existing systems treat perception and control as loosely coupled modules, often resulting in redundant sensing, inefficient communication, and degraded overall performance—particularly under heterogeneous sensing modalities and shifting geological conditions. To address these challenges, we propose a hierarchical Federated Meta-Transfer Learning (FMTL) framework that tightly integrates collaborative perception with adaptive control for swarm optimization. The framework operates at three levels: (1) Representation Learning aligns heterogeneous sensors in a shared latent space via a physics-informed contrastive objective, substantially reducing communication overhead; (2) Meta-Learning Adaptation enables rapid transfer and convergence in new environments with minimal data exchange; and (3) Energy-Aware Control realizes closed-loop exploration by coupling Federated Explainable AI (FXAI) with decentralized multi-agent reinforcement learning (MARL) for path planning under energy constraints. Validated in high-fidelity hardware-in-the-loop simulations and a digital-twin environment, FMTL outperforms state-of-the-art baselines, achieving an AUC of 0.94 for target identification. Furthermore, an energy–intelligence Pareto analysis demonstrates a 4.5× improvement in information gain per Joule. Overall, this work provides a physically consistent and communication-efficient blueprint for the optimization and control of next-generation intelligent marine swarms.
The development of robust autonomous maritime systems is fundamentally constrained by the “data silo” problem, where valuable operational data from disparate fleets remain isolated due to privacy concerns, severely limiting the scalability of general-purpose navigation intelligence. To address this barrier, we propose a novel Federated Meta-Transfer Learning (FMTL) framework that enables collaborative evolution of unmanned surface vehicle (USV) swarms while preserving data privacy. Our hierarchical approach orchestrates three synergistic stages: (1) transfer learning pre-trains a universal “Sea-Sense” foundation model on large-scale maritime data to establish fundamental navigation priors; (2) federated learning enables decentralized fleets to collaboratively refine this model through encrypted gradient aggregation, forming a distributed cognitive network; (3) meta-learning allows for rapid personalization to individual vessel dynamics with minimal adaptation trials. Comprehensive simulations across heterogeneous fleet distributions demonstrate that our federated model achieves a 95.4% average success rate across diverse maritime scenarios, significantly outperforming isolated specialist models (63.9–73.1%), while enabling zero-shot performance of 78.5% and few-shot adaptation within 8–12 episodes on unseen tasks. This work establishes a scalable, privacy-preserving paradigm for collective maritime intelligence through swarm-based learning.