Search Results (715)

The Internet of Things (IoT) has promoted emerging applications that require massive device collaboration, heavy computation, and stringent latency. Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) systems can provide flexible services for user devices (UDs) with wide coverage. The optimization of both latency and energy consumption remains a critical yet challenging task due to the inherent trade-off between them. Joint association, offloading, and computing resource allocation are essential to achieving satisfying system performance. However, these processes are difficult due to the highly dynamic environment and the exponentially increasing complexity of large-scale networks. To address these challenges, we introduce a carefully designed cost function to balance the latency and the energy consumption, formulate the joint problem into a partially observable Markov decision process, and propose two multi-agent deep-reinforcement-learning-based schemes to tackle the long-term problem. Specifically, the multi-agent proximal policy optimization (MAPPO)-based scheme uses centralized learning and decentralized execution, while the closed-form enhanced multi-armed bandit (CF-MAB)-based scheme decouples association from offloading and computing resource allocation. In both schemes, UDs act as independent agents that learn from environmental interactions and historic decisions, make decision to maximize its individual reward function, and achieve implicit collaboration through the reward mechanism. The numerical results validate the effectiveness and show the superiority of our proposed schemes. The MAPPO-based scheme enables collaborative agent decisions for high performance in complex dynamic environments, while the CF-MAB-based scheme supports independent rapid response decisions. Full article

This study proposes a lightweight adaptive neural network framework based on an improved YOLOv11n model to address the core challenges in identifying cabbage seedlings in visible light images captured by UAVs. These challenges include the loss of small-target features, poor adaptability to complex lighting conditions, and the low deployment efficiency of edge devices. First, the adaptive dual-path downsampling module (ADown) integrates average pooling and maximum pooling into a dual-branch structure to enhance background texture and crop edge features in a synergistic manner. Secondly, the Illumination Robust Contrast Learning Head (IRCLHead) utilizes a temperature-adaptive network to adjust the contrast loss function parameters dynamically. Combined with a dual-output supervision mechanism that integrates growth stage prediction and interference-resistant feature embedding, this module enhances the model’s robustness in complex lighting scenarios. Finally, a lightweight spatial-channel attention convolution module (LAConv) has been developed to optimize the model’s computational load by using multi-scale feature extraction paths and depth decomposition structures. Experiments demonstrate that the proposed architecture achieves an mAP@0.5 of 99.0% in detecting cabbage seedling growth cycles, improving upon the baseline model by 0.71 percentage points. Furthermore, it achieves an mAP@0.5:0.95 of 2.4 percentage points, reduces computational complexity (GFLOPs) by 12.7%, and drastically reduces inference time from 3.7 ms to 1.0 ms. Additionally, the model parameters are simplified by 3%. This model provides an efficient solution for the real-time counting of cabbage seedlings and lightweight operations in drone-based precision agriculture. Full article

Ensuring the reliability of power transmission systems depends on the accurate detection of defects in insulators, which are subject to environmental degradation and mechanical stress. Traditional inspection methods are time-consuming and often ineffective, particularly in complex aerial environments. This paper presents a fault detection framework that integrates the YOLOv8 object detection model with an Adaptive Context Refinement (ACR) mechanism. YOLOv8 provides real-time detection, while ACR incorporates multi-scale contextual information surrounding detected objects to improve classification and localization. The system is evaluated across 25 YOLO model variants (YOLOv8 to YOLOv12) using high-resolution UAV datasets from operational power distribution networks. Results show that ACR improves mean Average Precision (mAP) in all cases, with gains of up to 22.9% for YOLOv10n (from 0.556 to 0.684 mAP) and average improvements of 12.6% for YOLOv10, 8.6% for YOLOv12, 5.6% for YOLOv9, and 4.0% for YOLOv8. The method maintains computational efficiency and performs consistently under varied environmental and fault conditions, making it suitable for the real-time UAV-based inspection of power systems. Full article

In complex urban wireless environments, unmanned aerial vehicle–mobile edge computing (UAV-MEC) systems face challenges like link blockage and single-antenna eavesdropping threats. The traditional single reconfigurable intelligent surface (RIS), limited in collaboration, struggles to address these issues. This paper proposes a double-RIS cooperative UAV-MEC optimization scheme, leveraging their joint reflection to build multi-dimensional signal paths, boosting legitimate link gains while suppressing eavesdropping channels. It considers double-RIS phase shifts, ground user (GU) transmission power, UAV trajectories, resource allocation, and receiving beamforming, aiming to maximize secure energy efficiency (EE) while ensuring long-term stability of GU and UAV task queues. Given random task arrivals and high-dimensional variable coupling, a dynamic model integrating queue stability and secure transmission constraints is built using Lyapunov optimization, transforming long-term stochastic optimization into slot-by-slot deterministic decisions via the drift-plus-penalty method. To handle high-dimensional continuous spaces, an end-to-end proximal policy optimization (PPO) framework is designed for online learning of multi-dimensional resource allocation and direct acquisition of joint optimization strategies. Simulation results show that compared with benchmark schemes (e.g., single RIS, non-cooperative double RIS) and reinforcement learning algorithms (e.g., advantage actor–critic (A2C), deep deterministic policy gradient (DDPG), deep Q-network (DQN)), the proposed scheme achieves significant improvements in secure EE and queue stability, with faster convergence and better optimization effects, fully verifying its superiority and robustness in complex scenarios. Full article

Transmission lines are widely distributed in complex environments, making them susceptible to foreign object intrusion, which could lead to serious consequences, i.e., power outages. Currently, foreign object detection on transmission lines is primarily conducted through UAV-based field inspections. However, the captured data must be transmitted back to a central facility for analysis, resulting in low efficiency and the inability to perform real-time, industrial-grade detection. Although recent YOLO series models can be deployed on UAVs for object detection, these models’ substantial computational requirements often exceed the processing capabilities of UAV platforms, limiting their ability to perform real-time inference tasks. In this study, we propose a novel lightweight detection algorithm, SCL-YOLOv8, which is based on the original YOLO model. We introduce StarNet to replace the CSPDarknet53 backbone as the feature extraction network, thereby reducing computational complexity while maintaining high feature extraction efficiency. We design a lightweight module, CGLU-ConvFormer, which enhances multi-scale feature representation and local feature extraction by integrating convolutional operations with gating mechanisms. Furthermore, the detection head of the original YOLO model is improved by introducing shared convolutional layers and group normalization, which helps reduce redundant computations and enhances multi-scale feature fusion. Experimental results demonstrate that the proposed model not only improves the detection accuracy but also significantly reduces the number of model parameters. Specifically, SCL-YOLOv8 achieves a mAP@0.5 of 94.2% while reducing the number of parameters by 56.8%, FLOPS by 45.7%, and model size by 50% compared with YOLOv8n. Full article

To improve the unmanned aerial vehicle (UAV) detection and recognition rate based on radar detection technology, this paper proposes to take the radar range-Doppler planar graph that characterizes the echo information of the UAV as the input of the improved YOLOv8 network, uses the YOLOv8n-RFL network to detect and identify the UAV target. In the detection method of the UAV target, first, we detect the echo signal of the UAV through radar, and take the received echo model as the foundation, utilize the principle of generating range-Doppler planar data to convert the received UAV echo signals into range-Doppler planar graphs, and then, use the improved YOLOv8 network to train and detect the UAV target. In the detection algorithm, the range-Doppler planar graph is taken as the input of the YOLOv8n backbone network, the UAV target is extracted from the complex background through the C2f-RVB and C2f-RVBE modules to obtain more feature maps containing multi-scale UAV feature information; the shallow features from the backbone network and deep features from the neck network are integrated through the feature semantic fusion module (FSFM) to generate high-quality fused UAV feature maps with rich details and deep semantic information, and then, the lightweight sharing detection head (LWSD) is utilized to conduct unmanned aerial vehicle (UAV) feature recognition based on the generated fused feature map. By detecting the collected echo data of the unmanned aerial vehicle (UAV), it was found that the proposed improved algorithm can effectively detect the UAV. Full article

The main purpose of this paper is to explore the benefits of combining two radio interfaces onboard an unmanned aerial vehicle (UAV) to communicate with a ground control station (GCS) and other UAVs inside a swarm. The goals are to use the IEEE 802.11ah standard (Wi-Fi HaLow) combined with the IEEE 802.11ax specification (Wi-Fi 6/6E) to enable real-time video transmission from UAVs to the GCS. While airport runway inspection serves as the proof-of-concept use case, the proposed multi-hop architectures apply to other medium-range UAV operations (i.e., a few kilometers) requiring real-time video transmission, such as natural disaster relief and agricultural monitoring. Several scenarios in which a UAV swarm performs infrastructure inspection are emulated. During the missions, UAVs have to send real-time video to the GCS through a multi-hop network when some damage in the infrastructure is found. The different scenarios are studied by means of emulation. Emulated scenarios are defined using different network architectures and radio technologies. Once the emulations finish, different performance metrics related to time, energy and the multi-hop video transmission network are analyzed. The capacity of a multi-hop network is a limiting factor for the transmission of high-quality video. As a first contribution, an expression to find this capacity from distances between UAVs in the emulated scenario is found using the NS-3 simulator. Then, this expression is applied in the algorithms in charge of composing the multi-hop network to offer on-demand quality video. However, the main contribution of this work lies in the development of efficient mechanisms for exchanging control information between UAVs and the GCS, and for forming a multi-hop network to transmit video. Full article

In the context of Industry 4.0 and intelligent manufacturing, the scale and complexity of complex equipment systems are continuously increasing, making effective high-precision modeling, simulation, and prediction in the engineering field significant challenges. Digital twin technology, by establishing real-time connections between virtual models and physical systems, provides strong support for the real-time monitoring, optimization, and prediction of complex systems. However, traditional digital twin models face significant limitations when synchronizing with high-dimensional nonlinear and non-stationary dynamical systems due to the latter’s dynamic characteristics. To address this issue, we propose a multi-layer deep Koopman operator-based (MDK) credibility-based self-evolution algorithm for equipment digital twins. By constructing multiple time-scale embedding layers and combining deep neural networks for observability function learning, the algorithm effectively captures the dynamic features of complex nonlinear systems at different time scales, enabling their global dynamic modeling and precise analysis. Furthermore, to enhance the model’s adaptability, a trustworthiness-based evolution-triggering mechanism and an adaptive model fine-tuning algorithm are designed. When the digital twin model’s trustworthiness assessment indicates a decline in prediction accuracy, the evolution mechanism is automatically triggered to optimize and update the model with the fine-tuning algorithm to maintain its stability and robustness during dynamic evolution. The experimental results demonstrate that the proposed method achieves significant improvements in prediction accuracy within unmanned aerial vehicle (UAV) systems, showcasing its broad application potential in intelligent manufacturing and complex equipment systems. Full article

The widespread adoption of Unmanned Aerial Vehicles (UAVs) in civilian domains, such as airport security and critical infrastructure protection, has introduced significant safety risks that necessitate effective countermeasures. High-Energy Laser Systems (HELSs) offer a promising defensive solution; however, when confronting large-scale malicious UAV swarms, the Dynamic Resource Target Assignment (DRTA) problem becomes critical. To address the challenges of complex combinatorial optimization problems, a method combining precise physical models with multi-agent reinforcement learning (MARL) is proposed. Firstly, an environment-dependent HELS damage model was developed. This model integrates atmospheric transmission effects and thermal effects to precisely quantify the required irradiation time to achieve the desired damage effect on a target. This forms the foundation of the HELS–UAV–DRTA model, which employs a two-stage dynamic assignment structure designed to maximize the target priority and defense benefit. An innovative MADDPG-IA (I: intrinsic reward, and A: attention mechanism) algorithm is proposed to meet the MARL challenges in the HELS–UAV–DRTA problem: an attention mechanism compresses variable-length target states into fixed-size encodings, while a Random Network Distillation (RND)-based intrinsic reward module delivers dense rewards that alleviate the extreme reward sparsity. Large-scale scenario simulations (100 independent runs per scenario) involving 50 UAVs and 5 HELS across diverse environments demonstrate the method’s superiority, achieving mean damage rates of 99.65% ± 0.32% vs. 72.64% ± 3.21% (rural), 79.37% ± 2.15% vs. 51.29% ± 4.87% (desert), and 91.25% ± 1.78% vs. 67.38% ± 3.95% (coastal). The method autonomously evolved effective strategies such as delaying decision-making to await the optimal timing and cross-region coordination. The ablation and comparison experiments further confirm MADDPG-IA’s superior convergence, stability, and exploration capabilities. This work bridges the gap between complex mathematical and physical mechanisms and real-time collaborative decision optimization. It provides an innovative theoretical and methodological basis for public-security applications. Full article

Hyperspectral classification of wetland environments remains challenging due to high spectral similarity, class imbalance, and blurred boundaries. To address these issues, we propose a novel Multi-Branch Channel-Gated Swin Transformer network (MBCG-SwinNet). In contrast to previous CNN-based designs, our model introduces a Swin Transformer spectral branch to enhance global contextual modeling, enabling improved spectral discrimination. To effectively fuse spatial and spectral features, we design a residual feature interaction chain comprising a Residual Spatial Fusion (RSF) module, a channel-wise gating mechanism, and a multi-scale feature fusion (MFF) module, which together enhance spatial adaptivity and feature integration. Additionally, a DenseCRF-based post-processing step is employed to refine classification boundaries and suppress salt-and-pepper noise. Experimental results on three UAV-based hyperspectral wetland datasets from the Yellow River Delta (Shandong, China)—NC12, NC13, and NC16—demonstrate that MBCG-SwinNet achieves superior classification performance, with overall accuracies of 97.62%, 82.37%, and 97.32%, respectively—surpassing state-of-the-art methods. The proposed architecture offers a robust and scalable solution for hyperspectral image classification in complex ecological settings. Full article

Urban particulate matter (PM) pollution critically impacts public health and climate. However, traditional ground-based monitoring fails to resolve vertical PM distribution, limiting understanding of transport and stratification-coupled mechanisms. Vertical profiles collected by an unmanned aerial vehicle (UAV) over Hangzhou, a core megacity in China’s Yangtze River Delta, reveal the spatiotemporal heterogeneity and multi-scale drivers of regional PM pollution during two intensive ten-day campaigns capturing peak pollution scenarios (winter: 17–26 January 2019; summer: 21–30 August 2019). Results show stark seasonal differences: winter PM₁ and PM_2.5 averages were 2.6- and 2.7-fold higher (p < 0.0001) than summer. Diurnal patterns were bimodal in winter and unimodal (single valley) in summer. Vertically consistent PM₁ and PM_2.5 distributions featured sharp morning (08:00) concentration increases within specific layers (winter: 250–325 m; summer: 350–425 m). Analysis demonstrates multi-scale coupling of synoptic systems, boundary layer processes, and vertical wind structure governing pollution. Key mechanisms include a winter “Transport-Accumulation-Reactivation” cycle driven by cold air, and summer typhoon circulation influences. We identify hygroscopic growth triggered by inversion-high humidity coupling and sea-breeze-driven secondary aerosol formation. Leveraging UAV-based vertical profiling over Hangzhou, this study pioneers a three-dimensional dissection of layer-coupled PM dynamics in the Yangtze River Delta, offering a scalable paradigm for aerial–ground networks to achieve precision stratified control strategies in megacities. Full article

Cross-modal semantic segmentation of individual tree LiDAR point clouds is critical for accurately characterizing tree attributes, quantifying ecological interactions, and estimating carbon storage. However, in forest environments, this task faces key challenges such as high annotation costs and poor cross-domain generalization. To address these issues, this study proposes a cross-modal semantic transfer framework tailored for individual tree point cloud segmentation in forested scenes. Leveraging co-registered UAV-acquired RGB imagery and LiDAR data, we construct a technical pipeline of “2D semantic inference—3D spatial mapping—cross-modal fusion” to enable annotation-free semantic parsing of 3D individual trees. Specifically, we first introduce a novel Multi-Source Feature Fusion Network (MSFFNet) to achieve accurate instance-level segmentation of individual trees in the 2D image domain. Subsequently, we develop a hierarchical two-stage registration strategy to effectively align dense matched point clouds (MPC) generated from UAV imagery with LiDAR point clouds. On this basis, we propose a probabilistic cross-modal semantic transfer model that builds a semantic probability field through multi-view projection and the expectation–maximization algorithm. By integrating geometric features and semantic confidence, the model establishes semantic correspondences between 2D pixels and 3D points, thereby achieving spatially consistent semantic label mapping. This facilitates the transfer of semantic annotations from the 2D image domain to the 3D point cloud domain. The proposed method is evaluated on two forest datasets. The results demonstrate that the proposed individual tree instance segmentation approach achieves the highest performance, with an IoU of 87.60%, compared to state-of-the-art methods such as Mask R-CNN, SOLOV2, and Mask2Former. Furthermore, the cross-modal semantic label transfer framework significantly outperforms existing mainstream methods in individual tree point cloud semantic segmentation across complex forest scenarios. Full article

In disaster relief operations, integrating disaster reconnaissance, material delivery, and effect evaluation into a temporal task chain can significantly reduce emergency response cycles and improve rescue efficiency. However, since multiple types of heterogeneous UAVs need to be coordinated during the rescue temporal task chains assignment process, this places higher demands on the real-time dynamic decision-making and system fault tolerance of its task assignment algorithm. This study addresses the sequential dependencies among disaster reconnaissance, material delivery, and effect evaluation stages. A task allocation model for heterogeneous UAV swarm targeting temporal task chains is formulated, with objectives to minimize task completion time and energy consumption. A dynamic coalition formation algorithm based on temporary leader election and multi-round negotiation mechanisms is proposed to enhance continuous decision-making capabilities in complex disaster environments. A simulation scenario involving twenty heterogeneous UAVs and seven temporal rescue task chains is constructed. The results show that the proposed algorithm reduces average task completion time by 15.2–23.7% and average fuel consumption by 18.3–26.4% compared with cooperative network protocols and distributed auctions, with up to a 43% reduction in fuel consumption fluctuations. Full article

With the increasing deployment of Unmanned Aerial Vehicle (UAV) swarms in uncertain and dynamically changing environments, optimal cooperative control has become essential for ensuring robust and efficient system coordination. To this end, this paper designs a data-driven optimal bipartite containment tracking control scheme for multi-UAV systems under compound uncertainties. A novel Dynamic Iteration Regulation Strategy (DIRS) is proposed, which enables real-time adjustment of the learning iteration step according to the task-specific demands. Compared with conventional fixed-step data-driven algorithms, the DIRS provides greater flexibility and computational efficiency, allowing for better trade-offs between the performance and cost. First, the optimal bipartite containment tracking control problem is formulated, and the associated coupled Hamilton–Jacobi–Bellman (HJB) equations are established. Then, a data-driven iterative policy learning algorithm equipped with the DIRS is developed to solve the optimal control law online. The stability and convergence of the proposed control scheme are rigorously analyzed. Furthermore, the control law is approximated via the neural network framework without requiring full knowledge of the model. Finally, numerical simulations are provided to demonstrate the effectiveness and robustness of the proposed DIRS-based optimal containment tracking scheme for multi-UAV systems, which can reduce the number of iterations by 88.27% compared to that for the conventional algorithm. Full article

Sustainable highway infrastructure maintenance critically depends on precise lane line detection, yet conventional inspection approaches remain resource-depleting, carbon-intensive, and hazardous to personnel. To mitigate these constraints and address the low accuracy and high parameterization of existing models, this study utilizes unmanned aerial vehicle (UAV) imagery and proposes a UAV-based highway lane line segmentation method using an improved DeepLabV3+ model that resolves multi-scale lane line segmentation challenges in UAV imagery. MobileNetV2 is used as the backbone network to significantly reduce the number of model parameters. The Squeeze-and-Excitation (SE) attention mechanism is integrated to enhance feature extraction capabilities, particularly at lane line edges. A Feature Pyramid Network (FPN) is incorporated to improve multi-scale lane line feature extraction. We introduce a novel Waterfall Atrous Spatial Pyramid Pooling (WASPP) module, utilizing cascaded atrous convolutions with strategic dilation rate adjustments to progressively expand the receptive field and aggregate contextual information across scales. The improved model outperforms the original DeepLabV3+ by 5.04% mIoU (85.30% vs. 80.26%) and 3.35% F1-Score (91.74% vs. 88.39%) while cutting parameters by 85% (8.03 M vs. 54.8 M) and reducing training time by 2 h 50 min, thereby enhancing the model’s accuracy in lane line segmentation, reducing the number of parameters, and lowering the carbon footprint. Full article