Search Results (11,281)

Driven by the escalating global agricultural workforce shortage and the urgent need to meet the “Zero Hunger” mandate, the automation of harvest–transport workflows has emerged as a cornerstone of Agriculture 4.0. This paper highlights the latest research progress in multi-robot collaborative logistics scheduling across highly unstructured farming environments, underpinned by cutting-edge spatial perception and digital twin frameworks. Initially, we summarize the technological leap from conventional 2D geometric mapping to multi-modal semantic 3D reconstruction—fusing light detection and ranging (LiDAR), unmanned aerial vehicle (UAV) imagery, and spatial data—to enable high-fidelity forward-looking predictions. The discussion then transitions to algorithmic advancements, emphasizing the shift from traditional centralized operations research to decentralized, data-driven approaches such as Multi-Agent Reinforcement Learning (MARL). We also explore micro-kinematic predictive control mechanisms and the growing integration of ecological sustainability metrics into routing models. To demonstrate practical engineering progress, multi-agent implementations are analyzed across three typical spatial settings: high-throughput continuous relays in open fields, global navigation satellite system (GNSS)-denied discrete routing in dense orchards, and close-proximity human–robot collaboration (HRC) in smart greenhouses. Finally, we identify the remaining barriers to the large-scale commercialization of Agricultural Cyber-Physical Systems (ACPS), such as the “Sim-to-Real” gap restricted by edge-computing capacities, unclosed economic loops, and HRC ethical dilemmas, offering a forward-looking roadmap for next-generation resilient agricultural networks. Full article

Overhead power lines increasingly intersect alpine wetland and grassland habitats on the Qinghai–Tibet Plateau, but variation in wire conspicuity within collision-associated areas remains poorly quantified. We combined GPS-GSM tracking and field verification to document infrastructure-associated mortality and separately used standardized UAV RGB images to characterize power-line conspicuity at the Luanhaizi Wetland, Qinghai Province. From 2020 to November 2025, we monitored 40 Black-necked Cranes (Grus nigricollis); nine were alive at the data cutoff, 23 were confirmed dead, and eight were lost to follow-up. Among the confirmed deaths, nine were classified from field evidence as wire-mesh fence entanglements and 14 as power-line collisions. All 14 field-inferred collision deaths involved 110 kV lines in this monitored sample. Accordingly, the UAV assessment focused on a selected section within the documented 110 kV collision-associated area; this site-selection criterion does not demonstrate that 110 kV lines are intrinsically more hazardous than other local voltage classes. We analyzed 640 UAV images and calculated an image-based visibility index (VI) combining normalized RGB target–background contrast and edge strength. VI describes relative wire conspicuity in standardized photographs rather than Black-necked Crane visual perception or collision probability. Blocked non-parametric tests showed that VI was lower under overcast than clear conditions (p < 0.001) and varied with observation distance and relative UAV height (both p < 0.001), whereas viewing angle was not significant (p = 0.065) and time of day showed a weak effect (p = 0.030). VI rankings remained reasonably stable under alternative component weightings. This two-stage approach uses documented mortality to identify candidate sections for image-based assessment but does not test whether low VI predicts collisions. It can support targeted marker trials that require independent evaluation through standardized collision monitoring. Full article

Cauliflower emergence rate and seedling growth are key indicators of field conditions and varietal potential. Traditional manual surveys are unsuitable for continuous monitoring across multiple varieties. This study integrates UAV RGB imagery with the DualSlim-YOLO model to estimate cauliflower emergence rates and monitor seedling growth. Built on YOLOv11, the model incorporates a lightweight feature extraction structure and an optimized detection-scale configuration. It reduces computational complexity while maintaining detection accuracy, thereby improving the efficiency of cauliflower seedling detection. DualSlim-YOLO achieved P, R, F1-score, mAP@0.5, and mAP@0.5:0.95 of 95.35%, 96.75%, 96.05%, 98.55%, and 86.65%, respectively. The number of parameters was reduced by 38.61%, while the inference speed increased by 22.16%, demonstrating good lightweight performance. Based on this model, UAV images of 171 cauliflower varieties acquired at 7, 21, and 28 d after transplanting were used for seedling detection and emergence rate estimation. In addition, 18 time-series seedling phenotypic traits were extracted, enabling a comprehensive quantitative evaluation of emergence dynamics and early-growth performance across multiple cauliflower varieties. This method effectively screens cauliflower varieties for high emergence rates, rapid emergence, and excellent seedling growth performance. It provides technical support for high-throughput, nondestructive seedling phenotyping and early germplasm screening under field conditions. Full article

The present study experimentally investigates the influence of n-octanol addition to Jet-A fuel on the combustion performance and emission behavior of a micro-turboprop-based hybrid UAV (“Unmanned Aerial Vehicle”) power system. The experiments were conducted on a dedicated hybrid propulsion test bench equipped with a KingTech micro-turboprop engine mechanically coupled to a T-Motor electric generator and supplying a regulated 48 V DC bus. The system is capable of delivering approximately 3 kW of continuous electrical power, with peak values reaching 3.5 kW. Jet-A and three n-octanol/Jet-A blends containing 10%, 20%, and 30% n-octanol by volume, denoted O10, O20, and O30, respectively, were tested under four operating regimes ranging from idle to 2500 W electrical load. Exhaust gas temperature, carbon monoxide, sulfur dioxide, nitrogen oxides, electrical output, and near-field pollutant dispersion were evaluated. The results show that n-octanol addition affects engine behavior in a strongly load-dependent manner. At idle, the O10 blend reduced CO concentration from approximately 2520 ppm for Jet-A to approximately 2270 ppm, corresponding to a reduction of about 9.9%. At the same operating condition, O10 reduced exhaust gas temperature from approximately 498.3 °C to 463.2 °C, while O20 and O30 produced stronger cooling effects. At intermediate regimes, the oxygenated molecular structure of n-octanol contributed to lower CO formation in selected cases, indicating improved combustion-completeness behavior. At high load, however, exhaust gas temperatures converged toward or exceeded those of Jet-A, particularly for O30, showing that higher octanol fractions may introduce additional thermal constraints. Among the tested fuels, O10, corresponding to 10% n-octanol by volume, provided the most balanced behavior across the investigated operating range, from idle to 2500 W electrical load. The dispersion measurements performed at 30 m from the source further showed that ambient pollutant concentrations are strongly influenced by wind speed, wind direction, and plume transport. These findings support moderate n-octanol blending as a promising transitional strategy for small-scale hybrid UAV propulsion systems, while highlighting the need for future repeated testing, direct fuel-flow measurement, and numerical dispersion modeling. Full article

Unmanned aerial vehicle (UAV) remote sensing object detection remains challenging because aerial targets are often small, densely distributed, and embedded in complex background clutter, whereas onboard deployment requires compact computation and real-time inference. Existing real-time detectors commonly retain a conventional $P_3$–$P_5$ detection hierarchy, in which deep low-resolution stages may consume computation after fine-grained small-object cues have already been weakened. To address this issue, this paper presents feature-modulated and redundancy-suppressed YOLO (FMRS-YOLO), a UAV-oriented lightweight detector that improves the accuracy–efficiency trade-off through the redundancy-reduction (RR) scale allocation strategy and targeted feature refinement. Instead of extending the terminal hierarchy to the conventional $P_5$ scale, FMRS-YOLO replaces the original stride-2 $P_5$ transition with a stride-1 high-level transformation and omits the corresponding $P_5$ prediction branch, thereby concentrating detection on the $P_3$ and $P_4$ feature levels where small aerial targets retain more informative spatial cues. To enhance feature representation under the compact RR scale allocation framework, we propose Gaussian cross-feature modulation (GCFM) to strengthen spatial–semantic interaction, and design attention-weighted parallel pyramid fusion (AWPPF) to improve clutter-aware multi-scale aggregation while preserving unpooled spatial details. Experiments are conducted separately on VisDrone-2019, a drone-based object detection benchmark used as the primary benchmark, and UCAS-AOD, an aerial object detection benchmark for aircraft and cars used as an independent complementary benchmark. Compared with scale-matched YOLOv11 baselines on VisDrone-2019, FMRS-YOLO improves mAP by 1.9–2.4 percentage points and mAP${}_{50}$ by 2.3–2.9 percentage points, while reducing parameters by 41.0–64.9%, reducing FLOPs by 1.6–20.7%, and increasing FPS by 9.3–10.4%. On UCAS-AOD, FMRS-YOLOn achieves 71.3% mAP, 98.8% mAP${}_{50}$, and 88.3% mAP${}_{75}$, showing favorable localization performance under a compact model scale. Ablation and visualization results further indicate that the proposed architecture improves foreground focus, suppresses background interference, and strengthens small-object localization. These results demonstrate that FMRS-YOLO provides a practical accuracy–efficiency trade-off for UAV remote sensing object detection. Full article

Unmanned Aerial Vehicles (UAVs) have emerged as a flexible, cost-effective solution for connecting Internet of Things (IoT) devices where traditional infrastructure falls short. However, managing their limited energy alongside the diverse demands of densely deployed devices makes resource allocation a genuinely hard problem. This paper presents a Deep Reinforcement Learning (DRL) framework that jointly optimizes user scheduling, IoT device transmit power, bandwidth, and UAV movement in a 6G-enabled UAV-relay uplink network, using a deterministic large-scale air-to-ground path-loss channel model. The UAV acts as an aerial decode-and-forward relay between IoT devices and a Base Station (BS), with a Deep Q-Network (DQN) making decisions based on queue backlogs, channel conditions, UAV position, and remaining battery. The reward function balances Energy Efficiency (EE), queue stability, fairness, and battery longevity. We benchmark the DQN against six baselines; Round Robin (RR), Random Allocation (RA), the Single-to-Noise Ratio (Max-SNR), Proportional Fair (PF), a Lyapunov heuristic, and a GreedyEE scheme; across a range of device counts, traffic loads, battery budgets, and flight altitudes. Simulations consistently show that the DQN outperforms all baselines, including a RA baseline with equal access to UAV mobility; in EE, throughput, delay, and fairness, confirming that the gain stems from the learned joint control policy rather than from UAV mobility being available. Full article

Pasture quality monitoring is essential for optimizing grazing management and reducing the incidence of nutritional and metabolic disorders in ruminants, yet conventional field-based measurements remain labor-intensive and limited in spatial coverage. This review examines how remote sensing (RS) technologies can support pasture-based livestock systems by providing timely, scalable assessments of biomass, botanical composition, and nutritive attributes. Data from multispectral, hyperspectral, radio detection and ranging (RADAR), and light detection and ranging (LiDAR) sensors, acquired via satellite, unmanned aerial vehicle (UAV), and proximal platforms, are combined with machine learning (ML) methods and radiative transfer models to derive pasture biophysical and quality indicators. The reviewed evidence shows that RS reliably estimates pasture biomass and structural traits, while advances in spectral unmixing, data fusion, and artificial intelligence (AI) improve the characterization of heterogeneous swards and support emerging indicators related to forage quality. Integrating these remotely sensed metrics into grassland decision-support frameworks can enhance grazing allocation, inform fertilization and irrigation decisions, and help detect conditions associated with nutritional imbalances. Overall, the synthesis demonstrates that RS, particularly when combined with advanced modelling and cloud-based processing, offers a robust pathway for improving pasture monitoring and strengthening the nutritional management of ruminants, thereby supporting more sustainable and animal welfare-focused grazing systems. Full article

The actuator plays a crucial role in controlling the flight attitude of unmanned aerial vehicles (UAVs), making timely anomaly detection essential for operational reliability and flight safety. However, existing methods often have difficulty jointly modeling the complex temporal dynamics and inter-variable spatial dependencies of multivariate actuator signals, while their computational complexity can limit real-time deployment. Moreover, most existing approaches rely on univariate or weakly coupled representations, making them less effective in detecting simultaneous faults across multiple actuators. To address these challenges, this paper proposes a Multivariate Spatio-Temporal Feature Fusion Transformer (STF_Tran) framework for anomaly detection in fixed-wing UAV actuators. Unlike conventional transformer-based multivariate anomaly detection methods that employ a shared attention mechanism to model heterogeneous dependencies, STF_Tran adopts a dual-branch architecture that separately encodes temporal dynamics and spatial correlations from multivariate actuator signals. A self-learning mechanism enables each branch to learn discriminative representations directly from normal operating data without requiring explicit fault labels, while a feature fusion module integrates the complementary spatio-temporal representations for anomaly reconstruction and scoring. Faults are identified by comparing the resulting anomaly scores with predefined thresholds, enabling the detection of diverse and simultaneous actuator anomalies. Experimental results demonstrate the effectiveness of STF_Tran, achieving F1 scores of 0.9944 and 0.9949 for deviation and stuck anomalies, respectively, and consistently outperforming several state-of-the-art methods. Full article

This work addresses the problem of planning low-power ground radar networks for surveillance in urban airspace for Advanced Air Mobility, with a focus on complex contexts such as ports, intermodal hubs, energy plants, and airport perimeters. The proposed approach introduces a continuous, deployment-oriented surrogate sensing model, used to compute a normalized detection score for non-cooperative Unmanned Aerial Vehicles within the surveillance area. The methodology integrates operational and environmental constraints using polygons that represent eligible installation areas and priority interest zones to ensure that sensor placement reflects both siting feasibility and the relative value of monitored areas. The framework also includes a first-order electromagnetic exposure-screening layer to support early-stage visualization and comparison across scenarios. Regulatory limits are not enforced in the current optimization. The development includes an interactive geospatial interface, which supports the definition of realistic scenarios and the selection of candidate radar deployment configurations consistent with user-defined siting constraints and exposure-screening assumptions. Full article

Accurate radar tracking of highly maneuverable unmanned aerial vehicles (UAVs) is a key enabling technology for low-altitude airspace surveillance, counter-UAS defense, and UAS traffic management (UTM). Once a non-cooperative UAV has been detected, estimating its motion state must cope with nonlinear polar-coordinate observations, unknown maneuver-mode switching, and multi-scale state variations driven by agile drone flight, making it difficult for classical IMM/UKF filters and deep sequence models to preserve local maneuver response and long-term temporal consistency. We propose MSGate, a multi-scale gated temporal network organized along an “observation-representation-fusion-constraint” pipeline. A non-learnable physical front end maps polar measurements into a Cartesian observation trajectory of the same dimension as the UAV state. Multi-scale gated convolution and RoPE-Transformer encoding extract local maneuver responses and long-range dependencies. A shared gated dual-path decoder fuses the two paths adaptively at each time step and channel, and velocity-smoothness and position-velocity kinematic consistency terms regularize the predicted trajectory. On the real-UAV datasets UZH-FPV, EuRoC MAV, and NeuroBEM, under a unified range-azimuth observation protocol, MSGate attains the lowest average position and velocity errors (Pos-RMSE $0.0486\mathrm{m}$; Vel-RMSE $0.1767\mathrm{m}/\mathrm{s}$), outperforming the strongest time-series baseline TimeMixer, and generalizes to a separate nano-quadrotor dataset (NanoBench). MSGate provides an accurate, maneuver-robust solution for radar state estimation of highly maneuverable UAVs. Full article

Fixed offline prognostic models can lose accuracy when sensor-data distribution changes after model development. This paper presents a validation-selected incremental-learning framework for time-before-failure (TBF) regression in three simulated unmanned-aerial-vehicle (UAV) subsystems: avionics, power, and airframe structure. According to the dataset provider, the subsystem simulation records used in this paper were generated with a customized quadrotor model on the RflySim framework, and the original source arrays used in the experiments are publicly available through the research repository specified in the Data Availability Statement. A leakage-controlled protocol partitions 200 parameterized degradation realizations per subsystem before window use, fits normalization statistics on source-training realizations only, and creates a controlled target domain through standardized sensor bias, gain, noise, and contiguous dropout. CNN–LSTM, TCN–CNN, and Transformer–CNN candidates are compared over three random seeds; CNN–LSTM is selected for all three subsystems by the source-validation RMSE. The incremental benchmark compares no update, fine tuning, elastic weight consolidation (EWC), replay, learning without forgetting (LwF), and an L2 parameter constraint. Each trainable method receives four predeclared candidates, the same three seeds and five-epoch budget, and selection by the same old-plus-new validation score before held-out testing. The resulting stability–plasticity balance is subsystem and storage-condition dependent: replay gives the strongest balance for power and airframe when source storage is permitted, whereas tuned fine tuning gives the lowest forgetting for avionics among the replay-free updates. L2 remains a compact replay-free update but is not universally superior to the other tuned methods. Near-failure errors and threshold warning rates provide an additional maintenance-oriented acceptance check. The evidence establishes controlled simulation feasibility; real-flight, bench-test, and hardware-in-the-loop validation remain outside the present scope. Full article

Visible foliar damage in maize caused by fall armyworm(Spodoptera frugiperda)is commonly assessed through manual field scouting, a labor-intensive process that is difficult to scale across large planting areas. Multispectral and hyperspectral sensing can support more objective assessment but remain costly and impractical for routine field use. This exploratory case study evaluated whether low-cost red–green–blue (RGB) imagery can provide preliminary indicators of visible foliar damage associated with natural S. frugiperda infestation. RGB video was recorded in maize fields in Jerez, Zacatecas, Mexico, yielding seven field-acquired sequences and 302 extracted frames. The pipeline combined hue–saturation–value (HSV)-based foliar segmentation with four visible-spectrum indices—Excess Green (ExG), Excess Red (ExR), the Visible Atmospherically Resistant Index (VARI), and the Green Leaf Index (GLI)—an ExG-ratio damage threshold, and a 17-feature descriptor per frame used to train a Random Forest (RF) severity classifier. The study is positioned relative to RGB, Unmanned Aerial Vehicle (UAV)-based, deep learning, and multimodal approaches through its emphasis on traceability, low acquisition cost, and sequence-aware validation. Using the recovered canonical HSV/ExG-ratio pipeline, sequence-level mean damage ranged from 0.1086% to 0.4511%, with maximum frame-level damage up to 7.7401%. Severity labels were percentile-derived from the canonical damage index, yielding 100 Low, 99 Medium, and 103 High samples. Under a stratified frame-level split, the RF baseline reached 76.9% accuracy and a macro F1-score of 0.759. Under leave-one-sequence-out validation, performance decreased to 57.3% overall accuracy and 0.577 macro F1-score, indicating sequence-level dependence and supporting a conservative interpretation of classifier generalization. A zero-shot comparison using the Segment Anything Model (SAM) on a curated ten-frame-per-sequence subset produced higher damage estimates (SAM 1.30–11.67% versus HSV 0.82–2.61% on the same frames), suggesting HSV segmentation may under-detect pale or bleached tissue. These results provide preliminary, exploratory evidence that low-cost RGB indices can capture information associated with visible foliar damage in the studied recordings, without establishing agronomic validation, generalization beyond this dataset, or readiness for field deployment. Full article

Infrared defects in photovoltaic (PV) modules captured during unmanned aerial vehicle (UAV) inspection are typically small and low-contrast, while onboard edge platforms are constrained by memory, logic resources, and power consumption. To address these challenges, this paper proposes KD-PH-YOLO for PV infrared defect detection and deployment on the Zynq-7020 platform. Based on YOLOv8, PH-YOLO removes redundant deep-layer computation and introduces a P2 detection head to preserve fine-grained information for small defects. Hardware-friendly Weighted Feature Fusion (HWFF) and Lightweight Attention-CBAM (LA-CBAM) are incorporated to enhance multiscale feature fusion and defect responses. Soft-label and multiscale feature distillation are further employed to improve the lightweight student model without increasing inference complexity. For edge deployment, INT8 quantization and hardware-aware acceleration are applied to map the model onto the Zynq-7020. Experimental results show that KD-PH-YOLO achieves an mAP@0.5 of 92.4% with only 1.48 M parameters and 6.9 GFLOPs. After hardware deployment, the model retains an mAP@0.5 of 91.8%. The Zynq-7020 implementation achieves an average latency of 184.3 ms per frame and a throughput of 5.43 FPS, with power consumption of 3.2 W and an energy efficiency of 1.7 FPS/W. The proposed method therefore provides a favorable accuracy–complexity–energy-efficiency trade-off for resource-constrained PV edge inspection. Full article

Future transportation networks may require aerial communication platforms capable of providing flexible and reliable services to vehicular terminals. In conventional unmanned aerial vehicle (UAV) communication systems, the antenna geometry is commonly treated as fixed, which limits the attainable directional gain when the relative geometry between the UAV and users changes significantly. This work considered a UAV equipped with a mechanically reconfigurable antenna array and studied its joint motion and transmission control under finite-blocklength communication. A sequential optimization problem was formulated to maximize the accumulated user throughput by jointly optimizing the UAV trajectory, the array orientations, and the transmit beamforming vectors, subject to the UAV kinematic constraints, the UPA orientation constraints, and the transmission energy budget. The resulting problem involves nonlinear coupling among platform motion, antenna pointing, beamforming, and finite-blocklength rate expressions, making conventional optimization computationally demanding. To obtain an adaptive control policy, a soft actor–critic-based deep reinforcement learning method was developed. The simulation results showed that jointly controlling the UAV mobility, array orientation, and beamforming improves the achievable finite-blocklength transmission performance compared with benchmark schemes, demonstrating the effectiveness of the proposed framework in enhancing reliable data delivery for UAV-assisted transportation infrastructure applications. Full article

Litchi (Litchi chinensis Sonn.) is an economically important tropical and subtropical fruit crop, but frequent outbreaks of diseases and pests severely threaten yield and quality. Traditional field monitoring is inefficient and cannot meet requirements for early and accurate detection over large areas. Although various sensing technologies and artificial intelligence (AI)-based methods have been developed, the literature remains fragmented and lacks systematic comparison across different monitoring scales and technological approaches. This review summarizes recent advances in intelligent detection technologies for litchi diseases and pests across scales ranging from individual fruits to entire orchards. First, biological and spectral response mechanisms of infected tissues are introduced as a theoretical basis. Then, fruit-level sensing technologies, including near-infrared spectroscopy, multispectral and hyperspectral imaging, RGB imaging, fluorescence sensing, and data fusion, are reviewed. Orchard-scale monitoring using unmanned aerial vehicles (UAVs) and Internet of Things (IoT) is further analyzed. Machine learning and deep learning methods for feature extraction, recognition, and risk prediction are also summarized. Finally, advantages, limitations, and application scenarios of different technologies are compared in terms of their advantages, limitations, and suitable application scenarios. This review highlights the transition toward multimodal and intelligent monitoring systems and discusses future directions including edge intelligence, multimodal fusion, and collaborative monitoring for precision agriculture. Full article