Search Results (5,632)

Drones have long been explored by commercial and military users for supply. While several systems offering small payloads in drone delivery have seen operational use, large-scale supply drones have yet to be adopted. A range of setbacks cause this, including technological and operational challenges that hinder their adoption. Here, we evaluate these challenges from a conceptual modelling perspective and forecast their applicability once these barriers are overcome. This study uses technology trend modelling and bibliometric activity mapping methodologies to predict the applicability of specific technologies that are currently identified as operational challenges. Specifically for supply drones, we model trends in technological improvements of battery technology and aircraft control, and project its focus on landing zone autonomy and powertrain. The prediction also focuses on the current state of hybrid power and higher levels of automation required for landing zone operations. These models are validated through several published case studies of small delivery drones and then applied to assess the feasibility and constraints of larger supply drones. A case study involving the conceptual design of a supply drone large enough to move a shipping container is presented to illustrate the critical technologies required to transition large supply drones from concept to operational reality. Key technologies required for large-scale supply drones have yet to build up a critical mass of research activity, particularly on landing zone autonomy and powertrain. Moreover, additional constraints beyond technological and operational challenges could include limitations in autonomy, certification hurdles, regulatory complexity, and the need for greater social trust and acceptance. Full article

The spotted lanternfly (SLF, Lycorma delicatula) is an invasive planthopper causing severe agricultural and environmental damage in 20 U.S. states. SLF control remains constrained by (1) overreliance on broad-spectrum pesticides that harm nearby ecosystems, (2) inefficiency and ecological risk of alternative methods, and (3) underutilization of SLF behavioral traits and artificial intelligence (AI) in IPM. This study introduces AI-LyD, an AI-driven IPM framework integrating behavioral ecology, predictive modeling, image-based detection, and low-cost physical controls. Incorporating SLF behavioral constraints, including cold-exposure requirements for egg hatching, into ecological models improved prediction accuracy (AUC = 0.821, Sensitivity = 0.888, Kappa = 0.642) and reconstructed SLF distributions consistent with current proliferation trends. A YOLO-based detection model leveraging SLF clustering behavior improved identification accuracy from 84% to 96% and reduced false positives from 42% to 8% in real-world drone-collected imagery. Exploiting SLF crawling, jumping, and hydrophobic behaviors, the novel Aquabex water-moat device with an optimized 60° opening trapped 85% of Stage I–IV nymphs and reduced adult invasions by 67%, at an estimated cost below USD $0.50 per unit. Field deployments across four locations in Hunterdon County, New Jersey, achieved a 91% population reduction (95% CI: 90.1–92.0%). Together, these results establish AI-LyD as the first operational, scalable SLF IPM system, and this paradigm can be applied to controlling other invasive species. Full article

Drones are expected to support applications such as emergency response, parcel delivery, and infrastructure monitoring in dense urban airspaces, creating traffic levels that are unmanageable for human operators. Autonomous separation management is therefore essential, combining strategic and tactical control to prevent conflicts. This paper addresses the tactical landing phase by introducing a centralized landing flow manager—a reinforcement learning (RL) agent that adjusts drone speed and heading to merge landing flows safely and efficiently prior to a final approach fix. The objective of the work was to demonstrate the potential of reinforcement learning in this novel context, by implementing and evaluating it in simulation and testing its capabilities with 10 concurrent landing drones. The RL agent learns to successfully separate traffic, thereby lowering intrusion counts compared to the baseline autopilot, but is outperformed in safety by the decentralized Modified Voltage Potential (MVP) method due to outlier scenarios. Nevertheless, the RL-based system achieves faster scenario completion and thus a higher overall throughput, by speeding up the vehicles towards the final approach fix. Future work will explore improved network architectures, transfer learning across varied scenarios, and algorithmic fine-tuning to further enhance safety performance. Full article

A crucial problem for autonomous aerial operations is to provide dependable and strong control of unmanned aerial vehicles (UAVs) in adverse environmental circumstances. The current paper provides an extensive analysis of the vehicle dynamics and control of drones in strong wind fields with altitude-dependent wind shear, wind gusts, and turbulence. A comparative evaluation of sliding mode control (SMC), linear quadratic regulator (LQR), model predictive control (MPC), adaptive constrained adaptive linear control (ACALC), and higher-order control barrier function (HOCBF)-based control in the context of trajectory tracking performance, control effort, and robustness is carried out. Simulation outcomes show that SMC exhibits superior robustness to sudden wind disturbances and the most consistent tracking accuracy under stochastic variations; HOCBF and ACALC provide comparable high precision with added constraint enforcement and adaptive capability, respectively; MPC has smooth control and minimal energy consumption; and LQR has a high level of computational efficiency with significantly tolerable tracking performance. Monte Carlo calculations are conducted to measure tracking errors and control energy under the stochastic wind variations, and the capability of the proposed control strategies to remain resilient in uncertain conditions is brought to light. The results provide useful information about the architecture of effective controllers used in UAVs during severe weather conditions and underline the compromises between the accuracy of tracking, the control effort, and the energy consumption. The suggested framework offers an effective and scalable system suitable for reliable autonomous drone activity in complicated reality settings. Full article

Photovoltaic technology is the mainstream technology in the world at present, and its contribution to energy has also attracted wide attention from all mankind. However, the complex and changeable environment and some unknown factors have seriously affected the use efficiency of photovoltaic systems. Therefore, timely maintenance of the photovoltaic systems and finding out the defects in the photovoltaic panel have become the key to the development of photovoltaic technology. In this paper, through the analysis of infrared thermal imaging data in the defect detection of photovoltaic modules, aiming at the problems of small targets, high density, low detection accuracy, slow efficiency, and poor robustness of infrared defects of photovoltaic modules in the UAV patrol scene, advanced machine vision and deep learning algorithms in the field of artificial intelligence are used to carry out the research on defect detection of photovoltaic modules. In the end, the improved RT-DETR (Real-Time Detection Transformer) model achieved an accuracy of 83.3% in defect localization during detection, and an accuracy of 97.7% in determining the presence of defects in images. The accuracy and real-time performance of defect detection were significantly improved, reducing the daily operation and maintenance costs of photovoltaic power plants and fundamentally improving the power generation efficiency and overall profitability of photovoltaic enterprises. Full article

Ensuring product integrity across Malaysia’s East Malaysian states (Sabah and Sarawak) requires a cold chain that is resilient to tropical heat, long multimodal routes, intermittent power, and dispersed rural populations. This paper proposes a sustainability-first architecture for vaccine and blood component logistics that combines World Health Organization and the United Nations International Children’s Emergency Fund Effective Vaccine Management (EVM 2.0) criteria with energy-aware transport planning, solar-hybrid edge refrigeration, phase-change materials, and digital temperature monitoring compliant with ISO 23412 for temperature-controlled delivery services. In this study, a mixed-methods methodology was employed, including (1) route and mode optimization under temperature risk and carbon intensity constraints; (2) equipment right-sizing using duty-cycle energy models and IEC 60068 environmental tests as design baselines; (3) governance with real-time earned value management (EVM) and key performance indicators (KPIs); and (4) scenario analysis for riverine, road, air, and drone last-mile segments relevant to remote East Malaysian communities. Results from realistic logistic scenarios indicate a 45–65% reduction in dose-weighted temperature-excursion minutes, 28–41% reduction in CO₂e per successful dose delivered, and 35–52% reduction in product loss compared with status quo planning. For blood components, solar-hybrid storage and mixed-mode routing reduced breach risk by 37% while maintaining red cells (2–6 °C), platelets (20–24 °C, continuous agitation surrogate), and fresh frozen plasma (≤−18 °C) requirements aligned with WHO guidance and Malaysia’s national transfusion policies. We provide a reference architecture, implementation bill of materials, and an EVM-aligned KPI dashboard to guide scale-up. Full article

In complex traffic environments, image degradation caused by haze, low illumination, and occlusion significantly undermines the reliability of vehicle and pedestrian detection. To address these challenges, this paper proposes an aerial vision framework that tightly couples multi-level image enhancement with a lightweight detection architecture. At the image preprocessing stage, a cascaded “dehazing + enhancement” module is constructed, where a learning-based dehazing method is employed to restore long-range details affected by scattering artifacts. Additionally, structural fidelity is enhanced in low-light regions, while global brightness consistency is achieved. On the detection side, a lightweight yet robust detection architecture, termed GDEIM-SF, is designed. It adopts GoldYOLO as the lightweight backbone and integrates D-FINE as an anchor-free decoder. Moreover, two key modules, CAPR and ASF, are incorporated to enhance high-frequency edge modeling and multi-scale semantic alignment. Through evaluation on the VisDrone dataset, the proposed method achieves improvements of approximately 2.5 to 2.7 percentage points in core metrics such as mAP@50-90 compared to similar lightweight models, while maintaining a low parameter count and computational overhead. This ensures a balanced trade-off among detection accuracy, inference efficiency, and deployment adaptability, providing a practical and efficient solution for UAV-based visual perception tasks under challenging imaging conditions. Full article

Detecting surface potsherds using low-altitude remote sensing is challenging due to severe class imbalance and limited training data. This study develops and validates a semi-automatic detection methodology that adapts threshold-optimized boosting classifiers (AdaBoost, XGBoost) to maximize ceramic detection recall under extreme class imbalance in the Western Megaris archeological landscape, Greece. Models were trained on only 15% of the available data to simulate realistic field conditions. Evaluation emphasized recall-oriented metrics (precision, recall, F1-score, AUC) for the minority class, addressing the accuracy paradox where high overall accuracy masks poor rare-class performance. Threshold optimization enabled AdaBoost and XGBoost to achieve substantially improved recall compared to baseline methods, with detection-to-ground-truth ratios of 2.5 and 3.2, respectively, reflecting deliberate prioritization of recall over precision for exploratory survey purposes. The results demonstrate that this methodological framework provides archeologically interpretable screening tools for identifying high-probability ceramic locations, supporting more efficient field survey design and heritage documentation workflows in Mediterranean landscapes. Full article

Object detection is a fundamental task in computer vision. Bounding box regression (BBR) losses are critical to detector performance. However, evaluation measures that rely on the Intersection over Union (IoU) between the predicted and ground truth boxes are highly sensitive to positional deviations, which can hinder optimization. To alleviate this issue, we propose ATDIoU, a novel arctangent-differential loss for bounding-box regression. ATDIoU computes distance similarity between a predicted and a ground truth box by modeling the distances between their corresponding vertices as a two-dimensional arctangent differential distribution (ATD). This arctangent differential-based design mitigates bounding box drift and reduces sensitivity to localization errors. As a result, it guides the model to learn target positions more effectively. We evaluate ATDIoU by integrating it into YOLOv6 and conducting experiments on PASCAL VOC and VisDrone2019. The results demonstrate that ATDIoU yields improvements of 1.4% and 0.7% in mean average precision (mAP) relative to MPDIoU. Full article

To enhance the anti-jamming performance and operational reliability of drones, this paper presents the design, fabrication, and measurement of a novel polarization-reconfigurable metasurface antenna that meets these demands. The design process is guided systematically by characteristic mode analysis, in which the modal significance coefficient is used as a key tool to predict resonant frequencies and optimize bandwidth. A major innovation lies in the mechanical rotation mechanism, which enables the antenna to switch between left-hand circular polarization, linear polarization, and right-hand circular polarization, thereby avoiding losses associated with active electronic components. The antenna features a compact geometry of 0.49λ × 0.49λ and delivers strong performance across all polarization states. Impedance bandwidth exceeds 29.9%, average gain ranges from 5.1 to 6.0 dBi, and high polarization purity is achieved with an axial ratio bandwidth > 10% in circular polarization modes and cross-polarization discrimination >23 dB in the linear polarization state. Simulated and measured results are in good agreement, confirming the effectiveness and robustness of the proposed design for modern sub-6 GHz 5G drone terminals. Full article

To resolve the issue of degraded detection accuracy for unmanned aerial vehicle object detection under low-illumination environments, this paper introduces a parallel object detection model. First, a dual-branch architecture is established by parallelly integrating a Zero-Reference Deep Curve Estimation (Zero-DCE) illumination enhancement network with a You Only Look Once (YOLOv11n)-based object detection network, enabling collaborative feature training and real-time updates. Through a feature-sharing mechanism, the two branches are jointly optimized during training, thus enhancing the model’s generalization capability in low-illumination environments. Furthermore, to further improve detection accuracy, a Dynamic Pooling Synergy Attention (DPSA) module is introduced into the backbone of YOLOv11n. By integrating dynamic pooling-based channel attention with spatial attention, this module improves feature representation, improves performance under complex environments, and increases adaptability to multi-scale targets. In addition, a High and Low Frequency Spatially-adaptive Feature Modulation (HLSAFM) module is added to the detection network’s Neck. Through high- and low-frequency feature refinement, segmented feature processing, and dynamic modulation, the network is able to capture richer feature information, thereby strengthening feature representation and discriminative capability. Extensive experiments on the VisDrone (Night) and DroneVehicle (Night) datasets demonstrate superior performance over multiple existing methods under low-illumination object detection tasks. Compared with the original YOLOv11n model, the proposed model $mAP50$ increases by 6.0% and 1.0% and $mAP50:95$ increases by 3.1% and 0.8%, respectively. These results confirm the enhanced detection capability achieved by our method in challenging low-illumination unmanned aerial vehicle (UAV) scenarios. Full article

In oriented object detection from drone imagery, many existing RGB-infrared (RGB-IR) fusion methods derive modality weights from input statistics alone, without regard for downstream detection objectives. We present SGFNet, a Semantic-Guided Fusion Network that feeds detection-level semantics back into the fusion stage through learned importance masks. SGFNet comprises three modules: (1) a Frequency-aware Disentanglement Module (FDM) that separates high-frequency textures from low-frequency thermal structures through Laplacian and Gaussian filtering; (2) a Semantic-Guided Module (SGM) that generates P5-level semantic masks to steer fusion toward detection-critical regions; and (3) an Adaptive Geometric Convolution (AGC) whose rotation-aware sampling matches receptive fields to arbitrarily oriented objects. On the DroneVehicle benchmark (28,439 RGB-IR pairs, five vehicle categories), SGFNet achieves 82.0% mAP@0.5, surpassing the runner-up DMM by 3.2 percentage points while lowering mean angular error from 7.4° to 6.2° (−16%). Ablation analysis attributes the largest single-module gain (+1.7 pp) to the semantic feedback path. Full article

Object detection in aerial drone imagery has attracted increasing attention in Unmanned Aerial Vehicle(UAV) sensing applications. However, small objects occupying limited image regions, with large scale variations and similar background interference, make it challenging to perceive them. Meanwhile, the constrained computing power of the onboard platform imposes requirements on the speed and efficiency of the algorithm. In this paper, we propose an efficient object detection network for real-time UAV perception named ESO-Det. Our approach introduces three key innovations: (1) Dense Cross-branch Complementary Module, a lightweight model that dynamically integrates semantic and spatial information to improve the network’s understanding of scene details. (2) Large-Kernel Context Integration Module, a module that expands receptive fields to effectively aggregate multi-scale contextual information. (3) Lightweight Selective Aggregation Module, a model selectively aggregates fused multi-scale features through different functional branches. Extensive experiments demonstrate that the proposed method achieves higher performance than representative existing approaches while maintaining real-time processing capability. The results show that our method is suitable for real-time UAV object detection. Full article

This paper proposes a hybrid underwater drone communication system that combines underwater optical communication (UOC) and radio-frequency (RF) communication to support real-time video streaming in underwater environments. The system consists of a remotely operated vehicle (ROV) that transmits video to a surface gateway, which relays the video to onshore facilities through a 5G network. An outdoor experiment conducted in a maritime environment measured the received signal strength indicator (RSSI), signal-to-interference-plus-noise ratio (SINR), occupied bandwidth, and end-to-end (E2E) throughput at 700 MHz and 2600 MHz with video frame rates ranging from 10 to 60 fps. The results show that the 700 MHz frequency band provides higher RSSI and SINR, which support more reliable long-range communications, while the 2600 MHz frequency band provides lower RSSI and SINR but a larger bandwidth. The maximum E2E throughput achieved was 53.5 Mbps at 700 MHz and 58.64 Mbps at 2600 MHz. Increasing frame rates mainly affects throughput by reducing SINR. These results analyze the coverage–capacity trade-off and provide valuable insights for drone-assisted hybrid UOC-RF communication in underwater video streaming applications. Full article

Multimodal object detection utilizing RGB and infrared (IR) imagery has become a critical research area for unmanned aerial vehicle (UAV) surveillance applications, providing reliable perception under various lighting and environmental conditions. Nevertheless, current methods encounter three primary challenges: (1) insufficient utilization of frequency-domain properties in heterogeneous modalities, (2) restricted adaptability in crossmodal feature integration across different environmental scenarios, and (3) inadequate modeling of fine-grained spatial relationships for accurate object localization. To overcome these limitations, we introduce MFE-DETR, a novel Multimodal Feature-Enhanced Detection Transformer that achieves superior RGB-IR fusion through three complementary innovations. First, we present the Dual-Modality Enhancement Module (DMEM) with two specialized processing streams: the Haar wavelet decomposition stream (HWD-Stream) that conducts multi-resolution frequency-domain analysis to independently enhance low-frequency structural components and high-frequency textural information, and the Attention-guided Kolmogorov–Arnold Refinement Stream (AKR-Stream) that employs learnable spline-parameterized activation functions for adaptive nonlinear feature refinement. Second, we enhance the Cross-scale Channel Feature Fusion module by integrating an Adaptive Feature Fusion Module (AFAM) with complementary gating mechanisms that dynamically adjust modality contributions according to spatial informativeness. Third, we introduce the Bilinear Attention-Enhanced Detection Module (BADM) that models second-order feature interactions through factorized bilinear pooling, facilitating fine-grained crossmodal correlation analysis. Extensive experiments on the DroneVehicle benchmark show that MFE-DETR attains 78.6% mAP${}_{50}$ and 57.8% mAP${}_{50:95}$, outperforming state-of-the-art approaches by 5.3% and 3.7%, respectively. Additional evaluations on the VisDrone dataset further confirm the excellent generalization performance of our method, especially for small object detection with 18.6% AP${}_S$, achieving a 1.5% improvement over existing techniques. Comprehensive ablation studies and visualizations offer detailed insights into the effectiveness of each proposed component. Full article