Search Results (751)

In complex low-altitude environments, unmanned aerial vehicles (UAVs) require reliable positioning, yet Global Navigation Satellite System (GNSS) signals are vulnerable to occlusion and interference. Pseudolite-augmented cooperative localization, which combines ground base-station signals with inter-UAV relative observations, can complement GNSS in such environments. However, two practical issues remain in real-world deployment: UAV-to-base-station (U-B) and UAV-to-UAV (U-U) observations have markedly different error statistics that a unified noise adjustment cannot handle, and the conservative covariance estimates produced by Covariance Intersection (CI) fusion bias the innovation-based adaptive noise estimation in distributed architectures. To address these issues, this paper proposes a Distributed Group Covariance Compensation Adaptive Kalman Filter (DGCC-AKF) for collaborative enhancement of UAV regional localization. DGCC-AKF establishes a group adaptive mechanism that independently adjusts the noise covariance matrices of U-B and U-U observations, enabling observation-type-level adaptive weighting that suppresses anomalous U-B or U-U measurements at the group level. In addition, a bounded covariance compensation factor is incorporated to alleviate the CI-induced conservatism in the adaptive noise estimation. The proposed method is evaluated on a 2800 km² semi-physical testbed based on the Ground-based High-precision Local Positioning System (GH-LPS) pseudolite network using measured U-B observations and high-dynamic (>300 km/h) flight trajectories collected from a fixed-wing platform across three independent flight sessions. Results demonstrate that under observation fault periods, the proposed method improves 3D positioning accuracy by up to about 75% over single-UAV extended Kalman filter (EKF). Compared with two advanced algorithms in this field, variational Bayesian adaptive Kalman filter (VBAKF) and maximum correntropy criterion Kalman filter (MCC-EKF), it is the only scheme that remains accurate and stable across all UAVs and fault types. The framework provides a practical step toward field deployment for resilient multi-UAV cooperative navigation in pseudolite-augmented GNSS-denied regions. Full article

City-scale unmanned aerial vehicle vision-and-language navigation (UAV-VLN) requires accurate upstream target localization from an overhead map, onboard observation, and language description. Existing VLM-based methods often treat road names, landmarks, and spatial relations as raw text, leaving the model to search a large map and implicitly infer geometric constraints. This paper proposes GPOD, an inference-time candidate-prior interface for the upstream target-localization stage in city-scale UAV-VLN. GPOD converts language anchors, spatial relations, target-category cues, static map objects, and vehicle detections into ranked candidate priors through branch-specific candidate generation, thereby reformulating unconstrained full-map coordinate regression as candidate-prior-conditioned coordinate prediction. The static branch aligns language constraints with map-object geometries, while the dynamic branch uses YOLOv8l-VisDrone with Slicing Aided Hyper Inference (SAHI) to construct detection-conditioned vehicle candidates. In the GPOD-VLM setting, ranked candidates are injected as structured spatial prompts and the base VLM predicts the final continuous coordinates; GPOD-Direct is a candidate-direct diagnostic variant that directly uses candidate centers without VLM coordinate regression. On the CityNav localization protocol, GPOD improves FlightGPT Overall SR@20m from 15.23% to 25.61% and consistently reduces Mean Navigation Error (Mean NE) across splits and backbones. On Val-Unseen, GPOD-Direct (Top-1) reaches 32.59% SR@20m, showing that ranked candidate priors provide strong discrete localization signals. These results show that inference-time candidate priors can reduce city-scale search ambiguity without updating the base VLM parameters, while also revealing a candidate-utilization gap in the current prompt-based continuous coordinate-regression interface. Full article

In the context of dynamic environmental changes, accurate geospatial information is fundamental for evidence-based decision-making in land-use planning. As urban areas undergo rapid structural transformations, characterizing their spatial morphology becomes essential for assessing ecosystem conditions and identifying pressure points within the urban–rural gradient. Drawing on the indicators for ecosystem condition and pressure recommended by the Mapping and Assessment of Ecosystem Services (MAES) framework, reflecting their trends, this study presents a methodology for comprehensive geospatial mapping of urban and peri-urban morphology, using the Functional Urban Area (FUA) of Burgas, Bulgaria, as a case study. The approach enables multi-scale spatial analysis (regional and local), integrates the structure and functions of urban ecosystems, and reveals the spatial heterogeneity of complex socio-economic systems. At the regional level, ecosystems within the FUA were identified using the national land-use/land-cover database. At the local level, within the city of Burgas, urban morphology was classified by combining building and land-cover types into 14 distinct urban morphological zones (local climate zones—LCZs) using high-resolution unmanned aerial vehicle (UAV)-based orthophotos. This precise spatial data allowed for a detailed assessment of the balance between pervious and impervious surfaces within each LCZ. By integrating Google Earth Engine (GEE) data, the appropriate conditions and pressure indicators in the case study are assessed. Regional ecosystem pressure is effectively captured through the spatial distribution of the Final Pressure Index (IPr). Concurrently, the Urban Ecosystem Performance Index (UEPI) highlights sharp spatial polarization, with critical stress concentrated in the industrial and port zones of the urban core. The results provide policy-makers and stakeholders with critical insights into current pressures and environmental changes in urban and peri-urban ecosystems, offering a robust foundation for evidence-based management and climate change adaptation strategies. Full article

Road potholes pose a considerable threat to mobile robots, which are generally less stable than conventional vehicles and may become trapped or overturned when traversing damaged road surfaces. Accurate semantic segmentation of road potholes is therefore essential for safe and reliable robot navigation. To address this requirement, multimodal fusion methods using RGB (Red, Green, Blue) and disparity images have been developed for pothole detection. Nevertheless, these methods still face challenges in detecting small potholes and delineating their boundaries precisely. To overcome these limitations, we propose a novel multimodal fusion network for road-pothole semantic segmentation. Specifically, we design a feature fusion module that integrates global context and local details to fully exploit the complementary information provided by RGB and disparity images. This design improves multimodal feature interaction and enhances boundary segmentation accuracy. Furthermore, we develop three feature attention fusion modules by incorporating multiple complementary attention mechanisms into the fusion module. These modules improve small-pothole detection by focusing on informative features, emphasizing target regions, and reducing information loss. We evaluate the proposed network on a small-pothole subset of Pothole-600 under identical hardware settings and backbone configurations for all experimental models. On the small-pothole subset of Pothole-600, FAFMNet achieves 90.22% mPre, 92.32% mRec, 98.73% mAcc, 91.26% mF1, and 83.93% mIoU, outperforming the state-of-the-art method by 1.87 percentage points in mF1 and 3.12 percentage points in mIoU. A paired statistical test over three independent runs further confirms that the improvement over the baseline is statistically significant ($p<0.05$). Full article

In electric vehicles, power batteries consist of numerous individual cells connected in series or parallel. Variations in manufacturing, operating conditions, and aging can lead to differences among these cells. Such inconsistencies can compromise the battery pack’s performance, safety, and overall service life. Therefore, accurately diagnosing inconsistencies among battery cells is of great significance for enhancing the reliability of the battery system and ensuring the operational safety of the vehicle. To address the limited computational resources available in vehicles, this paper proposes an end-cloud collaborative fault diagnosis framework and validates its effectiveness using real-world vehicle driving data. On the cloud side, a deep learning-based reconstruction network is developed to enable high-precision reconstruction of cell voltages. On the vehicle side, a second-order equivalent circuit model is used to represent battery dynamics. An adaptive forgetting factor recursive least squares method is introduced for online estimation of the model parameters, enabling accurate local prediction of individual cell voltages. Using the cloud-reconstructed and vehicle-predicted cell voltages, the extreme difference value of voltage for each cell is computed. A comprehensive diagnosis of inconsistency faults is then performed by fusing the extreme difference in voltage results from both the cloud and vehicle sides via the Extended Kalman Filter (EKF); threshold judgment is conducted based on the fused results, and the Cumulative Sum (CUSUM) algorithm is designed to identify cell inconsistency faults. Experimental results show that the proposed method effectively detects battery inconsistency faults and demonstrates strong engineering applicability and practical potential. Full article

Underwater target detection via side-scan sonar is vital for defense and economy but hindered by sparse targets, high data costs, and feature extraction difficulties due to textureless acoustic data and limited samples. To overcome these limitations, particularly for few-shot, small-object detection, we propose a Spatial Distribution Probability-Guided Detection Framework to aid Unmanned Underwater Vehicles (UUVs) in precise localization and clustering. The framework features a novel module that leverages a pre-trained Vision Foundation Model (DINOv3) to generate spatial distribution probability maps, guiding a Transformer-based network for accurate detection with scarce data. Additionally, it incorporates a Target Position Calculation Module and a DBSCAN-based post-processing module to determine global geographic coordinates and cluster discrete points, respectively. Experiments were conducted on both a Public Mine Detection Dataset and a self-collected dataset containing simulated mines and buoys. Ablation studies and comparison experiments demonstrated that the proposed guidance mechanism significantly improves detection performance. Furthermore, two comb-search missions verified that the system could accurately locate and cluster targets, distinguishing real targets from false detections (noise). These results confirm the framework’s efficacy in enabling high-precision perception and autonomous operations for complex underwater inspection tasks. Full article

Infrared and visible image fusion is critical for unmanned aerial vehicle (UAV) wilderness search and rescue. By integrating thermal radiation of the targets and texture details of the scenario, it enables accurate search for the wounded and comprehensive perception of disaster areas, thereby significantly improving emergency rescue efficiency. To alleviate data scarcity, we construct UAV-MSR, an infrared-visible dataset for casualty search, comprising 3889 paired images captured under diverse weather, illumination, and scenarios. Existing Transformer-based fusion methods mainly focus on high-intensity pixels while inadequately modeling low-intensity complementary features, resulting in blurred details and degraded target contrast in fused images. To this end, we propose a novel differential cross-attention Transformer network to address the issue of complementary information loss. Specifically, the encoder integrates convolution operations for local detail extraction and self-attention mechanisms for global context modeling. Then, we design a differential cross-attention guided feature fusion module to enhance the representation and preservation of detailed complementary features. Furthermore, a pixel loss function with a segmentation strategy is employed to improve the saliency of the target, enabling the fused image to facilitate subsequent target detection tasks. Experimental results and ablation studies demonstrate that the proposed method achieves notable performance and generalization ability. In summary, this work delivers a multimodal dataset and an efficient infrared-visible image fusion network to enable comprehensive perception for UAVs in wilderness search and rescue scenarios. Full article

Long-horizon trajectory prediction for unmanned aerial vehicles (UAVs) operating in constrained environments remains challenging because of strongly nonlinear dynamics, hidden control effects, and evolving destination-oriented behavior. This challenge is particularly pronounced for highly maneuverable cross-domain unmanned aerial vehicles (CDUAVs), whose glide trajectories are strongly coupled with control and environmental constraints. To address this problem, this paper proposes an intent-aware CNN–Informer framework for accurate long-horizon trajectory prediction. First, a control-affine reformulation of the vehicle dynamics is used to construct physically interpretable DBL control parameters, which reduce the learning difficulty associated with hidden control effects. Second, three continuous intent features—tangential no-fly zone avoidance distance, heading error angle, and relative closing velocity—are introduced to encode destination tendency and avoidance requirements. These features are fused with historical trajectory states and fed into a hybrid CNN–Informer network, where the CNN extracts local maneuver patterns and the Informer captures long-range temporal dependencies. Experiments on a constrained trajectory dataset demonstrate that the proposed method achieves the best performance among all compared models, including SSD-LSTM, Transformer, iTransformer, DLinear, and Informer. Compared with Informer, the proposed approach reduces the average prediction error by 17.2% and significantly improves terminal and maximum prediction errors. These results indicate that the proposed framework provides an effective and physically interpretable solution for long-horizon UAV trajectory prediction in constrained flight scenarios, with potential extensions to behavior-aware forecasting and guidance support in autonomous aerial systems. Full article

Autonomous Underwater Vehicles (AUVs) are increasingly used in deep-sea exploration, environmental monitoring, and marine engineering. Their operational safety and mission performance rely heavily on accurate and long-endurance underwater localization. However, both single-sensor localization methods and existing multi-sensor fusion approaches have inherent limitations, making it difficult to achieve high-precision localization during long-duration missions. To address this issue, this study develops a deep-learning-based multi-source sensor fusion framework for AUV localization. In the proposed framework, high-frequency data from the Inertial navigation system (INS) and Doppler velocity log (DVL) are used for continuous position propagation, while low-frequency absolute position observations from the Ultra-short baseline (USBL) system and Sonar are used to periodically correct the propagated results. Based on this framework, three instantiated models are developed using a Deep neural network (DNN), a Long short-term memory (LSTM) network, and a Bayesian semi-supervised mixed shallow-layer neural network (BSsMSLNN), respectively. Comparative experiments are conducted against the Extended Kalman filter (EKF) and Simultaneous localization and mapping system using Sonar, Visual, Inertial, and Depth sensor (SVIn2). The results show that the proposed framework effectively suppresses long-term error accumulation and significantly improves localization accuracy. Among the evaluated models, the BSsMSLNN-based method achieves the best performance in terms of trajectory fitting, root mean square error (RMSE), and coefficient of determination (R²). The proposed method provides a feasible solution for high-precision autonomous navigation of AUVs in GPS-denied environments. Full article

Interior permanent magnet synchronous motor (IPMSM) has advantages with high power density, wide speed range, small size, and high efficiency, and is widely used in the drive system of electric vehicles. Compared to other types of motors, permanent magnet synchronous motors (PMSMs) have some irreplaceable advantages, but there are also some disadvantages. As a type of PMSM, IPMSMs have problems with large fluctuations in permanent magnet (PM) magnetic field and demagnetization. At present, irreversible demagnetization of PMs is the most serious problem faced by IPMSMs. Once irreversible demagnetization of PMs occurs, it can cause a decrease in the performance of IPMSMs and can even damage the entire drive system. This paper takes an IPMSM with 48 slots, 8 poles, and 66 kW as the research object. Based on the reasons for PM demagnetization, a PM demagnetization model is established to obtain the demagnetization law of PMs. Firstly, the magnetic properties of PM materials were described based on their characteristic curves. The demagnetization mechanism of PMs was analyzed, and the demagnetization process of PMs was studied in combination with the reasons for demagnetization. Secondly, the basic parameters and torque performance of IPMSMs were calculated and analyzed. We analyzed the demagnetization curves of PM materials at different temperatures, calculated the operating points of PMs under various working conditions, and analyzed whether PMs undergo irreversible demagnetization based on the relationship between the operating points of PMs and the knee points of demagnetization curves. A high-fidelity electromagnetic–thermal coupling simulation model has been established, combined with the characteristics of electric vehicle driving conditions, to accurately characterize the temperature rise distribution and electromagnetic parameter changes of IPMSMs under different operating conditions and achieve multi-physics field collaborative analysis. Finally, a finite element model is adopted to simulate uniform and local demagnetization of PMs, and the changing characteristics of motor performance parameters under demagnetization are summarized. Different magnitudes of d-axis reverse current are applied as demagnetization excitation to analyze PM behaviors under various demagnetization degrees. The variations in magnetic flux density, output torque, and no-load back electromotive force (EMF) before and after demagnetization are simulated and analyzed. For the investigated motor and specific magnet grade, this work summarizes the irreversible demagnetization characteristics and corresponding practical judgment references. Full article

Achieving long-term, continuous, and accurate localization for Unmanned Aerial Vehicles (UAVs) in outdoor GNSS-denied environments where pre-existing reference maps are available is challenging. To this end, this paper proposes a Cross-view Particle Filter Localization (CPFL) framework. Unlike existing particle filter approaches that rely on inertial sensors for state propagation or sparse semantic labels for observation updates, CPFL is a vision-driven solution. This framework introduces specific adaptations into the two core stages of particle filtering: In the motion propagation stage, it achieves visual state transition by calculating a feature-based inter-frame homography mapping to estimate the 2D global relative motion components, eliminating the dependency on inertial priors; in the observation correction stage, a Dual-Granularity Adaptive Gating (DGAG) cross-view network is designed to mitigate perceptual aliasing and generate discriminative absolute position weights for the particles. By fusing these two stages through a filter mechanism, the framework transforms unbounded cumulative drift into bounded absolute localization errors. Furthermore, addressing the measurement deficiencies of traditional single-frame metrics, this paper also proposes a Trajectory Continuity Index (TCI@d) tailored for continuous localization tasks. Experiments on the real-world MAFS dataset confirm that this framework achieves a mean localization error of 5.28 m and a localization success rate of 89.7% under a 10-m threshold. Compared with mainstream vision-only algorithms and IMU-fusion baselines, this framework demonstrates lower mean errors and improved trajectory continuity, validating its effectiveness for long-term robustness. Full article

Methane (CH₄) is a highly potent greenhouse gas whose accurate detection and quantification are essential for climate mitigation and compliance with emerging environmental regulations. Conventional monitoring approaches, including fixed monitoring stations and satellite-based observations, often exhibit limitations in terms of spatial resolution, operational flexibility, and accessibility for localized measurements. This paper presents CH4SCOUT, a modular unmanned aerial vehicle (UAV)-based platform designed for methane detection, environmental monitoring, and georeferenced data acquisition. The proposed system integrates a methane sensing module, environmental sensors, controlled airflow sampling, onboard data acquisition, and wireless communication capabilities within a UAV-compatible architecture. A three-stage signal-conditioning pipeline based on Median filtering, Hampel outlier suppression, and Exponential Moving Average (EMA) smoothing is implemented to improve measurement stability under dynamic flight conditions. Initial real-world validation flights demonstrate stable methane concentration measurements under realistic environmental conditions while maintaining reliable data transmission and telemetry synchronization. Results indicate that low-cost UAV-assisted sensing architectures can provide operationally useful methane measurements when supported by appropriate calibration and deterministic signal conditioning. Future work will focus on advanced plume localization algorithms, autonomous navigation strategies, and enhanced methane emission quantification capabilities. Full article

With the rapid development of unmanned aerial vehicle (UAV) remote sensing and deep learning, road crack detection has become an important component of road condition assessment and intelligent road maintenance. However, accurately detecting cracks from UAV images remains challenging due to complex background environments, slender crack structures, blurred boundaries, and irregular crack shapes and orientations. Traditional methods that rely solely on visual information often struggle to achieve stable and accurate detection performance under these conditions. To address these challenges, this paper proposes a Multimodal Crack Geometry-Consistent Network (MCGC-Net) for high-precision road crack detection in complex road scenes. First, a UAV-based multimodal road crack dataset with image-text annotations is constructed. Specifically, crack-related textual descriptions are automatically generated from crack annotations using predefined semantic templates, which summarize crack morphology, spatial distribution characteristics, and structural properties. These semantic descriptions provide high-level semantic prior information for crack representation learning. Second, a Multimodal Contrastive Semantic Gating module (MCSG) is introduced to leverage automatically generated crack semantic descriptions and in-batch image-text semantic differences to guide visual feature learning, thereby improving the discrimination between crack and non-crack regions under complex background conditions. Furthermore, a Crack-Aware Slenderness Loss (CASL) is proposed to explicitly constrain slenderness consistency between predicted boxes and ground-truth boxes, improving localization stability for slender crack targets. In addition, a KAN-based Nonlinear Channel Attention mechanism (KAN-CA) is introduced to enhance feature representation capability for complex crack structures. Experimental results demonstrate that the proposed MCGC-Net effectively improves crack detection accuracy and structural representation capability under complex road environments. The proposed method provides a practical and reliable solution for UAV-based intelligent road crack detection. Full article

The transportation sector is the primary consumer of vehicle fuel worldwide and is thus a major contributor to climate change via carbon dioxide (CO₂) emissions. In addition to severe environmental impacts, such as global warming, droughts, floods, and rising sea levels, these emissions have a negative effect on public health by increasing the prevalence of respiratory disease. Achieving environmental sustainability through regulatory oversight requires a strong understanding of vehicular fuel consumption and CO₂ emissions. However, accurate modeling of these remains challenging due to the complex non-linear relationships between various vehicular characteristics and the lack of interpretability of many predictive models. Traditional linear models often fail to capture high-dimensional data complexities, while black-box methods provide few actionable insights for policymaking. To address these gaps, we developed a robust and data-driven two-stage machine-learning (ML) framework designed to enhance model performance and reliability. First, we implemented standard data preprocessing, enhanced feature engineering, and hyperparameter tuning for 14 cutting-edge ML algorithms and three advanced modeling techniques to explore their predictive performance. Second, we introduced three interpretable explainable AI (XAI) approaches. These were evaluated on a publicly available Kaggle static dataset of 550 vehicles, dominated by gasoline-powered vehicles, with only two diesels and two electric vehicles. The tuned CatBoost model demonstrated strong predictive performance, achieving an impressive R² of 0.9260, a root mean square error (RMSE) of 1.1759, and a mean absolute error (MAE) of 0.8147. In parallel, we deterministically estimated CO₂ emissions from fuel consumption, which provide direct estimates of tailpipe emissions. To ensure transparency and model interpretability, we employed Shapley additive explanations, local interpretable model-agnostic explanations, and permutation importance to identify the key factors contributing to the model predictions. Across the explainability analyses, cylinder count, front-wheel drive (drive_fwd), and the displacement–year interaction were the primary contributors to the predicted combined miles per gallon; in other words, they strongly affected fuel consumption. Collectively, these findings demonstrate the ability of the proposed model to capture complex feature relationships; thus, it offers a valuable tool for researchers and policymakers in sustainability planning and emission control. Future research should focus on real-time driving or dynamic measurements data and enhancing practical applications to further reduce emissions and promote environmental sustainability. Full article

Object detection in wide-field-of-view (wide-FoV) unmanned aerial vehicle (UAV) imagery for Internet of Things (IoT) remote sensing applications requires accurate recognition of tiny objects under severe background redundancy and extreme scale variation. As the field of view expands, conventional dense detectors tend to waste substantial computation on non-informative regions, while feature downsampling and static receptive fields often cause the dilution of foreground information and scale confusion. To address these issues, we propose MFRC-Det, a unified framework built upon two complementary principles: mask-guided feature routing and adaptive context modeling. Specifically, a Superpixel-Masking Generator (SP-Masker) is introduced to estimate an image-space soft foreground prior by comparing Simple Linear Iterative Clustering (SLIC) superpixel histograms with a peripheral background reference, propagating the resulting scores on a superpixel adjacency graph, and projecting the refined region-level scores back to a pixel-level routing mask. Guided by these priors, a Greedy-Cutter (G-Cutter) converts dense feature maps into compact, foreground-focused patches without repeated backbone evaluation on cropped image regions, thereby reducing redundant background computation while preserving local structural coherence. On top of the retained regions, an Adaptive Receptive-field Selection Network (ARSNet) aggregates multi-scale contextual responses from several learnable receptive-field candidate branches. ARSNet predicts spatial selection weights conditioned on the input features, allowing each location to emphasize a suitable receptive-field response for object representation. Experimental results on VisDrone-DET and UAVDT demonstrate that MFRC-Det achieves competitive detection accuracy with favorable computational efficiency. Specifically, MFRC-Det obtains 36.1% AP, 60.4% $A{P}_{50}$, and 38.5 FPS on VisDrone-DET and 21.3% AP, 36.8% $A{P}_{50}$, and 37.4 FPS on UAVDT. These results validate the effectiveness of mask-guided feature routing and adaptive context modeling for wide-FoV UAV object detection and suggest their potential value for computation-efficient aerial perception in IoT remote sensing applications. Full article