Search Results (1,405)

As Unmanned Aerial Vehicle (UAV) technology advances, UAVs have attracted widespread attention across military and civilian fields due to their low cost and flexibility. In unknown environments, UAVs can significantly reduce the risk of casualties and improve the safety and covertness when performing missions. Reinforcement Learning allows agents to learn optimal policies through trials in the environment, enabling UAVs to respond autonomously according to the real-time conditions. Due to the limitation of the observation range of UAV sensors, UAV target search missions face the challenge of partial observation. Based on this, Partially Observable Deep Q-Network (PODQN), which is a DQN-based algorithm is proposed. The PODQN algorithm utilizes the Gated Recurrent Unit (GRU) to remember the past observation information. It integrates the target network and decomposes the action value for better evaluation. In addition, the artificial potential field is introduced to solve the potential collision problem. The simulation environment for UAV target search is constructed through the custom Markov Decision Process. By comparing the PODQN algorithm with random strategy, DQN, Double DQN, Dueling DQN, VDN, QMIX, it is demonstrated that the proposed PODQN algorithm has the best performance under different agent configurations. Full article

With the wide application of Residence Time Difference (RTD) fluxgate sensors in Unmanned Aerial Vehicle (UAV) aeromagnetic measurements, the requirements for their measurement accuracy are increasing. The core characteristics of the RTD fluxgate sensor limit its sensitivity; the high-permeability soft magnetic core is especially easily interfered with by the input noise. In this paper, based on the study of the excitation signal and input noise characteristics, the stochastic resonance is proposed to be realized by adding feedback by taking advantage of the high hysteresis loop rectangular ratio, low coercivity and bistability characteristics of the soft magnetic material core. Simulink is used to construct the sensor model of odd polynomial feedback control, and the Particle Swarm Optimization (PSO) algorithm is used to optimize the coefficients of the feedback function so that the sensor reaches a resonance state, thus reducing the noise interference and improving the sensitivity of the sensor. The simulation results show that optimizing the odd polynomial feedback coefficients with PSO enables the sensor to reach a resonance state, improving sensitivity by at least 23.5%, effectively enhancing sensor performance and laying a foundation for advancements in UAV aeromagnetic measurement technology. Full article

To evaluate the accuracy of Discrete Wavelet Transform (DWT) in monitoring the chlorophyll (CHL) content of maize canopies based on RGB images, a field experiment was conducted in 2023. Images of maize canopies during the jointing, tasseling, and grouting stages were captured using unmanned aerial vehicle (UAV) remote sensing to extract color, texture, and wavelet features and to construct a color and texture feature dataset and a fusion of wavelet, color, and texture feature datasets. Backpropagation neural network (BP), Stacked Ensemble Learning (SEL), and Gradient Boosting Decision Tree (GBDT) models were employed to develop CHL monitoring models for the maize canopy. The performance of these models was evaluated by comparing their predictions with measured CHL data. The results indicate that the dataset integrating wavelet features achieved higher monitoring accuracy compared to the color and texture feature dataset. Specifically, for the integrated dataset, the BP model achieved an R² value of 0.728, an RMSE of 3.911, and an NRMSE of 15.24%; the SEL model achieved an R² value of 0.792, an RMSE of 3.319, and an NRMSE of 15.34%; and the GBDT model achieved an R² value of 0.756, an RMSE of 3.730, and an NRMSE of 15.45%. Among these, the SEL model exhibited the highest monitoring accuracy. This study provides a fast and reliable method for monitoring maize growth in field conditions. Future research could incorporate cross-validation with hyperspectral and thermal infrared sensors to further enhance model reliability and expand its applicability. Full article

The unique challenges of polar ecosystems, coupled with the necessity for high-precision data, make Unmanned Aerial Vehicles (UAVs) an ideal tool for vegetation monitoring and conservation studies in Antarctica. This review draws on existing studies on Antarctic UAV vegetation mapping, focusing on their methodologies, including surveyed locations, flight guidelines, UAV specifications, sensor technologies, data processing techniques, and the use of vegetation indices. Despite the potential of established Machine-Learning (ML) classifiers such as Random Forest, K Nearest Neighbour, and Support Vector Machine, and gradient boosting in the semantic segmentation of UAV-captured images, there is a notable scarcity of research employing Deep Learning (DL) models in these extreme environments. While initial studies suggest that DL models could match or surpass the performance of established classifiers, even on small datasets, the integration of these advanced models into real-time navigation systems on UAVs remains underexplored. This paper evaluates the feasibility of deploying UAVs equipped with adaptive path-planning and real-time semantic segmentation capabilities, which could significantly enhance the efficiency and safety of mapping missions in Antarctica. This review discusses the technological and logistical constraints observed in previous studies and proposes directions for future research to optimise autonomous drone operations in harsh polar conditions. Full article

Peru is one of the most diverse countries from a geographical and climatic point of view, where there are three large ecosystem regions called coast, Sierra, and jungle. These characteristics result in the country having many hydrographic basins, with rivers of significant dimensions in terms of the width and length of the channel. In this sense, there is a permanent need to provide connectivity and promote trade between communities through road bridge infrastructure. Thus, Peru historically developed a road network and bridges during the Inca Empire in the Tawantinsuyu region, building a cobblestone road network and suspension bridges with rope cables made of plant fibers from vegetation called Coya-Ichu. This is how bridges in Peru have evolved to meet contemporary vehicular demands and provide structural stability and functionality throughout their useful life. This article presents the following sections: (a) an introduction to the evolution of bridges, (b) the current typology and inventory of bridges, (c) the characterization of the largest bridges, (d) a discussion on the architecture, engineering, construction, and structural health monitoring (AECSHM) of bridges in the face of climate change, earthquakes, and material degradation, and (e) conclusions. Finally, this article presents opportunities and challenges in terms of Peru’s architecture, engineering, construction, and structural health monitoring of road bridges. Special emphasis is given to the use of technologies from the era of Industry 4.0 to promote the digital construction and structural health monitoring of these infrastructures. Finally, it is concluded that the integration of technologies of sensors, the IoT (Internet of Things), AI (artificial intelligence), UAVs (Unmanned Aerial Vehicles), remote sensing, BIM (Building Information Modeling), and DfMA (Design for Manufacturing and Assembly), among others, will allow for more safe, reliable, durable, productive, cost-effective, sustainable, and resilient bridge infrastructures in Peru in the face of climate change. Full article

Aeromagnetic surveying technology detects minute variations in Earth’s magnetic field and is essential for geological studies, environmental monitoring, and resource exploration. Compared to conventional methods, residence time difference (RTD) fluxgate sensors deployed on unmanned aerial vehicles (UAVs) offer increased flexibility in complex terrains. However, measurement accuracy and reliability are adversely affected by environmental and sensor noise, including Barkhausen noise. Therefore, we proposed a novel denoising method that integrates Particle Swarm Optimization (PSO) with Wavelet Neural Networks, enhanced by a dynamic compression factor and an adaptive adjustment strategy. This approach leverages PSO to fine-tune the Wavelet Neural Network parameters in real time, significantly improving denoising performance and computational efficiency. Experimental results indicate that, compared to conventional wavelet transform methods, this approach reduces time difference fluctuation by 23.26%, enhances the signal-to-noise ratio (SNR) by 0.46%, and improves sensor precision and stability. This novel approach to processing RTD fluxgate sensor signals not only strengthens noise suppression and measurement accuracy but also holds significant potential for improving UAV-based geological surveying and environmental monitoring in challenging terrains. Full article

Recently, aerial manipulations are becoming more and more important for the practical applications of unmanned aerial vehicles (UAV) to choose, transport, and place objects in global space. In this paper, an aerial manipulation system consisting of a UAV, two onboard cameras, and a multi-fingered robotic hand with proximity sensors is developed. To achieve self-contained autonomous navigation to a targeted object, onboard tracking and depth cameras are used to detect the targeted object and to control the UAV to reach the target object, even in a Global Positioning System-denied environment. The robotic hand can perform proximity sensor-based grasping stably for an object that is within a position error tolerance (a circle with a radius of 50 mm) from the center of the hand. Therefore, to successfully grasp the object, a requirement for the position error of the hand (=UAV) during hovering after reaching the targeted object should be less than the tolerance. To meet this requirement, an object detection algorithm to support accurate target localization by combining information from both cameras was developed. In addition, camera mount orientation and UAV attitude sampling rate were determined by experiments, and it is confirmed that these implementations improved the UAV position error to within the grasping tolerance of the robot hand. Finally, the experiments on aerial manipulations using the developed system demonstrated the successful grasping of the targeted object. Full article

In order to contribute to the operation of unmanned aerial vehicles (UAVs) according to visual flight rules (VFR), this article proposes a monocular approach for cloud detection using an electro-optical sensor. Cloud avoidance is motivated by several factors, including improving visibility for collision prevention and reducing the risks of icing and turbulence. The described workflow is based on parallelized detection, tracking and triangulation of features with prior segmentation of clouds in the image. As output, the system generates a cloud occupancy grid of the aircraft’s vicinity, which can be used for cloud avoidance calculations afterwards. The proposed methodology was tested in simulation and flight experiments. With the aim of developing cloud segmentation methods, datasets were created, one of which was made publicly available and features 5488 labeled, augmented cloud images from a real flight experiment. The trained segmentation models based on the YOLOv8 framework are able to separate clouds from the background even under challenging environmental conditions. For a performance analysis of the subsequent cloud position estimation stage, calculated and actual cloud positions are compared and feature evaluation metrics are applied. The investigations demonstrate the functionality of the approach, even if challenges become apparent under real flight conditions. Full article

The development of reliable gas sensors is very important in many fields such as safety, environment, and agriculture, and is especially essential for industrial waste and air pollution monitoring. As the performance of mobile platforms equipped with sensors such as smartphones and drones and the technologies supporting them (wireless communication, battery performance, data processing technology, etc.) are spreading and improving, a lot of efforts are being made to perform these tasks by using portable systems such as smartphones or installing them on unmanned wireless platforms such as drones. For example, research is continuously being conducted on chemical sensors for field monitoring using smartphones and rapid monitoring of air pollution using unmanned aerial vehicles (UAVs). In this paper, we review the measurement results of various chemical sensors available on mobile platforms including drones and smartphones, and the analysis of detection results using machine learning. This topic covers a wide range of specialized fields such as materials engineering, aerospace engineering, physics, chemistry, environmental engineering, electrical engineering, and machine learning, and it is difficult for experts in one field to grasp the entire content. Therefore, we have explained various concepts with relatively simple pictures so that experts in various fields can comprehensively understand the overall topics. Full article

Thermal imaging drones have transformed wildlife monitoring by facilitating the efficient and noninvasive monitoring of animal populations across large areas. In this study, an optimized flight path design was developed for monitoring wildlife on Guleopdo Island, South Korea using the DJI Mavic 3T drone equipped with a thermal camera. We employed a strata-based sampling technique to reclassify topographical and land cover information, creating an optimal survey plan. Using sampling strata, key waypoints were derived, on the basis of which nine flight paths were designed to cover ~50% of the study area. The results demonstrated that an optimized flight path improved the accuracy of detecting Formosan sika deer (Cervus nippon taiouanus). Population estimates indicated at least 128 Formosan sika deer, with higher detection efficiency observed during cloudy weather. Customizing flight paths based on the habitat characteristics proved crucial for efficient monitoring. This study highlights the potential of thermal imaging drones for accurately estimating wildlife populations and supporting conservation efforts. Full article

Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data of precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features for ML model training comprise spectral, structural, and texture feature types generated from multispectral orthomosaics (spectral features), Digital Terrain and Surface Models (DTM/DSM- structural features), and Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). The specific features were selected based on extensive literature research, including especially the fields of precision agri- and viticulture. To integrate only vine canopy-exclusive features into ML classifications, different feature types were extracted and spatially aggregated (zonal statistics), based on a combined pixel- and object-based image-segmentation-technique-created vine row mask around each single grapevine position. The extracted canopy features were progressively grouped into seven input feature groups for model training. Model overall performance metrics were optimized with grid search-based hyperparameter tuning and repeated-k-fold-cross-validation. Finally, ML-based growth class prediction results were extensively discussed and evaluated for overall (accuracy, f1-weighted) and growth class specific- classification metrics (accuracy, user- and producer accuracy). Full article

The collection and real-time transmission of emergency environmental information are crucial for rapidly assessing the on-site situation of sudden disasters and responding promptly. However, the acquisition of emergency environmental information, particularly its seamless transmission, faces significant challenges under complex terrain and limited ground communication. This paper utilizes sensors, line-of-sight communication with unmanned aerial vehicles (UAVs), and LoRa long-distance communication to establish an integrated emergency environmental monitoring system that combines real-time monitoring, UAV-mounted LoRa gateway relaying, and backend data analysis. This system achieves real-time acquisition, seamless transmission, storage management, and visualization of environmental emergency information. First, a portable emergency environmental monitoring device was developed to collect and transmit environmental factor data. Second, a UAV-mounted LoRa gateway was designed to extend the data transmission coverage, ensuring seamless communication. Finally, multiple field experiments were conducted to evaluate the system’s performance. The experimental results indicate that the system possesses reliable capabilities for emergency data collection and transmission in complex environments, providing new technical solutions and practical support for developing and applying emergency environmental monitoring systems. Full article

Sensor selection is a vital part of Wireless Sensor Network (WSN) management. This becomes of increased importance when considering the use of low-cost, bearing-only sensor nodes for the tracking of Unmanned Aerial Vehicles (UAVs). However, traditional techniques commonly form excessively large sensor clusters, which result in the collection of redundant information, which can deteriorate performance while also increasing the associated network costs. Therefore, this work combines a predictive posterior distribution methodology with a novel simplified objective function for optimally identifying and forming smaller sensor clusters before activation and measurement collection. The goal of the proposed objective function is to reduce network communication and computation costs while still maintaining the tracking performance of using far more sensors. The developed optimisation algorithm results in reducing the size of selected sensor clusters by an average of 50% while still maintaining the tracking performance of general traditional techniques. Full article

Unmanned aerial vehicle (UAV)-based wireless sensor networks (WSNs) hold great promise for supporting ground-based sensors due to the mobility of UAVs and the ease of establishing line-of-sight links. UAV-based WSNs equipped with mobile edge computing (MEC) servers effectively mitigate challenges associated with long-distance transmission and the limited coverage of edge base stations (BSs), emerging as a powerful paradigm for both communication and computing services. Furthermore, incorporating simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) as passive relays significantly enhances the propagation environment and service quality of UAV-based WSNs. However, most existing studies place STAR-RISs in fixed positions, ignoring the flexibility of STAR-RISs. Some other studies equip UAVs with STAR-RISs, and UAVs act as flight carriers, ignoring the computing and caching capabilities of UAVs. To address these limitations, we propose an energy-efficient aerial STAR-RIS-aided computing offloading and content caching framework, where we formulate an energy consumption minimization problem to jointly optimize content caching decisions, computing offloading decisions, UAV hovering positions, and STAR-RIS passive beamforming. Given the non-convex nature of this problem, we decompose it into a content caching decision subproblem, a computing offloading decision subproblem, a hovering position subproblem, and a STAR-RIS resource allocation subproblem. We propose a deep reinforcement learning (DRL)–successive convex approximation (SCA) combined algorithm to iteratively achieve near-optimal solutions with low complexity. The numerical results demonstrate that the proposed framework effectively utilizes resources in UAV-based WSNs and significantly reduces overall system energy consumption. Full article

Improvements in the navigation systems incorporated into unmanned aerial vehicles (UAVs) and new sensors are improving the quality of 3D mapping results. In this study, two flights were compared over the archaeological remains of the castle of Almenara, situated in Cuenca, Spain. We performed one with a DJI Phantom 4 (DJI Innovations Co., Ltd., Shenzhen, China) and the other with a Matrice 300 RTK (DJI Innovations Co., Ltd., Shenzhen, China) and the new Zenmuse P1 camera (45 mp, RGB sensor). With the help of the new software incorporated into the Zenmuse P1 camera gimbal, we could significantly reduce the flight time. We analysed the data obtained with these two UAVs and the built-in RGB sensors, comparing the flight time, the point cloud, and its resolution and obtaining a three-dimensional reconstruction of the castle. We describe the work and the flights carried out, depending on the type of UAV and its RTK positioning system. The improvement in the positioning system provides improvements in flight accuracy and data acquisition. We compared the results obtained in similar studies, and thanks to the advances in UAVs and their sensors with better resolution, we managed to reduce the data collection time and obtained 3D models with the same results as those from other types of sensors. The accuracies obtained with the RTK and the P1 camera are very high. The volumes calculated for a future archaeological excavation are precise, and the 3D models obtained by these means are excellent for the preservation of the cultural asset. These models can have various uses, such as the preservation of an asset of cultural interest, or even its dissemination and analysis in various studies. We propose to use this technology for similar studies of archaeological documentation and the three-dimensional reconstruction and visualisation of cultural heritage in virtual visits on the web. Full article