Search

TUnmanned Aerial Systems (UAS), despite their relative novelty, are already an integral component of the general aviation structure, and, based on a number of complex and sophisticated solutions, including those related to artificial intelligence, are part of the spectrum of high technologies. UAS find application not only in the sphere of commerce, but also in the realisation of specific tasks of public administration, such as territory management, healthcare, emergency prevention and elimination, ensuring environmental safety and law and order, nature management. The purpose of the study, the results of which are presented in this publication, is to assess the current state and potential of the use of UAS in these areas based on a review of literature sources on the practice of their application in order to solve the tasks of public administration in different countries of the world. The main conclusion drawn from the analysis and characterising the general scientific novelty of the study is that, despite a significant number of specific examples, the breadth of UAS use range can be characterised as imaginary. The main and the only really significant application is various types of aerial survey in the interests of state control and supervision bodies. In the course of the work, a number of promising directions for the use of UAS have been identified. It is also noted that their wider implementation in the practice of public administration is hindered by the lack and/or imperfection of the relevant legal framework, typical for most legislative systems of the world, and postulates the need to actively address these issues in relation to the classification and certification of UAS, requirements for their operators and software, the procedure and rules of operation, the integration of unmanned aircraft (UAS) into the existing air traffic management system.

Forage yield estimates provide relevant information to manage and quantify ecosystem services in grasslands. We fitted and validated prediction models of forage yield for several prominent grasses used in restoration projects in semiarid areas. We used field forage harvests from three different sites in Northern Utah and Southern California, USA, in conjunction with multispectral, high-resolution UAV imagery. Different model structures were tested with simple models using a unique predictor, the forage volumetric 3D space, and more complex models, where RGB, red edge, and near-infrared spectral bands and associated vegetation indices were used as predictors. We found that for most dense canopy grasses, using a simple linear model structure could explain most (R2 0.7) of the variability of the response variable. This was not the case for sparse canopy grasses, where a full multispectral dataset and a non-parametric model approach (random forest) were required to obtain a maximum R2 of 0.53. We developed transparent protocols to model forage yield where, in most circumstances, acceptable results could be obtained with affordable RGB sensors and UAV platforms. This is important as users can obtain rapid estimates with inexpensive sensors for most of the grasses included in this study.

The production of Explorer roses has historically been attractive due to the acceptance of the product around the world. This species of roses presents high sensitivity to physical contact and manipulation, creating a challenge to keep the final product quality after cultivation. In this work, we present a system that combines the capabilities of intelligent computer vision and unmanned aerial vehicles (UAVs) to identify the state of roses ready for cultivation. The system uses a deep learning-based approach to estimate Explorer rose crop yields by identifying open and closed rosebuds in the field using videos captured by UAVs. The methodology employs YOLO version 5, along with DeepSORT algorithms and a Kalman filter, to enhance counting precision. The evaluation of the system gave a mean average precision (mAP) of 94.1% on the test dataset, and the rosebud counting results obtained through this technique exhibited a strong correlation (R2 = 0.998) with manual counting. This high accuracy allows one to minimize the manipulation and times used for the tracking and cultivation process.

Modern neural network technologies are actively used for Unmanned Aerial Vehicles (UAVs). Convolutional Neural Networks (CNN), are mostly used for object detection, classification, and tracking tasks, for example, for such objects as fires, deforestations, buildings, cars, or people. However, to improve effectiveness of CNNs it is necessary to perform their fine-tuning on new flight data periodically. Such training data should be labeled, which increases total CNN finetuning time. Nowadays, the common approach to decrease labeling time is to apply auto-labeling and labeled objects tracking. These approaches are not effective enough for labeling of 8 hours’ huge aerial sensed datasets that are common for long-endurance USVs. Thus, reducing data labeling time is an actual task nowadays. In this research, we propose a fast aerial data labeling pipeline especially for videos gathered by long-endurance UAVs cameras. The standard labeling pipeline was supplemented with several steps such as overlapped frames pruning, final labeling spreading over video frames. The other additional step is to calculate a Potential Information Value (PIV) for each frame as a cumulative estimation of frame anomality, frame quality, and auto-detected objects. Calculated PIVs are used than to sort out frames. As a result, an operator who labels video gets informative frames at the very beginning of the labeling process. The effectiveness of proposed approach was estimated on collected datasets of aerial sensed videos obtained by longendurance UAVs. It was shown that it is possible to decrease labeling time by 50 % in average in comparison with other modern labeling tools. The percentage of average number of labeled objects was 80 %, with them being labeled for 40 % of total pre-ranged frames. Proposed approach allows us to decrease labeling time for a new long-endurance flight video data significantly. This makes it possible to speed up neural network fine-tuning process. As a result, it became possible to label new data during the inter-flight time that usually takes about two or three hours and is too short for other labeling instruments. Proposed approach is recommended to decrease UAVs operators working time and labeled dataset creating time that could positively influence on the time necessary for the fine-tuning a new effective CNN models.

The article considers the problematic issues caused by the current circumstances, when the country is in a special legal regime of martial law and the importance and relevance of using an unmanned aerial vehicle (UAV) for reconnaissance of objects by the police on the ground are extremely high. The article analyses the effectiveness of different types of camouflage in countering reconnaissance using UAVs in different terrain; the optimal camera angle and the optimal flight altitude of UAVs for effective counteraction to the camouflage properties of the respective camouflage in different terrain are determined. Not only military camouflage, but also police uniforms are considered, which expands the scope of UAVs and makes the study more comprehensive. The study of the reconnaissance methodology using UAVs will allow the police to adapt quickly and effectively to new circumstances, as well as help optimise the performance of their combat missions. The effectiveness of the methodology of object reconnaissance on the ground in real scenarios is evaluated. Recommendations for improving the conduct of such operations as monitoring of mass disorders, rapid response to hazards, factors, etc. are provided. In developing the methodology for determining the optimal distance, the psychophysiological aspects of UAV operators are taken into account for the first time and the determination of optimal distances for effective detection and identification of objects is proposed.

• Synergistic use of drone, satellite, and machine learning technologies improves LAI estimation. • Robust validation and advanced performance metrics confirm model accuracy and precision. • Utilizing Vegetation Indices to enhance the precision of LAI quantification. In this study, we conducted a comprehensive assessment of Leaf Area Index (LAI) estimation using three distinct sources of satellite data: Sentinel-2 imagery, drone imagery (UAVs), and Mohammed VI satellite data. The main objective was to identify the most reliable and precise dataset for predicting LAI, with a focus on evaluating the performance of Random Forest models. For Sentinel-2 imagery, our Random Forest model achieves a robust R-squared (R2) value of 0.89, signifying a strong alignment between predicted and measured LAI values. The associated root-mean-square error (RMSE) is 0.4, indicating high predictive accuracy. In the context of UAVs, our Random Forest model excels, exhibiting an impressive R2 value of 0.93, highlighting a substantial correlation between predicted and measured LAI. The RMSE for drone imagery stands at 0.37, showcasing exceptional predictive accuracy. Finally, the Random Forest model trained on Mohammed VI satellite data yields an R2 value of 0.92, underlining its strong fit with measured LAI values. The RMSE for Mohammed VI imagery is 0.39, further underscoring the model's exceptional predictive accuracy. This comparative analysis underscores the importance of selecting the most suitable satellite data source for LAI estimation in Argania spinosa. UAV imagery emerges as the most accurate choice, closely followed by Mohammed VI Satellite and Sentinel-2 imagery. These findings offer valuable insights for effective monitoring of Argania spinosa and advancing sustainable land management practices in rural ecosystems. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles gained significant popularity in the last decade as demonstrated by their wide usage in various fields. From around the year 2001, the usage of unmanned aerial vehicles' technology was mainly confined to law enforcement agencies such as the military, police, and customs. In the contemporary, terrorists have also been observed to be using unmanned aerial vehicles to attack aviation facilities. The current paper examines the levels of vulnerability of the Namibian airports to possible intrusion and attack from unmanned aerial vehicles, a situation that could pose a serious threat to aviation and national security. Adopting a qualitative research approach, the study made use of a questionnaire and semi-structured interview guide to collect primary data from the participants. Microsoft Excel was used to analyse the data. The study establishes that Namibian airports are prone to attacks from unmanned aerial vehicles as there are no anti-unmanned aerial vehicle detection systems installed at all airports in the country. Thus, there is clear evidence that the Namibia Civil Aviation Authority and the Namibian Airport Company's regulations and policies on aviation safety and security did not prioritise the installation of anti-unmanned aerial vehicle detection systems at all airports in Namibia. The paper suggests that, in order to enhance aviation safety and security, a joint civil/military Information Technology Unit, responsible for spoofing, detection, and the monitoring of illicit unmanned aerial vehicle operations should be set up and operations activated at all airports and other public infrastructures in Namibia. [ABSTRACT FROM AUTHOR]

Drones offer significant safety and security advantages by enhancing situational awareness across various fields. However, realizing these benefits hinges on well-designed drone systems. This study builds upon previous research on drone deployment challenges and proposes the Drone Safety and Security Surveillance System (D4S). D4S aims to standardize similar drone-based systems, enhancing situational awareness and supporting decision-making processes. While initially tailored for safety and security, D4S holds potential for broader applications. Two system architectures have been proposed and evaluated with positive feedback from safety and security professionals. D4S has the potential to revolutionize safety practices, improve situational awareness, and facilitate timely decision making in critical scenarios. [ABSTRACT FROM AUTHOR]

Summary: Flying ad hoc network (FANET) comprising unmanned aerial vehicles (UAVs) emerges as a promising solution for numerous military and civil applications. Transferring data collected from the environment to the ground station (GS) is a primary concern for meeting the communication demands of most of these applications. However, the highly mobile UAVs with limited communication range, resulting in frequent topology change and intermittent connectivity, make data routing challenging. In such scenarios, geographic routing is a viable solution due to its scalability and robustness. However, the basic forwarding mechanism of geographic routing favors the neighboring UAV nearest to the destination, impacted substantially by link failures and routing holes in a dynamic environment. Additionally, routing decisions ignoring the current load over UAVs contribute to performance degradation due to the high concentration of data traffic near the GS. Thus, to address these issues, a geographic routing protocol named MF‐DLB comprising multimetric forwarding (MF) and a directed acyclic graph‐based load balancing (DLB) scheme is proposed to enhance packet forwarding in FANETs. MF takes account of multiple metrics related to connectivity, geographic progress, link lifetime, and residual energy to select the next hop with a stable communication link while effectively bypassing the routing holes. The second scheme, DLB, focuses on proactively maintaining routing paths near GS for load distribution among underutilized nodes to address the congestion problem. Simulations performed in network simulator ns‐3 confirm the outperformance of MF‐DLB over other related routing schemes in terms of different performance metrics. [ABSTRACT FROM AUTHOR]

This paper proposes a workflow to assess the uncertainty of the Normalized Difference Vegetation Index (NDVI), a critical index used in precision agriculture to determine plant health. From a metrological perspective, it is crucial to evaluate the quality of vegetation indices, which are usually obtained by processing multispectral images for measuring vegetation, soil, and environmental parameters. For this reason, it is important to assess how the NVDI measurement is affected by the camera characteristics, light environmental conditions, as well as atmospheric and seasonal/weather conditions. The proposed study investigates the impact of atmospheric conditions on solar irradiation and vegetation reflection captured by a multispectral UAV camera in the red and near-infrared bands and the variation of the nominal wavelengths of the camera in these bands. Specifically, the study examines the influence of atmospheric conditions in three scenarios: dry–clear, humid–hazy, and a combination of both. Furthermore, this investigation takes into account solar irradiance variability and the signal-to-noise ratio (SNR) of the camera. Through Monte Carlo simulations, a sensitivity analysis is carried out against each of the above-mentioned uncertainty sources and their combination. The obtained results demonstrate that the main contributors to the NVDI uncertainty are the atmospheric conditions, the nominal wavelength tolerance of the camera, and the variability of the NDVI values within the considered leaf conditions (dry and fresh). [ABSTRACT FROM AUTHOR]

This paper proposes a novel free-weighting matrix (FWM) approach for the event-triggered (ET) consensus and formation control of multi-agent systems over a directed graph. A new FWM equality for the consensus error is proposed. This FWM is applied to attain coherent behavior of systems via a fully distributed ET approach. The proposed approach is also extended for ET formation control to attain a specific pattern of agents. Furthermore, an FWM-based consensus controller design with practical ET cooperative control is considered to address consensus and formation control problems by using the in-degree information of a node rather than the algebraic connectivity of a graph or adaptation of parameters. Additionally, the controller gain is formulated using a more general transformation compared to that used in classical approaches. Moreover, the proposed ET scheme for the designed controller is applied on the transmission side to preserve computational resources by eliminating the Zeno behavior. In contrast to the existing methods, the proposed approach (i) provides a fully distributed protocol without using central information of network or adaptive gain; (ii) provides a practical ET mechanism to assure effective bandwidth and fewer energy consumption; and (iii) can be applied to the ET formation problem for mobile agents. Simulations involving six aerial vehicles are performed to demonstrate the efficacy of the proposed cooperative control strategy. [ABSTRACT FROM AUTHOR]

In this paper, we present a study investigating the impact of jamming in a Dual-Hop free-space optical (FSO) communication system assisted by reconfigurable intelligent surfaces (RIS) in the presence of a malicious jammer. We analyze the combined effects of atmospheric turbulence (AT), pointing error (PE), and angle of arrival (AoA) fluctuation of unmanned aerial vehicles (UAVs). Closed-form expressions for the overall average bit error rate (ABER) are derived while considering these impairments. To mitigate the jamming effect, we explore a Single-Input Multiple-Output (SIMO) FSO system and derive the end-to-end Average Bit Error Rate (ABER) under various jamming scenarios. Additionally, we conduct a comprehensive study by examining different placements of the malicious UAV jammer and RIS, drawing insightful conclusions on system performance. The analytically derived expressions are validated through Monte Carlo simulations. [ABSTRACT FROM AUTHOR]

Drones represent a significant technological shift at the convergence of on-demand cyber-physical systems and edge intelligence. However, realizing their full potential necessitates managing the limited energy resources carefully. Prior work looks at factors such as battery characteristics, intelligent edge sensing considerations, planning, and robustness in isolation. But a global view of energy awareness that considers these factors and looks at various tradeoffs is essential. To this end, we present results from our detailed empirical study of battery charge-discharge characteristics and the impact of altitude and lighting on edge inference accuracy. Our energy models, derived from these observations, predict energy usage while performing various manoeuvres with an error of 5.6%, a 2.5X improvement over the state-of-the-art. Furthermore, we propose a holistic energy-aware multi-drone scheduling system that decreases the energy consumed by 21.14% and the mission times by 46.91% over state-of-the-art baselines. To achieve system robustness in the event of link or drone failure, we observe trends in Packet Delivery Ratio to propose a methodology to establish reliable communication between nodes. We release an open-source implementation of our system. Finally, we tie all of these pieces together using a people-counting case study. [ABSTRACT FROM AUTHOR]

In the context of climate change, vineyard monitoring to better understand spatiotemporal patterns of grapevine development is of utter importance for precision viticulture. We present a time series analysis of hyperspectral in situ and multispectral UAV data for different irrigation systems in Lower Franconia and correlate results with sensor data for soil moisture, temperature, and precipitation. Analysis of Variance (ANOVA) and a Tukey's HSD test were performed to see whether Vegetation Indices (VIs) are significantly different with respect to irrigation systems as well as topographic position in the vineyard. Correlation between in situ measurements and UAV data for selected VIs is also investigated for upscaling analysis. We find significant differences with respect to irrigation, as well as for topographic position for most of the VIs investigated, highlighting the importance of adapted water management. Correlation between in situ and UAV data is significant only for some indices (NDVI and CIRedEdge, r 2 of 0.33 and 0.49, respectively), while shallow soil moisture patterns correlate well with in situ-derived VIs such as the CIRedEdge and RG index ( r 2 of 0.34 and 0.46). [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) equipped with remote-sensing object-detection devices are increasingly employed across diverse domains. However, the detection of small, densely-packed objects against complex backgrounds and at various scales presents a formidable challenge to conventional detection algorithms, exacerbated by the computational constraints of UAV-embedded systems that necessitate a delicate balance between detection speed and accuracy. To address these issues, this paper proposes the Efficient Multidimensional Global Feature Adaptive Fusion Network (MGFAFNET), an innovative detection method for UAV platforms. The novelties of our approach are threefold: Firstly, we introduce the Dual-Branch Multidimensional Aggregation Backbone Network (DBMA), an efficient architectural innovation that captures multidimensional global spatial interactions, significantly enhancing feature distinguishability for complex and occluded targets. Simultaneously, it reduces the computational burden typically associated with processing high-resolution imagery. Secondly, we construct the Dynamic Spatial Perception Feature Fusion Network (DSPF), which is tailored specifically to accommodate the notable scale variances encountered during UAV operation. By implementing a multi-layer dynamic spatial fusion coupled with feature-refinement modules, the network adeptly minimizes informational redundancy, leading to more efficient feature representation. Finally, our novel Localized Compensation Dual-Mask Distillation (LCDD) strategy is devised to adeptly translate the rich local and global features from the higher-capacity teacher network to the more resource-constrained student network, capturing both low-level spatial details and high-level semantic cues with unprecedented efficacy. The practicability and superior performance of our MGFAFNET are corroborated by a dedicated UAV detection platform, showcasing remarkable improvements over state-of-the-art object-detection methods, as demonstrated by rigorous evaluations conducted using the VisDrone2021 benchmark and a meticulously assembled proprietary dataset. [ABSTRACT FROM AUTHOR]

Visual impact is defined as the modification of a visual resource of the landscape, generating an effect on the perception of potential observers. This effect is evaluated using the value of the landscape that has not been altered or destroyed (visual quality of the landscape), as is the case with building projects that generate visible changes in residential areas. Numerous authors have developed methodologies to evaluate visual intrusion; however, deficiencies exist, such as the predominance of subjectivity in procedures and the lack of evaluations for buildings. Therefore, this paper proposes a methodology to evaluate and quantify the visual impact of a new building in a high population density environment. This research is divided into a description of the basic methodology, the proposal of the methodology to capture and process photographs and information, and the application of a case study of a high-rise building in a sector of Valparaíso, Chile. The main contribution of this work is the delivery of a methodological proposal that allows the evaluation and quantification of the visual quality before and after the new structure to complement structural and urban design. [ABSTRACT FROM AUTHOR]

Recently, the unmanned aerial vehicle (UAV)-assisted edge computing is proposed to improve the quality of service in some scenarios within sparse or unavailable base stations (BSs). Meanwhile, the caching technology is adopted to reduce the wireless traffic load and the data transmission delay. However, due to the limited storage capacity of edge nodes, the edge nodes cannot store all of the contents required by user equipment (UE). So, how to select the reasonable contents for caching on edge nodes to reduce the content delivery delay becomes a challenge in the UAV-assisted edge computing environment. In this paper, the Dijkstra algorithm based cooperative caching strategy for UAV-assisted edge computing system is proposed. Specially, the content transmission delay between two nodes is computed. Then, for each requested content, the weighted edge-undirected graph (WEUG), in which one vertex represents one node, is built. Furthermore, Dijkstra algorithm is adopted to achieve the minimal content transmission delay from the edge node caching the requested content to UE. Finally, the optimization problem of content caching is built, and the corresponding cache strategy is achieved by solving the optimization problem. The experimental results imply that the proposed cooperative caching algorithm can achieve better performance on the average content transmission delay, the average cache hit rate, and the total of hops, respectively, comparing with the benchmark algorithms. [ABSTRACT FROM AUTHOR]

In modern and future communication systems, we expect peaks of traffic that largely exceed the capacity of the system, since they are originally designed to support normal traffic loads. Such peaks can be caused by emergency events and cultural or sporting gatherings, among others. Indeed, implementing more channels than the ones required in normal traffic conditions would entail higher costs and energy consumption. As such, when a traffic peak arrives, the system performance is greatly affected. To this end, we propose the use of mobile channels that assist cellular systems to increase the capacity of the network for a certain period. In this paper, we derive the blocking probability of a UAV (Unmanned Aerial Vehicle)-assisted cellular system to temporarily increase the capacity of the communication network in case of a traffic overload. The analysis presented in this work allows a careful design of future communication systems requiring fewer channels, that can serve users in normal traffic load conditions while using UAVs to maintain an adequate blocking probability when the traffic load increases. To this end, we develop the ErlangU formula, similar to the ErlangB formula for a conventional voice service cellular system. [ABSTRACT FROM AUTHOR]

Accurate and precise measures of channel morphology are important when monitoring a stream post-restoration to determine changes in stability, water quality, and aquatic habitat availability. Practitioners often rely on traditional surveying methods such as a total station for measuring channel metrics (e.g., cross-sectional area, width, depth, and slope). However, these methods have limitations in terms of coarse sampling densities and time-intensive field efforts. Drone-based lidar or drone laser scanning (DLS) provides much higher resolution point clouds and has the potential to improve post-restoration monitoring efforts. For this study, a 1.3-km reach of Stroubles Creek (Blacksburg, VA, USA), which underwent a restoration in 2010, was surveyed twice with a total station (2010 and 2021) and twice with DLS (2017 and 2021). The initial restoration was divided into three treatment reaches: T1 (livestock exclusion), T2 (livestock exclusion and bank treatment), and T3 (livestock exclusion, bank treatment, and inset floodplain). Cross-sectional channel morphology metrics were extracted from the 2021 DLS scan and compared to metrics calculated from the 2021 total station survey. DLS produced 6.5 times the number of cross sections over the study reach and 8.8 times the number of points per cross section compared to the total station. There was good agreement between the metrics derived from both surveying methods, such as channel width (R2 = 0.672) and cross-sectional area (R2 = 0.597). As a proof of concept to demonstrate the advantage of DLS over traditional surveying, 0.1 m digital terrain models (DTMs) were generated from the DLS data. Based on the drone lidar data, from 2017 to 2021, treatment reach T3 showed the most stability, in terms of the least change and variability in cross-sectional metrics as well as the least erosion area and volume per length of reach. [ABSTRACT FROM AUTHOR]

The objective of the undertaken research was to characterize and evaluate the impact of weather and lighting conditions on recording terrain anomalies in the photographs obtained during a UAV photogrammetric flight. The present work describes the use and capabilities of the UAV in the mapping of photo acquisition conditions similar to those performed during inspection flights with the use of a manned helicopter equipped with a hyperspectral camera, in the target range of visible light. The research was conducted in the southern part of Poland (between Gliwice and Katowice), where 7 routes were selected, differing from one another in terms of terrain anomalies (buildings, types of land areas, vehicles, vegetation). In the studies, which involved photogrammetric flights performed using a UAV, different seasons and times of day as well as changes in light intensity were taken into account. The flight specification was based on the main parameters with the following assumptions: taking only perpendicular (nadir) RGB photographs, flight altitude 120 m AGL, strip width 160 m, GSD =0.04 m and overlap ≥83%. The analysis of the photographic material obtained made it possible to correct the catalog of anomalies defined previously, since the recognition of some objects is very difficult, being usually below the orthophotomap resolution. When making and evaluating orthophotomaps, problems with mapping the shape of objects near the edges of the frame were found. When a 12 mm lens is used, these distortions are significant. It was decided that for the purpose of generating training data from orthophotomaps, only the fragments containing objects which shape would be mapped in accordance with the real one would be used. Thus, the effective width of orthophotomaps obtained from simulated flights will be approximately 100 m. [ABSTRACT FROM AUTHOR]

This paper addresses the intricate challenges of coastal management, particularly in rapidly forming tidal flats, emphasizing the need for innovative monitoring strategies. The dynamic coastal topography, exemplified by a newly formed tidal flat in Shanghai, underscores the urgency of advancements in coastal risk recognition. By utilizing a digital twin framework integrated with state-of-the-art unmanned aerial vehicles (UAVs), we systematically evaluate three configurations and identify the optimal setup incorporating real-time kinematics (RTK) and light detection and ranging (LiDAR). This UAV configuration excels in efficiently mapping the 3D coastal terrain. It has an error of less than 0.1 m when mapping mudflats at an altitude of 100 m. The integration of UAV data with a precise numerical ocean model forms the foundation of our dynamic risk assessment framework. The results showcase the transformative potential of the digital twin framework, providing unparalleled accuracy and efficiency in coastal risk recognition. Visualization through Unity Engine or Unreal Engine enhances accessibility, fostering community engagement and awareness. By predicting and simulating potential risks in real-time, this study offers a forward-thinking strategy for mitigating coastal dangers. This research not only contributes a comprehensive strategy for coastal risk management but also sets a precedent for the integration of cutting-edge technologies in safeguarding coastal ecosystems. The findings are significant in paving the way for a more resilient and sustainable approach to coastal management, addressing the evolving environmental pressures on our coastlines. [ABSTRACT FROM AUTHOR]

Telemetry has enabled ecologists to link animal movement trajectories and environmental features at a fine spatiotemporal resolution; however, the effects of social interactions on individual choice within large mobile groups remain largely unknown. Estimating the effect of social interaction in the wild remains challenging because existing long‐term tracking tools such as GPS collars focus on the movements of a single individual and cannot observe the behavior of other individuals within the group. The progression of socially informed movement models requires measuring simultaneous trajectories of many individuals at once, as well as the instantaneous social cues to which individuals may be responding. The availability of low‐flying unmanned aerial vehicles (UAVs) and low‐cost open‐source electronics presents a promising opportunity to collect fine‐scale data on social interactions in order to advance our understanding of collective behavior. Here, we present a tracking system that enables the repeated localization and observation of a collared individual and its near neighbors using nadir video footage collected from a commercial UAV. We make use of open‐source electronics combined with the UAV's in‐built functionality that allows it to follow a stream of GPS locations to create an automated system that can follow a specific individual without user control. We demonstrate the tracking systems' performance by studying the group movements of a herd of Exmoor ponies (Equus ferus caballus), and as a proof of concept, we examine the position of the focal individual (collared animal) in relation to the center of the video frame. We also collect information about the focal individual's nearest neighbors. The automated animal observation tool is effective at consistently keeping the focal individual close to the center of the video frame, offering a new dimension to existing remote telemetry tools. For instance, the repeated observation of the same individual in different physiological states, seasons, and demographic groups potentially opens new avenues in collective movement ecology research. By making our design, software, and firmware freely available, we aim to encourage continuous improvements to collective behavior research and to facilitate replicable approaches across other species and ecosystems. [ABSTRACT FROM AUTHOR]

This paper assesses evidence-based applications of Remote Sensing for Sustainable and Precision Agriculture in the Northern Savanna Regions of Ghana for three decades (1990–2023). During this period, there have been several government policy intervention schemes and pragmatic support actions from development agencies towards improving agriculture in this area with differing level of success. Over the same period, there have been dramatic advances in remote sensing (RS) technologies with tailored applications to sustainable agriculture globally. However, the extent to which intervention schemes have harnessed the incipient potential of RS for achieving sustainable agriculture in the study area is unknown. To the best of our knowledge, no previous study has investigated the synergy between agriculture policy interventions and applications of RS towards optimizing results. Thus, this study used systematic literature review and desk analysis to identify previous and current projects and studies that have applied RS tools and techniques to all aspects of agriculture in the study area. Databases searched include Web of Science, Google Scholar, Scopus, AoJ, and PubMed. To consolidate the gaps identified in the literature, ground-truthing was carried out. From the 26 focused publications found on the subject, only 13 (54%) were found employing RS in various aspects of agriculture observations in the study area. Out of the 13, 5 studies focused on mapping the extents of irrigation areas; 2 mapped the size of crop and pasturelands; 1 focused on soil water and nutrient retention; 1 study focused on crop health monitoring; and another focused on weeds/pest infestations and yield estimation in the study area. On the type of data, only 1 (7%) study used MODIS, 2 (15%) used ASTER image, 1 used Sentinel-2 data, 1 used Planetscope, 1 used IKONOS, 5 used Landsat images, 1 used Unmanned Aerial Vehicles (UAVs) and another 1 used RADAR for mapping and monitoring agriculture activities in the study area. There is no evidence of the use of LiDAR data in the area. These results validate the hypothesis that failing agriculture in the study area is due to a paucity of high-quality spatial data and monitoring to support informed farm decision-making. [ABSTRACT FROM AUTHOR]

The occurrence of surface strata movement in underground coal mining leads to the generation of numerous ground fissures, which not only damage the ecological environment but also disrupt building facilities, lead to airflow and easily trigger coal spontaneous combustion, induce geological disasters, posing a serious threat to people's lives, property, and mining production. Therefore, it is particularly important to quickly and accurately obtain the information of ground fissures and then study their distribution patterns and the law of spatial-temporal evolution. The traditional field investigation methods for identifying fissures have low efficiency. The rapid development of UAVs has brought an opportunity to address this issue. However, it also poses new questions, such as how to interpret numerous fissures and the distribution law of fissures with underground mining. Taking a mine in the Shenfu coalfield on the semi-desert aeolian sand surface as the research area, this paper studies the fissure recognition from UAV images by deep learning, fissure development law, as well as the mutual feed of surface condition corresponding to the under-ground mining progress. The results show that the DRs-UNet deep learning method can identify more than 85% of the fissures; however, due to the influence of seasonal vegetation changes and different fissure development stages, the continuity and integrity of fissure recognition methods need to be improved. Four fissure distribution patterns were found. In open-cut areas, arc-shaped fissures are frequently observed, displaying significant dimensions in terms of depth, length, and width. Within subsidence basins, central collapse areas exhibit fissures that form perpendicular to the direction of the working face. Along roadways, parallel or oblique fissures tend to develop at specific angles. In regions characterized by weak roof strata and depressed basins, abnormal reverse-"C"-shaped fissures emerge along the mining direction. The research results comprehensively demonstrate the process of automatically identifying ground fissures from UAV images as well as the spatial distribution patterns of fissures, which can provide technical support for the prediction of ground fissures, monitoring of geological hazards in mining areas, control of land environmental damage, and land ecological restoration. In the future, it is suggested that this method be applied to different mining areas and geotechnical contexts to enhance its applicability and effectiveness. [ABSTRACT FROM AUTHOR]

This article presents the design and modeling of a new aerial manipulator system, called Q-PRR, composed of three joints with a fixed base in the center of mass of the multirotor considered as a whole system. This structure has a prismatic joint as a first joint which allows to keep the center of gravity of the Q-PRR as close as possible to the center of gravity of the multirotor. This will also allow to reduce the influence of arm motion on the multirotor roll thus to ensure the stability of the system on trajectory tracking with dynamic changes in the multirotor's center of gravity. Furthermore, the configuration of the manipulator arm for the desired position of the end-effector given by the inverse kinematics model is kept without any change in the position and attitude of the multirotor. This article develops both forward and inverse kinematics models for a nonlinear underactuated system using the Denavit–Hartenberg notation. When a new algorithm is presented for the inverse kinematics based on Levenberg–Marquardt algorithm. Then, the dynamic model in the joint spaces is developed with the Lagrangian formalism. The Q-PRR is controlled using a model-free control with a comparison of two states, a free fly and disturbance forces applied to the whole system with manipulator arm movement. [ABSTRACT FROM AUTHOR]

Compared to terrestrial transportation systems, the expansion of urban traffic into airspace can not only mitigate traffic congestion, but also foster establish eco-friendly transportation networks. Additionally, unmanned aerial vehicle (UAV) task allocation and trajectory planning are essential research topics for an Urban Air Mobility (UAM) scenario. However, heterogeneous tasks, temporary flight restriction zones, physical buildings, and environment prerequisites put forward challenges for the research. In this paper, multigene and improved anti-collision RRT* (IAC-RRT*) algorithms are proposed to address the challenge of task allocation and path planning problems in UAM scenarios by tailoring the chance of crossover and mutation. It is proved that multigene and IAC-RRT* algorithms can effectively minimize energy consumption and tasks' completion duration of UAVs. Simulation results demonstrate that the strategy of this work surpasses traditional optimization algorithms, i.e., RRT algorithm and gene algorithm, in terms of numerical stability and convergence speed. [ABSTRACT FROM AUTHOR]

Mistletoe detection and sampling remain challenging for arborists, dendrologists, forest ecologists, and other specialists because of the limited access to host tree canopy. In this review, smart solutions for mistletoe detection based on airborne platforms are discussed. Airborne remote sensing (ARS) has the developing potential to provide rapid, accurate, and cost-efficient detection and research of mistletoe on tree level and large areas within the complex terrain. Herein, such mistletoe ARS research methods as image spectroscopy, infrared thermography, light detection and ranging, and structure from motion are overviewed. [ABSTRACT FROM AUTHOR]

Copyright of Arab Journal for Scientific Publishing is the property of Research & Development of Human Recourses Center (REMAH) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, aquaculture has seen tremendous growth worldwide due to technological advancements, leading to research and development of various innovations. Aquaculture farmers prioritise early diagnosis for timely treatment to achieve better productive and economic performance. Aquatic animal health experts still employ traditional diagnostic methods using visual diagnosis, cell culture, media culture, histopathology and serology. However, the developments of technologies in aquamedicine, such as sequencing, biosensors and CRISPR, have enabled rapid disease detection within minutes. Furthermore, integrating sensors, drones, artificial intelligence and the internet in aquaculture farm monitoring has helped farmers take decisive actions to improve production. Advancements in diagnostic techniques have significantly enhanced the efficient detection of bacterial, viral, parasitic and fungal diseases in aquatic animals. Moreover, monitoring water quality, aquatic animal health and animal behaviour on farms has become exceptionally streamlined with cutting‐edge tools like drones, sensors and artificial intelligence. Summarising research and development in aquatic animal health and monitoring aids efficient technology adoption in aquaculture. With these advanced technologies' continued development and adoption in developed countries, the aquaculture industry is experiencing growth and increased efficiency, benefiting farmers and consumers in these regions. However, farmers and educators in developing countries lack information about these technologies. Training of agricultural educators and efficient dissemination of knowledge and technologies through advertising and publication in collaboration with companies is essential. This review delves into emerging technologies capable of replacing the conventional diagnostic and monitoring methods utilised in aquaculture. We also explore their strengths, limitations and potential future applications within aquaculture settings. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Forestry Society of Croatia / Sumarski List Hrvatskoga Sumarskoga Drustva is the property of Forestry Society of Croatia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The purpose of the article is to assess the current state of the unmanned aerial vehicles market in the world, to review the classifications of unmanned aerial vehicles by type of construction, size, purpose, range, and to forecast trends in the development of their use in various fields of activity. Based on the analysis of the use of modern technologies for the production and transportation of goods, the author proposes to investigate the logistical possibilities of using unmanned aerial vehicles (hereinafter – UAVs) as delivery vehicles, including their technical and technological capabilities in the analysis. Based on the study of the drone market, taking into account the existing limitations and prospects for the development of the UAV market, the authors of the article aim to develop technological recommendations to ensure promptness in time, efficiency in terms of cost of delivery of the required goods. The logistics component of the study involves building consistent chains of interaction between market participants of this service in time, delivery method and payment sequence, depending on the stage and status of delivery of goods. The study also aims to develop recommendations to improve the efficiency and safety of UAV delivery, and to generalize the advantages of delivering goods by drones over similar consumer actions by purchasing them themselves in a retail network or on the manufacturer's field using their own vehicles. It is also necessary to evaluate the advantages and disadvantages of delivering food products using UAVs in terms of their safety during transportation and to identify areas for further research and development to improve the safety and reliability of UAVs. Methodology. The study uses a monographic method of researching scientific knowledge based on analysis and synthesis. The use of traditional economic methods of systemic and comparative analysis made it possible to structure the objects of research according to their existing characteristics. The review of scientific publications, technical reports, patents and other sources of information allowed the authors of the article, as economists, to draw certain technical conclusions on UAVs, and on the basis of their basic conclusions, to draw conclusions regarding the safety, reliability and efficiency of using drones to provide food services to consumers. Research results. The authors propose the scientific idea of further studying the technical, technological, socio-economic components of the use of drones for further experiments and development of improved new approaches to such services. Thus, the use of a systematic, comprehensive methodological approach will allow us to obtain a comprehensive picture of the effectiveness and safety of UAVs for food delivery. Practical implications. The use of UAVs in the delivery of food and agricultural products has the potential to significantly change the logistics industry by providing fast, reliable and environmentally friendly solutions for the delivery of goods. Value/originality. Based on the study, the authors formulate conclusions and recommendations that may also be useful in developing programs and measures to counter climate challenges and aimed at sustainable development of the agro-industrial complex of Ukraine in peacetime.

The advancement technology of artificial intelligence and e-commerce has increased and this has called for new ways to improve last-mile transportation, which is regarded as an essential part of the logistics value chain, especially in smart logistics. This paper addresses the problem of developing effective routes for autonomous drones in last-mile logistics using deep Q-learning. This paper aims to improve the process of delivery by utilizing the flexibility and intelligence of self-driven autonomous drones in smart logistics transportation. The key challenge for the effective provision of last-mile delivery services remains the decision on the routing of many aerial drones in an indoor urban environment, concerning the restrictions of a time window for delivery, energy consumption and traffic. This paper implements a deep Q-learning paradigm that allows drones to relearn their flight paths and delivery strategy during the lifecycle, thereby reducing the cost in the long run while using the costing strategies as part of the re-engineering process. The approach has been validated through extensive experimentation and simulations. Results obtained indicate that the delivery drones modified for the study attained the designed requirements of deep Q-learning, including optimal navigation and performance that attained 12.8% shorter delivery time, an increase in energy efficiency by 8.4%, and a route quality improvement of 20.1%. Furthermore, highlights the performance of the system in various situations where deep Q-learning and standard routing approaches are compared. This paper not only aids in the minimization of the last-mile delivery constraint by the use of shipping drones but also emphasizes the capacities of reinforcement learning strategies such as deep Q-learning in tackling the routing problems in smart logistics systems. At last, it advocates carrying on deeper into the application of reinforcement learning in the solving of complex optimization problems in various other fields.

The emergence of maize tassels is the turning of vegetative stage to reproductive stage of maize (Zea mays L.), which is critical for estimating maize grain yields. Recent advances in unmanned aerial vehicles (UAVs) remote sensing and deep learning-based object detection technique have provided a new approach for detecting maize tassels. Meanwhile, there still exists challenges for accurate detection due to the uncertainties in the complex field environment. The existing object detection networks fall in accurately detecting overlapping or small-scale maize tassels, as well as exhibiting insufficient detection capability in strong lighting conditions. Furthermore, the current dataset exhibits a limited temporal scope, unable to encompass the whole tasseling progress. In this study, we proposed FMTS dataset, designed a novel approach called RESAM-YOLOv8n (Residual Spatial Attention Module-You Only Look Once v8n), introducing the RESAM module and training the network with larger input image sizes. These enabled RESAM-YOLOv8n to focus on important tassel features and neglect irrelevant information, thereby enhancing its detection capability. The RESAM-YOLOv8n network was trained and evaluated using FMTS dataset, the mAP0.5, mAP0.75, Recall, Precision, and F1 of the network were 95.74 %, 66.70 %, 89.28 %, 95.59 %, and 92.00 %, respectively. Furthermore, in counting the number of maize tassels, the R2 value between the network’s detection and the ground truth reached 0.976, with a low RMSE of 1.56 tassels. The results showed the better performance of the RESAM-YOLOv8n network, providing an effective method for accurately identifying the maize tassels.

Considering the rapid time-varying channel conditions and large Doppler frequency fluctuations caused by high-speed movement of unmanned aerial vehicles, this paper proposes a non-stationary channel emulation scheme for Unmanned Aerial Vehicles(UAVs) using a field-programmable gate array platform. The proposed scheme adopts the sum of frequency modulation method to generate non-stationary channel fading and proposes a real-time algorithm for generating channel parameters to improve the real-time performance of channel emulation and ensure the real-time updating of channel status. In addition, to address the issue of power random fluctuation caused by large Doppler frequency fluctuations, this paper designs an adaptive power equalization module that ensures the stability of fading power by limiting the maximum fluctuation to only 1.13%. Finally, the results of hardware resource consumption analysis demonstrate that the proposed approach in this study significantly reduces the utilization of storage resources compared to replay-based and pre-stored solutions, with reductions of 52.44% and 9.31%, respectively. This makes the proposed approach well-suited for simulating long-duration non-stationary channel fading in UAV scenarios. Additionally, the measured analysis results demon-strate that the channel characteristics output by the proposed hardware emulation scheme, such as path loss and Doppler power spectrum density,closely align with theoretical results when compared to the emulation scheme without the equalizer. This research can be applied to the design and optimization of UAVs communication systems.

Most researches associated with target encircling control are focused on moving along a circular orbit under an ideal environment free from external disturbances. However, elliptical encirclement with a time-varying observation radius, may permit a more flexible and high-efficacy enclosing solution, whilst the non-orthogonal property between axial and tangential speed components, non-ignorable environmental perturbations, and strict assignment requirements empower elliptical encircling control to be more challenging, and the relevant investigations are still open. Following this line, an appointed-time elliptical encircling control rule capable of reinforcing circumnavigation performances is developed to enable Unmanned Aerial Vehicles (UAVs) to move along a specified elliptical path within a predetermined reaching time. The remarkable merits of the designed strategy are that the relative distance controlling error can be guaranteed to evolve within specified regions with a designer-specified convergence behavior. Meanwhile, wind perturbations can be online counteracted based on an unknown system dynamics estimator (USDE) with only one regulating parameter and high computational efficiency. Lyapunov tool demonstrates that all involved error variables are ultimately limited, and simulations are implemented to confirm the usability of the suggested control algorithm.

Unmanned Aerial Vehicles (UAVs), commonly known as drones, are increasingly being employed across a broad spectrum of applications, ranging from military operations to commercial purposes. However, as UAVs become more integrated into everyday life, security and privacy concerns are similarly escalating due to vulnerabilities arising from operating on open wireless channels and having limited onboard computational resources. Moreover, with the emergence of quantum computers, conventional cryptographic methods that ensure the security and privacy of UAV communications are at severe risk. These risks encompass the possibility of unauthorized access, breaches of data, and cyber-physical attacks that jeopardize the integrity, confidentiality, and availability of UAV operations. Quantum computers are expected to break the conventional cryptography methods, such as symmetric and asymmetric schemes, with the support of Grover’s and Shor’s algorithms, respectively. Consequently, traditional cryptographic algorithms must give way to quantum-resistant algorithms, referred to as Post-Quantum Cryptography (PQC) algorithms. Although researchers actively develop, test, and standardize new PQC algorithms, the threat persists despite the progress made through these consistent efforts. This review article first examines the security and privacy landscape, including threats and requirements of UAVs. This article also discusses PQC and various PQC families and the status of the NIST’s implementation and standardization process. Lastly, we explore challenges and future directions in implementing PQC for UAVs.

Achieving successful collaboration among a swarm of Unmanned Aerial Vehicles (UAVs) requires an accurate relative localization system. UAVs operating autonomously using GPS-aided inertial navigation eventually require an alternative navigation aid during GPS outages. Without an alternative, these UAVs must rely on dead-reckoning navigation based on data from the Inertial Measurement Unit (IMU) alone, which can cause the location estimates to accumulate and the navigation solution to drift. This paper presents a range-aided navigation system, where an Extended Kalman Filter (EKF) combines IMU data with range observations from onboard sensors that measure the distance between nodes in the swarm. This method, typically called range-only EKF navigation, mitigates the growth of position, navigation, and timing (PNT) errors during periods of GPS signal loss. To demonstrate the effectiveness of this approach, a combination of software simulations and hardware experiments were conducted. These involved a swarm of six drones in various scenarios, including circular, square, and blue-angels flight trajectories. The trajectories were designed to minimize significant geometric dilution of precision (GDOP). Statistical analysis of the simulation results indicates that this approach improves the estimates compared with dead-reckoning alone, thereby reducing the growth of velocity and location errors when GPS is intermittently unavailable.

The emergence of small-drone technology has revolutionized the way we use drones. Small drones leverage the Internet of Things (IoT) to provide precise navigation and location-based services, making them versatile tools for various applications. However, small drones’ structural and design vulnerabilities expose them to significant security and privacy threats. To ensure the secure and reliable operation of small drones, developing a robust network infrastructure and implementing tailored security and privacy mechanisms is essential. The research evaluates the performance of deep learning (DL) models, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), CNN-LSTM, and ConvLSTM, in detecting intrusions within UAV communication networks. The study utilizes five diverse and realistic datasets, namely KDD Cup-99, NSL-KDD, WSN-DS, CICIDS2017, and Drone datasets, to simulate real-world intrusion scenarios. Notably, the ConvLSTM model consistently achieves an accuracy of 99.99%, showcasing its potential in securing UAVs from cyber threats. This research underscores the significance of robust cybersecurity measures in the ever-expanding realm of UAV technology and highlights the pivotal role played by high-quality datasets in enhancing UAV security. As UAVs become increasingly integral to various industries, this study contributes to ensuring their safety, security, and reliability in the face of evolving cyber risks.

This study introduces a novel trajectory planning approach for the transportation of cable-suspended loads employing three quadrotors, relying on a reinforcement learning (RL) algorithm. The primary objective of this path planning method is to transport the cargo smoothly while avoiding its swing. Within this proposed solution, the value function of the RL is estimated through a feature vector and a parameter vector tailored to the specific problem. The parameter vector undergoes iterative updates via a batch method, subsequently guiding the generation of the desired trajectory through a greedy strategy. Ultimately, this desired trajectory is communicated to the quadrotor controller to ensure precise trajectory tracking. Simulation outcomes demonstrate the capability of the trained parameters to effectively fit the value function.

The combination of Software-Defined Networking (SDN) with Unmanned Aerial Vehicles (UAVs) has transformed wireless communication and data transmission. However, this advancement introduces new security challenges, specifically Distributed Denial of Service (DDoS) attacks, which can significantly disrupt network operations. Existing solutions often rely on single-model detection methods that may not adequately address these evolving threats. These methods may struggle with new and sophisticated attack patterns, leading to higher false positives and negatives. This work presents a new network architecture and novel approach that combines Ensemble learning with honeypot UAV to detect and mitigate DDoS attacks within SDN-UAV networks effectively. The initial phase involves detecting DDoS attacks from network traffic. Instead of relying on a single model, we use two models combined through a bagging-based ensemble method to integrate their results. In this setup, the detected attacks are promptly relayed to subordinate SDN controllers for the implementation of proactive security measures. A honeypot UAV is integrated into the architecture to enhance the system’s effectiveness. This honeypot UAV collects data on potential threats, allowing constant updates and refinement of the ensemble learning model. Furthermore, the system can proactively block traffic from these sources with this data, strengthening the defense mechanisms against DDoS attacks within the SDN-UAV network. To assess the effectiveness of our approach, we conducted training and testing experiments using the InSDN dataset. Experimental results are evaluated using various metrics, demonstrating that the proposed method consistently outperforms the state-of-the-art methods.

Unmanned aerial vehicles (UAVs) are envisioned to play a pivotal role in modern telecommunication and wireless sensor networks, offering unparalleled flexibility and mobility for communication and data collection in diverse environments. This paper presents a comprehensive investigation into the performance of supervised machine learning (ML) models for path loss (PL) prediction in UAV-assisted millimeter-wave (mmWave) radio networks. Leveraging a unique set of interpretable geometrical features, six distinct ML models–linear regression (LR), support vector regressor (SVR), K nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGBoost), and deep neural network (DNN)–are rigorously evaluated using a massive dataset generated from extensive raytracing (RT) simulations in a typical urban environment. Our results demonstrate that the RF algorithm outperforms other models showcasing superior predictive performance for the test dataset with a root mean square error (RMSE) of 2.38 dB. The proposed ML models demonstrate superior accuracy compared to 3GPP and ITU-R models for mmWave radio networks. This study thoroughly investigates the adaptability of these models to unseen environments and examines the feasibility of training them with sparse datasets to improve accuracy. The reduction in computation time achieved by using ML models instead of extensive RT computations for sparse training datasets is evaluated, and an efficient algorithm for training such models is proposed. Additionally, the sensitivity of ML models to noisy input features is analyzed. We also assess the importance of geometrical features and the impact of sequentially increasing the number of these features on model performance. The results emphasize the significance of the proposed geometrical features and demonstrate the potential of ML models to provide computationally efficient and relatively accurate PL predictions in diverse urban environments.

This paper presents a design paradigm to implement convolutional neural networks (CNNs) on low-power commercial microcontrollers for the detection of landing pads in small-size drone applications. A neural architecture search (NAS) strategy generates and selects CNN architectures automatically; candidate networks are compared in terms of their computing costs and representation capabilities. The proposed NAS procedure adopts a teacher-student learning paradigm, in which the ‘student’ network should mimic the ‘teacher’s’ intermediate representation. The associate selection strategy aims to attain an efficient feature representation that can take into account the peculiarities of the problem at hand. This approach allowed the generation of tiny networks capable of real-time execution on commercial micro-controllers (STM32 family). Experimental results confirmed that the resulting architectures could trade off generalization capabilities and computing costs effectively, and outperformed state-of-the-art solutions for landing-pad detection in small-size drones.

Unmanned Aerial Vehicles (UAVs) have emerged as a transformative technology across diverse sectors, offering adaptable solutions to complex challenges in both military and civilian domains. Their expanding capabilities present a platform for further advancement by integrating cutting-edge computational tools like Artificial Intelligence (AI) and Machine Learning (ML) algorithms. These advancements have significantly impacted various facets of human life, fostering an era of unparalleled efficiency and convenience. Large Language Models (LLMs), a key component of AI, exhibit remarkable learning and adaptation capabilities within deployed environments, demonstrating an evolving form of intelligence with the potential to approach human-level proficiency. This work explores the significant potential of integrating UAVs and LLMs to propel the development of autonomous systems. We comprehensively review LLM architectures, evaluating their suitability for UAV integration. Additionally, we summarize the state-of-the-art LLM-based UAV architectures and identify novel opportunities for LLM embedding within UAV frameworks. Notably, we focus on leveraging LLMs to refine data analysis and decision-making processes, specifically for enhanced spectral sensing and sharing in UAV applications. Furthermore, we investigate how LLM integration expands the scope of existing UAV applications, enabling autonomous data processing, improved decision-making, and faster response times in emergency scenarios like disaster response and network restoration. Finally, we highlight crucial areas for future research that are critical for facilitating the effective integration of LLMs and UAVs.

In recent years, due to their ability to transmit and relay wireless signals in challenging terrains, Unmanned Aerial Vehicles (UAVs) and High Altitude Platform Stations (HAPS) have become indispensable in various operations in security, emergency, and military campaigns. However, these networks’ ad-hoc structure and open nature make them highly vulnerable to numerous threats and, in particular, to severe jamming attacks. Furthermore, the communication link between a HAPS and multiple UAVs is also under the threat of multiple and different jamming attacks. Addressing these challenges requires innovative and novel methods capable of interactive and proactive defence strategies. To this end, in this study, we propose a method that combines a pseudo-random (PR) algorithm for initial channel selection with a Transformer-based module to predict jammer behavior. This proactive approach significantly enhances the robustness of UAV communications. Our results demonstrate substantial improvements in transmission success rates and prediction accuracy, offering a robust solution for secure UAV and HAPS communications under adverse conditions.

Unmanned Aerial Vehicles (UAVs) have proliferated across diverse domains. However, optimal UAV operations necessitate precise and reliable navigation systems. UAVs predominantly rely on the Global Navigation Satellite System (GNSS), such as the Global Positioning System (GPS), for navigation. Nevertheless, GNSS signals are susceptible to blockage, reflection, and spoofing, introducing significant risks, including navigation loss and potential UAV loss. This research investigates cutting-edge navigation solutions, emphasizing deep learning-based visual localization approaches tailored for UAVs. Our focus is on scenarios characterized by GPS-denied environments where GPS signals may be absent or unreliable. We provide a comprehensive review of contemporary deep learning-based visual localization approaches and compare them to traditional aerial visual localization methods, such as template matching and feature matching. This comparison highlights both the potential benefits and challenges associated with these approaches. Furthermore, we systematically evaluate and classify recent deep learning-based methods based on main criteria, including model type/architecture, reference imagery, operational context, and resultant accuracy levels. Our findings underscore the substantial promise inherent in various approaches while also shedding light on their unique deployment challenges. Finally, we discuss potential research directions, to inspire further innovations and progress in this domain. The ultimate goal is to develop more accurate, dependable, and secure navigation solutions for UAVs.

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in recent years, with a wide range of applications in areas such as surveying, delivery, and security. UAV technology plays an important role in human life. Integrating Artificial Intelligence (AI) techniques into UAVs can significantly enhance their capabilities and performance. After the integration of AI in UAVs, their efficiency can be improved. It can automatically detect any object and highlight those objects with detailed information using AI. In most of the security surveillance places, UAV technology is beneficial. In this paper, we comprehensively reviewed the most widely used UAV communication protocols, including Wi-Fi, Zigbee, and Long-Range Wi-Fi (LoRaWAN). The review further explores valuable insights into the strengths and weaknesses of these protocols and how cognitive abilities such as perceptions and decision-making can be incorporated into UAV systems for autonomy. This paper provides a comprehensive overview of the state-of-the-art UAV object detection in remote sensing environments, as well as its types and use cases in different applications. It highlights the potential applications of these techniques in various domains, such as wildlife monitoring, search and rescue operations, and surveillance. The challenges and limitations of these methods and open research issues are given for future research.