Specific Unmanned Aerial Vehicles Research Articles

Heuristic data-driven anchor generation for UAV-based maritime rescue image object detection

The specificity of scenarios and tasks in Unmanned Aerial Vehicles (UAV)-based maritime rescue poses challenges for detecting targets within images captured by drones in such environments. This study focuses on leveraging heuristic methods to extract data features from specific UAV maritime rescue images to optimize the generation of anchor boxes in detection models. Experiments conducted on the large-scale SeaDronesSee maritime rescue dataset, using the MMDetection object detection framework, demonstrated that the optimized anchor boxes, improved model performance by 48.9% to 62.8% compared to the framework's default configuration, with the most proficient model surpassing the official highest SeaDronesSee baseline by over 49.3%. Further analysis of the results revealed the variation in detection difficulty for different objects within the dataset and identified the reasons behind these differences. The methodology and analysis presented in this study hold promise for optimizing UAV-based maritime rescue object detection models as well as refining data analysis and enhancement.

Airfoil Lift Coefficient Optimization Using Genetic Algorithm and IGP Parameterization: Volume 1

The objective of this study is to develop a genetic algorithm that uses the IGP parameterization to increase the lift coefficient (CL) of three airfoils to be used on wings of unmanned aerial vehicles (UAVs). The geometry of three baseline airfoils was modified by developing a genetic algorithm that operates with the IGP parameterization and performs the aerodynamic analysis using XFOIL in the MATLAB environment. Subsequently, a numerical model was made for each baseline and optimized airfoil using a commercial computational fluid dynamics (CFD) code to analyze the behavior of the lift coefficient. An increase in the average CL was obtained for the Eppler 68, MH 70, and Wortmann FX 60-126 airfoils for angles of attack ranging from 0 to 10, obtaining increments of 17.243%, 14.967%, and 10.708%, respectively. Additionally, an average 5.027% uncertainty was obtained in lift coefficient calculations between XFOIL and CFD. The utility of the IGP method and genetic algorithms for parameterizing and optimizing airfoils was demonstrated. In addition, airfoils could be tailored for a specific UAV depending on the mission profile. Volume 2 of this study will include experimental data from wind tunnel.

An efficient authentication and key agreement scheme for security-aware unmanned aerial vehicles assisted data harvesting in Internet of Things

The Internet of Things (IoT) devices are majorly used for remote collection and delivery of data for the operation of systems such as precision agriculture, military, e-health, and weather forecast. On most occasions, these devices are sited in remote locations without existing or reliable telecommunication networks, which makes real-time data delivery impossible. To mitigate this, unmanned aerial vehicles (UAVs) assisted system has been integrated into IoT data harvesting. However, this requires an authentication and key-agreement scheme capable of securing the harvested data and performing dynamic accessibility-mapping of IoT devices to a specific UAV such that each UAV will be able to identify its devices during harvesting without compromising the integrity and confidentiality of the harvested data. In this paper, we propose an authentication and key-agreement scheme for UAVs assisted IoT data harvesting. To achieve this, we developed n-Divide Loyalty Pairing (n-DLP) and a linear time sequence-based cartesian tree structure to secure the harvested data, and Chinese remainder theorem for a dynamic accessibility-mapping of different IoT devices to different UAVs. The experimental results and security analysis showed that the scheme secured the harvested data at low communication and computation overheads. Also, the results showed that the scheme has an insignificant effect on the mean waiting times of the data harvesting system.

Unmanned Aerial Vehicles for Search and Rescue: A Survey

In recent years, unmanned aerial vehicles (UAVs) have gained popularity due to their flexibility, mobility, and accessibility in various fields, including search and rescue (SAR) operations. The use of UAVs in SAR can greatly enhance the task success rates in reaching inaccessible or dangerous areas, performing challenging operations, and providing real-time monitoring and modeling of the situation. This article aims to help readers understand the latest progress and trends in this field by synthesizing and organizing papers related to UAV search and rescue. An introduction to the various types and components of UAVs and their importance in SAR operations is settled first. Additionally, we present a comprehensive review of sensor integrations in UAVs for SAR operations, highlighting their roles in target perception, localization, and identification. Furthermore, we elaborate on the various applications of UAVs in SAR, including on-site monitoring and modeling, perception and localization of targets, and SAR operations such as task assignment, path planning, and collision avoidance. We compare different approaches and methodologies used in different studies, assess the strengths and weaknesses of various approaches, and provide insights on addressing the research questions relating to specific UAV operations in SAR. Overall, this article presents a comprehensive overview of the significant role of UAVs in SAR operations. It emphasizes the vital contributions of drones in enhancing mission success rates, augmenting situational awareness, and facilitating efficient and effective SAR activities. Additionally, the article discusses potential avenues for enhancing the performance of UAVs in SAR.

Vision geometry-based UAV flocking

AbstractA distributed UAV (unmanned aerial vehicle) flocking control method based on vision geometry is proposed, in which only monocular RGB (red, green, blue) images are used to estimate the relative positions and velocities between drones. It does not rely on special visual markers and external infrastructure, nor does it require inter-UAV communication or prior knowledge of UAV size. This method combines the advantages of deep learning and classical geometry. It adopts a deep optical flow network to estimate dense matching points between two consecutive images, uses segmentation technology to classify these matching points into background and specific UAV, and then maps the classified matching points to Euclidean space based on the depth map information. In 3D matching points, also known as 3D feature point pairs, each of their classifications is used to estimate the rotation matrix, translation vector, velocity of the corresponding UAV, as well as the relative position between drones, based on RANSAC and least squares method. On this basis, a flocking control model is constructed. Experimental results in the Microsoft Airsim simulation environment show that in all evaluation metrics, our method achieves almost the same performance as the UAV flocking algorithm based on ground truth cluster state.

About the organization of regional situational centers of the intellectual system “Control_TEP” with the use of UAVS

The basics of the principles of creation and filling of the technopark of unmanned aerial vehicles (UAV) are offered. The business process of UAV registration in the technopark of the situation center robots is described. The use of attrib-utes (tags) to the UAV will increase the efficiency of a suitable device selection with a complete set that meets the task. It is proposed to organize regional situational centers, which will coordinate the work of state systems, urban life sup-port systems, private services on the one hand and UAV on the other as executors. An example of automatic UAV selection for operative solution of the set task is given. The system should be based on the classification of the UAV during registration and on the basis of the UAV compliance function to the specific task, key features of the UAV, the time required to complete the task, the distance to the task and the policy to involve the UAV in such tasks to select those devices, who can quickly perform tasks. The function of classification of a specific UAV by tasks is offered. The function takes into account the configuration of the UAV. For each task, experts and automation select weights that indicate how large the impact of certain typical modules to perform a particular task, and for each UAV in the data-base stores information about whether the UAV takes into account a certain characteristic, or there is a corresponding module. To update the approach to vocational training today, the task of creating interactive mock-up training sys-tems in real physical space is one of the main ones. The composition of the basic laboratory stand, its complete set and control system of the mobile modular robot which promotes mastering of basic functions of the UAV or mobile work of unearthly base are described.

A Security Review in the UAVNet Era: Threats, Countermeasures, and Gap Analysis

Unmanned Aerial Vehicles (UAVs) are becoming one of the main technological supports for commercial applications, embracing many domains ranging from human safety to the medical field, agriculture and environment, multimedia production, and even commercial delivery. This rise in popularity, however, is causing an increasing interest from criminals, making UAVs the target of new attacks. To fully characterize the current UAV cybersecurity landscape, we perform a complete literature review, digging into drone security historic facts and scientific studies on the matter, reviewing specialized articles and scientific papers focusing on cybersecurity threats and gaps in the context of small UAVs in commercial applications. Being a recent research and development area, most of the articles have been published between 2016 and 2020 as a direct consequence of the increase of security concerns and interest in the drone field. Papers in this review deal with UAV cyberthreats and related vulnerabilities, identifying flaws experimented in a lab or describing incidents detected in the field. Communication, sensors, and system misconfigurations are among the most important threat vectors, while sensor spoofing/jamming and malware DoS/control are among the most cited threats. Threat vectors permit depicting a complete overview of the topic and potential countermeasures known to date, with related gap analysis, also accounting for the recent Unmanned Aircraft System evolution toward ad hoc or cloud-based UAV networks. Countermeasures include the adoption of traditional communication encryption and standard protocols, GPS spoofing/jamming mitigation, encryption and privacy-aware implementations, and counter-malware techniques, to name the most adopted. It also emerges that often attacks are simply ported or adapted from other attacks in similar domains, while peculiar attacks still remain such as targeted physical attacks, specific UAV malware, and GPS spoofing/jamming.

About the Organization of Regional Situational Centers of the Intellectual System “Control_Tee” with the Use of Uavs

The basics of the principles of creation and filling of the technopark of unmanned aerial vehicles (UAV) are offered. The business process of UAV registration in the technopark of the situation center robots is described. The use of attributes (tags) to the UAV will increase the efficiency of a suitable device selection with a complete set that meets the task. It is proposed to organize regional situational centers, which will coordinate the work of state systems, urban life support systems, private services on the one hand and UAV on the other as executors. At this time, principles and methods of automatic selection of UAVs are being developed for the prompt solution of the given task. The system should be based on the classification of the UAV during registration and on the basis of the UAV compliance function to the specific task, key features of the UAV, the time required to complete the task, the distance to the task and the policy to involve the UAV in such tasks to select those devices, who can quickly perform tasks. The function of classification of a specific UAV by tasks is offered. The function takes into account the configuration of the UAV. For each task, experts and automation select weights that indicate how large the impact of certain typical modules to perform a particular task, and for each UAV in the database stores information about whether the UAV takes into account a certain characteristic, or there is a corresponding module. To update the approach to professional training today, one of the main tasks is to create interactive mock-up training systems in real physical space. The principles of building a basic laboratory stand, its equipment and the control system of a mobile modular robot, which helps to master the basic functions of a UAV or mobile operation of a ground base, are under development.

Разработка алгоритма равномерного покрытия территории группой беспилотных летательных аппаратов

Subject of study. The paper proposes an algorithm for uniform distribution of unmanned aerial vehicles (UAV) with a given action radius in order to monitor a limited area. At present, the problem is relevant in various civil applications.Materials and methods. The developed algorithm allows to calculate the maximum and minimum possible distances between UAVs, so they are in the visible range of each other. In addition, the algorithm allows to fully cover the entire monitoring territory by the UAVs uniform distribution. The developed algorithm is verified by an empirical study using the CoppeliaSim simulation software tool. Main results. The UAVs position on a given territory should consider the number and range of UAVs. The presented algorithm’s implementation is flexible in relation to the monitoring area size, and to the specific UAVs technical characteristics, which allows to adjust the algorithm to the user’s and/or application’s requirements. Conclusion. The proposed algorithm allows to calculate the necessary and sufficient distance between UAVs to cover a given territory, and to calculate the minimal required UAVs number for their uniform distribution over the territory. The solution to the addressed problem is of practical importance, for example, in such applications as ground searching or monitoring operations.

Collaborative Design of Multi-UAV Trajectory and Resource Scheduling for 6G-Enabled Internet of Things

The 6th generation (6G) communication envisions a highly integrated network where aerial vehicles connect satellites and terrestrial systems. As low altitude vehicle, unmanned aerial vehicle (UAV) is able to quickly establish wireless networks without resorting to terrestrial infrastructure. Due to strong invulnerability, synergistic cooperation and flexible scheduling, the multi-UAV communication system can significantly improve system performance through collaboratively designing multi-UAV trajectory and radio resource scheduling. This article proposes a multi-UAV wireless powered communication (WPC) system for 6G-enabled Internet of Things (IoT). Specifically, each time slot is split into uplink and downlink subslot. In the downlink subslot, multiple UAVs dispatched as aerial communication platforms transfer energy to multiple IoT users. In the uplink subslot, the association between UAVs and users is designed, and then the scheduled user uploads data to the specific UAV by using the harvested energy. According to the proposed system, we propose a collaborative scheme of multi-UAV trajectory optimization and resource scheduling. By synergistically optimizing UAV-user association, subslot duration, user transmit power, and multi-UAV trajectory, we maximize the minimum average achievable rate among all users. Particularly, the nonconvex optimization problem can be efficiently figured out by an alternative iteration algorithm proposed in this article. Finally, numerical results show that our design can not only optimize multi-UAV flight path, but also achieve higher objective value than benchmark schemes.

RF Fingerprinting Unmanned Aerial Vehicles With Non-Standard Transmitter Waveforms

The universal availability of unmanned aerial vehicles (UAVs) has resulted in many applications where the same make/model can be deployed by multiple parties. Thus, identifying a specific UAV in a given swarm, in a manner that cannot be spoofed by software methods, becomes important. We propose RF fingerprinting for this purpose, where a neural network learns subtle imperfections present in the transmitted waveform. For UAVs, the constant hovering motion raises a key challenge, which remains a fundamental problem in previous works on RF fingerprinting: Since the wireless channel changes constantly, the network trained with a previously collected dataset performs poorly on the test data. The main contribution of this paper is to address this problem by: (i) proposing a multi-classifier scheme with a two-step score-based aggregation method, (ii) using RF data augmentation to increase neural network robustness to hovering-induced variations, and (iii) extending the multi-classifier scheme for detecting a new UAV, not seen earlier during training. Importantly, our approach permits RF fingerprinting on manufacturer-proprietary waveforms that cannot be decoded or altered by the end-user. Results reveal a near two-fold accuracy in UAV classification through our multi-classifier method over the single-classifier case, with an overall accuracy of 95% when tested with data under unseen channel. Our multi-classifier scheme also improves new UAV detection accuracy to a near perfect 99%, up from 68% for a single neural network approach.

Reducing systematic dome errors in digital elevation models through better UAV flight design

AbstractIt is well established that digital elevation models (DEMs) derived from unmanned aerial vehicle (UAV) images and processed by structure from motion may contain important systematic vertical errors arising from limitations in camera geometry modelling. Even when significant, such ‘dome’‐shaped errors can often remain unnoticed unless specific checks are conducted. Previous methods used to reduce these errors have involved: the addition of convergent images to supplement traditional vertical datasets, the usage of a higher number of ground control points, precise direct georeferencing techniques (RTK/PPK) or more refined camera pre‐calibration. This study confirms that specific UAV flight designs can significantly reduce dome errors, particularly those that have a higher number of tie points connecting distant images, and hence contribute to a strengthened photogrammetric network. A total of 22 flight designs were tested, including vertical, convergent, point of interest (POI), multiscale and mixed imagery. Flights were carried out over a 300 × 70 m2 flat test field area, where 143 ground points were accurately established. Three different UAVs and two commercial software packages were trialled, totalling 396 different tests. POI flight designs generated the smallest systematic errors. In contrast, vertical flight designs suffered from larger dome errors; unfortunately, a configuration that is ubiquitous and most often used. By using the POI flight design, the accuracy of DEMs will improve without the need to use more ground control or expensive RTK/PPK systems. Over flat terrain, the improvement is especially important in self‐calibration projects without (or with just a few) ground control points. Some improvement will also be observed on those projects using camera pre‐calibration or with stronger ground control. © 2020 John Wiley & Sons, Ltd.

Application of Machine Learning Method to Quantitatively Evaluate the Droplet Size and Deposition Distribution of the UAV Spray Nozzle

Unmanned Aerial Vehicle (UAV) spray has been used for efficient and adaptive pesticide applications with its low costs. However, droplet drift is the main problem for UAV spray and will induce pesticide waste and safety concerns. Droplet size and deposition distribution are both highly related to droplet drift and spray effect, which are determined by the nozzle. Therefore, it is necessary to propose an evaluating method for a specific UAV spray nozzles. In this paper, four machine learning methods (REGRESS, least squares support vector machines (LS-SVM), extreme learning machine, and radial basis function neural network (RBFNN)) were applied for quantitatively evaluating one type of UAV spray nozzle (TEEJET XR110015VS), and the case of twin nozzles was investigated. The results showed REGRESS and LS-SVM are good candidates for droplet size evaluation with the coefficient of determination in the calibration set above 0.9 and root means square errors of the prediction set around 2 µm. RBFNN achieved the best performance for the evaluation of deposition distribution and showed its potential for determining the droplet size of overlapping area. Overall, this study proved the accuracy and efficiency of using the machine learning method for UAV spray nozzle evaluation. Additionally, the study demonstrated the feasibility of using machine learning model to predict the droplet size in the overlapping area of twin nozzles.

Implementation and optimization of the cascade classifier algorithm for UAV detection and tracking

A number of vision-based algorithms designed to detect and track unmanned aerial vehicles (UAVs) from on board a second UAV have been researched, implemented, and experimentally validated over the last decade. However, the successful methods have tended to rely on characteristics such as color or shape, meaning they require the target UAV to have particular markings or geometries. This paper uses the Viola–Jones cascade classifier, a computer vision algorithm originally designed to detect human faces in video streams, and demonstrates its capability for detecting and tracking an arbitrary type of UAV with excellent performance in either indoor or outdoor environments and with a variety of backgrounds. The Viola–Jones algorithm is applied to two specific quadrotor UAV models, the Solo from 3D Robotics and the AR.Drone 2.0 from Parrot. Experimental testing demonstrates that the resulting system achieves very good detection and tracking performance in real time on each UAV type for both indoor and outdoor flight tests.

An improvement of flight performance in the level flight of tilted quadrotors by attaching a fixed-wing

Wide range information is required to be collected by unmanned aerial vehicles (UAVs) and the area for its take-off and landing is limited in the event of a disaster. Therefore, research on the development of a specific UAV, which has two functions of a long distance flight like a fixed-wing aircraft and of a hovering like a rotorcraft, is drawing attention recently. In this study, we focus on a hybrid tilted quadrotor, in which four rotors are tiltable and a wing is fixed. It is clarified, from a simulation comparison in a level flight mode, that the flight performance is effectively improved by adding a fixed-wing, where a tilted quadrotor is assumed to take a level flight by using a controller for a vertical-flight mode and by controlling the angles of some tiltable rotors. It is shown finally that adding a fixed-wing can save the rotor thrust about 77% per flight distance.

COMPREHENSIVE ANALYSIS OF FLYING ALTITUDE FOR HIGH RESOLUTION SLOPE MAPPING USING UAV TECHNOLOGY

Abstract. Unmanned Aerial Vehicle (UAV) is one of the geoinformation data acquisition technologies that popularly used for slope mapping. UAV is capable to produce high resolution imageries in a short period. In order to obtained suitable results in slope mapping, specific UAV mapping factors have to be followed and the selection of the optimum Ground Control Point (GCP) and the UAV flying altitude become the most important factors. This paper presents the production of high resolution slope map using UAV technology. The research involved with the following steps, (i) preparation of field work (i.e. determination of the number of GCPs and flying altitude) and the flight mission; (ii) processing and evaluating of UAV images, and (iii) production of slope map. The research was successfully conducted at Kulim, Kedah, Malaysia as the condition of slope in that area is prone to the landslide incidences. A micro rotary wing UAV system known as DJI Phantom 4 was used for collecting the high resolution images with various flying altitudes. Due to the un-accessibility of the slope area, all the GCPs are measured from the point cloud data that was acquired from the Pheonix AL-32 LiDAR system. The analysis shows that the coordinates (X, Y and Z) accuracy is influenced by the flying altitude. As the flying altitude increases, the coordinate’s accuracy also increased. Furthermore, the results also show that the coverage slope area and number of tie point increases when the flying altitude increases. This practical study contributed to the slope work activities where the specific requirements for flying altitudes have been clearly stated.

Comprehensive Energy Consumption Model for Unmanned Aerial Vehicles, Based on Empirical Studies of Battery Performance

Unmanned aerial vehicles (UAVs) are fast gaining popularity in a wide variety of areas and are already being used for a range of tasks. Despite their many desirable features, a number of drawbacks hinder the potential of UAV applications. As typical UAVs are powered by on-board batteries, limited battery lifetime is identified as a key limitation in UAV applications. Thus, in order to preserve the available energy, planning UAV missions in an energy efficient manner is of utmost importance. For energy efficient UAV mission planning, it is necessary to predict the energy consumption of specific UAV manoeuvring actions. Accurate energy prediction requires a reliable and realistic energy consumption model. In this paper, we present a consistent and complete energy consumption model for UAVs based on empirical studies of battery usage for various UAV activities. We considered the impact of different flight scenarios and conditions on UAV energy consumption when developing the proposed model. The energy consumption model presented in this paper can be readily used for energy efficient UAV mission planning.

Switching topology approach for UAV formation based on binary-tree network

Formation control is one of the most active topics within the realm of coordination fields for unmanned aerial vehicles (UAVs). The formation pattern is an essential aspect which mainly influences the status of formation flight. This paper focuses on the switching topology approach for a few specific quadrotor UAV formations. A novel switching method based on the binary-tree network (BTN) is developed to realize the transformations between the V-shape and the complete binary tree shape (CBT-shape) topologies. The typical feature of the BTN is the chain structure. Based on the cascaded form of the BTN, a low level feedback controller is designed for the guidance and coordination of UAV swarms. Simulation results demonstrate that the BTN based approach is more superior in the computational cost and real-time performances than several traditional methods.

Measuring the influence of unmanned aerial vehicles on Adélie penguins

Unmanned aerial vehicles (UAVs) have become a useful tool in polar research. While their performance is already proven, little is known about their impact on wildlife. To assess the disturbance caused on the penguins, flights with a UAV were conducted over an Adelie penguin (Pygoscelis adeliae) colony. Vertical and horizontal flights were performed between 10 and 50 m in altitude. Penguins’ reactions were video-recorded, and the behavioural response was used to indicate the level of disturbance. During any flight mode, disturbance increased immediately after takeoff and remained elevated at all altitudes between 20 and 50 m. When the UAV descended below 20 m, the disturbance increased further with almost all individuals being vigilant. Only at these low altitudes, vertical flights caused an even higher level of disturbance than horizontal ones. Repetitions of horizontal overflights showed no short-term habituation occurring. Since the results are only valid for the specific UAV model used, we recommend a more extensive approach with different UAV specifications. As the highest flight altitudes already caused detectable but not subjectively visible responses, we also recommend to regard subjective impressions of disturbance with caution.

STOCHASTIC REASONING FOR UAV SUPPORTED RECONSTRUCTION OF 3D BUILDING MODELS

Abstract. The acquisition of detailed information for buildings and their components becomes more and more important. However, an automatic reconstruction needs high-resolution measurements. Such features can be derived from images or 3D laserscans that are e.g. taken by unmanned aerial vehicles (UAV). Since this data is not always available or not measurable at the first for example due to occlusions we developed a reasoning approach that is based on sparse observations. It benefits from an extensive prior knowledge of probability density distributions and functional dependencies and allows for the incorporation of further structural characteristics such as symmetries. Bayesian networks are used to determine posterior beliefs. Stochastic reasoning is complex since the problem is characterized by a mixture of discrete and continuous parameters that are in turn correlated by nonlinear constraints. To cope with this kind of complexity, the implemented reasoner combines statistical methods with constraint propagation. It generates a limited number of hypotheses in a model-based top-down approach. It predicts substructures in building facades – such as windows – that can be used for specific UAV navigations for further measurements.