Unmanned Aerial Vehicle Applications Research Articles

Real-Time Optimal States Estimation with Inertial and Delayed Visual Measurements for Unmanned Aerial Vehicles.

Motion estimation is a major issue in applications of Unmanned Aerial Vehicles (UAVs). This paper proposes an entire solution to solve this issue using information from an Inertial Measurement Unit (IMU) and a monocular camera. The solution includes two steps: visual location and multisensory data fusion. In this paper, attitude information provided by the IMU is used as parameters in Kalman equations, which are different from pure visual location methods. Then, the location of the system is obtained, and it will be utilized as the observation in data fusion. Considering the multiple updating frequencies of sensors and the delay of visual observation, a multi-rate delay-compensated optimal estimator based on the Kalman filter is presented, which could fuse the information and obtain the estimation of 3D positions as well as translational speed. Additionally, the estimator was modified to minimize the computational burden, so that it could run onboard in real time. The performance of the overall solution was assessed using field experiments on a quadrotor system, compared with the estimation results of some other methods as well as the ground truth data. The results illustrate the effectiveness of the proposed method.

Mapping of Manado State Polytechnic campus area with web-based Geographic Information System (GIS): A Small Unmanned Aerial Vehicle (SUAV) application

Technology is continuously developing, especially in mapping and information technology. Geographic Information System (GIS) is a system used to collect, store, analyze, and display geographic data. Geographic data is information about location or geography, such as maps, satellite imagery, digital elevation models, or data associated with a particular location. This study aims to produce a web-based GIS map by visualizing spatial data containing each room's location, parking area, and landscape in the Manado State Polytechnic campus area. The method used in this study was to collect location data using a Small Unmanned Aerial Vehicle (SUAV) to take aerial photos, Ground Control Point (GCP), and tagging photos. Data processing uses Agisoft Metashape Software to combine all aerial photographs to become an exclusive photo and ArcGIS for programming. The result is creating a digital map that makes it easy for users to get the position of buildings with a visual display along with the information contained therein.

Physics-informed Neural Network for Quadrotor Dynamical Modeling

The explosive growth of civil applications of Unmanned Aerial Vehicles (UAVs) calls for control algorithms that enable safe and trustworthy operations, especially in complex environments to facilitate real-world deployment. Although Model-Based Control (MBC) has found great applicability in the last decades, it relies heavily on the accuracy of the underlying mathematical models. Thanks to their powerful approximation capability, data-driven approaches such as Artificial Neural Networks (ANNs) have raised a great interest in UAV dynamical modeling in recent years. Despite the promising results achieved in learning either full or partial dynamics such as aerodynamic effects, prior studies merely pay little to no attention to the black-box nature of ANNs, yielding poorly interpretable learning processes and implying a lack of generalization capability due to undesirably learned spurious relationships among features and labels. While nowadays practitioners and society are far from being concerned just with performance, such risk evidently reduces the overall trustworthiness of the control system with ANNs as control-oriented models. With the goal of both accurate and interpretable neural modeling of nonlinear dynamics, we propose a novel modeling approach that utilizes Physics-Informed Neural Networks (PINN), designed to seamlessly embed physical laws into Deep Neural Networks (DNN). To further enhance model interpretability, we adopt the Covariance Confidence Ellipse (CCE) as post-hoc visualization to help understand the model behavior. We also set up a visual and physical simulator based on AirSim with custom implementation on quadrotor ground effect, which is made publicly available to facilitate further experiments for the community. An extensive simulation campaign validates our approach on data sets including aerodynamics and periodic wind, highlighting advantages regarding the accuracy and physical consistency, pointing to further insight on the development of learning-based control-oriented models for quadrotors, and facilitating flight controller design with performance guarantees.

Application of unmanned aerial vehicles (UAV) in building 2D maps and 3D current status models for planning design

The article presents the topographic survey work using unmanned aerial vehicle (UAV) images to build 2D maps and 3D current status models. This technology has been used in many areas of life, but in Vietnam in planning design, it has not been widely applied.. Planning architects still follow the traditional method of relying on the 2D basemap database plus input data collected from various sources and at the request of the Investor to analyze and design the plan.. The products created from the above inputs are 2D detailed design drawings and 3D design models. It will be difficult to avoid shortcomings and limitations that will affect quality and slow progress due to design adjustments.. The design and application of the results from UAV equipment such as 2D topographic maps, image maps, 3D current status models, digital elevation models (DEM), point cloud data, etc. will improve the quality of design and planning management, in addition to adding an approach to green, sustainable design, responding to climate change and natural disasters.

Research of a novel aerodynamic evaluation method for fixed-wing UAV

The aerodynamic parameters of unmanned aerial vehicles (UAVs) play an important role in the newly designed drone. For the purpose of the real-time measurement of the aerodynamic performance parameters of the UAV in flight status, based on the self-development connected-wing configuration airplane, a novel airborne aerodynamics test scheme is researched and verified in this work. The findings of this study indicate that the effectiveness of numerical calculations can be verified by comparison with both results of the numerical simulation and airborne flight test in the same conditions. The newly designed UAV equipped with this test system in the future, not only achieves quick and reliable results of aerodynamic performance and powered system efficiency but also can save the expense of wind tunnel experiments, which is of high potential to the UAV application.

A Multiple Object Tracker with Spatiotemporal Memory Network

Target tracking is an important application of unmanned aerial vehicles (UAVs). The template is the identity of the target and has a great impact on the performance of target tracking. Most methods only keep the latest template of the target, which is intuitive and convenient but has poor ability to resist the change of target appearance, especially to reidentify a target that has disappeared for a long time. In this paper, we propose a practical multiobject tracking (MOT) method, which uses historical information of targets for better adapting to appearance variations during tracking. To preserve the spatial-temporal information of the target, we introduce a memory pool to store masked feature maps at different moments, and precise masks are generated by a segmentation network. Meanwhile, we fuse the feature maps at different moments by calculating the pixel-level similarity between the current feature map and the masked historical feature maps. Benefiting from the powerful segmentation features and the utilization of historical information, our method can generate more accurate bounding boxes of the targets. Extensive experiments and comparisons with many trackers on MOTS, MOT17, and MOT20 demonstrate that our method is competitive. The ablation study showed that the introduction of memory improves the multiobject tracking accuracy (MOTA) by 2.1.

Cost Analysis of Using UAV Sprayers for Olive Fruit Fly Control

Unmanned Aerial Vehicles (UAVs) are a novel up-and-coming technology with wide applicability and great potential to be used in agricultural systems for spraying applications. However, the cost-effectiveness of this application is still rather uncertain. The present study utilized actual data from field applications to analyze the critical components and parameters in the potential case of using UAV sprayers for the control of olive fruit flies in order to assess the operational costs. The results are compared with the costs of two traditional spraying methods: manual spaying by workers using backpack sprayers and manual spraying assisted by a tractor. The case of the olive fruit fly was selected because it involves costly, time consuming, and laborious manual spraying. Furthermore, the bait character of spraying in these applications does not require full canopy coverage, making it ideal for UAV applications. A parameterized computational model was developed to assess the costs of labor, capital spending, repair and maintenance, energy, licensees, fees and taxes, and storage for each of the three methods. In addition, the cost for surveillance was also accounted for with the UAV method. Consequently, a sensitivity analysis was performed to examine the impact of the most crucial parameters. The results showed that the cost of spraying with a UAV was 1.45 to 2 times higher than the traditional methods, mainly due to the high capital spending resulting from a low economic life. There are opportunities, however, of improving the economic performance, making it compatible to the traditional methods, by using a smaller UAV with longer lasting batteries and by expanding its annual use beyond the needs of olive fruit fly control.

Methodology for performing bathymetric measurements of shallow waterbodies using an UAV, and their processing based on the SVR algorithm

State-of-art methods of bathymetric measurements for shallow waterbodies use Global Navigation Satellite System (GNSS) receiver, bathymetric Light Detection and Ranging (LiDAR) sensor or satellite imagery. Currently, photogrammetric methods with the application of Unmanned Aerial Vehicles (UAV) are gathering great importance. This publication aims to present step-by-step methodology for carrying out the bathymetric measurements of shallow waterbodies with the use of UAV-Structure from Motion (SfM) and Support Vector Regression (SVR) algorithms. Proposed model is explained and verified on the basis of measurement campaign on Raduńskie Górne Lake located in Poland. The campaign included GNSS Real Time Kinematic (RTK) bathymetric measurements for robust training dataset and photogrammetric flight pass for SfM point cloud. The presented methodology will allow to perform bathymetric measurements with the accuracy provided for the International Hydrographic Organization (IHO) Special Order (horizontal position error ≤ 2 m (p = 0.95), vertical position error ≤ 0.25 m (p = 0.95)).

Undertaking wildlife surveys with unmanned aerial vehicles in rugged mountains with dense vegetation: A tentative model using Sichuan Snub-nosed monkeys in China

Unmanned aerial vehicles (UAVs) have broad applications. However, their use for wildlife surveys in rugged mountains with dense vegetation is uncommon. Therefore, developing appropriately designed methods, selecting suitable facilities, establishing effective monitoring processes, and managing databases that align with a region’s distinctive geographic landscapes, environments, ecology, and habitats are essential. This study focuses on the Giant Panda National Park in China’s densely vegetated Qinling Mountains to carry out surveys using UAVs to assess the Sichuan snub-nosed monkey population size (Rhinopithecus roxellana) over an area of 30,000 ha. The results indicate that eight distinct groups were identified, totaling 648–755 individuals. Thus, this study offers proof-of-principle for using UAVs for surveying wildlife in remote mountainous regions with complex landscapes and dense vegetation and demonstrates how UAVs can be used in animal monitoring and conservation. Furthermore, the study highlights the broader potential application of UAVs in other remote mountainous regions, where animal demographic information is urgently needed to establish database-driven conservation strategies.

CPA-YOLOv7: Contextual and pyramid attention-based improvement of YOLOv7 for drones scene target detection

Target detection in unmanned aerial vehicle application scenarios has other problems, such as dense targets. The existing unmanned aerial vehicle target detection model with high computational complexity makes it difficult to meet real-time unmanned aerial vehicle target detection, and the detection accuracy of small targets is low. To address these problems, we propose an improved YOLOv7 small target detection model based on context and pyramidal attention that can cope with dense unmanned aerial vehicle scenarios - CPA-YOLOv7. This model embeds our proposed lightweight multi-scale attentional feature spatial pyramid pooling module, which can better distinguish between small and large target features, reducing the computational effort while improving the detection accuracy of the model. Secondly, we design a contextual dynamic fusion attention module in the network to fuse global and local contextual information and dynamically assign features to multiple groups of channels; in the multi-scale fusion process, it effectively increases the characterization ability of small target features and enables the network to better focus on small target information. Finally, we improve Wise-Intersection-over-Union loss as the regression loss function, add a moderation factor to retain some of the high and low-quality sample weights to improve the regression accuracy of high-quality anchor frames, and use the dynamic non-monotonic focusing mechanism to increase the model's focus on ordinary quality anchor frames to improve the model's localization performance and robustness to low-quality samples. Numerous experimental results show that on the unmanned aerial vehicle datasets VisDrone2021-DET and AI-TOD, the mAP values of our model are 2.3% and 1.1% higher than those of the YOLOv7 model with fewer parameters introduced, and the computational speed reaches 146 frames per second (FPS), which can meet the real-time requirements of unmanned aerial vehicle detection.

Deep-Reinforcement-Learning-Based Joint 3-D Navigation and Phase-Shift Control for Mobile Internet of Vehicles Assisted by RIS-Equipped UAVs

Unmanned aerial vehicles (UAVs) are utilized to improve the performance of wireless communication networks (WCNs), notably, in the context of Internet-of-things (IoT). However, the application of UAVs, as active aerial base stations (BSs)/relays, is questionable in the fifth-generation (5G) WCNs with quasi-optic millimeter wave (mmWave) and beyond in 6G (visible light) WCNs. Because path loss is high in 5G/6G networks that attenuate, even, the line-of-sight (LoS) communicating signals propagated by UAVs. Besides, the limited energy/size/weight of UAVs makes it cost-deficient to design aerial multi-input/output BSs for active beamforming to strengthen the signals. Equipping UAVs with the reconfigurable intelligent surface (RIS), a passive component, can help to address the problems with UAV-assisted communication in 5G and optical 6G networks. We propose adopting the RIS-equipped UAV (RISeUAV) to provide aerial LoS service and facilitate communication for mobile Internet-of-vehicles (IoVs) in an obstructed dense urban area covered by 5G/6G. RISeUAV-aided wireless communication facilitates vehicle-to-vehicle/everything communication for IoVs for updating IoT information required for sensor fusion and autonomous driving. However, autonomous navigation of RISeUAV for this purpose is a multilateral problem and is computationally challenging for being optimally implemented in real-time. We intelligently automated RISeUAV navigation using deep reinforcement learning to address the optimality and time complexity issues. Simulation results show the effectiveness of the method.

State of the Art and Future Perspectives of Atmospheric Chemical Sensing Using Unmanned Aerial Vehicles: A Bibliometric Analysis.

In recent years, unmanned aerial vehicles (UAVs) have been increasingly used to monitor and assess air quality. The interest in the application of UAVs in monitoring air pollutants and greenhouse gases is evidenced by the recent emergence of sensors with the most diverse specifications designed for UAVs or even UAVs designed with integrated sensors. The objective of this study was to conduct a comprehensive review based on bibliometrics to identify dynamics and possible trends in scientific production on UAV-based sensors to monitor air quality. A bibliometric analysis was carried out in the VOSViewer software (version 1.6.17) from the Scopus and Web of Science reference databases in the period between 2012 and 2022. The main countries, journals, scientific organizations, researchers and co-citation networks with greater relevance for the study area were highlighted. The literature, in general, has grown rapidly and has attracted enormous attention in the last 5 years, as indicated by the increase in articles after 2017. It was possible to notice the rapid development of sensors, resulting in smaller and lighter devices, with greater sensitivity and capacity for remote work. Overall, this analysis summarizes the evolution of UAV-based sensors and their applications, providing valuable information to researchers and developers of UAV-based sensors to monitor air pollutants.

The application of UAVs in marathon public security risk early warning

The UAV (Unmanned Aerial Vehicle) has the advantages of mobility and flexibility, rapid concealment and holistic vision. Coordinating with the intelligent and efficient precise dispatching of the “decision module” of the command centre, UAVs can meet the public safety needs of significant events. The marathon is an open, long-distance, gathering sporting event, so on-site security is hard to guarantee. To study the application of UAVs in marathon public security risk early warning, we examine the Hangzhou Marathon as an example, analysing the potential public security risks of a marathon and the application scenarios of UAVs by modelling the data of population and vehicles near the fundamental security early warning places of the marathon through theoretical discussion and modelling research. We propose a marathon risklevel intelligent identification and early warning model, establish the deployment and control scheme of UAVs in marathon public security, and conceive a comprehensive command platform for UAVs to promote the integration of UAVs into marathon security by taking intelligent security as an example.

Review on Patch Antennas for Unmanned Aerial Vehicle Application

The wide-ranging Unmanned Aerial Vehicle (UAV) applications making them be one of the Internet of Things promising technologies. The vast potential of monitoring and surveillance for public safety threats using drones be a current issue for researchers. Antennas play an important part in UAV to create reliable communication links. There are different types of antennas that can be used for UAV application depend on antennas size, efficiency, gain, angle of radiation pattern, polarization, etc. This paper mainly focuses on patch antennas for UAV applications. In general, there are two types of patch antenna is described which are single patch antenna and array antenna. The review of patch antennas can be a useful guideline to choose or design antenna for UAV applications in the future.

Aerodynamic Interference Analysis for a Nonoverlapping Multirotor UAV Based on Dynamic Vortex Tube

With the wide application of unmanned aerial vehicles, interest in multirotor conifgurations has increased. The unique features of multirotor con guration have been intensely investigated, including aerodynamic interference, which is particularly important because it in uences the vibration, noise, and handling quality of rotorcraft. Most previous studies have used high-fidelity approaches, such as computational fluid dynamics to identify such interference. However, such an approach is inappropriate for real-time flight simulations. In this study, an improved aerodynamic interference analysis based on a dynamic vortex tube was established for performance prediction in real-time ight simulation. A simple and effective formulation is proposed for integration with rotor aerodynamics to evaluate the interference of multirotor con gurations. The present analysis is validated on various multirotor configurations. An investigation of interference in a multirotor unmanned aerial vehicle (UAV) is then presented. The analysis results exhibit good agreement with experimental results and high-fidelity predictions. Although the accuracy of the proposed analysis is lower than that of experimental studies and high-fidelity analyses, it is suf cient for capturing interference trends. The proposed analysis can account for aerodynamic interference in the flight simulation of a multirotor UAV.

Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible

UAV-based Herbicide Application for Efficient Weed Management in Direct-seeded Rice

Background: Weeds are the key pest, which reduce crop productivity. Direct-seeded rice is very prone to early-stage weed infestation during initial crop development. Cultural and mechanical methods are difficult due to unavailability of labour and poor work efficiency. Hence, use of herbicides is an effective method for timely weed control. However, the efficacy of agrochemicals depends on the efficiency of spraying equipment. Conventional knapsack sprayers are used most often to spray herbicides but they are highly time-consuming, labour intensive and labour drudgery practices. Hence, the current experiment was aimed to study the efficiency of unmanned aerial vehicles (UAVs) on weed management. Methods: A field experiment was conducted at Tamil Nadu Agricultural University, Coimbatore during summer, 2022 to evaluate the efficacy of UAV-based herbicide application in direct-seeded rice. The study comprised of five weed management treatments such as pre emergence application of pretilachlor with safener and pyrazosulfuron through both UAV and knapsack sprayer and unweeded check as control. The experimental plot was laid out in a randomized block design with four replications. Result: The experimental findings showed that the application of pre-emergence pretilachlor significantly reduced the density and dry weight of grasses, sedges and broad leaved weeds in knapsack application. Moreover, it was found on par with UAV application of same herbicide without any phytotoxicity to rice seedlings. From the experiment, the application of pre-emergence pretilachlor through UAV is found to be more effective for timely weed control during early stages in direct-seeded rice, which reduce the labour intensity and drudgery than knapsack application.

High-Quality Object Detection Method for UAV Images Based on Improved DINO and Masked Image Modeling

The extensive application of unmanned aerial vehicle (UAV) technology has increased academic interest in object detection algorithms for UAV images. Nevertheless, these algorithms present issues such as low accuracy, inadequate stability, and insufficient pre-training model utilization. Therefore, a high-quality object detection method based on a performance-improved object detection baseline and pretraining algorithm is proposed. To fully extract global and local feature information, a hybrid backbone based on the combination of convolutional neural network (CNN) and vision transformer (ViT) is constructed using an excellent object detection method as the baseline network for feature extraction. This backbone is then combined with a more stable and generalizable optimizer to obtain high-quality object detection results. Because the domain gap between natural and UAV aerial photography scenes hinders the application of mainstream pre-training models to downstream UAV image object detection tasks, this study applies the masked image modeling (MIM) method to aerospace remote sensing datasets with a lower volume than mainstream natural scene datasets to produce a pre-training model for the proposed method and further improve UAV image object detection accuracy. Experimental results for two UAV imagery datasets show that the proposed method achieves better object detection performance compared to state-of-the-art (SOTA) methods with fewer pre-training datasets and parameters.

An Intelligent UAV Path-Planning Method Based on the Theory of the Three-Dimensional Subdivision of Earth Space

With the rapid development of the big data era, Unmanned Aerial Vehicles (UAVs) are being increasingly adopted for various complex environments. This has imposed new requirements for UAV path planning. How to efficiently organize, manage, and express all kinds of data in complex scenes and intelligently carry out fast and efficient path planning for UAVs are new challenges brought about by UAV application requirements. However, traditional path-planning methods lack the ability to effectively integrate and organize multivariate data in dynamic and complicated airspace environments. To address these challenges, this paper leverages the theory of the three-dimensional subdivision of earth space and proposes a novel environment-modeling approach based on airspace grids. In this approach, we carried out the grid-based modeling and storage of the UAV flight airspace environment and built a stable and intelligent deep-reinforcement-learning grid model to solve the problem of the passage cost of UAV path planning in the real world. Finally, we designed multiple sets of experiments to verify the efficiency of the global subdivision coding system as an environmental organization framework for path planning compared to a longitude–latitude system and to demonstrate the superiority of the improved deep-reinforcement-learning model in specific scenarios.

A Three-Dimensional Full-Coverage Operation Path Planning Method for Plant Protection Unmanned Aerial Vehicles Based on Energy Consumption Modeling

With the rapid development of precision agriculture technology worldwide, plant protection unmanned aerial vehicles (UAVs) have been widely applied in the prevention and control of agricultural pests and diseases due to their advantages such as unrestricted terrain, strong maneuverability, hover capability, and high operational efficiency. In view of the fact that most of the current path planning methods for plant protection UAVs are mainly applicable to large fields with relatively flat terrain, and there is a lack of three-dimensional path planning methods applicable to hilly orchards, as well as a lack of intuitive evaluation of the advantages and disadvantages of the paths by utilizing the amount of energy consumption, this paper proposes a three-dimensional (3D) path planning method for plant protection UAVs in hilly orchards. The method utilizes the three-dimensional (3D) coordinates of the operational area obtained from a realistic 3D model of the area, and determines the 3D operational path through the use of Boustrophedon Cellular Decomposition and the height variations of the operational area. Based on the induced power used by the plant protection UAV for flight and the power needed to overcome wind resistance, combined with the change of the load of the plant protection UAV and the supply situation, the relative energy consumption model of the plant protection UAV is constructed. Then, by optimizing the operational heading angle (1–180°), the 3D path with the minimum relative energy consumption is obtained. Through a simulation test, it is demonstrated that the path with the minimum relative energy consumption (operational heading angle of 133°) reduces the average relative energy consumption by 62.44% and 47.21% compared to the path with the maximum relative energy consumption (operational heading angle of 51°) and the average relative energy consumption, respectively. This proves the feasibility of the proposed path planning method in hilly orchard environments and provides a reference for the application of plant protection UAVs in such orchards.