Unmanned Aerial Vehicles Research Articles

Structural design of a single-rotor variant transmedia unmanned aerial vehicle

ABSTRACT Water air cross-medium vehicles have the advantage of cross-domain flight and have gradually become a research hotspot. However, existing technologies cannot provide better hydrodynamic performance while achieving efficient cross-medium vehicle efficiency. In this paper, A variant mechanism was designed based on the external characteristics of the submarine to achieve integrated of the rotor and the main hull of the aircraft, ensuring the underwater hydrodynamic performance of the aircraft. A tiltable tail rotor was designed to ensure stable flight of the aircraft in the airspace. To ensure the feasibility of the design, a computational fluid dynamics simulation was conducted on the hydrodynamic and aerodynamic performance of the spacecraft and rotor. The results show that the spacecraft can not only achieve stable navigation underwater and in the air, with good hydrodynamic and aerodynamic performance but also have advantages such as improving the efficiency of cross-medium vehicles and increasing their service.

Enhanced visual detection of litchi fruit in complex natural environments based on unmanned aerial vehicle (UAV) remote sensing

Enhanced visual detection of litchi fruit in complex natural environments based on unmanned aerial vehicle (UAV) remote sensing

Multi-UAV cooperative task assignment based on multi-strategy improved DBO

Effective task assignment technology plays a pivotal role in optimizing Unmanned Aerial Vehicles operations during the collaboration of multiple Unmanned Aerial Vehicles (multi-UAV) in combat scenarios. Therefore, aiming at the cooperative task assignment of multi-UAV, this paper takes the value and time window of the ground target into consideration, takes the total fuel consumption, execution time, and execution cost of all tasks completed by multi-UAV as the objective functions, constructs a multi-objective multi-task assignment mathematical model, and proposes a multi-strategy improved Dung Beetle Optimizer (MIDBO) to solve the model. The MIDBO employs Sinusoidal chaotic mapping to generate the initial population, enhancing population diversity. Additionally, it integrates the nonlinear convergence factor and spiral search factor to augment the exploration capabilities of the rolling dung beetles. Moreover, by incorporating the subtraction average strategy, the algorithm bolsters the prowess of the foraging dung beetles, leading to improved algorithmic performance and attaining high-quality solutions. The experimental results show that the multi-UAV collaborative task assignment based on the MIDBO can enhance the global optimization ability and assign the optimal task sequence to multi-UAV.

A Comparative Study on Battery Modelling via Specific Hybrid Pulse Power Characterization Testing for Unmanned Aerial Vehicles in Real Flight Conditions

A Comparative Study on Battery Modelling via Specific Hybrid Pulse Power Characterization Testing for Unmanned Aerial Vehicles in Real Flight Conditions

A dexterous and compliant aerial continuum manipulator for cluttered and constrained environments

Aerial manipulators can manipulate objects while flying, allowing them to perform tasks in dangerous or inaccessible areas. Advanced aerial manipulation systems are often based on rigid-link mechanisms, but the balance between dexterity and payload capacity limits their broader application. Combining unmanned aerial vehicles with continuum manipulators emerges as a solution to this trade-off, but these systems face challenges with large actuation systems and unstable control. To address these challenges, we propose Aerial Elephant Trunk, an aerial continuum manipulator inspired by the elephant trunk, featuring a small-scale quadrotor and a dexterous, compliant tendon-driven continuum arm for versatile operation in both indoor and outdoor settings. We develop state estimation for the quadrotor using an Extended Kalman Filter, shape estimation for the continuum arm based on piecewise constant curvature, and whole-body motion planning using minimum jerk principles. Through comprehensive fundamental verifications, we demonstrate that our system can adapt to various constrained environments, such as navigating through narrow holes, tubes, or crevices, and can handle a range of objects, including slender, deformable, irregular, or heavy items. Our system can potentially be deployed in challenging conditions, such as pipeline maintenance or electricity line inspection at high altitudes.

Plant Detection in RGB Images from Unmanned Aerial Vehicles Using Segmentation by Deep Learning and an Impact of Model Accuracy on Downstream Analysis.

Crop field monitoring using unmanned aerial vehicles (UAVs) is one of the most important technologies for plant growth control in modern precision agriculture. One of the important and widely used tasks in field monitoring is plant stand counting. The accurate identification of plants in field images provides estimates of plant number per unit area, detects missing seedlings, and predicts crop yield. Current methods are based on the detection of plants in images obtained from UAVs by means of computer vision algorithms and deep learning neural networks. These approaches depend on image spatial resolution and the quality of plant markup. The performance of automatic plant detection may affect the efficiency of downstream analysis of a field cropping pattern. In the present work, a method is presented for detecting the plants of five species in images acquired via a UAV on the basis of image segmentation by deep learning algorithms (convolutional neural networks). Twelve orthomosaics were collected and marked at several sites in Russia to train and test the neural network algorithms. Additionally, 17 existing datasets of various spatial resolutions and markup quality levels from the Roboflow service were used to extend training image sets. Finally, we compared several texture features between manually evaluated and neural-network-estimated plant masks. It was demonstrated that adding images to the training sample (even those of lower resolution and markup quality) improves plant stand counting significantly. The work indicates how the accuracy of plant detection in field images may affect their cropping pattern evaluation by means of texture characteristics. For some of the characteristics (GLCM mean, GLRM long run, GLRM run ratio) the estimates between images marked manually and automatically are close. For others, the differences are large and may lead to erroneous conclusions about the properties of field cropping patterns. Nonetheless, overall, plant detection algorithms with a higher accuracy show better agreement with the estimates of texture parameters obtained from manually marked images.

ALDNet: a lightweight and efficient drone detection network

Abstract With the growing use of unmanned aerial vehicles (UAVs), it poses a potential threat to public safety, so drone detection has become an increasingly important research direction. However, the irregular shooting angles, deformations, significant target scale variations, and complex backgrounds in UAV imagery pose challenges for existing object detection models. To address these issues, we propose ALDNet, a precise and lightweight UAV image object detection network built on an improved RT-DETR model. First, we introduce the Position Accurate Continuous Convolution (PAC), which dynamically adjusts convolution kernel coordinates, allowing flexibility in detecting objects of varied shapes. PAC improve the ability of backbone network to capture objects with different shapes. Second, we present an enhanced multi-scale feature fusion (EMF) approach that integrates spatial information more effectively, reducing the loss of fine-grained details during fusion. Additionally, we propose the Inner-GIOU loss function, which reduces interference and accelerates the convergence of bounding box optimisation, thus improving the overall detection performance. We conducted experiments on three UAV image datasets, Det-Fly, ARD-MAV and VisDrone, and compared the ALDNet results with the RT-DETR model. The experimental results show that ALDNet achieved 98.3\%, 97.4\% and 48.1\% mAP50 values on Det-Fly, ARD-MAV and VisDrone, which are 1.5\%, 0.4\% and 1.9\% higher than RT-DETR, respectively, and the number of parameters and computation amount of ALDNet are 25\% and 14\% less than the baseline, respectively. Experimental results show that ALDNet achieves greater efficiency and effectiveness with less computational power.

An Intent Recognition Method for Aerial Swarm Based on Attention Pooling Mechanism

In the realm of unmanned aerial vehicle (UAV) swarm intent recognition, conventional approaches predominantly focus on the attributes derived from singular targets at discrete instances. This trend leads to a significant limitation: the inability to effectively harness and capture the collective feature information of the entire swarm over temporal sequences. To address this gap, this study introduces a comprehensive end-to-end UAV swarm intent recognition approach. Initially, this method utilizes the distance threat coefficient and angular threat coefficient between UAVs to construct the graphical structural representation of the UAV swarm. Subsequently, an innovative deep learning framework, designated as attention-pool based on graph attention network and long short-term memory, which integrates a graph attention network, a novel graph pooling strategy, and a long short-term memory, is developed. This architecture can process the graphically structured data derived from the swarm modeling and accurately deduce the collective intent. Through experimental validation and analyses against existing methodologies, as well as ablation studies, it is evidenced that the model outperforms state-of-the-art methods in terms of accuracy of intent recognition.

An improved DeepLabv3 + railway track extraction algorithm based on densely connected and attention mechanisms

The railway track extraction using unmanned aerial vehicle (UAV) aerial images suffers from issues such as low extraction accuracy and high time consumption. In response to these problems, this paper presents a lightweight algorithm DA-DeepLabv3 + based on densely connected and attention mechanisms. Firstly, the lightweight MobileNetV2 network is employed to replace the Xception feature extraction network, thereby reducing the number of model parameters. Secondly, the receptive field is enlarged by cascading atrous convolutions with different dilation rates in the ASPP (atrous spatial pyramid pooling) module, and other feature maps are concatenated using the multi-scale attention module to enhance the extraction accuracy of the model. Finally, a multi-level upsampling module is designed to enhance the accuracy of boundary contour extraction. Furthermore, a dedicated dataset for railway track segmentation was established to train and evaluate the proposed method. The experimental results indicate that DA-DeepLabv3 + demonstrates significant improvement on the railway track segmentation dataset as well as the DeepGlobe dataset. It achieves mIoU scores of 87.52% and 85.01%, along with accuracy rates of 97.59% and 94.84%, respectively. Compared to classical semantic segmentation networks such as U-Net and DeepLabv3 + , DA-DeepLabv3 + achieves higher extraction accuracy and shorter running time.

Innovative segmentation technique for aerial power lines via amplitude stretching transform

Accurate segmentation of power line targets helps quickly locate faults, evaluate line conditions, and provides key image data support and analysis for the safe and stable operation of the power system.The aerial power line in segmentation due to the target is small, and the imaging reflected energy is weak, so the Unmanned Aerial Vehicle (UAV) aerial power line image is very susceptible to the interference of the environment line elements and noise, resulting in the detection of the power line target in the image of the defective, intermittent, straight line interferences and other low accuracy and real-time efficiency is not high. For this reason, this paper designs a pure amplitude stretching kernel function to form a Fourier amplitude vector field and uses this amplitude vector field to implement the stretching transformation of the amplitude field of the aerial power line image, so that the angular field after the Fourier inverse transformation can better react to the spatial domain line targets, and finally, after the Relative Total Variation (RTV) processing, the power line can be well detected. The proposed algorithm is compared with the main power line segmentation algorithms, such as Region Convolutional Neural Networks(R-CNN) and Phase Stretch Transform(PST). The average values of evaluation indicators PPA, MMPA and MMIoU of the image segmentation results of the proposed algorithm reach 0.96, 0.96 and 0.95 respectively, and the average time lag of detection is less than 0.2s, indicating that the accuracy and real-time performance of the segmentation results of the proposed algorithm are significantly better than those of the above algorithms.

Practical error prediction in UAV imagery-based 3D reconstruction: assessing the impact of image quality factors

ABSTRACT Over the past decade, Structure-from-Motion (SfM) and Multi-View Stereo (MVS) techniques have been highly effective in generating high-quality 3D point clouds, especially when integrated with Unmanned Aerial Vehicles (UAVs). However, accurately predicting errors in these point clouds remains challenging. This study introduces a predictive model for quantifying errors in point clouds generated using SfM-MVS, based on 2D image error propagation. We analysed the impact of four key image quality factors – exposure, resolution, blur (including motion and out-of-focus blur), and noise – on 2D image errors. These factors are determined using nine practical parameters belonging to camera settings (ISO, shutter speed, F-number, and pixel resolution), UAV flight methods (speed and distance), camera specifications (sensor size and focal length), and illumination conditions. To account for variations in SfM-MVS output quality due to software and camera model differences, we introduced two experimentally calibratable constants: the maximum template size and the noise sensitivity coefficient. We validated our error prediction model by comparing the predicted errors with observations from a reference indoor target, utilizing a total of 258 image sets acquired with varying parameter combinations. The model demonstrated high predictive accuracy, achieving an R2 value of 0.84. This confirms the effectiveness and feasibility of our model in accurately predicting point cloud errors using the nine parameters.

Control and Applications of Intelligent Unmanned Aerial Vehicles

Control and Applications of Intelligent Unmanned Aerial Vehicles

RCFormer: radiation correction method for degraded multispectral UAV images using vision transformers

ABSTRACT In modern remote sensing technology, Unmanned Aerial Vehicles (UAVs) have become crucial data acquisition platforms. However, low-altitude remote sensing images from UAVs are often affected by atmospheric scattering and absorption, particularly under conditions like haze, which severely degrade image quality. Traditional radiation correction methods cannot accurately capture the true reflectance of ground objects under these conditions. This paper introduces RCFormer, an innovative Transformer-based network architecture. It combines the self-attention mechanism of Swin Transformer with a novel network structural design, especially incorporating parallel convolutional structures to enhance the extraction capability of surface features. Additionally, with the integration of atmospheric characteristic refinement module (ACRM) and Multi-scale Feature Fusion Gate (MFFG), the proposed RCFormer not only captures atmospheric information from deep features but also effectively fuses features across different scales, thereby improving the accuracy, transferability and robustness of the radiation correction model. Finally, quantitative and qualitative evaluations using real-world data demonstrate that RCFormer outperforms other dehazing networks in both degraded and haze-free images while also offering good efficiency and ease of operation.

Detection of Crop Damage in Maize Using Red–Green–Blue Imagery and LiDAR Data Acquired Using an Unmanned Aerial Vehicle

Detection of Crop Damage in Maize Using Red–Green–Blue Imagery and LiDAR Data Acquired Using an Unmanned Aerial Vehicle

A framework for upscaling aboveground biomass from an individual tree to landscape level and qualifying the multiscale spatial uncertainties for secondary forests

ABSTRACT Secondary forests, a typical forest type in the sub-frigid zone of Northeast China, have significant potential for carbon sequestration. Accurate estimation of the Aboveground Biomass (AGB) of secondary forests and assessment of multiscale uncertainties are crucial for promoting Reduced Emissions from Deforestation and Degradation. This study developed a novel framework to upscale the AGB estimation from the tree to the landscape level and assessed multiscale uncertainties based on multi-platform laser scanning data and Unmanned Aerial Vehicle (UAV) hyperspectral images. The framework included two stages: (1) quantifying multiple uncertainties (uncertainties of individual tree crown delineation, individual tree parameters estimation, and tree species classification) in individual tree-based AGB estimation using Monte Carlo simulations; (2) upscaling the plot to the landscape level estimated AGB using the Nonlinear Simultaneous Equation (NSE) with error-in-variables and quantifying the uncertainties of model residuals, model parameters, and model independent variables. The findings revealed a high accuracy from tree to plot AGB estimation (R2: 0.75, Root Mean Square Error (RMSE): 6.65 Mg/ha, relative RMSE (rRMSE): 5.40%), with the total and relative uncertainties of 16.85 Mg/ha and 16.29%, respectively, with the highest uncertainty (9.73 Mg/ha) observed in tree species classification. The AGB estimation using NSE achieved an R2 of 0.69, with an RMSE of 9.91 Mg/ha and an rRMSE of 10.43% from the plot to landscape level; and the uncertainties caused by model parameters, independent variables, and residuals were 5.52 Mg/ha, 14.56 Mg/ha, and 25.25 Mg/ha, respectively, accounting for 3.46%, 24.09%, and 72.45% of the total uncertainty. This study develops a framework for large-scale AGB estimation of mixed forests based on the individual tree approach and uncertainty quantification of multiscale estimates and provides a foundation for precise forestry, sustainable forest management, and carbon neutrality.

Exploration of Three-dimensional Modeling by Unmanned Aerial Vehicles for Application in Practical Engineering

Citing actual engineering cases, this paper aims to enhance the application of the model in actual engineering by describing the experience gained in the process of generating 3D stereo models generated by UAV aerial surveys, as well as the characteristics of the aerial photography and model generation process.

Research on Sensitivity Improvement Methods for RTD Fluxgates Based on Feedback-Driven Stochastic Resonance with PSO.

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

Model-based definition-assisted asset administration shell as enabler for smart production line

ABSTRACT The smart production line needs to adapt continuously to satisfy the growing demand for customized products. However, the inability of equipment to interoperate effectively hampers the quick reconfiguration of smart production lines. The Reference Architecture Model for Industry 4.0 (RAMI4.0) introduces the Asset Administration Shell (AAS) as a novel method to enhance interoperability in Industry 4.0 (I4.0). AAS creates a digital representation of assets. To further enhance the efficiency of AAS configuration, this paper presents the Model-Based Definition (MBD)-assisted AAS (MBD-AAS) specifically for designing smart production lines. MBD-AAS streamlines AAS configuration and facilitates plug-and-play (PnP) capabilities for equipment in smart production lines. This study validates the practicality and advantages of MBD-AAS through a case study focused on an unmanned aerial vehicle (UAV) production line design. The experimental findings indicate that MBD-AAS enhances the interoperability of AAS and decreases the design time for UAV production lines.

Edge Computing-Aided Dynamic Wireless Charging and Trip Planning of UAVs

In today’s era of rapid technological advancement, unmanned aerial vehicles (UAVs) are transforming sectors such as remote delivery, surveillance, and disaster response. However, challenges related to energy consumption and operational efficiency continue to hinder their broader adoption. To address these issues, this study proposes an integrated system design combining dynamic wireless charging (DWC), intelligent trip planning, and intelligent edge computing (IEC). The proposed system leverages IEC for local data processing to reduce latency and optimize energy management, 6G networks for real-time vehicle-to-infrastructure (V2I) communication, and DWC to enable efficient, on-the-go energy replenishment. Additionally, a dynamic arrival management algorithm is introduced to minimize UAV wait times to enhance operational efficiency. Simulations of this system demonstrated significant improvements: larger UAVs achieved an average charging efficiency of 91.2%, while smaller UAVs achieved 92.75%, with dynamic arrival management reducing wait times by an average of 1.5 min for smaller UAVs and 5.0 min for larger UAVs. These findings underscore the system’s effectiveness in optimizing UAV operations and charging efficiency. This integrated approach offers a scalable framework to enhance UAV capabilities and sets a benchmark for future advancements in operational efficiency and charging technology for urban and environmental applications.

Efficient Threshold Attribute-Based Signature Scheme for Unmanned Aerial Vehicle (UAV) Networks

Unmanned aerial vehicles (UAVs) are highly versatile and cost-effective, making them an attractive option for various applications. In UAV networks, it is essential to implement a digital signature scheme to ensure the integrity and authentication of commands sent to UAVs. Moreover, this digital signature scheme not only maintains the real-time performance of UAVs while executing commands but also protects the identity privacy of the signer. To meet these needs, we propose an efficient threshold attribute-based proxy signature (t-ABPS) scheme that integrates a threshold predicate specifically designed for UAV networks. The formal security proof for the t-ABPS scheme demonstrates its existential unforgeability under selective-attribute and chosen-message attacks (EUF-sA-CMA) in the random oracle model. This scheme also ensures the identity privacy of the signer. Furthermore, we evaluate the computational costs and communication costs associated with the proposed scheme. Our analysis indicates that the t-ABPS scheme is more computationally efficient than other existing attribute-based proxy signature schemes, but it has higher communication costs.