Ability Of Unmanned Aerial Vehicles Research Articles

İnsansız Hava Araçları (İHA) İçin Küresel Navigasyon Uydu Sistemi (GNSS) Bağımsız Navigasyon

The ability of Unmanned Aerial Vehicles (UAV) to perform autonomous navigation depends on the accurate determination of their positions provided by the Global Navigation Satellite System (GNSS). For position determination and environmental orientation during flight, UAVs are usually equipped with electronic equipment such as GNSS, Inertial Measurement Unit (IMU), gyroscope and accelerometer. However, the GNSS signal may be lost or distorted due to poor weather, obstacles or terrain, the unfavorable position of satellites, spoofing and jamming. In such cases of GNSS signal loss or deterioration, the IMU alone becomes unable to provide reliable UAV location information. Especially in cases where there is not enough visibility and the UAV cannot be brought to the take-off point by manual operation, the loss of the GNSS signal causes great losses. In this paper, GNSS independent flight and navigation studies are included. It is seen that the use of hybrid navigation solutions has great importance in GNSS independent UAV flights.

Spectral purification improves monitoring accuracy of the comprehensive growth evaluation index for film-mulched winter wheat

In order to further improve the utility of unmanned aerial vehicle (UAV) remote-sensing for quickly and accurately monitoring the growth of winter wheat under film mulching, this study examined the treatments of ridge mulching, ridge–furrow full mulching, and flat cropping full mulching in winter wheat. Based on the fuzzy comprehensive evaluation (FCE) method, four agronomic parameters (leaf area index, above-ground biomass, plant height, and leaf chlorophyll content) were used to calculate the comprehensive growth evaluation index (CGEI) of the winter wheat, and 14 visible and near-infrared spectral indices were calculated using spectral purification technology to process the remote-sensing image data of winter wheat obtained by multispectral UAV. Four machine learning algorithms, partial least squares, support vector machines, random forests, and artificial neural network networks (ANN), were used to build the winter wheat growth monitoring model under film mulching, and accuracy evaluation and mapping of the spatial and temporal distribution of winter wheat growth status were carried out. The results showed that the CGEI of winter wheat under film mulching constructed using the FCE method could objectively and comprehensively evaluate the crop growth status. The accuracy of remote-sensing inversion of the CGEI based on the ANN model was higher than for the individual agronomic parameters, with a coefficient of determination of 0.75, a root mean square error of 8.40, and a mean absolute value error of 6.53. Spectral purification could eliminate the interference of background effects caused by mulching and soil, effectively improving the accuracy of the remote-sensing inversion of winter wheat under film mulching, with the best inversion effect achieved on the ridge–furrow full mulching area after spectral purification. The results of this study provide a theoretical reference for the use of UAV remote-sensing to monitor the growth status of winter wheat with film mulching.

Leaf area index estimation of pergola-trained vineyards in arid regions using classical and deep learning methods based on UAV-based RGB images

Timely and accurate mapping of leaf area index (LAI) in vineyards plays an important role for management choices in precision agricultural practices. However, only a little work has been done to extract the LAI of pergola-trained vineyards using higher spatial resolution remote sensing data. The main objective of this study was to evaluate the ability of unmanned aerial vehicle (UAV) imageries to estimate the LAI of pergola-trained vineyards using shallow and deep machine learning (ML) methods. Field trials were conducted in different growth seasons in 2021 by collecting 465 LAI samples. Firstly, this study trained five classical shallow ML models and an ensemble learning model by using different spectral and textural indices calculated from UAV imageries, and the most correlated or useful features for LAI estimations in different growth stages were differentiated. Then, due to the classical ML approaches need the arduous computation of multiple indices and feature selection procedures, another ResNet-based convolutional neural network (CNN) model was constructed which can be directly fed by cropped images. Furthermore, this study introduced a new image data augmentation method which is applicable to regression problems. Results indicated that the textural indices performed better than spectral indices, while the combination of them can improve estimation results, and the ensemble learning method showed the best among classical ML models. By choosing the optimal input image size, the CNN model we constructed estimated the LAI most effectively without extracting and selecting the features manually. The proposed image data augmentation method can generate new training images with new labels by mosaicking the original ones, and the CNN model showed improved performance after using this method compared to those using only the original images, or augmented by rotation and flipping methods. This data augmentation method can be applied to other regression models to extract growth parameters of crops using remote sensing data, and we conclude that the UAV imagery and deep learning methods are promising in LAI estimations of pergola-trained vineyards.

Simulation and modeling of manipulator for unmanned aerial vehicles

In order to improve the operation ability of unmanned aerial vehicles (UAV), this paper designs a lightweight manipulator for quadrotor UAV. First, according to the requirements of the task and the load of the UAV, an aerial manipulator with lightweight and small moment of inertia is designed, and the 3D model of the manipulator is established in the Creo software. The maximum deformation and stress under different load conditions were analyzed by Ansys Workbench software, and the dynamic analysis was carried out in ADAMS software to obtain the driving moment required by each joint of the manipulator under load conditions. Finally, the dynamic model of the aerial manipulator system is established according to the Newton-Euler method, and the maximum workspace of the manipulator in the hovering state is generated by the Monte Carlo method. The research results show that the deformation and stress level are small, and the workspace meets the operation requirements, which proves that the designed manipulator has certain engineering application value.

Monitoring maize canopy chlorophyll density under lodging stress based on UAV hyperspectral imagery

Lodging causes severe decreases in crop yield, reduces grain quality, and increases the difficulty of mechanical harvesting. Obtaining the spatial distribution information of maize lodging grades in a timely and accurate manner is essential for yield loss assessment, post-stress management, and insurance claims settlements. The purpose of this study is to explore the ability of unmanned aerial vehicle (UAV) imaging technology to monitor maize lodging stress. With the support of maize lodging control experiments, the canopy chlorophyll density (CCD) of maize populations under stress from different lodging grades was used as the characterization index. The responses between hyperspectral characteristic parameters and CCD with different lodging grade stresses were analyzed. The monitoring model of the maize CCD under lodging stress was constructed using the sensitive characteristic parameters of original canopy spectra (OCS), first-order differential (FOD), wavelet coefficient (WC), and vegetation index (VI). The results showed that the reflectance of the stalk was significantly higher than that of the leaf in hyperspectral imagery, which was the main reason for the change in the original canopy spectra under lodging stress. The original canopy spectral reflectance increased with the severity of lodging stress. The accuracy of the CCD model was VI > WC > FOD > OCS (R2 = 0.63, 0.61, 0.59, 0.57, respectively), in which the accuracy of VI was the highest (R2 = 0.63, RMSE = 0.36 g/m3). This is because CCD considers not only the change in canopy spatial structure after maize lodging, but also the change in physiological activity of maize plants under lodging stress. The maize lodging grades were evaluated according to the CCD model based on the UAV hyperspectral imagery.

UAV cooperative air combat maneuver decision based on multi-agent reinforcement learning

In order to improve the autonomous ability of unmanned aerial vehicles (UAV) to implement air combat mission, many artificial intelligence-based autonomous air combat maneuver decision-making studies have been carried out, but these studies are often aimed at individual decision-making in 1v1 scenarios which rarely happen in actual air combat. Based on the research of the 1v1 autonomous air combat maneuver decision, this paper builds a multi-UAV cooperative air combat maneuver decision model based on multi-agent reinforcement learning. Firstly, a bidirectional recurrent neural network (BRNN) is used to achieve communication between UAV individuals, and the multi-UAV cooperative air combat maneuver decision model under the actor-critic architecture is established. Secondly, through combining with target allocation and air combat situation assessment, the tactical goal of the formation is merged with the reinforcement learning goal of every UAV, and a cooperative tactical maneuver policy is generated. The simulation results prove that the multi-UAV cooperative air combat maneuver decision model established in this paper can obtain the cooperative maneuver policy through reinforcement learning, the cooperative maneuver policy can guide UAVs to obtain the overall situational advantage and defeat the opponents under tactical cooperation.

Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance

Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The R2 values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (R2 = 0.625) and limited (R2 = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat.

Optimal Edge Computing for Infrastructure-Assisted UAV Systems

The ability of Unmanned Aerial Vehicles (UAV) to autonomously operate is constrained by the severe limitations of their on-board resources. The limited processing capacity and energy storage of these devices inevitably makes the real-time analysis of complex signals – the key to autonomy – challenging. In urban environments, the UAVs can leverage the communication and computation resources of the surrounding city-wide Internet of Things infrastructure to enhance their capabilities. For instance, the UAVs can interconnect with edge computing resources and offload computation tasks to improve response time to sensor input and reduce energy consumption. However, the complexity of the urban topology and large number of devices and data streams competing for the same network and computation resources create an extremely dynamic environment, where poor channel conditions and edge server congestion may penalize the performance of task offloading. This paper develops a framework enabling optimal offloading decisions as a function of network and computation load parameters and current state. The optimization is formulated as an optimal stopping time problem over a semi-Markov process. We solve the optimization problem using Dynamic Programming and Deep Reinforcement learning at different levels of abstraction and prior knowledge of the system underlying stochastic processes. We validate our results in a realistic scenario, where a UAV performs a building inspection task while connected to an edge server.

Infrared and Visible Airborne Targets Image Fusion with Applications to Sense and Avoid

Machine vision has revealed great potential in recent years for Sense and Avoid (SAA) ability of Unmanned Aerial Vehicle (UAV). However, the target perception capability of machine vision largely depends on illumination, which restricts UAV to move safely in dark environment. Since images acquired by infrared and visible sensors are complementary in most cases, enhancing image qualities in dark environments by fusion of infrared and visible images is a promising solution. By considering the difficulties of image fusion for airborne targets, a Convolutional Sparse Representation (CSR) based infrared and visible airborne targets image fusion algorithm is proposed in this paper for enhancing SAA capability of UAV in dark environments, which contains three parts: image decomposition, image transformation and image reconstruction. A series of registered infrared and visible images containing airborne targets are selected to evaluate the algorithm proposed in this paper. Simulation results demonstrate the algorithm proposed in this paper effectively increases image qualities in dark environments. In the aspects of fusion metrics, the algorithm proposed in this paper can achieve favorable performance against other image fusion algorithms.

Small unmanned aerial model accuracy for photogrammetrical fluvial bathymetric survey

Fluvial systems offer a challenging and varied environment for topographic survey, displaying a rapidly varying morphology, vegetation assemblage and degree of submergence. Traditionally theodolite or GPS based systems have been used to capture cross-section and breakline based topographic data which has subsequently been interpolated. Advances in survey technology has resulted in an improved ability to capture larger volumes of information with infrared terrestrial and aerial LiDAR systems capturing high density (<0.02 m) point data across terrestrial surfaces. The rise of Structure from Motion (SfM) photogrammetry, coupled with small unmanned aerial vehicles (sUAV), has potential to record elevation data at reach scale sub decimetre density. The approach has the additional advantage over LiDAR of seeing through clear water to capture bed detail, whilst also generating ortho-rectified photographic mosaics of the survey reach. However, data accuracy has yet to be comprehensively assessed. Here we present a survey protocol for sUAV deployment and provide a reach scale comparison between a theodolite and SfM sUAV survey on the River Sprint, Kendal, the River Ehen at Egremont, England and the Afon Elwy, at Llanfair Talhaiarn, Wales. Comparative analysis between theodolite survey and SfM suggest similar accuracy and precision across terrestrial surfaces with error lowest over solid surfaces, increasing with vegetation complexity. Submerged SfM data, captured bed levels generally to within ±0.25 m with only a weak relationship recorded between error and flow depth. Significantly, associated error when linked to channel D50 highlights the ability of unmanned aerial vehicles to capture accurate fluvial data across a range of river biotopes and depths to 2.4 m.

UAV data for multi-temporal Landsat analysis of historic reforestation: a case study in Costa Rica

ABSTRACTThe use of the Landsat constellation to quantify historic deforestation and reforestation over time is well established. This analysis, however, requires ground-referenced data that is often inaccessible in remote areas or expensive if no existing high-resolution satellite imagery exists. In response, we evaluate the capability of unmanned aerial vehicle (UAV) imagery to serve as ground-reference data for identifying land-cover classes in Landsat imagery. We then apply these classes to quantify 30 years of historical deforestation and reforestation of an ecological reserve in Costa Rica. While spatial and spectral disparities between the sensors limit the generalization of the approach, our results demonstrate the ability of UAV and Landsat data to inexpensively classify a reserve’s historic land cover over time and suggest an 11 year period for land cover to transition from pasture to secondary forest in lowland tropical environments.