Artificial Intelligence Assisted Autonomous Unmanned Aerial Vehicles (UAVs) and Aerial drones based on Machine Vision for Enhancing Remote Sensing of Precision crop Health Monitoring

Fixed-wing vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV)s are designed to combine the advantages of multi-rotor UAVs and fixed-wing UAVs in different flight phases in a single UAV. Fixed-wing VTOL UAVs can achieve the mobility of multi-rotor UAVs in hovering, vertical take-off and landing flight phases. Since fixed-wing UAVs are known for their efficiency in power consumption, fixed-wing VTOL UAVs were created to efficiently perform the cruise phase of the flight for a similar reason. In this paper, we made the conceptual design of a fixed-wing VTOL UAV which is called “DOGA”. The mission of DOGA is to carry 0.5 kg. payload. Firstly, maximum take-off weight was calculated, and then the airfoil profile, wings geometry, and the propulsion systems were determined. Also, design and performance parameters of DOGA were calculated. As a result, conceptual design of DOGA was completed and all the needed parameters for the detail design of the fixed-wing VTOL UAV were derived.

In recent years, inspired by technological progress and the outstanding performance of Unmanned Aerial Vehicles (UAVs) in several local wars, the UAV industry has witnessed explosive development, widely used in communication relay, logistics, surveying and mapping, patrol, surveillance, and other fields. Vertical Take-Off and Landing fixed-wing UAV has both the advantages of vertical take-off and landing of rotorcraft and the advantages of long endurance of fixed-wing UAV, which broadened its application field and is the most popular UAV at present. Recently, fixed-wing UAV failure analysis highlights that cruise engine shutdown is the most common reason for emergency landing, which is also a governing factor for Vertical Take-Off and Landing (VTOL) fixed-wing UAV failures. Nevertheless, the emergency landing trajectory of the latter UAV type after engine shutdown is different from that of the conventional fixed-wing UAVs due to the VTOL power system. Hence, spurred by the requirement of a safe emergency landing trajectory for VTOL fixed-wing UAVs, this paper develops an architecture capable of safe emergency landing for such platforms. The suggested method develops a particle dynamics model of the VTOL UAV and analyzes its aerodynamic characteristics utilizing Computational Fluid Dynamics (CFD) results. The UAV’s trajectory is divided into three parts for enhanced planning. For the guidance stage, the initial position and heading angle are arbitrary. Hence, the Dubins shortest cross-range and the fastest descent trajectory are adopted to steer the UAV above the landing window quickly. The spiral stage comprises a conical and cylindrical part combined with a spiral descent trajectory of variable radius for energy management and landing course alignment. Given the limited energy storage of VTOL power systems, the landing stage exploits an optimal control trajectory problem solved by a Gaussian pseudospectral method, involving trajectory conventional landing planning, unpowered landing, distance optimal landing, and wind-resistant landing. All trajectories meet the dynamics constraints, terminal constraints, and sliding performance constraints and cover both 2-dimensional and 3-dimensional trajectories. A large number of simulation experiments demonstrate that the proposed trajectories manage broad applicability and strong feasibility for VTOL fixed-wing UAVs.

Fixed-Wing Unmanned Aerial Vehicles (UAVs) have been improving significantly in application and versatility, sharing design similarities with airplanes, particularly at the design stage, when the take-off mass is used to estimate other characteristics. In this work, an internal database of UAVs is built to allow their comparison with airplanes under different parameters and assess key differences in patterns across UAV powertrains. The existing literature on speed vs. take-off mass is updated with 534 UAV entries, and a range vs. take-off mass diagram is created with 503 UAVs and 193 airplanes. Additionally, different transportation efficiency metrics are compared between UAVs and airplanes, highlighting scenarios advantageous for UAVs. A new paradigm focused on useful energy is then used to understand the underlying effectiveness of UAV implementations. Increasing useful energy is more effective in increasing the speed, transport work, and surveying work of internal combustion UAVs and more effective in increasing the range and endurance of battery-electric UAVs. Finally, it is observed that the mass of all fixed-wing aerial vehicles, both UAVs and airplanes, except for battery electric and solar, adheres to a well-defined scaling law based on useful energy. A parallel to this scaling law is suggested to describe future battery-electric UAVs and airplanes.

Various types of small drones constitute a modern threat for infrastructure and hardware, as well as for humans; thus, special-purpose radar has been developed in the last years in order to identify such drones. When studying the radar signatures, we observed that the majority of the scientific studies refer to multirotor aerial vehicles; there is a significant gap regarding small, fixed-wing Unmanned Aerial Vehicles (UAVs). Driven by the security principle, we conducted a series of Radar Cross Section (RCS) simulations on the Euclid fixed-wing UAV, which has a wingspan of 2 m and is being developed by our University. The purpose of this study is to partially fill the gap that exists regarding the RCS signatures and identification distances of fixed-wing UAVs of the same wingspan as the Euclid. The software used for the simulations was POFACETS (v.4.1). Two different scenarios were carried out. In scenario A, the RCS of the Euclid fixed-wing UAV, with a 2 m wingspan, was analytically studied. Robin radar systems’ Elvira Anti Drone System is the simulated radar, operating at 8.7 to 9.65 GHz; θ angle is set at 85° for this scenario. Scenario B studies the Euclid RCS within the broader 3 to 16 Ghz spectrum at the same θ = 85° angle. The results indicated that the Euclid UAV presents a mean RCS value (σ ¯) of −17.62 dBsm for scenario A, and a mean RCS value (σ ¯) of −22.77 dBsm for scenario B. These values are much smaller than the values of a typical commercial quadcopter, such as DJI Inspire 1, which presents −9.75 dBsm and −13.92 dBsm for the same exact scenarios, respectively. As calculated in the study, the Euclid UAV can penetrate up to a distance of 1784 m close to the Elvira Anti Drone System, while the DJI Inspire 1 will be detected at 2768 m. This finding is of great importance, as the obviously larger fixed-wing Euclid UAV will be detected about one kilometer closer to the anti-drone system.

ABSTRACTThe application of adequate nitrogen (N) fertilizers to grass seed crops is important to achieve high seed yield. Application of N will inevitably result in over-fertilization on some fields and, concomitantly, an increased risk of adverse environmental impacts, such as ground- and/or surface-water contamination. This study was designed to estimate the N status of two grass seed crops: red fescue (Festuca rubra L.) and perennial ryegrass (Lolium perenne L.) using images captured with an unmanned aerial vehicle (UAV) mounted multispectral camera. Two types of UAV, a fixed-wing UAV and a multi-rotor UAV, operating at two different heights and mounted with the same multispectral camera, were used in different field experiments at the same location in Denmark in the period from 432 to 861 growing degree-days. Seven vegetation indices, calculated from multispectral images with four bands: red, green, red edge and near infrared (NIR), were evaluated for their relationship to dry matter (DM), N concentration, N uptake and N nutrition index (NNI). The results showed a better prediction of N concentration, N uptake and NNI, than DM using vegetation indices. Furthermore, among all vegetation indices, two red-edge-based indices, normalized difference red edge (NDRE) and red edge chlorophyll index (CIRE), performed best in estimating N concentration (R2 = 0.69–0.88), N uptake (R2 = 0.41–0.84) and NNI (R2 = 0.47–0.86). In addition, there was no effect from the choice of UAV, and thereby flight height, on the estimation of NNI. The choice of UAV type therefore seems not to influence the possibility of diagnosing N status in grass seed crops. We conclude that it is possible to estimate NNI based on multispectral images from drone-mounted cameras, and the method could guide farmers as to whether they should apply additional N to the field. We also conclude that further research should focus on estimating the quantity of N to apply and on further developing the method to include more grass species.

A synergetic control theory (SCT) approach is proposed in this paper to control the longitudinal flight dynamics of a fixed-wing Unmanned Aerial Vehicle (UAV) in the presence of wind disturbances with input constraints. The main goal of this work is to design a synergetic method for the synthesis of nonlinear control systems for a fixed-wing UAV, which guarantees the asymptotic stability of the closed-loop systems when moving along a given trajectory, stability and adaptability with significant nonlinearity of mathematical models for controlling fixed-wing UAVs in the presence of wind disturbances. Furthermore, an important task in the synthesis of control systems for various objects, including UAV, is to take into account constraints on the control inputs of the UAV. The effectiveness of the proposed approach to the synergetic synthesis of control strategies is confirmed by the results of a computer simulation of the synthesized nonlinear vector control system of fixed-wing UAV. The proposed synergetic method of control system synthesis for fixed-wing UAV can be applied for the development of advanced flight simulation and navigation complexes that simulate the fixed-wing UAV behavior in the presence of wind disturbances and serve as a basis for improving the flight performance of the fixed-wing UAV.

Chapter 18 - Conceptual design and computational investigations of fixed wing unmanned aerial vehicle for medium-range applications

The use of recycled glass in the concrete mix instead of natural coarse aggregates and supplemental cementitious material has several advantages, including the conservation of natural resources, the reduction of CO2 emissions, and cost savings. However, due to their qualities, the mechanical properties of concrete containing Ground Glass Particles (GGP) differ from those of natural aggregates concrete. As a result, assessing the compressive strength (CS) of concrete with GGP is crucial. Therefore, this paper proposes the hybrid Machine Learning (ML) model including the Gradient Boosting (GB) and Bayesian optimization (BO) algorithms for predicting the compressive strength of concrete containing GGP. The hybrid ML model is developed and validated based on the training dataset (70% of the data) and the test dataset (30% of the remaining data), respectively. The performance of hybrid ML model is evaluated by three criteria, such as the Pearson correlation coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The K-Fold Cross-Validation technique is also used to verify the reliability of the hybrid ML model). The best performance of the hybrid ML model is determined with the R = 0.9843, RMSE = 1.7256 (MPa), and MAE = 1.3154 (MPa) for training dataset and R = 0.9784, RMSE = 2.4338 (MPa) and MAE = 1.9618 (MPa) for testing dataset. Based on the best hybrid ML model, the sensitivity analysis including SHapley Additive exPlanation (SHAP) and Partial Dependence Plots (PDP) 2D are investigated to obtain an in-depth examination of each individual input variable on the predicted compressive strength of concrete contaning GGP. The sensitivity analysis shows that four factors, such as curing age, surface area, TiO2, and temperature have the most effect on the compressive strength of concrete containing GGP.

Due to economic and environmental considerations, there exists a need for effective, efficient, and nondestructive methods for locating buried agricultural drainage pipes. The traditional ways of locating buried drainage pipe involve the use steel rod tile probes or trenching machinery, which can be tedious, time consuming, and/or cause pipe damage. Under certain circumstances, ground penetrating radar (GPR) has proven to be a viable, nondestructive method of finding drainage pipes. The effectiveness of GPR drainage pipe detection is influenced by a number of factors including; soil type, shallow hydrologic conditions, antenna frequency, orientation of the drain line relative to the GPR measurement transect, drainage pipe depth, GPR equipment settings, and computer processing steps. By integrating GPR with Real-Time Kinematic (RTK) Global Navigation Satellite System (GNSS) technology, up to 20 ha of field area can be mapped for subsurface drainage in a single day. For field areas greater than 20 ha, a more efficient drainage mapping method is required, and imagery obtained by Unmanned Aerial Vehicles (UAVs) offer a potential solution. Fixed-wing UAVs can easily cover a 80 ha field area in a single one-hour flight. A fixed-wing UAV mounted with a visible color (VIS-C), multispectral (MS), or thermal infrared (TIR) camera was tested at agricultural field sites across the Midwest U.S. Overall results showed that UAV VISC, MS, TIR imagery detected at least some of the drainage pipe present at 48%, 59%, and 69% of the sites, respectively. To date, there have been five key findings. (1) Although TIR generally worked best, there were sites where either VIS-C or MS proved more effective than TIR for mapping subsurface drainage systems. (2) Timing of UAV surveys relative to recent rainfall can sometimes, but not always, have an important impact on drainage pipe detection. (3) Linear features representing drain lines and farm field operations can be confused with one another and are often both depicted on UAV imagery, but knowledge of subsurface drainage system installation and farm field operations can be employed to distinguish between the two. (4) The drain line response depicted by UAV TIR imagery can change during the day, and relative humidity, which also changes during the day, can impact TIR image quality. (5) Although UAV imagery obtained outside the growing season is generally better for drainage mapping, good results are sometimes achieved with crops in place. Although UAV surveys are more efficient than GPR for drainage mapping, GPR can still be useful for ground truth of drain line locations determined by UAV imagery. With GPR, drainage pipe depth information can be obtained, which is not possible with UAV imagery. Consequently, there are cases where the complementary employment of both GPR and UAV methods are needed for agricultural drainage mapping applications.

This paper gives the dynamic modeling and design of a controller for autonomous Vertical take-off and landing (VTOL) Tri-Tilt rotor hybrid Unmanned Aerial Vehicle (UAV). Nowadays, UAVs have experienced remarkable progress and mainly categorized into fixed-wing UAVs and rotary-wing UAVs. The Tri Tiltrotor UAV models are derived mathematically using Euler's force and moment equations for VTOL to horizontal flight and vice-versa using MATLAB. The development of fully autonomous and self-guided UAVs would reduce the risk to human life. The applications consist of inspection of coasts, terrain, border, patrol buildings, rescue teams, police, and pipelines. A Proportional-Integral-Derivative control method is proposed for UAVs attitude and altitude stabilization. The results reveal that the controller accomplishes adaptability, robust performance and stability in the transition mode.

<div>In this dissertation, methods for real-time trajectory generation and autonomous obstacle avoidance for fixed-wing and quad-rotor unmanned aerial vehicles (UAV) are studied. A key challenge for such trajectory generation is the high computation time required to plan a new path to safely maneuver around obstacles instantaneously. Therefore, methods for rapid generation of obstacle avoidance trajectory are explored. The high computation time is a result of the computationally intensive algorithms used to generate trajectories for real-time object avoidance. Recent studies have shown that custom solvers have been developed that are able to solve the problem with a lower computation time however these designs are limited to small sized problems or are proprietary. Additionally, for a swarm problem, which is an area of high interest, as the number of agents increases the problem size increases and in turn creates further computational challenges. A solution to these challenges will allow for UAVs to be used in autonomous missions robust to environmental uncertainties.</div><div><br></div><div>In this study, a trajectory generation problem posed as an optimal control problem is solved using a sequential convex programming approach; a nonlinear programming algorithm, for which custom solver is used. First, a method for feasible trajectory generation for fast-paced obstacle-rich environments is presented for the case of fixed-wing UAVs. Next, a problem of trajectory generation for fixed-wing and quad-rotor UAVs is defined such that starting from an initial state a UAV moves forward along the direction of flight while avoiding obstacles and remaining close to a reference path. The problem is solved within the framework of finite-horizon model predictive control. Finally, the problem of trajectory generation is extended to a swarm of quad-rotors where each UAV in a swarm has a reference path to fly along. Utilizing a centralized approach, a swarm scenario with moving targets is studied in two different cases in an attempt to lower the solution time; the first, solve the entire swarm problem at once, and the second, solve iteratively for a UAV in the swarm while considering trajectories of other UAVs as fixed.</div><div><br></div><div>Results show that a feasible trajectory for a fixed-wing UAV can be obtained within tens of milliseconds. Moreover, the obtained feasible trajectories can be used as initial guesses to the optimal solvers to speed up the solution of optimal trajectories. The methods explored demonstrated the ability for rapid feasible trajectory generation allowing for safe obstacle avoidance, which may be used in the case an optimal trajectory solution is not available. A comparative study between a dynamic and a kinematic model shows that the dynamic model provides better trajectories including aggressive trajectories around obstacles compared to the kinematic counterpart for fixed-wing UAVs, despite having approximately the same computational demands. Whereas, for the case of quad-rotor UAVs, the kinematic model takes almost half the solution time than with a reduced dynamic model, despite having approximately the similar range of values for the cost function. When extended to a swarm, solving the problem for each UAV is four to seven times computationally cheaper than solving the swarm as a whole. With the improved computation time for trajectory generation for a swarm of quad-rotors using centralized approach, the problem is now reasonably scalable, which opens up the possibility to increase the number of agents in a swarm using high-end computing machines for real-time applications. Overall, a custom solver jointly with a sequential convex programming approach solves an optimization problem in a low computation time.</div>

<div>In this dissertation, methods for real-time trajectory generation and autonomous obstacle avoidance for fixed-wing and quad-rotor unmanned aerial vehicles (UAV) are studied. A key challenge for such trajectory generation is the high computation time required to plan a new path to safely maneuver around obstacles instantaneously. Therefore, methods for rapid generation of obstacle avoidance trajectory are explored. The high computation time is a result of the computationally intensive algorithms used to generate trajectories for real-time object avoidance. Recent studies have shown that custom solvers have been developed that are able to solve the problem with a lower computation time however these designs are limited to small sized problems or are proprietary. Additionally, for a swarm problem, which is an area of high interest, as the number of agents increases the problem size increases and in turn creates further computational challenges. A solution to these challenges will allow for UAVs to be used in autonomous missions robust to environmental uncertainties.</div><div><br></div><div>In this study, a trajectory generation problem posed as an optimal control problem is solved using a sequential convex programming approach; a nonlinear programming algorithm, for which custom solver is used. First, a method for feasible trajectory generation for fast-paced obstacle-rich environments is presented for the case of fixed-wing UAVs. Next, a problem of trajectory generation for fixed-wing and quad-rotor UAVs is defined such that starting from an initial state a UAV moves forward along the direction of flight while avoiding obstacles and remaining close to a reference path. The problem is solved within the framework of finite-horizon model predictive control. Finally, the problem of trajectory generation is extended to a swarm of quad-rotors where each UAV in a swarm has a reference path to fly along. Utilizing a centralized approach, a swarm scenario with moving targets is studied in two different cases in an attempt to lower the solution time; the first, solve the entire swarm problem at once, and the second, solve iteratively for a UAV in the swarm while considering trajectories of other UAVs as fixed.</div><div><br></div><div>Results show that a feasible trajectory for a fixed-wing UAV can be obtained within tens of milliseconds. Moreover, the obtained feasible trajectories can be used as initial guesses to the optimal solvers to speed up the solution of optimal trajectories. The methods explored demonstrated the ability for rapid feasible trajectory generation allowing for safe obstacle avoidance, which may be used in the case an optimal trajectory solution is not available. A comparative study between a dynamic and a kinematic model shows that the dynamic model provides better trajectories including aggressive trajectories around obstacles compared to the kinematic counterpart for fixed-wing UAVs, despite having approximately the same computational demands. Whereas, for the case of quad-rotor UAVs, the kinematic model takes almost half the solution time than with a reduced dynamic model, despite having approximately the similar range of values for the cost function. When extended to a swarm, solving the problem for each UAV is four to seven times computationally cheaper than solving the swarm as a whole. With the improved computation time for trajectory generation for a swarm of quad-rotors using centralized approach, the problem is now reasonably scalable, which opens up the possibility to increase the number of agents in a swarm using high-end computing machines for real-time applications. Overall, a custom solver jointly with a sequential convex programming approach solves an optimization problem in a low computation time.</div>

Fixed-wing unmanned aerial vehicles (UAVs) and multi-rotor UAVs are widely utilized in large-area (>1 km2) environmental monitoring and small-area (<1 km2) fine vegetation surveys, respectively, having different characteristics in terms of flight cost, operational efficiency, and landing and take-off methods. However, large-area fine mapping in complex forest environments is still a challenge in UAV remote sensing. Here, we developed a method that combines a multi-rotor UAV and a fixed-wing UAV to solve this challenge at a low cost. Firstly, we acquired small-scale, multi-season ultra-high-resolution red-green-blue (RGB) images and large-area RGB images by a multi-rotor UAV and a fixed-wing UAV, respectively. Secondly, we combined the reference data of visual interpretation with the multi-rotor UAV images to construct a semantic segmentation model and used the model to expand the reference data. Finally, we classified fixed-wing UAV images using the large-area reference data combined with the semantic segmentation model and discuss the effects of different sizes. Our results show that combining multi-rotor and fixed-wing UAV imagery provides an accurate prediction of tree species. The model for fixed-wing images had an average F1 of 92.93%, with 92.00% for Quercus wutaishanica and 93.86% for Juglans mandshurica. The accuracy of the semantic segmentation model that uses a larger size shows a slight improvement, and the model has a greater impact on the accuracy of Quercus liaotungensis. The new method exploits the complementary characteristics of multi-rotor and fixed-wing UAVs to achieve fine mapping of large areas in complex environments. These results also highlight the potential of exploiting this synergy between multi-rotor UAVs and fixed-wing UAVs.

ABSTRACTSilybum marianum (L.) Gaertn weed has the tendency to grow in patches. In order to perform site-specific weed management, determining the spatial distribution of weeds is important for its eradication. Remote sensing has been used to perform species discrimination and it offers promising techniques for operational weed mapping. In the present study, the feasibility of high-resolution imaging for S. marianum detection and mapping is reported. A multispectral camera (green–red–near-infrared) mounted on a fixed wing unmanned aerial vehicle (UAV) was used for the acquisition of high-resolution images with pixel size of 0.1 m. The maximum likelihood (ML) classifier was used to classify the S. marianum among other weed species present in a field, with Avena sterilisL. being predominant. As input to the classifier, the three spectral bands and the texture were used. The scale of the mapping was varied by degrading the image resolution to evaluate classification performance, with 1 m resolution providing the highest classification accuracy. The classification rates obtained using ML reached an overall accuracy of 87.04% with a K-hat statistic of 74%. The results prove the feasibility of operational S. marianum mapping using UAV and multispectral imaging.

The use of UAV (unmanned aerial vehicle) based imaging in agriculture adds the ability to incorporate vast amounts of data into analyses designed to improve efficiency in the use of agricultural inputs. One reason this ability has not yet been realized is that producing UAV based radiometrically calibrated images for the purpose of ensuring data reliability is difficult at the large scale. This paper presents an investigation of field-based image-mosaic calibration procedures using a commercial off-the-shelf fixed-wing small UAV and a five-band multispectral sensor. To determine the quality of the radiometric calibration procedure for UAV image mosaics, images were also collected with an identical camera on a manned aircraft, and ground based radiometric calibration tarps were used to produce high-quality calibrated field images. Satellite images were also collected on the same day as the aircraft images in a two-hour flight window centered on solar noon. The manned aircraft and satellite images were large enough for a single image to cover the entire field. The multispectral camera used enables two kinds of exposure settings; auto exposure allows the camera to automatically select exposure and gain settings for each image in a flight, and manual exposure allows the user to select settings preflight which are used for all the images in that flight. In this work we compare the radiometrically calibrated UAV images, collected with both auto-exposure and manual-exposure methods, to the radiometrically calibrated single-frame image generated with the manned aircraft, as well as to a satellite image.