No description available.

Unmanned aerial vehicles (UAVs) with high-resolution cameras are common in today’s society. Industries, such as the forestry industry, use drones to get a fast overview of tree populations. More advanced sensors, such as near-infrared light or depth data, can increase the amount of information that UAV images provide, providing information about the forest, such as; tree quantity or forest health. However, the fast-expanding field of deep learning could help expand the information acquired using only RGB cameras. Three deep learning models, FasterR-CNN, RetinaNet, and YOLOR were compared to investigate this. It was also investigated if initializing the models using transfer learning from the MS COCO dataset could increase the performance of the models. The dataset used was Swedish Forest Agency (2021): Forest Damages-Spruce Bark Beetle 1.0 National Forest Data Lab and drone images provided by IT-Bolaget Per & Per. The deep learning models were to detect five different tree species; spruce, pine, birch, aspen, and others. The results show potential for the usage of deep learning to detect tree species in images from UAVs. / Obemannade drönare med högupplösta kameror är vanliga i dagens samhälle. Branscher, så som skogsindustrin, kan använda sig av sådana drönare för att få en snabb översikt över ett skogsområde.Mer avancerade sensorer, som använder nära-infrarött ljus eller djupdata, kan öka mängden information som drönarna kan samla in, information såsom; trädmängd eller data om skogens hälsa. Det snabbt växande området djup-maskinlärning kan dock hjälpa till att utöka informationen som kan extraheras vid användning av endast RGB-kameror. Tre modeller för djupinlärning, Faster R-CNN, RetinaNet och YOLOR, jämfördes för att undersöka detta. Det undersöktes också om initiering med för-tränade vikter, med överföringsinlärning från datasetet MS COCO, skulle kunna öka modellernas prestanda. Datasetet som användes var Skogsstyrelsen (2021): Skogsskador-Granbarkborre1.0 Nationell Forest Data Lab samt drönarbilder tillhandahållna av IT-Bolaget Per & Per. Det tredjupinlärnings-modellerna skulle detektera fem olika trädarter: gran, tall, björk, asp, och övrigt.Resultaten visar potential för användning av djupinlärning för att upptäcka trädarter i bilder från drönare.

Nowadays inspections of civil engineering structures are performed manually at close range to be able to assess damages. This requires specialized equipment that tends to be expensive and to produce closure of the bridge. Furthermore, manual inspections are time-consuming and can often be a source or risk for the inspectors. Moreover, manual inspections are subjective and highly dependent on the state of mind of the inspector which reduces the accuracy of this kind of inspections. Image-based inspections using cameras or unmanned aerial vehicles (UAV) combined with image processing have been used to overcome the challenges of traditional manual inspections. This type of inspection has also been studied with the use of machine learning algorithms to improve the detection of damages, in particular cracks. This master’s thesis presents an approach that combines different aspects of the inspection, from the data acquisition, through the crack detection to the quantification of essential parameters. To do this, both digital cameras and a UAV have been used for data acquisition. A convolutional neural network (CNN) for the identification of cracks is used and subsequently, different quantification methods are explored to determine the width and length of the cracks. The results are compared with control measures to determine the accuracy of the method. The results present low to no false negatives when using the CNN to identify cracks. The quantification of the identified cracks is performed obtaining the highest accuracy estimation for 0.2mm cracks.

An original approach for measuring wind speed and direction by the use ofdrones was proposed and compared to an existing one. The original approach allowed the drone to drift with the wind and use the translatory velocity for input into a non-linear estimator, while the existing approach used a stationary hovering drone and its tilt for input to an estimator. A simulation environment was set up in Simulink and Matlab and validated using outputs from previous researchers performing similar tasks. The first test exposed the two approaches to wind tunnel-like environment with a strictly horizontal wind, while the second test used real wind data collected on-board a meteorological research vessel. Results showed that the original approachperformed better for estimating both direction and speed, but it required a largearea to drift in during operation. / En egen teknik för att mäta vindhastighet och vindrikting med en drönare föreslogs och jämfördes med en befintlig teknik. Det egna sättet tillät drönaren att driva med vinden och använde dess egna hastighet för att estimera vinden, medan den existerande tekniken höll drönarens position konstant och estimerade vinden med hjälp av farkostens lutning. En simuleringsmiljö inrättades i Simulink och Matlab som validerades medhjälp av resultat från tidigare liknande forskning. Det första testet som genomfördes exponerade de två tillvägagångsätten för vindtunnel-liknande förhållanden, medan det andra testet använde verklig vinddata som samlats in ombordett meteorologiskt forskningsfartyg. Resultaten visade att den egna teknikenproducerade noggrannare upskattningar av både vindhastighet och riktning,men krävde betydligt större fritt flygrum.

Cooperation is increasingly being applied in the control of interconnected multi-agent systems, and it introduces many benefits. In particular, cooperation can improve the efficiency of many types of missions, and adds flexibility and robustness against external disturbances or unknown obstacles. This thesis investigates cooperative maneuvers for aerial vehicles autonomously landing on moving platforms, and how to safely and robustly perform such landings on a real system subject to a variety of disturbances and physical and computational constraints. Two specific examples are considered: the landing of a fixed-wing drone on top of a moving ground carriage; and the landing of a quadcopter on a boat. The maneuvers are executed in a cooperative manner where both vehicles are allowed to take actions to reach their common objective while avoiding safety based spatial constraints. Applications of such systems can be found in, for example, autonomous deliveries, emergency landings, and search and rescue missions. Particular challenges of cooperative landing maneuvers include the heterogeneous and nonlinear dynamics, the coupled control, the sensitivity to disturbances, and the safety criticality of performing a high-velocity landing maneuver. The thesis suggests the design of a cooperative control algorithm for performing autonomous and cooperative landings. The algorithm is based on model predictive control, an optimization-based method where at every sampling instant a finite-horizon optimal control problem is solved. The advantages of applying this control method in this setting arise from its ability to include explicit dynamic equations, constraints, and disturbances directly in the computation of the control inputs. It is shown how the resulting optimization problem of the autonomous landing controller can be decoupled into a horizontal and a vertical sub-problem, a finding which significantly increases the efficiency of the algorithm. The algorithm is derived for two different autonomous landing systems, which are subsequently implemented in realistic simulations and on a drone for real-world flight tests. The results demonstrate both that the controller is practically implementable on real systems with computational limitations, and that the suggested controller can successfully be used to perform the cooperative landing under the influence of external disturbances and under the constraint of various safety requirements. / Samarbete tillämpas i allt högre utsträckning vid reglering av sammankopplade multiagentsystem, vilket medför både ökad robusthet och flexibilitet mot yttre störningar, samt att många typer av uppgifter kan utföras mer effektivt. Denna licentiatavhandling behandlar kooperativa och autonoma landningar av drönare på mobila landingsplatformar, och undersöker hur sådana landningar kan implementeras på ett verkligt system som påverkas av externa störningar och som samtidigt arbetar under fysiska och beräkningsmässiga begränsningar. Två exempel betraktas särskilt: först landingen av ett autonomt flygplan på en bil, därefter landning av en quadcopter på en båt. Landningarna utförs kooperativt, vilket innebär att båda fordonen har möjlighet att påverka systemet för att fullborda landningen. Denna typ av system har applikationer bland annat inom autonoma leveranser, nödlandningar, samt inom eftersöknings- och räddningsuppdrag. Forskningen motiveras av ett behov av effektiva och säkra autonoma landingsmanövrar, för fordon med heterogen och komplex dynamik som samtidigt måste uppfylla en mängd säkerhetsvillkor. I avhandlingen härleds  kooperativa regleralgoritmer för landningsmanövern. Reglermetoden som appliceras är modell-prediktiv reglerteknik, en optimeringsbaserad metod under vilken ett optimalt reglerproblem med ändlig horisont löses  varje samplingsperiod. Denna metod tillför här fördelar såsom explicit hantering av systemdynamik, och direkt inkludering av störningshantering och bivillkor vid beräkning av insignaler. På så sätt kan vi direkt i optimeringslösaren hantera säkerhetsvillkor och externa störningar. Det visas även hur lösningstiden för optimeringen kan effektiviseras genom att separera den horisontella och den vertikala dynamiken till två subproblem som löses sekvensiellt. Algoritmen implementeras därefter för två olika landingssystem, för att därefter tillämpas och utvärderas i realistiska simuleringsmiljöer med olika typer av störningar, samt med flygtester på en verklig plattform. Resultaten visar dels att reglermetoden ger önskade resultat med avseende både på störningshantering och uppfyllande av bivillkor från säkerhetskrav, och dels att algoritmen är praktiskt implementerbar även på system med begränsad beräkningskraft. / <p>QC 20190315</p>

This thesis presents the design, modeling, and control of a fully-actuated multi-rotor unmanned aerial vehicle (UAV). Unlike conventional multi-rotors, which suffer from two degrees of underactuation in their propeller plane, the choice of an unconventional propeller configuration in the new drone leads to an even distribution of actuation across the entire force-torque space. This allows the vehicle to produce any arbitrary combination of forces and torques within a bounded magnitude and hence execute motion trajectories unattainable with conventional multi-rotor designs. This system, referred to as the \omninospace, decouples the position and attitude controllers, simplifying the motion control problem. Position control is achieved using a PID feedback loop with gravity compensation, while attitude control uses a cascade architecture where the inner loop follows an angular rate command set by the outer attitude control loop. A novel model is developed to capture the disturbance effects among interacting actuator airflows of the \omninospace. Given a desired actuator thrust, the model computes the required motor command using the current battery voltage and thrusts of disturbing actuators. A system identification is performed to justify the use of a linear approximation for parameters in the model to reduce its computational footprint in real-time implementation. The \omni benefits from two degrees of actuation redundancy resulting in a control allocation problem where feasible force-torques may be produced through an infinite number of actuator thrust combinations. A novel control allocation approach is formulated as a convex optimization to minimize the \omnis energy consumption subject to the propeller thrust limits. In addition to energy savings, this optimization provides fault tolerance in the scenario of a failed actuator. A functioning prototype of the \omni is built and instrumented. Experiments carried out with this prototype demonstrate the capabilities of the new drone and its control system in following various translational and rotational trajectories, some of which would not be possible with conventional multi-rotors. The proposed optimization-based control allocation helps reduce power consumption by as much as 6\%, while being able to operate the drone in the event of a propeller failure. / Thesis / Master of Applied Science (MASc)

Through this research, a robust aircraft design methodology is developed for analysis and optimization of the Air Vehicle (AV) segment of Unmanned Aerial Vehicle (UAV) systems. The analysis functionality of the AV design is integrated with a Genetic Algorithm (GA) to form an integrated Multi-disciplinary Design Optimization (MDO) methodology for optimal AV design synthesis. This research fills the gap in integrated subsonic fixed-wing UAV AV MDO methods. No known single methodology captures all of the phenomena of interest over the wide range of UAV families considered here. Key advancements include: 1) parametric Low Reynolds Number (LRN) airfoil aerodynamics formulation, 2) UAV systems mass properties definition, 3) wing structural weight methods, 4) self-optimizing flight performance model, 5) automated geometry algorithms, and 6) optimizer integration. Multiple methods are provided for many disciplines to enable flexibility in functionality, level of detail, computational expediency, and accuracy. The AV design methods are calibrated against the High-Altitude Long-Endurance (HALE) Global Hawk, Medium-Altitude Endurance (MAE) Predator, and Tactical Shadow 200 classes, which exhibit significant variations in mission performance requirements and scale from one another. Technology impacts on the design of the three UAV classes are evaluated from a representative system technology year through 2025. Avionics, subsystems, aerodynamics, design, payloads, propulsion, and structures technology trends are assembled or derived from a variety of sources. The technology investigation serves the purposes of validating the effectiveness of the integrated AV design methods and to highlight design implications of technology insertion through future years. Flight performance, payload performance, and other attributes within a vehicle family are fixed such that the changes in the AV designs represent technology differences alone, and not requirements evolution. The optimizer seeks to minimize AV design gross weight for a given mission requirement and technology set. All three UAV families show significant design gross weight reductions as technology improves. The predicted design gross weight in 2025 for each class is: 1) 12.9% relative to the 1994 Global Hawk, 2) 6.26% relative to the 1994 Predator, and 3) 26.3% relative to the 2000 Shadow 200. The degree of technology improvement and ranking of contributing technologies differs among the vehicle families. The design gross weight is sensitive to technologies that directly affect the non-varying weights for all cases, especially payload and avionics/subsystems technologies. Additionally, the propulsion technology strongly affects the high performance Global Hawk and Predator families, which have high fuel mass fractions relative to the Tactical Shadow 200 family. The overall technology synergy experienced 10-11 years after the initial technology year is 6.68% for Global Hawk, 7.09% for Predator, and 4.22% for the Shadow 200, which means that the technology trends interact favorably in all cases. The Global Hawk and Shadow 200 families exhibited niche behavior, where some vehicles attained higher aerodynamic performance while others attained lower structural mass fractions. The high aerodynamic performance Global Hawk vehicles had high aspect ratio wings with sweep, while the low structural mass fraction vehicles had straight, relatively low aspect ratios and smaller wing spans. The high aerodynamic performance Shadow 200 vehicles had relatively low wing loadings and large wing spans, while the lower structural mass fraction counterparts sought to minimize physical size. / Ph. D.

Building facades, serving mainly to protect occupants and structural components from natural forces, require periodic inspections for the detection and assessment of building façade anomalies. Over the past years, a growing trend of utilizing camera-equipped drones for periodical building facade inspection has emerged. Building façade anomalies, such as cracks and erosion, can be detected through analyzing drone-captured video, photographs, and infrared images. Such anomalies are known to have an impact on various building performance aspects, e.g., thermal, energy, moisture control issues. Current research efforts mainly focus on the design of drone flight schema for building inspection, 3D building model reconstruction through drone-captured images, and the detection of specific façade anomalies with these images. However, there are several research gaps impeding the improvement of automation level during the processes of building façade inspection with UAV (Unmanned Aerial Vehicle). These gaps are (1) lack effective ways to store multi-type data captured by drones with the connection to the spatial information of building facades, (2) lack high-performance tools for UAV-image analysis for the automated detection of building façade anomalies, and (3) lack a comprehensive management (i.e., storage, retrieval, analysis, and display) of large amounts and multi-media information for cyclic façade inspection. When seeking inspirations from nature, the process of drone-based facade inspection can be compared with caching birds' foraging food through spatial memory, visual sensing, and remarkable memories. This dissertation aims at investigating ways to improve the management of UAV-captured data and the automation level of drone-based façade anomaly inspection with inspirations from caching birds' foraging behavior. Firstly, a 2D spatial model of building façades was created in the geographic information system (GIS) for the registration and storage of UAV-images to assign façade spatial information to each image. Secondly, computational methods like computer vision and deep learning neural networks were applied to develop algorithms for automated extraction of visual features of façade anomalies within UAV-captured images. Thirdly, a GIS-based database was designed for the comprehensive management of heterogeneous inspection data, such as the spatial, multi-spectral, and temporal data. This research will improve the automation level of storage, retrieval, analysis, and documentation of drone-captured images to support façade inspection during a building's service lifecycle. It has promising potential for supporting the decision-making of early-intervention or maintenance strategies to prevent façade failures and improve building performance. / Doctor of Philosophy / Building facades require periodic inspections and maintenance to protect occupants and structures from natural forces like the sun, wind, rain, and snow. Over the past years, a growing trend of utilizing drones for periodical building facade inspection has emerged. Building façade anomalies, such as cracks and corrosion, can be detected from the drone-captured photographs or video. Such anomalies are known to have an impact on various building performance aspects, such as moisture issues, abnormal heat loss, and additional energy consumptions. Existing practices for detecting façade anomalies from drone-captured photographs mainly rely on manual checking by going through numerous façade images and repetitively zooming in and out these high-resolution images, which is time-consuming and labor-intensive with potential risks of human errors. Besides, this manual checking process impedes the management of drone-captured data and the documentation of façade inspection activities. At the same time, the emerging technologies of computer vision (CV) and artificial intelligence (AI) have provided many opportunities to improve the automation level of façade anomaly detection and documentation. Previous research efforts have explored the image-based generation of 3D building models using computer vision techniques, as well as image-based detection of specific anomalies using deep learning techniques. However, few studies have looked into the comprehensive management, including the storage, retrieval, analysis, and display, of drone-captured images with the spatial coordinate information of building facades; there is also a lack of high-performance image analytics tools for the automated detection of building façade anomalies. This dissertation aims at investigating ways to improve the automation level of analyzing and managing drone-captured images as well as documenting building façade inspection information. To achieve this goal, a building façade model was created in the geographic information system (GIS) for the semi-automated registration and storage of drone-captured images with spatial coordinates by using computer vision techniques. Secondly, deep learning was applied for automated detection of façade anomalies in drone-captured images. Thirdly, a GIS-based database was designed as the platform for the automated analysis and management of heterogeneous data for drone-captured images, façade model information, and detected façade anomalies. This research will improve the automation level of drone-based façade inspection throughout a building's service lifecycle. It has promising potential for supporting the decision-making of maintenance strategies to prevent façade failures and improve building performance.

Unmanned aerial vehicle (UAV) networks, a flying platform, are a promising wireless communications infrastructure with wide-ranging applications in both commercial and military domain. Owing to the appealing characteristics, such as high mobility, high feasibility, and low cost, UAV networks can be applied in various scenarios, such as emergency communications, cellular networks, device-to-device (D2D) networks, and sensor networks, regardless of infrastructure and spatial constraints. To handle complicated missions, provide wireless coverage for a large range, and have a long lifetime, a UAV network may consist of a large amount of UAVs, working cooperatively as a swarm, also referred to as swarm UAV networks. Although high mobility and numerous UAVs offer high flexibility, high scalability, and performance enhancement for swarm UAV networks, they also incur some technical challenges. One of the major challenges is the routing protocol design. With high mobility, a dynamic network topology may be encountered. As a result, traditional routing protocols based on routing path discovery are not applicable in swarm UAV networks, as the discovered routing path may be outdated especially when the amount of UAVs is large causing considerable routing path discovery delay. Multicast is an essential and key technology in the scenarios, where swarm UAV networks are employed as aerial small base station (BSs), like relay or micro BS. Swarm UAV networks consisting of a large amount of UAVs will encounter severe multicast delay with existing multicast methods using acknowledgement (ACK) feedback and retransmissions. This issue will be deteriorated when a swarm UAV network is deployed far away from BSs, causing high packet loss. Data exchange is another major technical challenge in swarm UAV networks, where UAVs exchange data packets with each other, such as requesting and retrieving lost packets. Due to numerous UAVs, data exchange between UAVs can cause message and signaling storm, resulting in a long data exchange delay and severe ovehead. In this dissertation, I focus on developing novel routing protocols, multicast schemes, and data exchange schemes, enabling efficient, robust, and high-performance routing, multicast, and data exchange in swarm UAV networks. To be specific, two novel flooding-based routing protocols are designed in this dissertation, where random network coding (RNC) is utilized to improve the efficiency of the flooding-based routing in swarm UAV networks without relying on network topology information and routing path discovery. Using the property of RNC that as long as sufficient different versions of encoded packets/generations are accumulated, original packets could be decoded, RNC is naturally able to accelerate the routing process. This is because the use of RNC can reduce the number of encoded packets that are required to be delivered in some hop. In a hop, the receiver UAV may have already overheard some generations in previous hops, so that it only needs to receive fewer generations from the transmitter UAV in the current hop. To further expedite the flooding-based routing, the second flooding-based routing protocol is designed, where each forwarding UAV creates a new version of generation by linearly combining received generations rather than by decode original packets. Despite the flooding-based routing significantly hastened by RNC, the inherent drawback of the flooding-based routing is still unsolved, namely numerous hops. Aiming at reducing the amount of hops, a novel enhanced flooding-based routing protocol leveraging clustering is designed, where the whole UAV network will be partitioned into multiple clusters and in each cluster only one UAV will be selected as the representative of this cluster, participating in the flooding-based routing process. By this way, the number of hops is restricted by the number of representatives, since packets are only flooded between limited representatives rather than numerous UAVs. To address the multicast issue in swarm UAV networks, a novel multicast scheme is proposed based on clustering, where a UAV experiencing packet loss will retrieve the lost packets by requesting other UAVs in the same cluster without depending on retransmissions of BSs. In this way, the lost packet retrieval is carried out through short-distance data exchange between UAVs with reliable transmissions and a short delay. Tractable stochastic geometry tools are used to model swarm UAV networks with a dynamic network topology, based on which comprehensive analytical performance analysis is given. To enable efficient data exchange between UAVs in swarm UAV networks, a data exchange scheme is proposed utilizing unsupervised learning. With the proposed scheme, all UAVs are assigned to multiple clusters and a UAV can only carry out data exchange within its cluster. By this way, UAVs in different clusters perform data exchange in a parallel fashion to expedite data exchange. The agglomerative hierarchical clustering, a type of unsupervised learning, is used to conduct clustering in order to guarantee that UAVs in the same cluster are able to supply and supplement each other's lost packets. Additionally, a data exchange mechanism, including a novel random backoff procedure, is designed, where the priorities of UAVs in data exchange determined by the number of their lost packets or requested packets that they can provide. As a result, each request-reply process would be taken fully advantage, maximally supplying lost packets not only to the UAV sending request, but also to other UAVs in the same cluster. For all the developed technologies in this dissertation, their technical details and the corresponding system procedures are designed based on low-complexity and well-developed technologies, such as the carrier sense multiple access/collision avoidance (CSMA/CA), for practicability in practice and without loss of generality. Moreover, extensive simulation studies are conducted to demonstrate the effectiveness and superiority of the proposed and developed technologies. Additionally, system design insights are also explored and revealed through simulations. / Doctor of Philosophy / Compared to fixed infrastructures in wireless communications, unmanned aerial vehicle (UAV) networks possess some significant advantages, such as low cost, high mobility, and high feasibility, making UAV networks have a wide range of applications in both military and commercial fields. However, some characteristics of UAV networks, including dynamic network topology and numerous UAVs, may become technical barriers for wireless communications. One of the major challenges is the routing protocol design. Routing is the process of selecting a routing path, enabling data delivered from a node (source) to another desired node (destination). Traditionally, routing is performed based on routing path discovery, where control packets are broadcasted and the path, on which a control packet first reaches the destination, will be selected as routing path. However, in UAV networks, routing path discovery may experience a long delay, as control packets go through many UAVs. Besides, the discovered routing path may be outdated, as the topology of UAV networks change over time. Another key technology in wireless communications that may not work well in UAV networks is multicast, where a transmitter, like a base station (BS), broadcasts data to UAVs and all UAVs are required to receive this data. With numerous UAVs, multicast delay may be severe, since the transmitter will keep retransmitting a data packet to UAVs until all UAVs successfully receive the packet. This issue will be deteriorated when a UAV network is deployed far away from BSs, causing high packet loss. Data exchange between UAVs is a fundamental and important system procedure in UAV networks. A large amount of UAV in a UAV network will cause serious data exchange delay, as many UAVs have to compete for limited wireless resources to request or send data. In this dissertation, I focus on developing novel technologies and schemes for swarm UAV networks, where a large amount of UAVs exist to make UAV networks powerful and handle complicated missions, enable efficient, robust, and high-performance routing, multicast, and data exchange system procedures. To be specific, two novel flooding-based routing protocols are designed, where random network coding (RNC) is utilized to improve the efficiency of flooding-based routing without relying on any network topology information or routing path discovery. The use of RNC could naturally expedite flooding-based routing process. With RNC, a receiver can decode original packets as long as it accumulates sufficient encoded packets, which may be sent by different transmitters in different hops. As a result, in some hops, fewer generations may be required to be transmitted, as receivers have already received and accumulated some encoded in previous hops. To further improve the efficiency of flooding-based routing, another routing protocol using RNC is designed, where UAVs create new encoded packets by linearly combining received encoded packets rather than linearly combing original packets. Apparently, this method would be more efficient. UAVs do not need to collect sufficient encoded packets and decode original packets, while only linearly combining all received encoded packets. Although RNC could effectively improve the efficiency of flooding-based routing, the inherent drawback is still unsolved, which is a large amount of hops caused by numerous UAVs. Thus, an enhanced flooding-based routing protocol using clustering is designed, where the whole UAV network will be partitioned into multiple clusters. In each cluster only one UAV will be selected as the representative of this cluster, participating in the flooding-based routing process. By this way, the number of hops could be greatly reduced, as packets are only flooded between limited representatives rather than numerous UAVs. To address the multicast issue in swarm UAV networks, a novel multicast scheme is proposed, where a UAV experiencing packet loss will retrieve its lost packets by requesting other UAVs in the same cluster without depending on retransmissions of BSs. In this way, the lost packet retrieval is carried out through short-distance data exchange between UAVs with reliable transmissions and a short delay. Then, the optimal number of clusters and the performance of the proposed multicast scheme are investigated by tractable stochastic geometry tools. If all UAVs closely stay together in a swarm UAV network, long data exchange delay would be significant technical issue, since UAVs will cause considerable interference to each other and all UAVs will compete for spectrum access. To cope with that, a data exchange scheme is proposed leveraging unsupervised learning. To avoid interference between UAVs and a long-time waiting for spectrum access, all UAVs are assigned to multiple clusters and different clusters use different frequency bands to carry out data exchange simultaneously. The agglomerative hierarchical clustering, a type of unsupervised learning, is used to conduct clustering, guaranteeing that UAVs in the same cluster are able to supply and supplement each other's lost packets. Additionally, a data exchange mechanism is designed, facilitating that a UAV with more lost packets or more requested packets has a higher priority to carry out data exchange. In this way, each request-reply process would be taken fully advantage, maximally supplying lost packets not only to the UAV sending request, but also to other UAVs in the same cluster. For all the developed technologies in this dissertation, their technical details and the corresponding system procedures are designed based on low-complexity and well-developed technologies, such as the carrier sense multiple access/collision avoidance (CSMA/CA), for practicability in reality and without loss of generality. Moreover, extensive simulation studies are conducted to demonstrate the effectiveness and superiority of the developed technologies. Additionally, system design insights are also explored and revealed through simulations.

The development of Unmanned Aerial Vehicles (UAVs) and fifth-generation (5G) wireless technology provides more possibilities for wireless networks. The application of UAVs is gradually evolving from individual UAVs performing tasks to UAV swarm performing tasks in concert. A UAV swarm network is when many drones work cooperatively in a swarm mode to achieve a particular goal. Due to the UAV swarm's easy deployment, self-organization, self-management, and high flexibility, it can provide robust and efficient wireless communications in some unique scenarios, such as emergency communications, hotspot region coverage, sensor networks, and vehicular networks. Therefore, UAV networks have attracted more and more attention from commercial and military; however, many problems need to be resolved before UAV cellular communications become a reality. One of the most challenging core components is the routing protocol design in the UAV swarm network. Due to the high mobility of UAVs, the position of each UAV changes dynamically, so problems such as high latency, high packet loss rate, and even loss of connection arise when UAVs are far apart. These problems dramatically reduce the transmission rate and data integrity for traditional routing protocols based on path discovery. This thesis focuses on developing, emulating, and optimizing a flooding-based routing protocol for UAV swarm using Random Linear Network Coding (RLNC) to improve the latency and bit rate and solve the packet loss problem without routing information and network topology. RLNC can reduce the number of packets demand in some hops. Due to this feature of RLNC, when relay transmitter UAVs or the destination receiver UAV receive sufficient encoded packets from any transmitter UAVs, the raw data can be decoded. For those relay transmitter UAVs in the UAV swarm network that already received some encoded packets in previous hops but not enough to decode the raw data, only need to receive the rest of the different encoded packets needed for decoding. Thus, flooding-based routing protocol significantly improves transmission efficiency in the UAV swarm network. / Master of Science / People are used to using fiber, 4G, and Wi-Fi in the city, but numerous people still live in areas without Internet access. Moreover, in some particular scenarios like large-scale activities, remote areas, and military operations, when the cellular network cannot provide enough bandwidth or good signal, UAV wireless network would be helpful and provide stable Internet access. Successful UAV test flights can last for several weeks, and researchers' interest in high-altitude long-endurance (HALE) UAVs are booming. HALE UAVs will create Wi-Fi or other network signals for remote areas, including polar regions, which will allow millions of people to enter the information society and connect to the Internet. The development of UAV and 5G provides more possibilities for wireless networks. UAV applications have evolved from individual UAV performing tasks to UAV swarm performing tasks. A UAV swarm network is where multiple drones work in tandem to achieve a particular goal. It can provide robust and efficient wireless communications in unique scenarios. As a result, UAVs are receiving attention from both commercial and military. However, there are still many problems that need to be resolved before the actual use of UAVs. One of the biggest challenges is routing protocol which is how UAVs communicate with each other and select routes. As the location of UAVs is constantly changing, this leads to delays, data loss, or complete loss of connectivity. Ultimately these issues can lead to slow transmission speed and lack of data integrity for traditional routing protocols based on path discovery. This thesis focuses on developing, emulating, and optimizing a flooding-based routing protocol for the UAV swarm. Specifically, this protocol uses RLNC, which can reduce the number of packets demand in some hops so that the latency and transmission speed will be improved, and the data loss problem will also be solved. Due to this feature of RLNC, when any receiver receives enough encoded packets from any transmitter, the original data can be decoded. Some receivers that already received some encoded packets in the previous transmission only need to receive the rest of the different encoded packets needed for decoding. Therefore, flooding-based routing protocol significantly improves transmission efficiency for UAV swarm networks.