The ability for unmanned autonomous aerial vehicles (UAV) to localize themselves in an environment is fundamental for them to be able to function, even if they do not have access to a global positioning system. Recently, with the success of deep learning in vision based tasks, there have been some proposed methods for absolute geolocalization using vison based deep learning with satellite and UAV images. Most of these are only tested in urban environments, which begs the question: How well do they work in non-urban areas like forests and fields? One drawback of deep learning is that models are often regarded as black boxes, as it is hard to know why the models make the predictions they do, i.e. what information is important and is used for the prediction. To solve this, several neural network interpretation methods have been developed. These methods provide explanations so that we may understand these models better. This thesis investigates the localization accuracy of one geolocalization method in both urban and non-urban environments as well as applies neural network interpretation in order to see if it can explain the potential difference in localization accuracy of the method in these different environments. The results show that the method performs best in urban environments, getting a mean absolute horizontal error of 38.30m and a mean absolute vertical error of 16.77m, while it performed significantly worse in non-urban environments, getting a mean absolute horizontal error of 68.11m and a mean absolute vertical error 22.83m. Further, the results show that if the satellite images and images from the unmanned aerial vehicle are collected during different seasons of the year, the localization accuracy is even worse, resulting in a mean absolute horizontal error of 86.91m and a mean absolute vertical error of 23.05m. The neural network interpretation did not aid in providing an explanation for why the method performs worse in non-urban environments and is not suitable for this kind of problem. / Obemannade autonoma luftburna fordons (UAV) förmåga att lokaliera sig själva är fundamental för att de ska fungera, även om de inte har tillgång till globala positioneringssystem. Med den nyliga framgången hos djupinlärning applicerat på visuella problem har det kommit metoder för absolut geolokalisering med visuell djupinlärning med satellit- och UAV-bilder. De flesta av dessa metoder har bara blivit testade i stadsmiljöer, vilket leder till frågan: Hur väl fungerar dessa metoder i icke-urbana områden som fält och skogar? En av nackdelarna med djupinlärning är att dessa modeller ofta ses som svarta lådor eftersom det är svårt att veta varför modellerna gör de gissningar de gör, alltså vilken information som är viktig och används för gissningen. För att lösa detta har flera metoder för att tolka neurala nätverk utvecklats. Dessa metoder ger förklaringar så att vi kan förstå dessa modeller bättre. Denna uppsats undersöker lokaliseringsprecisionen hos en geolokaliseringsmetod i både urbana och icke-urbana miljöer och applicerar även en tolkningsmetod för neurala nätverk för att se ifall den kan förklara den potentialla skillnaden i precision hos metoden i dessa olika miljöer. Resultaten visar att metoden fungerar bäst i urbana miljöer där den får ett genomsnittligt absolut horisontellt lokaliseringsfel på 38.30m och ett genomsnittligt absolut vertikalt fel på 16.77m medan den presterade signifikant sämre i icke-urbana miljöer där den fick ett genomsnittligt absolut horisontellt lokaliseringsfel på 68.11m och ett genomsnittligt absolut vertikalt fel på 22.83m. Vidare visar resultaten att om satellitbilderna och UAV-bilderna är tagna från olika årstider blir lokaliseringsprecisionen ännu sämre, där metoden får genomsnittligt absolut horisontellt lokaliseringsfel på 86.91m och ett genomsnittligt absolut vertikalt fel på 23.05m. Tolkningsmetoden hjälpte inte i att förklara varför metoden fungerar sämre i icke-urbana miljöer och är inte passande att använda för denna sortens problem.

Distributed networks, meaning a network in which several agents work together unanimously to perform some task in order to reach goals has become a field with a wide range of applications. One such applications may exist in the form of drones with a purpose of observing and detecting forest fires. In such applications it can be of paramount importance to be able to agree over some opinions or values between the agents. This value could be something such as event detection or a general direction to fly in. However in such a network there might not exist a central hub and it would not be possible for all drones to communicate directly with each other. In order for such a network to be able to reach consensus or agreement, values have to be exchanged between the agents. This thesis focuses on a subset of this problem known as distributed averaging. In the thesis it is investigated how a networks ability to detect forest fires and communicate both efficiently and quickly can change when the number of agents are adjusted in the network. The results showed that, when operating in a fixed area, for a small network of drones the increasing effective energy cost per drone were higher, than that of a larger network. It was also discovered that the speed at which a network could reach an agreement was not necessarily affected by the size of the network. But as the field area being observed was increased, adverse effects were observed in terms of communication and event detection. / Distribuerade nätverk bestående av flera agenter som har som uppgift att tillsammans nå gemensamma resultat har blivit allt mer populärt. Ett sådant användningsområde är hur drönare kan användas för att observera och upptäcka skogsbränder över en given yta. I en sådan tillämpning är det av stor vikt att drönarnätverket kan kommunicera och kongruera över värden nätverket delar med varandra. Dessa värden kan representera händelser som nätverket har som uppgift att upptäcka eller en riktning för drönarna att flyga i. Det är inte alltid garanterat att det finns en central kommunikationscentral för sådana nätverk, utan blir beroende på att kommunicera med varandra för att utbyta och kongruera över värden. Den här rapporten fokuserar på en avgränsad del av det ovanstående problemet som kallas för distribuerat konsensusvärde (eng. distributed averaging). Rapporten undersöker hur ett sådant nätverks konvergeringsförmåga, totala energikostnad samt täckning påverkas när fler drönare tillförs till nätverket. När arbetsytan var satt till statisk storlek visade resultaten att den tillförda energikostnaden per drönare var högre för små nätverk än för större nätverk. Det visades också att hastigheten som nätverket når ett kongruerande värde inte nödvändigtvis påverkas av storleken av nätverket. När arbetsytan ökade i takt med storleken på nätverket observerades däremot motsatt effekt för energikostnad och hastigheten för att nå ett konsensusvärde.

Unmanned aerial vehicles (UAVs) are emerging as enablers for supporting many applications and services, such as precision agriculture, search and rescue, temporary network deployment, coverage extension, and security. UAVs are being considered for integration into emerging wireless networks as aerial users, aerial relays (ARs), or aerial base stations (ABSs). This dissertation proposes employing UAVs to contribute to physical layer techniques that enhance the security performance of advanced wireless networks and services in terms of availability, resilience, and confidentiality. The focus is on securing terrestrial cellular communications against eavesdropping with a cellular-connected UAV that is dispatched as an AR or ABS. The research develops mathematical tools and applies machine learning algorithms to jointly optimize UAV trajectory and advanced communication parameters for improving the secrecy rate of wireless links, covering various communication scenarios: static and mobile users, single and multiple users, and single and multiple eavesdroppers with and without knowledge of the location of attackers and their channel state information. The analysis is based on established air-to-ground and air-to-air channel models for single and multiple antenna systems while taking into consideration the limited on-board energy resources of cellular-connected UAVs. Simulation results show fast algorithm convergence and significant improvements in terms of channel secrecy capacity that can be achieved when UAVs assist terrestrial cellular networks as proposed here over state-of-the-art solutions. In addition, numerical results demonstrate that the proposed methods scale well with the number of users to be served and with different eavesdropping distributions. The presented solutions are wireless protocol agnostic, can complement traditional security principles, and can be extended to address other communication security and performance needs.

Methods were developed for the design of a solar powered UAV capable of tracking the sun to achieve maximum solar energy capture. A single-axis solar tracking system was designed and constructed. This system autonomously rotated an onboard solar panel to find the angle of maximum solar irradiance while the UAV was airborne. A microcontroller was programmed and implemented to control the solar tracking system. A solar panel and an efficient airframe capable of housing the solar tracking system was designed and constructed. Each of these subsystems was tested individually with either ground or flight tests. Ultimately, the final assembled system was tested. These tests were used to determine where and when a UAV with an onboard solar tracker would be advantageous over a conventional solar powered UAV with PV cells statically fixed to its wings. The final UAV had a wingspan of 3.2 meters, a length of 2.6 meters, and weighed 4.1 kilograms. Its solar panel provided a maximum power output of 37.7 watts. The predicted system performance, airframe drag, and system power requirements were validated with a battery powered flight test. The UAV's analytical model predicted the drag to be 41% lower than the actual drag found from flight testing. Full system functionality was verified with a solar powered flight test. The results and analysis of the system tests are presented in this thesis. The net energy increase from the solar tracking UAV over a conventional solar powered UAV for the duration of a day is dependent on season and geographical location. The solar tracking UAV that was developed was found to have a maximum net energy gain of 34.5% over a conventional solar powered version of the UAV. The minimum net energy gain of the solar tracking UAV was found to be 0.8%.

[pt] Com recentes avanços em poder computacional, o uso de novos modelos de controle complexos se tornou viável para realizar o controle de quadrotores. Um destes métodos é o aprendizado por reforço profundo (do inglês, Deep Reinforcement Learning, DRL), que pode produzir uma política de controle que atende melhor as não-linearidades presentes no modelo do quadrotor que um método de controle tradicional. Umas das não-linearidades importantes presentes em veículos aéreos transportadores de carga são as propriedades variantes no tempo, como tamanho e massa, causadas pela adição e remoção de carga. A abordagem geral e domínio-agnóstica de um controlador por DRL também o permite lidar com navegação visual, na qual a estimação de dados de posição é incerta. Neste trabalho, aplicamos um algorítmo de Soft Actor- Critic com o objeivo de projetar controladores para um quadrotor a fim de realizar tarefas que reproduzem os desafios citados em um ambiente virtual. Primeiramente, desenvolvemos dois controladores de condução por waypoint: um controlador de baixo nível que atua diretamente em comandos para o motor e um controlador de alto nível que interage em cascata com um controlador de velocidade PID. Os controladores são então avaliados quanto à tarefa proposta de coleta e alijamento de carga, que, dessa forma, introduz uma variável variante no tempo. Os controladores concebidos são capazes de superar o controlador clássico de posição PID com ganhos otimizados no curso proposto, enquanto permanece agnóstico em relação a um conjunto de parâmetros de simulação. Finalmente, aplicamos o mesmo algorítmo de DRL para desenvolver um controlador que se utiliza de dados visuais para completar um curso de corrida em uma simulação. Com este controlador, o quadrotor é capaz de localizar portões utilizando uma câmera RGB-D e encontrar uma trajetória que o conduz a atravessar o máximo possível de portões presentes no percurso. / [en] With recent advances in computational power, the use of novel, complex control models has become viable for controlling quadrotors. One such method is Deep Reinforcement Learning (DRL), which can devise a control policy that better addresses non-linearities in the quadrotor model than traditional control methods. An important non-linearity present in payload carrying air vehicles are the inherent time-varying properties, such as size and mass, caused by the addition and removal of cargo. The general, domain-agnostic approach of the DRL controller also allows it to handle visual navigation, in which position estimation data is unreliable. In this work, we employ a Soft Actor-Critic algorithm to design controllers for a quadrotor to carry out tasks reproducing the mentioned challenges in a virtual environment. First, we develop two waypoint guidance controllers: a low-level controller that acts directly on motor commands and a high-level controller that interacts in cascade with a velocity PID controller. The controllers are then evaluated on the proposed payload pickup and drop task, thereby introducing a timevarying variable. The controllers conceived are able to outperform a traditional positional PID controller with optimized gains in the proposed course, while remaining agnostic to a set of simulation parameters. Finally, we employ the same DRL algorithm to develop a controller that can leverage visual data to complete a racing course in simulation. With this controller, the quadrotor is able to localize gates using an RGB-D camera and devise a trajectory that drives it to traverse as many gates in the racing course as possible.

In recent years, Unmanned aerial vehicles (UAVs) have developed rapidly due to advances in aerospace technology, and wireless communication systems. As a result of their versatility, cost-effectiveness, and flexibility of deployment, UAVs have been developed to accomplish a variety of large and complex tasks without terrain restrictions, such as battlefield operations, search and rescue under disaster conditions, monitoring, etc. Data collection and offloading missions in The internet of thingss (IoTs) networks can be accomplished with the use of UAVs as network edge nodes. The fundamental challenge in such scenarios is to develop a UAV movement policy that enhances the quality of mission completion and avoids collisions. Real-time learning based on neural networks has been proven to be an effective method for solving decision-making problems in a dynamic, unknown environment. In this thesis, we assume a real-life scenario in which a UAV collects data from Ground base stations (GBSs) without knowing the information of the environment. A UAV is responsible for the MOO including collecting data, avoiding obstacles, path planning, and conserving energy. Two Deep reinforcement learnings (DRLs) approaches were implemented in this thesis and compared. / Under de senaste åren har UAV utvecklats snabbt på grund av framsteg inom flygteknik och trådlösa kommunikationssystem. Som ett resultat av deras mångsidighet, kostnadseffektivitet och flexibilitet i utbyggnaden har UAV:er utvecklats för att utföra en mängd stora och komplexa uppgifter utan terrängrestriktioner, såsom slagfältsoperationer, sök och räddning under katastrofförhållanden, övervakning, etc. Data insamlings- och avlastningsuppdrag i IoT-nätverk kan utföras med användning av UAV:er som nätverkskantnoder. Den grundläggande utmaningen i sådana scenarier är att utveckla en UAV-rörelsepolicy som förbättrar kvaliteten på uppdragets slutförande och undviker kollisioner. Realtidsinlärning baserad på neurala nätverk har visat sig vara en effektiv metod för att lösa beslutsfattande problem i en dynamisk, okänd miljö. I den här avhandlingen utgår vi från ett verkligt scenario där en UAV samlar in data från GBS utan att känna till informationen om miljön. En UAV är ansvarig för MOO inklusive insamling av data, undvikande av hinder, vägplanering och energibesparing. Två DRL-metoder implementerades i denna avhandling och jämfördes.

Den ökade tekniska utvecklingen och användandet av obemannade system ställer krav på en förståelse för dess inverkan på krigföringen. Urban miljö är ofta oundviklig vid markstrid och medför utmaningar som korta stridsavstånd, ökad risk för vådabekämpning och snabba stridsförlopp. Ett system som patrullrobot kan bidra till förbandens förmågor genom spaning, verkan och möjlighet till flexibel manövrering. Arbetet besvarar frågeställningen ”Hur kan patrullrobotsystem medföra militär nytta vid ett markförbands anfall i bebyggelse?” med utgångspunkt i den teoretiska referensramen militär nytta. Analysverktygen utgörs av SWOT-analyser och teorins dimensioner för militär effektivitet, militär lämplighet samt överkomlig kostnad. Syftet med arbetet är att utforska hur patrullrobotsystem kan medföra militär nytta vid anfall mot hastigt uppkomna mål. Resultatet visade att patrullrobotsystem kan anses ha flera möjligheter till att medföra militär nytta. Anledningen är främst de karaktäristiska egenskaperna gällande dess sensorer och en inbyggd verkansdel som bidrar till möjlighet för spaning och precisionsbekämpning. Det tekniska systemet har således en god övergripande förmåga att utföra uppdrag i urban miljö genom exempelvis ökad underrättelseinhämtning och reducerad risk för sidoskador. Patrullrobotsystemet tyder även ha en god förmåga att kunna interageras med andra system och bidra till en synergieffekt. Vidare är den ekonomiska faktorn oftast lägre i jämförelse med andra vapensystem som har liknande precision vid långa avstånd. Likt andra militära system är det dock av vikt att användandet övervägs och är i enlighet med de lagar, förordningar och etiska principer som är fastställda. Tydliga målsättningar underlättar ett optimerat användande av systemet. / The increased technological development and the use of unmanned systems are requiring an understanding of their impact on warfare. Urban environments are often unavoidable in ground combat and bring challenges such as short combat distances, increased risk of friendly fire and rapid combat progress. A system such as a loitering munition can contribute to the unit's abilities through reconnaissance, damage and the possibility of flexible maneuvering. This thesis report answers the question "How can loitering munition systems entail military utility in the context of a ground unit's attack in urban warfare?" based on the theoretical frame of military utility. The analysis tools consist of SWOT analysis and the theory's dimensions of military effectiveness, military suitability and affordability. The purpose is to explore how loitering munition systems can entail military utility in attacks against rapidly emerging targets. The result showed that loitering munition systems can be considered to have several opportunities to entail military utility. The reason is mainly the characteristic features regarding its sensors and a built-in warhead that contributes to the possibility of reconnaissance and precision strike. Thus, the technical system has a comprehensive ability to carry out missions in an urban environment through, for instance, increased intelligence and reduced risk of collateral damage. The loitering munition system also indicates a great ability to interact with other systems and contributes to a synergy effect. Furthermore, the economic factor is usually lower in comparison to other weapon systems with equivalent precision throughout long distances. Nonetheless, as for other military systems, it is important that the use is considered and is in accordance with the laws, regulations and ethical principles that have been established. Clear objectives make it easier to optimize the use of the system.

A unique Unmanned Aerial Manipulator (UAM), also termed an aerial robot, is the subject of this thesis. A UAM is composed of a floating base attached to a manipulator that enables it to interact physically with the environment. The floating base is an Unmanned Aerial Vehicle (UAV) and the manipulator is defined as a two-cable underactuated Cable Driven Parallel Robot (CDPR). This specific design of a UAM is, to the author’s best knowledge, a novel concept. The thesis is done in collaboration with Airforestry, a company currently developing a solution for aerial forest thinning aiming to provide a more sustainable and efficient way to thin forests. Forest thinning today involves using heavy ground equipment that can cause damage to the surrounding environment and climate. The solution includes a UAV hovering over a chosen tree and attaching a tool (the manipulator) to it, cutting it, lifting it, and then transporting it. The thesis presents a planar model, control method, and simulation of the UAM system. The kinematic and dynamic models of the UAM are derived. A Proportional-Derivative (PD) controller is implemented for flying the UAV and another for controlling the cables. The model is simulated and examined by commanding the UAM to specific set-points under different circumstances such as comparing the UAV flying with and without the tool, changing the length of the cables, and changing the placement of the manipulators Center of Mass (CoM). Overall, the degree project provides a solid model foundation for the specific UAM which can be built upon and further improved. / En specifik Obemannad Flygande Manipulator (UAM), även kallad en flygande robot, är ämnet för denna avhandling. En UAM består av en flytande bas som är fäst vid en manipulator, vilket gör det möjligt för den att interagera med omgivningen. Den flytande basen är ett Obemannat Flygfordon (UAV) och manipulatorn definieras som en tvåkabel-aktuerad kabeldriven parallellrobot (CDPR). Denna specifika design av en UAM är, enligt författarens bästa kunskap, ett nytt koncept. Avhandlingen utförs i samarbete med Airforestry, ett företag som för närvarande utvecklar en lösning för skogsavverkning från luften i syfte att erbjuda ett mer hållbart och effektivt sätt att tunna ut skogar. Skogsavverkning idag innebär användning av tunga markmaskiner som kan skada den omgivande miljön och klimatet. Lösningen inkluderar en UAV som svävar över ett valt träd och fäster ett verktyg (manipulatorn) på det, skär det, lyfter det och transporterar det sedan bort. Avhandlingen presenterar en planarmodell, kontrollmetod och simulering av UAM-systemet. De kinematiska och dynamiska modellerna för UAM härleds. En proportionell-derivativ (PD) kontroller implementeras för att styra UAV:n och en annan för att kontrollera kablarna. Modellen simuleras och undersöks genom att styra UAM:n till specifika målpunkter under olika omständigheter, såsom att jämföra UAV-flygning med och utan verktyget, ändra längden på kablarna och ändra placeringen av manipulatorns masscentrum (CoM).svis ger examensarbetet en stabil modellgrund för den specifika UAM:n, som kan byggas vidare och förbättras.

This study aimed to develop a novel end-to-end plant diagnosis model for the analysis of plant health conditions in near real-time to optimize the rate of production on farmlands for an intensive, yet environmentally safe farming production to preserve the natural environment. First, field research was conducted to determine the extent of the problems faced by farmers in agricultural production. This allowed us to refine the research statement and the level of technology involved in the production processes. The advantages of unmanned aerial systems were exploited in the continuous monitoring of farm plantations to develop automated and accurate measures of farm conditions. To this end, this thesis applies the Precision Agricultural technology as a data based management system that takes into account spatial variations by using the Global Positioning System, Geographical Information System, remote sensing, yield monitors, mapping, and guidance system for variable rate applications. An unmanned aerial vehicle embedded with an optic and radiometric sensor was used to obtain high spectral resolution images of plantation status during normal production/growth cycle. Then, an ensemble of classifiers with Convolution Neural Networks (CNN) was used as off the shelf feature extractor to train images to develop an end-to-end feature detection and multiclass classification system for plant overall health’s conditions. Whereby previous works have concentrated on using CNN as off the shelf feature extractor and model training to detect only plant diseases from plants. To date, no research has yet been carried out to develop an end-to-end model for the overall plant diagnosis system. Previous studies focused on the detection of diseases at any given time, making it difficult to implement comprehensive real-time PA systems. Applying the pretrained model to the new images showed that the model can accurately predict any plant condition with an average of 97% accuracy.

No description available.