APRÈN. Portal de la producció docent del professorat de la UPC

Unmanned aerial vehicles (UAVs) are becoming more and more common, and this trend is predicted to continue in the coming years. Although there are many uses for UAVs, this bachelor's thesis will focus on the three-dimensional (3D) digital reconstruction of still real-world objects. On the one hand, there are UAVs that are able to obtain 3D reconstruction of environments and large objects using complex systems like LiDAR (Light Detection and Ranging) sensors or cameras with high resolution and quality. On the other hand, there are UAVs that are used to enable 3D reconstructions inside houses or structures using the aforementioned systems or more complex ones. In this work, the focus will be on testing the capabilities of UAVs with limited resources and smaller than the rest (in this case the smallest UAV on the market will be tested). Using Structure from Motion (SfM) systems and the support of Generative AI approaches, the aim of this thesis is to prove that, with limited capabilities, a coherent and precise 3D reconstruction is possible. The focus will be on proving that low-capability UAVs can be competent enough to habilitate anomaly detection on small objects. This will enable new applications to the UAVs on zones that are of hard reachability. These smaller UAVs can also be used to obtain 3D reconstructions of structures easily with UAVs that have less economical cost to the end user, generating a pipeline for obtaining the whole reconstruction. The Bitcraze framework's autonomous positioning feature for the UAV had to be enabled before the experiments could begin. For this, an anchor-based LoCo positioning system from Bitcraze had to be set up in the testing environment. The objective was to have the UAV (a Crazyflie 2.1) follow a static trajectory, capturing images of an object that is at the centre of this path. These tests considered different scenarios. After that, the Generative Artificial Intelligence (GenAI) pipeline was used. For using this pipeline, three approaches were used: Nerfacto, Instant-ngp and Splatfacto. On one hand, these 3 approaches were compared using 1 UAV, and after that they were compared using 2 UAVs. Here it is important to say that Colmap, another SfM tool, was used for the processing of the data. On the other hand, after that, the positions obtained by the UAV at the moment of taking the images were used to later align the estimated positions by Colmap. All of this was tested to see which is the best model, see if the corrected positions helped with the 3D reconstruction, and finally, but most importantly, to see if, with these 3D reconstructions, it is possible to enable the anomaly detection of small objects feature for small UAVs with limited capabilities. Finally, some results of performance of the mesh extraction, point cloud generation and of the render quality of the different models. These were done and successfully made, fullfiling the objectives and generate new challenges for future works.

The goal of this thesis is to develop a drone-based Search And Rescue (SAR) system that leverages cellular network technology to locate individuals in areas without coverage. The system is designed to detect and communicate with mobile phones carried by missing persons using a drone equipped with a Software Defined Radio (SDR) device. The solution aims to improve SAR missions by allowing rescuers to locate individuals based on their phone signals. The methodology involves the integration of an SDR-based GSM base station onto a DJI Matrice 350 RTK drone. Several hardware components were evaluated to meet the constraints of weight, power, and performance required for airborne operation. Open-source cellular network frameworks were used to implement the mobile network. Both GSM and LTE technologies were considered for the system, but development efforts focused primarily on the GSM implementation, while the system architecture was designed to support both technologies. Field experiments were conducted to measure key performance indicators, and multilateration techniques were applied to estimate the location of the detected phones based on signal data collected during test flights. The results demonstrate the practicality of the system for SAR operations. Successful field tests validated its ability to detect mobile phones and reduce the effective search area, offering significant potential for reducing search times in remote or inaccessible areas. The project also identifies areas for future improvement, such as optimizing power consumption, refining location algorithms, and integrating real-time voice communication. This developed solution offers a cost-effective and efficient alternative to traditional SAR methods, improving the ability to locate missing persons in areas without cellular coverage.

La familia de microcontroladores STM32 de 32 bits es la más ampliamente utilizada para el diseño de controladores de drones en la actualidad. En este trabajo se propone el diseño e implementación de un dron cuadricóptero freestyle controlado mediante un microcontrolador de la familia STM32. Los drones de tipo freestyle son drones con un estilo de vuelo que requiere un alto grado de habilidad de los pilotos y en los que pueden ocurrir fácilmente impactos que afecten gravemente la integridad del dron. Se solicita así desarrollar y validar un sistema de detección y prevención de impactos que se integrará con los diferentes elementos que componen un sistema cuadricóptero con el fin de obtener un prototipo final completamente funcional que permita su reconfiguración y mejora en función de necesidades futuras.

Currently the drone sector, also referred to as Unmanned Aircraft System (UAS) or Remotely Piloted Aircraft System (RPAS), has experienced exponential growth due to the versatility it offers in various areas, whether in leisure, in inspections of infrastructure or agriculture, rescues or even the use of these in police forces and government security forces. The mechanisms for remote control of drones depend on the system they incorporate, using different frequencies for each case. In general, they can be distinguished between control by radio, by Wi-Fi and by LTE (4G, 5G, etc.). Regarding radio and Wi-Fi control, they have a couple of disadvantages, range and interference with obstacles. Although there are methods to be able to increase the operational range of the remote controller, its use for it to be optimal must be in an open field, without obstacles. On the other hand, the systems controlled by LTE offer more range due to the fact that they have a connection to the mobile communication network. Even so, this last system needs ground stations or antennas that provide the network, meaning that in remote places or without network access or poor connection, it cannot be used. Also, satellite communication can offer to fill this last problem, since no ground station would be needed, as the connection is made directly with the satellites. In this project, carried out in the German drone company Dronivo GmbH, it will seek to implement a satellite communication system (primarily with Starlink, due to its recognition and high capabilities) and adapt it in UAS or remote control systems in order to study the benefits and disadvantages that this would entail, either in data transfer, video transmission, remote control or even the implementation in the system. During this project, a market study is presented in order to have an idea of which devices could be used, which devices will finally be used together with their integration and configuration in the system, a series of initial tests to find errors and thus carry out the necessary changes and additional integrations for the correct operation of the system, and the performance of a series of final tests to be able to draw good conclusions from the final system, with the expectation of opening a new chapter in drones communications.

La família de microtroladors STM32 de 32 bits és la més àmpliament utilitzada per a disseny de controladores de drons en l'actualitat. En aquest treball es proposa el disseny i implementació de sistemes de localització avançats que puguin ser incorporats a un dron quadrirotor controlat mitjançant un microcontrolador de la família STM32. D'una banda, s'estudia la viabilitat de la incorporació i programació dins del codi base del dron d'un sistema de geolocalització i la seva integració en el sistema de control de vol del dron. D'altra banda, s'estudia la incorporació d'un sistema de càmera dual estereoscòpica per a la localització d'objectes, considerant la seva identificació mitjançant intel·ligència artificial. Opcionalment, es busca dissenyar i implementar l'enviament posterior de les dades de localització a una estació terrestre en la que es puguin implementar funcions addicionals avançades. Es desenvolupen diferents sistemes de localització i la seva integració en el sistema del quadrirotor per tal d'aconseguir un prototipus final plenament funcional que permet la seva reconfiguració i millora el funció de necessitats futures. Addicionalment s'estudien teòricament: diversos sistemes de localització, identificació de punts clau en imatges, estimació de profunditat en múltiples imatges, com realitzar una intel·ligència artificial entre d'altres. A més a més s'han realitzat altres estudis teòrics i pràctics com pot ser: vSLAM (Localització i mapeig visual simultani), sistemes de posicionament amb visió en primera persona i test estructurals per al hardware. Així com l'estudi, la comparació i possibles millores d'aquest sistemes. Tot aquest treball s'ha desenvolupat amb diferents softwares com: STMCubeProgrammer (STM32 codificador), Matlab, Arduino (en el STM32), Linux (a la raspberry pi), U-center (GNSS evaluator), etc.

Bluetooth technology is very common for communication between devices such as mobile phones, headphones, and even watches. Nowadays, it is difficult to find someone who does not have at least one of them. This opens the door to the possibility of detecting these devices using this technology, and with it, the individual carrying them. Over the years, many people have gotten lost in forests or mountainous areas due to disorientation, sudden weather changes, or countless other reasons. A lost and uncommunicated individual represents an emergency that requires quick and effective rescue methods. The methods used today by rescue teams, such as helicopters and drones equipped with cameras, involve visually searching for the individual, which can slow down the process and increase the risk to the lost person. To address this problem, this project, based on the integration of two previous projects, has designed a system capable of measuring Bluetooth signal strength, a parameter called RSSI, in different orientations in space. This system is mounted on a drone, allowing large areas to be covered in a short period of time. Throughout this thesis, we will explore the different hardware components used for detection, how they are connected, and the supports designed to safely mount the system on the drone while minimizing payload. The software and intelligence used to capture and process RSSI data will be detailed. Finally, the project will conclude by presenting the results of flight tests conducted in controlled environments, such as the university facilities, as well as in more realistic environments to observe the system's behavior at greater distances and in wooded areas. Overall, this project aims to combine the conclusions from two previous projects to create a system capable of detecting Bluetooth signal strength and its direction of origin. This opens up new possibilities in the field of locating people using drone technology

Nowadays, the space industry is experiencing exponential growth, fueled by private companies and the conception of new and ambitious challenges. In recent years, the cost of reaching space has been drastically reduced, and to a certain extent, reusable rockets are to blame for that cost reduction. Unfortunately, and it has always been so, the space industry has always required a lot of resources and funding, and even with the drastic cost reduction with the incorporation of this new type of rockets, the development of technologies by students and researchers from universities around the world is still very difficult. To address this problem, this thesis will attempt, by reducing the cost to a maximum, to develop a system where it can study the dynamics of reusable rockets and be able to develop technologies around them. To do this, an unmanned aircraft system (UAS) will be designed from scratch with the main objective of imitating the behavior of this type of rocket while trying to reuse as many components already used by the university as possible, helping to reduce costs, and also helping to reduce the environmental impact of the project itself. Through the different chapters of this work, it can be seen, from the conception of the initial requirements and selection of the different components, to the 3D design and subsequent manufacturing of the system itself, which will be calibrated and tested in different test flights, taking advantage of the university's facilities. Ultimately, this work aims to serve as a useful tool for future students and researchers to deepen their knowledge of the attitude control of this type of rockets, and furthermore, to develop new technologies around the system that is intended to be designed and manufactured in this thesis.

This master thesis consists of a research and development project¿s documentation about Electrical Vertical Take off and Landing (EVTOL) technology. The main target is providing an investigation about this technology, reviewing its history since its origins to the future lines, understanding how it works by revising all the technical aspects such as the mechanical part, hardware components, software systems, structural stress design¿ In addition, a market study is carried out around this technology to come up with a first prototype. Based on a research for the applications and utilities that it can offer regarding the future problems that humanity is facing. Furthermore, this thesis documents the analog and digital methodologies that are being used throughout the entire creative process combining design and engineering workflows in order to achieve the proposed objectives. The project¿s value resides on the creative design aspect, therefore all the content is based from the pre-production design perspective. As the most technical part involving the product production such as the stress design aspect to select the right components, or quality validation process would be carried out on further stages by the engineers.

Drones are an emerging tool for traffic surveillance; however, they inherently lack the capability to solely obtain vehicle speed on the road. This Bachelor's thesis presents the design, implementation and study of a system to detect the position, velocity and type of vehicles using the video stream obtained from drones. The solution is created to be used with any kind of aerial vehicle but is tailored for the drones in the European project LABYRINTH, of which the thesis has been a part. The tool utilizes the video feed from a sole camera and the telemetry data from the drone to detect, track and project the objects present on the road from the image into reality. This allows for an estimation of their position and speed. The detection and tracking algorithm implemented is the Simple Online Real Time algorithm, which is often referred to as SORT. Once the position has been acquired, another stream is generated that displays the same video, but with the bounding boxes, velocity and confidence ratings of all identified vehicles, with an overall computing time lower than the frame rate. After implementation, the tool underwent testing in a simulated environment to determine its assets and shortcomings, and was used during the LABYRINTH traffic monitoring flight tests. The Bachelor's thesis achieves the aimed objectives with minimum resource utilization, using readily available logic and open-source software to strike an optimal balance between real-time functionality and precise detection of vehicle position.

The Eurofighter Typhoon is a high-performance multi-role combat aircraft developed collaboratively by European aerospace companies, including Airbus, and it holds significance as a technologically advanced and versatile fighter jet in modern air forces. This thesis focuses on the development of a flight simulation gimbal for the Eurofighter Typhoon, with the goal of enabling real-time data visualization of flight maneuvers. Simulations have become a crucial tool across various disciplines for solving complex problems and gaining in-depth insights into intricate systems. By analyzing simulation models in 3D, concepts and solutions become more comprehensible and communicable. Engineers heavily rely on simulations to enhance their understanding of systems, and this thesis aims to extend these benefits to the development teams and pilots of the Eurofighter Typhoon aircraft at Airbus. The primary objective is to facilitate visualizing and comprehending the aircraft's flight behavior during its development and optimization phases. Furthermore, this visualization tool seeks to enhance pilots' comprehension of the aircraft's capabilities and ultimately attract new customers. The simulation gimbal is designed to precisely represent the flight motion of all the Euler angles of the Eurofighter aircraft model. The simulation system not only focuses on visual representation of the angles but also incorporates realistic movement of the aircraft's main control surfaces, enhancing the fidelity of the flight dynamics. These control surfaces include the flaps, foreplanes, rudder, and airbrake. The thesis is structured into two main parts. The first chapters provide an overview of the mechanical and hardware aspects. This includes the detailed implementation of the Eurofighter Typhoon model within the simulation environment and an in-depth exploration of motor control mechanisms that enable realistic motion simulation. The second part of the thesis elaborates on the detailed implementation of the software for the project's full control. Including software to control all the motors and software to monitor and configure the gimbal. This thorough examination of hardware, software, and model implementation aspects provides a comprehensive guide for building and utilizing such simulation tools in the future.

In this Bachelor's Degree Final Project, a mobile application for person identification using a DJI drone and the DJI Mobile SDK and DJI UX SDK software libraries is designed, implemented, and tested. The application tries to identify a specific person among those that are detected in the image. Our proposal, for this, is that the person who wants to be identified wears a GPS device to merge the information from the people detector with the location information provided by the GPS. The operation of the application mainly involves monitoring an MQTT server where different devices will upload their position using geodetic coordinates. Then, based on these coordinates, the application will perform a coordinate system transformation to obtain the pixel coordinates where the device is located. With these coordinates, the device's position can be overlaid on the video. Additionally, the application includes other visual functionalities such as a manager for photos and videos taken by the drone, a mini-map to visualize the drone's and surrounding devices' positions, a coordinate converter from screen points to geodetic coordinates, and the ability to write device data and drone position and attitude data to a text file. For the development of the application, various Software Development Kits (SDKs) are used, which provide the necessary resources for application development. Some of the SDKs used include the Android SDK, DJI UX SDK, and DJI Mobile SDK, with the latter two being from DJI. The MQTT protocol is used for message exchange between the drone and the different devices in the field. This protocol is based on centralized data exchange on a server and utilizes a publish-subscribe system. Furthermore, three different devices are used to obtain the user's location through GPS and send it to the MQTT server for the drone to access. One of these devices is created using a Raspberry Pi, another is an Android app, and the last one is based on a board from ArduSimple. Upon completing the application development, the project's initial objectives have been successfully achieved. A functional application has been programmed, and a device compatible with the specified requirements has been developed.

Bluetooth is a technology widely used in device pairing. Everybody has got a device with Bluetooth: a mobile phone, headphones, a smart watch¿ Therefore, this technology can be used in order to detect these devices. The aim of this work is to apply people detection with a drone detecting Bluetooth devices. One of the main problems is when the police forces need to control a huge crowd. An important information for them is the number of people. Nowadays image sensing is used with drones, but other possibilities can be studied. In this investigation, Bluetooth technology will be used in order to count how many people are in a specific place. Running races are the main tests performed in order to conclude if it is possible to know how many people are concentrated. Another problem is when people get lost in forests. The search and rescue teams nowadays use helicopters and drones equipped with cameras in order to search people, but it is difficult to distinguish people if the aircraft is flying in high altitudes. Bluetooth detection can be a solution for this problem. The RSSI from a device will be used in order to know if the drone is near or far from it, and therefore, from the person. There are many factors that must be taken into account such as transmission power, drone speed, altitude¿ The devices that are detected can be divided into two categories. The passive search is the one using people's devices like mobile phones, smart watches and other personal devices. The active search is the one done using devices specially designed for this task and carried by the people. The conclusion is that Bluetooth is a technology that can not be used in order to count how many people are in a specific area as devices change their addresses very frequently and there are many devices detected, resulting in erroneous people counting. However, Bluetooth can be used in order to detect people in remote areas without the need of the internet. The precision and accuracy of the detection is really high and the application has got many benefits, like time saving for search and rescue teams.

The main objective of this project is the creation of drone coordination software, understanding coordination as the drones respect the previously designed positions and timings, as well as the design of the required systems to provide the required level of precision and accuracy to the drones positions and a LED system to illuminate the drones with lighting coordination. The two currently available solutions require the use of modified firmware. The use of modified firmware restricts the upgradability of the firmware of the drone as only one company is responsible for developing the custom firmware and therefore deciding when to upgrade the system. Moreover, the use of custom firmware could leave the drones unusable for other applications as some functionality may be removed in order to add the functionality needed for the coordination. Therefore the drone coordination software has to function without modifying the firmware. Drone coordination without modified firmware can be achieved with the addition of onboard computers, which are responsible for doing all the required processes and calculations in order to assure drone coordination. This led to the creation of multiple systems with each iteration improving the errors found in the previous iterations. The final iteration lead to a working scalable system in the simulations that due to time constraints and chip shortage was unable to be tested in the real world and after a brief cost assessment resulted in not being commercially viable on a large scale due to the increased cost of each drone compared to the commercially available solutions, and the availability of the components of the drone as with current stock it would be impossible to create a large fleet of drones to perform a large scale test.

In this Final Degree Project, an application for Android devices is designed, implemented and tested for the control of DJI drones using the DJI Mobile SDK software library. The operation of the application consists mainly in the monitoring and control of a DJI aircraft through a ground station that meets the requirements stipulated in the project. The application implements various functionalities such as sending telemetry, takeoff, landing, taking pictures and returning to the previously marked point called home. It also includes visual functionalities such as the manager of photos and videos taken by the drone and the functionalities mentioned before, but visually activated. Several Software Development Kits (SDK) are used, a tool which provides the necessary resources for the development of the application. These are: Android SDK, DJI UX SDK and mainly DJI Mobile SDK. These last two SDKs are provided by DJI to program applications compatible with its drones. Also, a software library created by the ICARUS research group called Rima Communications is used for the exchange of messages between the drone and the ground station. To enable communication between the application and the ground station, the MQTT protocol is used to facilitate the exchange of messages. This protocol is based on the exchange of centralized data on a server and uses a publish and subscribe system. At the end of the development of the application, most of the different initial objectives proposed have been achieved. A functional and, above all, extensible application has been programmed, with which future projects will be developed.

This document sets out the report of the final degree thesis which aims to design and implement a software architecture for the control and monitoring of drones from a web application. In addition, it is intended to provide the tools so that the application can be improved by the school community with other final thesis. To achieve this objective, a series of videos have been made in tutorial format in which the basics for installing and using the main technologies are explained. After an analysis and comparison of some of the many technological possibilities to carry out the work, starting from the architecture of the Drone Engineering Ecosystem (architecture under test that is used in the drone master based on a desktop application), it is decided to develop the frontend with Vue.js, test RabbitMQ and the AMQP protocol as a messaging protocol on the drone, develop a backend as a WebSockets server and a REST API based on the Flask library. Moreover a MongoDB database is installed in the drone with a storage system with an onboard REST API together with new functionalities and features. The result is a web application from which the user can view telemetry data, take photos with the drone and display them on the same page, turn on and off a sequence of leds, control the drone (arm it, take off to a certain height and move it to certain coordinates), see the drone on a map in real-time and design and execute a flight plan with different options. This application also contains a gallery to see the photos taken during the flight with information about the coordinates and time at which they were taken. A separate web app is also produced to view what the drone's camera is recording live. The results are very satisfactory, as it has been possible to implement and test the operation of up to 3 different architectures in the Campus drone lab: two of them depending if you want to work in an internet connection environment (for testing, for example) or in a global environment that requires an internet connection. For the third architecture, the backend that manages subscriptions and publications of the messaging broker is dispensed by connecting the broker directly to the frontend. The only aspect that has not been possible to implement correctly is the automated deployment with Docker of the onboard software.

Following a project is presented where a programme capable of simulating airport traffic is developed using an algorithm explicitly designed to optimise arrivals and departures at an airport. The purpose of the algorithm is to find the optimal route between two points by taking into account, and analysing, all the vehicles moving through the airport. With all vehicles sharing a route, it must analyse whether it generates a potential conflict. Conflict shall be understood as those situations in which both vehicles or aircraft arrive at the same point with a time difference of less than that established by the Runway Safety Regulations and therefore the Safety of the airport may be put at risk. In addition, the algorithm shall take into account those taxiways that are closed in order not to propose routes that pass over them. Optimum means the shortest route in terms of time between two points. At all airports, the longer a vehicle or aircraft is in movement through the Aeronautical Safety and Security Zone (ASZO), the more likely it is to generate or suffer an incident that compromises Safety and, in its worst consequence, may compromise the safety of people. The purpose of the programme will be to simulate all arrivals and departures, either freely or by reading a document containing the traffic of an airport time slot, using the algorithm designed. The report is divided into two main chapters. In the first, the different types of algorithms are analysed and an algorithm capable of analysing the airport environment (vehicles in movement and closed taxiways) is created. The second chapter develops how the programme was created by explaining the logical and graphical part of the programme.

The scope of this project is aimed on studying how UAS can navigate in GPS denied environments. In the first chapter, a research and study of the different existing systems will be performed in order to get in touch with the technology used for this navigation technique. Once the research is done and we have studied some of the different options available, one of the solutions will be chosen and will be implemented in our drone in order to perform different flight tests. Second chapter will show how to recreate the drone used in the flight tests from 0, starting with all the independent components and ending up in the final drone with all the configurations and connections done, ready to use in the field test. Once the drone is ready to flight, third chapter will propose several flight tests to be done, according to the different scenarios that we expect to give us the maximum changes in the behaviour of the drone. Next step after all the flights are done will consist in analysing which are the more important factors that have affected to our flights. After seeing the results, we will be able to conclude if the technology used for positioning in GPS denied environments is effective and helpful to our drone, or on the other hand, not as useful as expected and not worth to be used.

Los sistemas no tripulados de uso civil han experimentado un gran crecimiento y evoluci ´on tecnol ´ogica en los ´ultimos a˜nos, especialmente desde la popularizaci ´on de los drones. Una de las piezas fundamentales de estos sistemas son los mecanismos de pilotaje autom´ atico, que tienen la capacidad de dirigir el veh´ıculo siguiendo rutas y planes preestablecidos mediante el uso de sensores y elementos de detecci´on del entorno. En general, est ´an compuestos por un computador conocido como placa controladora y por un software con el que gestiona cualquier tipo de tarea para la que est´e programado. En este proyecto se lleva a cabo una comparativa entre autopilotos para veh´ıculos no tripulados, centr ´andose en las plataformas de hardware y software de c´odigo abierto m´as relevantes. Se estudian los est ´andares de placas controladoras creados por la organizaci ´on Pixhawk, as´ı como los dos desarrolladores de software libre Dronecode y Ardupilot. En concreto se eval ´uan las diferencias entre las placas Pixhawk 4 y Pixhawk 2.1 Cube, adem´as de los dos firmwares PX4 (de Dronecode) y Ardupilot, que son algunas de las opciones m´as comunes en sistemas no tripulados dentro del ´ambito de la investigaci ´on. El objetivo principal es proporcionar informaci´on ´ util sobre todos estos elementos y determinar cuales conviene m´as usar dependiendo del tipo de veh´ıculo y de las aplicaciones que se les quiera dar. El estudio consta de una parte te ´ orica y otra pr ´ actica. En primer lugar se investigan en profundidad las placas controladoras y las plataformas de software mencionadas, concluyendo cuales son las ventajas y desventajas que tienen entre si. Por otro lado, la parte experimental consiste en pruebas realizadas con diferentes tipos de sistemas no tripulados, uno a´ereo y otro terrestre. Dichas pruebas son recorridos que cada veh´ıculo tiene que seguir autom´aticamente y que se repiten con las dos placas de Pixhawk junto a los firmwares de PX4 y Ardupilot en igualdad de condiciones. Finalmente se lleva a cabo un an´ alisis de los resultados con Matlab a partir de los datos registrados durante los experimentos.

A día de hoy la tecnología es necesaria para el desarrollo humano ya que gracias a ella, hemos sido capaces de crear aplicaciones que cubren muchas necesidades imprescindibles para mejorar la calidad de vida y tener soluciones ante muchos problemas. Actualmente, una de las tecnologías de la que todo el mundo habla y conoce son los Drones, t écnicamente llamados RPAS (Remotely Piloted Aircraft System). Estos son vehículos no tripulados los cuales est án en pleno desarrollo y que pueden ofrecer infinitas aplicaciones para cubrir necesidades en nuestra vida cotidiana. Este proyecto tiene como objetivo explorar cómo la tecnología de realidad aumentada (AR) puede mejorar la visualizaci ón y procesado de datos de sensores integrados en un RPAS. Para ello se va a desarrollar una aplicaci ón m´ ovil con AR que permitir á visualizar los datos generados por los sensores del RPAS, en tiempo real y en tiempo diferido. La aplicaci ón se ha desarrollado utilizando Unity 3D, un entorno de desarrollo multiplataforma que nos permite crear aplicaciones de AR. Para poder evaluar la aplicaci ón desarrollada y determinar las ventajas de utilizar la tecnología de AR para la visualizaci ón de datos en estos entornos, se integrar á la aplicaci ón desarrollada con los datos obtenidos de un RPAS con un detector de radiactividad. Una de las m´ ultiples aplicaciones que tienen los RPAS, y que es en la que nos basamos en este trabajo, es la detección de radiactividad mediante un detector que pueden llevar integrado estos vehículos. Esta detecci ón se hace a partir de un plan de vuelo encima de una superficie en la cual hay distintas fuentes radiactivas, donde el RPAS con el detector, detecta dichas fuentes y guarda los datos de localizaci ón y nivel de radiaci ón para después poder ser estudiados. Debido a que la radiaci ón no se puede percibir con el ojo humano, con la aplicaci ón será posible visualizar objetos 3D en las ubicaciones en las cuales se han detectado niveles de radiaci ón, pudiendo ver el nivel de radiaci ón e información del vehículo. Dentro de este proyecto hemos desarrollado distintas versiones de esta aplicaci ón para qu´ e, según las necesidades del usuario, pueda utilizar una u otra. Esto puede suceder si se necesita un an´ alisis post-procesado, es decir, analizar las muestras obtenidas después de realizar el vuelo, o en tiempo real, durante el vuelo. Para el an´ alisis post-procesado tenemos las versiones OFF-LINE y ON-LINE, las cuales una no necesita de conexi ón a internet para utilizarla y la otra si, ya que es necesario conectarse a un servidor para leer el fichero con los datos obtenidos. Para el procesado en tiempo real tenemos otras dos versiones, las llamadas MQTT y RUNTIME, las cuales utilizan, a parte de conexi ón a internet, un protocolo el cual permite la transmisión en tiempo real de los datos que est á captando el RPAS en todo momento.