Aprèn - Miguel Valero García

This project presents the design and development of a drone control system integrated into the Drone Engineering Ecosystem, utilizing voice recognition technology to guide unmanned aerial vehicles. The main objective of the project was to add a new functionality that allows users to dictate flight plans verbally, which are then interpreted and executed by the drone autonomously. The project integrates various technologies, including Python's SpeechRecognition library and Google's cloud-based voice recognition services, to capture and process voice commands, transforming them into actionable flight directions. The system was implemented following a modular architecture that enables scalability and future enhancements, such as the integration of more advanced neural networks for natural language processing. Tests demonstrate that the system accurately captures and stores flight plans and allows seamless drone navigation based on these plans. The results underscore the potential of voice-controlled drones for a wide range of applications, enhancing accessibility and operational flexibility in the field of autonomous aerial systems.

Este proyecto presenta el diseño y desarrollo de un sistema de control de drones integrado en el Drone Engineering Ecosystem, utilizando tecnología de reconocimiento de voz para guiar vehículos aéreos no tripulados. El principal objetivo del proyecto fue añadir una nueva funcionalidad que permite a los usuarios dictar planes de vuelo verbalmente, los cuales son interpretados y ejecutados de manera autónoma por el dron. El proyecto integra diversas tecnologías, como la biblioteca SpeechRecognition de Python y los servicios de reconocimiento de voz en la nube de Google, para capturar y procesar comandos de voz, transformándolos en direcciones de vuelo ejecutables. El sistema se implementó siguiendo una arquitectura modular que permite escalabilidad y futuras mejoras, como la integración de redes neuronales más avanzadas para el procesamiento del lenguaje natural. Las pruebas realizadas demuestran que el sistema captura y almacena con precisión los planes de vuelo, permitiendo una navegación fluida del dron basada en dichos planes. Los resultados resaltan el potencial de los drones controlados por voz para una amplia gama de aplicaciones, mejorando la accesibilidad y flexibilidad operativa en el ámbito de los sistemas aéreos autónomos.

Contribució al Drone Engineering Ecosystem: Implementació d'un gestor de base de dades

Bachelor thesis

Ferrer Fallouk, Omar

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

This work is primarily based on the development and implementation of a database manager within the Drone Engineering Ecosystem (DEE), an environment designed to facilitate the use and management of drones on the EETAC (UPC) campus. The main objective has been to create a tool that allows for the centralized management of flight plans and flights, providing smooth interaction with the air and ground APIs via the MQTT protocol, ensuring data integrity and compatibility with the standards established within the DEE. To achieve this goal, two new microservices were created, one for the ground API and one for the air API, which facilitate communication between the database manager and the various DEE modules. Additionally, the Data Base Manager has been fully integrated into the DEE Dashboard, allowing users to easily manage, visualize, duplicate, and delete flight plans and flights. During the development, significant modifications were also made to the air and ground APIs, adding methods essential for the implementation of the database manager and ensuring proper communication with other DEE components. Furthermore, a system was implemented to visualize flight routes and points of interest, such as photo and video capture locations, on a graphical interface. Another relevant aspect of the work was the resolution of conflicts and issues that arose during the integration of the manager into the existing system, such as the difficulty of transferring flights between APIs due to the unique identifiers of the images and videos associated with each flight.

Aquest treball es basa principalment en el desenvolupament i implementació d'un gestor de base de dades dins del Drone Engineering Ecosystem (DEE), un entorn destinat a facilitar l'ús i gestió de drons en el campus de l'EETAC (UPC). L'objectiu principal ha estat crear una eina que permeti la gestió centralitzada de plans de vol i vols, oferint una interacció fluida amb les API d'aire i de terra mitjançant el protocol MQTT, assegurant la integritat de les dades i la compatibilitat amb les normatives establertes dins del DEE. Per assolir aquest objectiu, s'han creat dos nous microserveis, un per a l'API terrestre i un per a l'API aèria, que faciliten la comunicació entre el gestor de base de dades i els diferents mòduls del DEE. Així mateix, s'ha integrat completament el Data Base Manager al Dashboard del DEE, oferint als usuaris la possibilitat de gestionar, visualitzar, duplicar i eliminar plans de vol i vols amb facilitat. Durant el desenvolupament, també s'han dut a terme modificacions importants a les API d'aire i terra, afegint mètodes que han estat essencials per a la implementació del gestor de base de dades i per assegurar la correcta comunicació amb els altres components del DEE. A més, s'ha implementat un sistema que permet visualitzar els recorreguts de vol i els seus punts d'interès, com ara la captura de fotos i vídeos, sobre una interfície gràfica. Un altre aspecte rellevant del treball ha estat la resolució de conflictes i problemes sorgits durant la integració del gestor al sistema existent, com la dificultat de traslladar vols entre les API a causa dels identificadors únics de les imatges i vídeos associats a cada vol.

Desenvolupament d'un dron de seguiment hibrid per al Drone Engineering Ecosystem

Bachelor thesis

Carrasco Castro, Carles

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

This project is part of the Drone Engineering Ecosystem (DEE), an academic platform aimed at promoting the development of drone technologies through collaborative projects. The main goal of the project is to develop a hybrid tracking system for a person using artificial vision technologies and drone control. The system uses FPV cameras to capture real-time images and, through image processing with Python and OpenCV, detects the person's position to keep the drone following them accurately and smoothly. To achieve this, a PID controller has been implemented to optimize the drone's movements, along with a Web App that facilitates the drone's relocation in case the target person is lost. This application is designed to transmit the user's coordinates to the drone via the MQTT protocol, improving the system's efficiency. Additionally, the project involved the integration of technologies such as Vue.js, Ionic, and Paho MQTT to ensure communication between different devices. Through various tests and demos, satisfactory results have been achieved, allowing the system to be refined. This work contributes to the DEE ecosystem, offering an innovative and open solution that other users can incorporate into their own drone projects.

Aquest projecte s'emmarca dins del Drone Engineering Ecosystem (DEE), una plataforma acadèmica destinada a promoure el desenvolupament de tecnologies de drons mitjançant projectes col·laboratius. L'objectiu principal del projecte és desenvolupar un sistema de seguiment hibrid d'una persona utilitzant tecnologies de visió artificial i control de drons. El sistema utilitza càmeres FPV per captar imatges en temps real i, mitjançant el processament d'imatges amb Python i OpenCV, detecta la posició de la persona per mantenir el dron seguint-la de manera precisa i suau. Per a això, s'ha implementat un controlador PID per optimitzar els moviments del dron, així com una Web App que facilita la reubicació del dron en cas de pèrdua de la persona objectiu. Aquesta aplicació ha estat dissenyada per transmetre les coordenades de l'usuari al dron a través del protocol MQTT, millorant l'eficiència del sistema. A més, el projecte ha implicat la integració de tecnologies com Vue.js, Ionic i Paho MQTT per garantir la comunicació entre els diferents dispositius. A través de diverses proves i demos, s'han obtingut resultats satisfactoris que han permès refinar el sistema. Aquest treball contribueix a l'ecosistema DEE, oferint una solució innovadora i oberta perquè altres usuaris puguin incorporar-la en els seus projectes de drons.

AeroVox: a web app developed for voice controlled drone operations with 3D spatial constraints

Bachelor thesis

López Amor Vender, Mateo

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

This project presents the development of a web-based application designed to enable voice-controlled drone operation, while incorporating 3D spatial constraints to ensure safe and controlled flights. Traditional drone control systems predominantly rely on manual inputs through controllers, which can be cumbersome and limit the operator's ability to react swiftly in dynamic or high-pressure environments. By implementing voice recognition technology, this system allows users to operate drones hands-free, offering greater flexibility and ease of use, particularly for those with less technical expertise. In addition to voice control, the integration of 3D geofencing ensures that drones operate within predefined areas, significantly enhancing operational safety by preventing unintended zone breaches. The motivation for this project stemmed from the need to improve both user accessibility and safety in drone operations. It was carried out within the context of the Drone Engineering Ecosystem (DEE) at the Escola d'Enginyeria de Telecomunicació i Aeroespacial de Castelldefels (EETAC). Initially, the project was intended to build upon existing applications within the DEE, but challenges with the original codebase and programming language led to a shift toward developing a new web application from scratch. This application was built using Vue.js for the front-end interface, combined with the MQTT communication protocol to facilitate real-time messaging between the drone and control system. Extensive testing was conducted through both simulation and real-world flight trials to evaluate system performance. The results confirmed the system's ability to accurately interpret and execute voice commands in real-time, while maintaining drone flight within the designated spatial boundaries. These tests demonstrated the effectiveness of the voice control system, providing intuitive command capabilities without compromising safety. While future improvements could focus on increasing the accuracy of voice recognition and expanding the complexity of 3D geofencing, this project provides a strong foundation for further innovation in human-drone interaction and paves the way for safer, more accessible drone control solutions.

MultiDronBoard: una aplicación para la gestión de múltiples drones

Bachelor thesis

Sandu Lefcu, Tomi Riccardo

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Recent development projects have increasingly focused on drone technology. In response to this growing interest, the Drone Engineering Ecosystem has proposed developing an application capable of creating custom geofence scenarios and managing connections to multiple drones, enabling comprehensive monitoring and control. This application will facilitate guided tours of the center, allowing visitors to operate drones within controlled boundaries using pre-configured scenarios created by operators through the integrated editor. This document details the system's design and implementation process, explaining the rationale behind each decision while aiming to develop the most effective tool possible, thus establishing a foundation for future developments in this field. The project has contributed to the ecosystem's libraries by implementing new features and functionalities. Additionally, this work includes a series of simulation and real-world experiments conducted to validate the application's reliability and practical utility. The final evaluation, performed by external users, provides valuable feedback on the application's user experience.

Los drones han sido el centro de atención de numerosos proyectos de desarrollo recientemente. En respuesta a este creciente interés, el Ecosistema de Ingeniería de Drones ha propuesto desarrollar una aplicación capaz de crear escenarios personalizados y gestionar conexiones con múltiples drones, permitiendo su monitorización y control integral. Esta aplicación facilitará las visitas guiadas al centro, permitiendo a los visitantes operar drones dentro de márgenes controlados mediante escenarios preconfigurados creados por los operadores a través del editor integrado. Este documento detalla el proceso de diseño e implementación del sistema, explicando el fundamento de cada decisión mientras se busca desarrollar la herramienta más efectiva posible, estableciendo así una base para futuros desarrollos en este campo. El proyecto ha contribuido a las bibliotecas del ecosistema mediante la implementación de nuevas características y funcionalidades. Además, este trabajo incluye una serie de experimentos de simulación y pruebas reales realizadas para validar la fiabilidad y utilidad práctica de la aplicación. La evaluación final, realizada por usuarios externos, proporciona retroalimentación valiosa sobre la experiencia de usuario de la aplicación.

Autonomous drone operation using UWBS

Bachelor thesis

Duan, Hongxuan

Tutor / Supervisor: Valero García, Miguel; Paternain, Carlos

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Procedure for obtaining accreditation as a drone testing laboratory (ISO 17025) for the organisation CATUAV S.L

Master thesis

Tutusaus Garcia, Júlia

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Aportación al Tello Engineering Ecosystem: enjambre de drones y efectos de magia

Bachelor thesis

Martínez Jiménez, Juan

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Reconocimiento de objetos para el control de drones en el Drone Engineering Ecosystem

Bachelor thesis

Marcos Paya, Pol

Tutor / Supervisor: Salamí San Juan, Esther; Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

The main objective of this final degree project is to develop software that allows a drone to identify and classify objects in real time through the use of a camera. To achieve this, advanced computer vision techniques and artificial intelligence algorithms have been used, ensuring the correct integration between the developed software and the drone control system. A specific use case is to guide the movement of the drone following a route marked by objects strategically located on the ground. The methodology used to meet the objectives set out focused on the implementation of an object detection module based on the YOLO (You Only Look Once) algorithm, a convolutional neural network optimised for object detection in real time. The module was developed in Python, and its integration into the Drone Engineering Ecosystem (DEE), a drone control platform, enabled the identification of objects and subsequent decision-making by the drone. During the development process, different YOLOv8 models (v8n, v8s, v8m, v8l, v8x) were selected and evaluated, and then retrained using a proprietary dataset that included classes such as banana, ball, box and backpack. Several tests were performed, both in simulated environments and in a laboratory with a real drone, to measure the accuracy and efficiency of the system. The results were satisfactory, achieving an improvement in object detection compared to pre-trained models, with accuracy increases of up to 53% in some cases. Despite the achievements, the project had limitations, such as the impossibility of implementing object detection on the drone's Raspberry Pi due to technical problems with the library used, which restricted image processing to the ground equipment. In addition, the resolution of the drone's camera was not optimal for detecting small objects, and some false positives were observed that diverted the drone from its route at times. In conclusion, the project demonstrated the effectiveness of integrating an advanced object detection system into the DEE, opening the door to future improvements in model accuracy and drone functionality. Future lines of development are suggested to optimise the system, such as the reduction of false positives and the integration of processing on the Raspberry Pi.

Contribución al desarrollo del Drone Engineering Ecosystem (28)

Bachelor thesis

Gallardo Serra, Àdam

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Innovaciones en el DEE: Mejoras en Flutterapp y desarrollo de tecnología para vuelos interiores

Bachelor thesis

Moncho Roig, Eloi

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

DroneLink EETAC: Nuevas librerías para el drone engineering ecosystem

Bachelor thesis

Carneros Mateu, Daniel

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Contribución al drone engineering Ecosystem: implementación de obstáculos

Bachelor thesis

Álvarez Fernández, Miguel

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

Prototipado de visión por computadora para la detección de objetos en drones autónomos

Bachelor thesis

Pérez Calderón, Anthony Demostenes

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

In the contemporary era, drones have transcended their initial function of capturing aerial images to become versatile tools with applications in multiple fields. This project focuses on exploring the autonomous vision capabilities of drones, particularly in the use of machine learning for object detection. The primary goal is to challenge the negative prejudices associated with the military use of drones and to highlight their transformative capabilities in civilian and recreational contexts. The project spans from exploring the physical limits of drones to developing adaptable algorithms through the fusion of programming and computer vision technologies. An exhaustive process of prototyping and implementing an object detection algorithm has been carried out, integrating trained models with advanced tools such as Roboflow and using the Tello drone as a test platform. The result is a system capable of capturing real-time images, processing them, and detecting objects accurately, demonstrating the autonomous vision capabilities of these devices. The project is structured into chapters that detail each stage of development, starting with the introduction of the Tello drone and its engineering ecosystem, followed by programming in Python and the use of specific libraries. A description of the image annotation process with CVAT is included, which is crucial for creating a high-quality dataset. Subsequently, in the model training phase in Roboflow, model configuration, hyperparameter tuning, and performance evaluation are covered. The integration of the trained model in Python, using PyCharm, addresses real-time video capture and processing from the Tello drone and the use of advanced inference tools. Significant technical challenges were encountered at this stage, such as connecting to two networks and optimising image processing, which were addressed through innovative solutions and constant testing. In the conclusion, the achievements are reflected upon, and recommendations for future work are provided, establishing a solid foundation for future studies in autonomous drone vision and inviting the community to build upon these foundations. Besides its technical contribution, the project aims to change public perception of drones, promoting their use in accessible and recreational contexts. The innovative synthesis of technologies presented in this project heralds an exciting future where drones and machine learning converge to inspire significant advancements in multiple disciplines.

INFORMÀTICA 1 (Examen parcial, 2n quadrimestre) Restricted access to the UPC academic community

Exam

Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

INFORMATICS I - 300207

Access to the full text

INFORMÀTICA 1 (Examen parcial, 2n quadrimestre) Restricted access to the UPC academic community

Exam

Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

INFORMATICS I - 300207

Access to the full text

Dockerización de los servicios de a bordo y mejora en la planificación y ejecución de planes de vuelo en el Drone Engineering Ecosystem

Bachelor thesis

Llaveria Núñez, Jordi

Tutor / Supervisor: Valero García, Miguel

Publication date: 2024

Castelldefels School of Telecommunications and Aerospace Engineering (EETAC)

View detail Access to the full text

The aim of this work is primarily the adaptation of the communication structure and its environment, in which the on-board services of the Drone Engineering Ecosystem (DEE) are located. The objective is to facilitate the installation and use of these services within the drone, also improving their efficiency while being executed, through the use of a technology known as Docker, commonly employed in many production environments. To achieve this goal, the corresponding Dockerfile will be developed for each required image, with the intention of creating the set of containers that will form the Docker-based ecosystem. All these containers will be grouped according to the configuration established in a file named docker-compose.yml, based on the Docker Compose tool, used for the management of several containers. In addition to this development, this project also focuses on the creation of an air backend, located on the drone's Raspberry Pi, and a ground backend, located on the Classpip server, available as part of another collaborative project within the EETAC. The goal of the development of these two storage points, is to save in them information associated with flight plans and executed flights, in relation with Dashboard application and the Flutter developed mobile application, two different components within the drone ecosystem. Once these two new storage components are implemented within the ecosystem, the necessary modifications and contributions will be made to enable these mentioned applications, both the Dashboard and the one developed in Flutter, to create flight plans, capture images and videos, and subsequently visualize all these multimedia files within the applications themselves, for a proper analysis of the obtained results. With the intention of verifying the set of contributions made to the ecosystem, the relevant tests will be conducted on real flights at the DroneLab, to assess the effectiveness of the implemented modifications, communications, and structures in both the on-board software and the modified applications. Throughout the entire report, efforts will be made to document and explain accurately the set of changes made to existing components, or the new ones developed, with the view of serving as a guide for future students intending to continue this work or make use of the developed tools.