Projecte llegit
Títol: Sistema de evasión de colisiones de drones autónomos mediante comunicaciones 5G
Estudiants que han llegit aquest projecte:
- MORENO ÁLVAREZ, SERGIO (data lectura: 13-09-2024)
- Cerca aquest projecte a Bibliotècnica
- MORENO ÁLVAREZ, SERGIO (data lectura: 13-09-2024)
- Cerca aquest projecte a Bibliotècnica
Director/a: ALONSO ZÁRATE, LUIS
Departament: TSC
Títol: Sistema de evasión de colisiones de drones autónomos mediante comunicaciones 5G
Data inici oferta: 26-01-2024 Data finalització oferta: 26-09-2024
Estudis d'assignació del projecte:
- DG ENG AERO/SIS TEL
- DG ENG AERO/TELEMÀT
- DG ENG SISTE/TELEMÀT
Tipus: Individual | |
Lloc de realització: EETAC | |
Paraules clau: | |
UAS, drones, RPAS, comunicaciones, simulador | |
Descripció del contingut i pla d'activitats: | |
El proyecto tiene como objetivo desarrollar un sistema para evitar colisiones de drones autónomos mediante un sistema basado en comunicaciones 5G y la aplicación de IA. Para ello, se definirá un escenario con un cierto número de servicios con diferentes prioridades de paso y se asignarán drones a dichos servicios. Se definirán procedimientos y protocolos para tener un sistema que optimice las trayectorias y evite posibles colisiones en situaciones donde el tiempo de respuesta y la seguridad en el transporte sea un elemento crítico para el servicio. La arquitectura propuesta se basará en comunicaciones 5G, combinando transmisiones directas de información entre drones así como intercambio con servidores de control. Se realizarán simulaciones a nivel de sistema para analizar diferentes parámetros de rendimiento (KPIs) de cara a evaluar las ventajas que ofrezca la propuesta respecto a los sitemas actualmente en funcionamento. | |
Overview (resum en anglès): | |
The drone sector has experienced significant growth, with applications in various areas aimed at optimising operations in hard-to-reach locations, reducing costs, and enhancing safety. In this context, the main objective of the project is the development of a collision avoidance system for drones using 5G communications, a technology that offers advantages such as low latency, high availability, and the ability to handle large volumes of data.
The primary goal of this work is to develop a system that enables drones to avoid collisions in an increasingly congested airspace, utilising 5G technology. The system is based on detecting nearby drones through requests to a central server and direct communications when drones are in close proximity. This approach aims to ensure that drones can perform evasive manoeuvres efficiently and safely. To achieve this goal, the project details the implementation of an avoidance algorithm that defines hierarchical roles among conflicting drones, assigning a master drone that maintains its route and a slave drone that executes the necessary evasive manoeuvres. Additionally, a simulator has been developed in C# and Windows Forms with a MySQL database to test and visualise the behaviour of the algorithm under different scenarios, evaluating the impact on flight time, distance travelled, battery consumption, and the number of evasive manoeuvres executed, among other key factors that help understand how these affect the overall system performance. The project objectives have been successfully achieved. The developed avoidance system has proven to be highly functional, demonstrating a strong capability to reduce the likelihood of collisions in a dense air environment. 5G communications have been shown to be crucial, both for detecting other drones and for the effectiveness of evasive manoeuvres. The priority hierarchy has allowed greater emphasis on emergency services, ensuring that critical missions are not compromised. Moreover, the simulator has enabled an exhaustive analysis of the system, identifying optimal configurations that improve the efficiency of manoeuvres and reduce conflicts. Although this system is presented as a first version, it has significant potential for evolution, with future research lines aimed at improving realism in simulations, implementing artificial intelligence, and dynamically adapting protection areas. Finally, it is concluded that the project is sustainable in the long term from an environmental, economic, and social perspective, contributing to the reduction of pollution and operational costs, while generating new employment opportunities in the technology sector. |