Ofertes treballs fi d'estudis

Títol: IA-based technique for obstacle detection and UAV flight control

Director/a: Soria Perez, Jose antonio

Email del professor/a: jasoria@eel.upc.edu

Departament del professor/a: 710-EEL

• 2010 - GRAU EN ENGINYERIA EN VEHICLES AEROESPACIALS

Identificador de l'oferta: 205-06803

Modalitat: Universitat

Possibilitat de beca/finançament: No

Idioma d'elaboració del treball: Anglès

Paraules clau:

Descripció:

Autonomous navigation of UAVs requires real-time obstacle detection and trajectory correction. Most commercial drones offer collision avoidance functionality based on phenomena detected by built-in sensors. New research, focus on implementing this utility in more economical and small UAVs, which take advantage of IA-based computer vision models to run this utility remotely.

Objectius:

To delvelop an IA-based remote mechanism which, operating in a real-time fashion, can detect obstacles and modifies its flight path acordingly

Tasques a realitzar / Característiques:

To carry out this project, thge following stages are expected. 1) Review on ML and state-of-the art UAV control methods 2) Selection and adaptation of detection algorithms (e.g., YOLO, SSD). 3) Scripts for Implementation of object detection and flight control with the drone API. 4) Test and results 5) Technical report.

Tema: ENGINYERIA AERONÀUTICA

Tipus: Estudi

Càrrega de treball:

24 ECTS

Requisits:

The recomended student's profile for this project is the following: - Advanced level of Python language programming. - Knowledge in real-time image processing. - Understanding of UAV flight dynamics and acquintance with Deep Learning and IA-based vision models for object detection is a plus.

Temàtica ambiental: No

Confidencial (informatiu): No

Ambit de cooperació: No

Publicació: 20/01/2026

Caducitat: 19/01/2027