Projecte llegit
Títol: Prediction of 4D drone trajectories from demonstration data
Estudiants que han llegit aquest projecte:
- VÁZQUEZ HUSILLOS, LAURA (data lectura: 12-09-2022)
- Cerca aquest projecte a Bibliotècnica
Director/a: BARRADO MUXÍ, CRISTINA
Departament: DAC
Títol: Prediction of 4D drone trajectories from demonstration data
Data inici oferta: 15-02-2022 Data finalització oferta: 15-10-2022
Estudis d'assignació del projecte:
- GR ENG SIST AEROESP
Tipus: Individual | |
Lloc de realització: EETAC | |
Paraules clau: | |
Drones, UAM, U-Space, Machine Learning, VLD, Colab | |
Descripció del contingut i pla d'activitats: | |
Aircraft trajectory prediction is a challenging and very useful task that consists in anticipating the most accurate 4D locations that an aircraft will flight. A 4D location is a point in a 4 dimensions space, this is, a vector of 4 numerical values: latitude, longitude, altitude and time. For the prediction of aircraft trajectory, historical data can be used consisting, essentially, in the flight plan and the actual radar traces. Uncertainties such as weather, late departures and air traffic control interventions are the source of errors in the predictive task.
In the future, the expectation is to have an increasing number of automated flights originated by urban air mobility, basically using drones. These vehicles will flight supported by the U-space, a digital version of the air traffic control services. In the CORUS-XUAM project a number of demonstration flights are being conducted using drones. The flight plans and the telemetry of the drones are available to create the historical data base to feed a machine learning model able to learn accurate predictions. In the TFG the student will have to manage the formats of the flight plans and the telemetry and homogenize both formats, study the differences and find the best way to insert this information in a machine learning model, probably related with time-series, train the model and validate the performance of the predictions using quality indicators such as R2 or RMSE. |
|
Overview (resum en anglès): | |
Drones are nowadays an air vehicle with many possible applications and with a huge field of development and research. This work deals, more specifically, with the delivery drones used for the distribution of packages to citizens. That is, they could be considered as a new way of distributing packages to the city. Today, this is seen as a hypothetical, because in order to achieve this, many points must be studied and new tools for their control and security must be developed.
This work studies the field of predicting the trajectory of drones through Machine Learning and thus, providing a new point of view in the research and development of this new branch of aviation. The aim of this work is to predict, through Machine Learning, the trajectory of a drone in 4D based on the data collected in the test flights made by the different air operators participating in the CORUS-XUAM. The objective is to achieve results with sufficient precision to be able to project them valid in terms of air safety. To carry out this work, it has been necessary the data previously collected from the VLDs operated and the processing of them by means of the code made in Google Coolab. For this reason, different libraries have been needed, such as "Pandas", "Matplotlib", "Numpy" or "Geopandas", among others. Finally, a Machine Learning has been used to carry out the predictions. To do this, it has been necessary to decide which will be the best method used, in our case it has been seen that the most appropriate is the Regression model. Regarding the results, it has been confirmed that the chosen method has been correct, since the margins of error are quite low and acceptable and the accuracy of it could be considered good with a margin error of maximum 3 minutes. |