CBL - Campus del Baix Llobregat

Projecte llegit

Títol: Assessing drone trajectory error and improving flightpath predictability

Estudiants que han llegit aquest projecte:

Director/a: BARRADO MUXÍ, CRISTINA

Departament: DAC

Títol: Assessing drone trajectory error and improving flightpath predictability

Data inici oferta: 15-02-2023     Data finalització oferta: 15-10-2023


Estudis d'assignació del projecte:
    GR ENG SIST AEROESP
Tipus: Individual
 
Lloc de realització: EETAC
 
Paraules clau:
4D trajectory, Flight plan, Predictability, Drone, U-space
 
Descripció del contingut i pla d'activitats:
Aviation world is well-known by its safety standards, successfully built upon the swiss-cheese model. All layers of the safety net (airspace design, demand-capacity balance, strategical deconfliction, tactical separation and last-minute collision avoidance systems) contribute to it. But demand pressure, in particular for the expected rapid increase of the unmanned traffic, needs to improve parts of this safety net. In particular, a good strategical deconfliction can eliminate pressure to the rest of layers. Trajectory prediction has been one of the most difficult topics of research for many years, but little work has been done to improve the prediction of drone delivery flights. Strategic deconfliction is the essential safety service for U-space volumes Y according to the CORUS-XUAM project, a SESAR project proposing the Concept of Operations of drones for urban air mobility.
In this work we aim at improving the predictability of the U-space for small drones, as the ones used in the Very Large Demonstrator of CORUS-XUAM conducted in Castelldefels in March 2022. The telemetry of up to 85 flights were recorded during the VLD and further data is expected to be obtained from new operators. The analysis of this telemetry against the flight plans and the U-space prediction can highlight the current error of U-space prediction. New models can be generated to improve the prediction of future flights. The application of clustering algorithms, time series analysis and machine learning prediction models will be tested as part of this work.
 
Overview (resum en anglès):
The rapid growth of the drone industry aims to develop applications and implement them in a wide range of areas. This includes busy urban areas for services such as
surveillance, deliveries and monitoring. In this context, it is essential to have an excellent design of the airspace.
This thesis focuses on the analysis of a dataset from the Very Large Demonstration project of CORUSXUAM, which contributes to the U-Space mission of developing a safe,
sustainable, efficient and fully digitalized airspace for integrated Urban Air Mobility which does not interfere with current ATM operations. The dataset includes flight plans, telemetry, and U-space predictions for 72 drone flights.
The analysis involves comparing intended trajectories with actual flight paths to identify factors contributing to deviations from the flight plan and computing
relevant performance parameters to assess the adherence of the drones to the flight plan. This is done with the use of dynamic time warping algorithms in order to establish a link between the telemetry points and the flight plan, which
sets the basis for the next section of the project.
Having processed the data, during this project we develop machine learning models to predict telemetry parameters based on the input flight plan. Several models are tested and evaluated to find the most suitable one for our objective.
The project also involves visualizing and interpreting the data to gain insights of the drone performance and adherence to the flight plan.
Position prediction opens up a new area of research and in this project the approach is to use an alternative method to define the spacing and size of the airways that compose the flight plans so as to dictate safety areas to prevent any possible conflict that could appear in future flights in a busy area if the spacing were to be below the thresholds.
The results of this study demonstrate a successful progression from raw data to a comprehensive analysis, offering valuable insights for evaluating drone performance and predicting flight times. The development of various data visualization functions enabled efficient and effective interpretation of the data.
While the obtained results with the available dataset are remarkable, the potential for further improvement lies mainly in acquiring a larger dataset with more features and samples, which would enhance the performance of the machine learning models and yield even more accurate predictions.

© CBLTIC Campus del Baix Llobregat - UPC