CBL - Campus del Baix Llobregat

Projecte ofert

Títol: Prediction of pseudo-pilot response times using real-time air traffic control simulation data


Per assignar-vos el projecte us heu de dirigir al director/a perquè us l'assigni.


Director/a: OZDEMIR, MUSTAFA

Departament: FIS

Títol: Prediction of pseudo-pilot response times using real-time air traffic control simulation data

Data inici oferta: 18-11-2026     Data finalització oferta: 29-01-2027



Estudis d'assignació del projecte:
    GR ENG SIST AEROESP
Tipus: Individual
 
Lloc de realització: EETAC
 
Paraules clau:
Air traffic control, Pseudo-pilot, Response time, Real-time simulation, Machine learning, Human performance
 
Descripció del contingut i pla d'activitats:
Real-time air traffic control (ATC) simulations are widely used for controller training and research. In these environments, pseudo-pilots simulate aircraft crews by responding to ATC instructions and executing the corresponding maneuvers. The time required to respond to these instructions may vary depending on traffic conditions, instruction characteristics, and pseudo-pilot workload.

This project aims to investigate the factors influencing pseudo-pilot response times and develop predictive models using data collected from real-time ATC simulations. The study will explore whether response times can be estimated from operational and traffic-related variables using statistical and machine learning techniques.

The main activities will include:

1. Literature review: Review relevant studies on response times, pseudo-pilot operations, human performance, and predictive modelling in ATC simulations.
2. Data preparation: Examine the available simulation records, identify relevant events and timestamps, define response-time measurements, and prepare the dataset for analysis.
3. Exploratory data analysis: Investigate response-time distributions and their relationships with traffic complexity, instruction characteristics, and other available variables.
4. Predictive modelling: Develop and compare baseline statistical and machine learning models, such as linear regression and random forest, to estimate pseudo-pilot response times.
5. Model evaluation: Assess prediction accuracy using appropriate performance metrics and investigate the most influential predictors and sources of prediction error.
6. Results and discussion: Interpret the findings, discuss methodological limitations, and explore potential applications for improving the realism of ATC simulations.

Expected outcomes: A reproducible data-analysis and prediction workflow, a comparative evaluation of predictive models, and a technical report presenting the methodology, results, and conclusions.
 
Orientació a l'estudiant:
Basic knowledge of Python programming, data analysis, and statistics is recommended. Familiarity with machine learning techniques would be an advantage but is not required.

The project is suitable for students interested in air traffic management, simulation, data science, and predictive modelling. Previous experience with air traffic control or real-time simulation environments is not necessary.

The student is expected to work independently, with regular supervision meetings and guidance throughout the project.
 
Requereix activitats hardware: No
 
Requereix activitats software: Sí    Sistema operatiu: Windows    Disc (Gb): 8
 
Horari d'atenció a estudiants per a l'assignació de projecte:
Meetings by appointment. Interested students are welcome to contact the supervisor via UPC email to discuss the project.

© CBLTIC Campus del Baix Llobregat - UPC