Summary
ORCI will explore innovative AI-based solutions to help increase runway throughput using advanced automation support tools in the TMA domain. Specifically, the objective is to provide key information to Air Traffic Controllers in final approach sectors, to support informed decisions on when to issue vectoring instructions to aircraft for optimal spacing between consecutive arrivals during medium, high, very high-density and increasingly complex TMA airspace operations.
To achieve this objective, the project will develop an AI model that is trained using radar surveillance data and ATC voice communications between pilots and controllers.
During the project, Barcelona and Lisbon approach operations will be assessed. This will include interviews with ATCO experts from the respective ANSP partners, as well as in-depth analysis of local arrival characteristics (e.g. geometries, procedures, etc.). In addition, high amounts of radar surveillance and voice communications data will be collected and processed, to support and guide the training and testing of the AI models.
The validation of the AI model will be supported by Human in the loop and Fast Time simulation techniques (using the RAMS Plus tool) to ensure that the performance of the AI model is evaluated in a realistic and controlled environment, and to get some initial human performance and safety related feedback.
The successful implementation of the AI model is anticipated to optimize delivery of vectoring instructions, leading to enhanced capacity, efficiency, environmental performance, and overall improvements to arrival air traffic management that are consistent with SESAR performance targets. Additional benefits also extend to optimization of the runway throughput by reducing both ATC workload and the potential for human error. The expected solution could also be extended to incorporate the use of time-based separation for arrivals and digitally shared trajectory information coming from the flight-deck
To achieve this objective, the project will develop an AI model that is trained using radar surveillance data and ATC voice communications between pilots and controllers.
During the project, Barcelona and Lisbon approach operations will be assessed. This will include interviews with ATCO experts from the respective ANSP partners, as well as in-depth analysis of local arrival characteristics (e.g. geometries, procedures, etc.). In addition, high amounts of radar surveillance and voice communications data will be collected and processed, to support and guide the training and testing of the AI models.
The validation of the AI model will be supported by Human in the loop and Fast Time simulation techniques (using the RAMS Plus tool) to ensure that the performance of the AI model is evaluated in a realistic and controlled environment, and to get some initial human performance and safety related feedback.
The successful implementation of the AI model is anticipated to optimize delivery of vectoring instructions, leading to enhanced capacity, efficiency, environmental performance, and overall improvements to arrival air traffic management that are consistent with SESAR performance targets. Additional benefits also extend to optimization of the runway throughput by reducing both ATC workload and the potential for human error. The expected solution could also be extended to incorporate the use of time-based separation for arrivals and digitally shared trajectory information coming from the flight-deck
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101167539 |
| Start date: | 01-06-2024 |
| End date: | 30-11-2026 |
| Total budget - Public funding: | 819 493,75 Euro - 819 493,00 Euro |
Cordis data
Original description
ORCI will explore innovative AI-based solutions to help increase runway throughput using advanced automation support tools in the TMA domain. Specifically, the objective is to provide key information to Air Traffic Controllers in final approach sectors, to support informed decisions on when to issue vectoring instructions to aircraft for optimal spacing between consecutive arrivals during medium, high, very high-density and increasingly complex TMA airspace operations.To achieve this objective, the project will develop an AI model that is trained using radar surveillance data and ATC voice communications between pilots and controllers.
During the project, Barcelona and Lisbon approach operations will be assessed. This will include interviews with ATCO experts from the respective ANSP partners, as well as in-depth analysis of local arrival characteristics (e.g. geometries, procedures, etc.). In addition, high amounts of radar surveillance and voice communications data will be collected and processed, to support and guide the training and testing of the AI models.
The validation of the AI model will be supported by Human in the loop and Fast Time simulation techniques (using the RAMS Plus tool) to ensure that the performance of the AI model is evaluated in a realistic and controlled environment, and to get some initial human performance and safety related feedback.
The successful implementation of the AI model is anticipated to optimize delivery of vectoring instructions, leading to enhanced capacity, efficiency, environmental performance, and overall improvements to arrival air traffic management that are consistent with SESAR performance targets. Additional benefits also extend to optimization of the runway throughput by reducing both ATC workload and the potential for human error. The expected solution could also be extended to incorporate the use of time-based separation for arrivals and digitally shared trajectory information coming from the flight-deck
Status
SIGNEDCall topic
HORIZON-SESAR-2023-DES-ER2-WA1-1Update Date
01-10-2024
Images
No images available.
Geographical location(s)
