Summary
TADA is a project aimed at improving Terminal Airspace (TMA) performance through the use of ATCO generated historical data and ML to provide the ATCO with decision and action selection for future situations, presented in a human centric way.
TMAs, especially those serving major airport hubs and/or multi-airport systems, are areas of heavy congested traffic. Busy TMAs could benefit from further automation that would improve capacity, flow and trajectory efficiency and safety. The current ATC paradigm in TMAs consists of having flights and their intentions identified by the air traffic controllers (ATCOs), supported by a series of information acquisition and analysis tools, such as AMAN (providing a sequence), trajectory predictions, safety nets and instruction adherence monitoring, most of which are integrated into the ATM system in use. ATCOs assimilate the information available, incorporate other background information, make decisions and instruct the flights. They also interact with the ATM system to keep it up to date with the decisions and the feedback received from the flights.
This ATCO data gathered through this interaction is currently barely used beyond the immediate information update cycles and possibly post ops investigations. This wealth of big-data,together with the introduction of machine learning (ML) algorithms that will learn to predict patterns and ATC instructions can be taken advantage of much more to improve capacity, efficiency and safety by providing decision making support to ATCOs and delegation of certain tasks. A digital assistant and corresponding HMI will be developed through TADA and AMAN will benefit from an improvement through the use of the same data and ML.
TADA will be carried out by a consortium of 6 partners from 6 different EU countries including academia, ANSP, ATM system provider and an expert company in AI, bringing complimentary academic, technical, human factors and operational skills and expertise to the project.
TMAs, especially those serving major airport hubs and/or multi-airport systems, are areas of heavy congested traffic. Busy TMAs could benefit from further automation that would improve capacity, flow and trajectory efficiency and safety. The current ATC paradigm in TMAs consists of having flights and their intentions identified by the air traffic controllers (ATCOs), supported by a series of information acquisition and analysis tools, such as AMAN (providing a sequence), trajectory predictions, safety nets and instruction adherence monitoring, most of which are integrated into the ATM system in use. ATCOs assimilate the information available, incorporate other background information, make decisions and instruct the flights. They also interact with the ATM system to keep it up to date with the decisions and the feedback received from the flights.
This ATCO data gathered through this interaction is currently barely used beyond the immediate information update cycles and possibly post ops investigations. This wealth of big-data,together with the introduction of machine learning (ML) algorithms that will learn to predict patterns and ATC instructions can be taken advantage of much more to improve capacity, efficiency and safety by providing decision making support to ATCOs and delegation of certain tasks. A digital assistant and corresponding HMI will be developed through TADA and AMAN will benefit from an improvement through the use of the same data and ML.
TADA will be carried out by a consortium of 6 partners from 6 different EU countries including academia, ANSP, ATM system provider and an expert company in AI, bringing complimentary academic, technical, human factors and operational skills and expertise to the project.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101166972 |
| Start date: | 01-09-2024 |
| End date: | 28-02-2027 |
| Total budget - Public funding: | 1 769 978,75 Euro - 1 769 978,00 Euro |
Cordis data
Original description
TADA is a project aimed at improving Terminal Airspace (TMA) performance through the use of ATCO generated historical data and ML to provide the ATCO with decision and action selection for future situations, presented in a human centric way.TMAs, especially those serving major airport hubs and/or multi-airport systems, are areas of heavy congested traffic. Busy TMAs could benefit from further automation that would improve capacity, flow and trajectory efficiency and safety. The current ATC paradigm in TMAs consists of having flights and their intentions identified by the air traffic controllers (ATCOs), supported by a series of information acquisition and analysis tools, such as AMAN (providing a sequence), trajectory predictions, safety nets and instruction adherence monitoring, most of which are integrated into the ATM system in use. ATCOs assimilate the information available, incorporate other background information, make decisions and instruct the flights. They also interact with the ATM system to keep it up to date with the decisions and the feedback received from the flights.
This ATCO data gathered through this interaction is currently barely used beyond the immediate information update cycles and possibly post ops investigations. This wealth of big-data,together with the introduction of machine learning (ML) algorithms that will learn to predict patterns and ATC instructions can be taken advantage of much more to improve capacity, efficiency and safety by providing decision making support to ATCOs and delegation of certain tasks. A digital assistant and corresponding HMI will be developed through TADA and AMAN will benefit from an improvement through the use of the same data and ML.
TADA will be carried out by a consortium of 6 partners from 6 different EU countries including academia, ANSP, ATM system provider and an expert company in AI, bringing complimentary academic, technical, human factors and operational skills and expertise to the project.
Status
SIGNEDCall topic
HORIZON-SESAR-2023-DES-ER2-WA2-1Update Date
01-10-2024
Images
No images available.
Geographical location(s)
Structured mapping
Unfold all
/
Fold all
