In short

Back to Projects Portal

Website

Link to Cordis
PROJECT ID

ARTIMATION
PROJECT TYPE

Exploratory research

FLAGSHIP

Not applicable
STATUS

Completed

SESAR PROGRAMME

SESAR 2020
PROJECT DURATION

2021-01-01 > 2022-12-31
TOTAL COST

€ 999 375,00
EU CONTR.

€ 999 375,00
GRANT ID

894238
PARTICIPANTS

Malardalens Universitet, Deep Blue, Ecole Nationale De L' Aviation Civile (ENAC), Universita degli Studi Di Roma La Sapienza

Society is becoming increasingly dependent on artificial intelligence (AI) which raises the importance of installing trust and security in its use. This becomes easier once humans understand how AI systems think and operate. 


The aim of ARTIMATION was to address challenges related to transparency of automated systems in air traffic management using explainable AI (XAI ). The research was limited to main use cases: Conflict detection and resolution; and delay prediction and propagation. It proposed tools which aim to improve explainability through AI algorithms based on data-driven storytelling and immersive analytics with the purpose of assessing the effectiveness of different visualization techniques.

Both conflict detection and resolution and delay prediction and propagation concepts are useful applications that support controllers’ everyday tasks and help air navigation service providers to improve performance in air traffic management, including the human having full control of the AI decision support. By introducing data-driven and user-driven storytelling for each use case, researchers were able to help explore how the machine learning could be applied to support controllers, air navigation service providers, and generic end users in their activities.

The project also explored how to integrate different levels of explanation in an adaptive passive brain-computer interface. This would enable the AI development to fit controllers’ contextual explainability needs and accommodate changes in mental and emotional states (e.g., workload, stress) measured by neurophysiological measures.

ARTIMATION represents a small step along the path to building trust and dependency on AI systems. It demonstrated the importance of effective and immersive data visualization towards increasing end-users’ acceptance, using examples of machine learning. The main outcome of this effort was an improved understanding of how machine learning should be developed, and the identification of measures aimed at keeping the human-in-the-loop through transparent AI models provided by novel data visualization.

 

  Benefits

  • Transparent AI models
  • Increased trust in AI
  • Human-centred design

 

Participants

MAELARDALENS HOEGSKOLA

Website
DEEP BLUE SRL

Website
ECOLE NATIONALE DE L AVIATION CIVILE

Website
UNIVERSITA DEGLI STUDI DI ROMA LA SAPIENZA

Website
EUROCONTROL - EUROPEAN ORGANISATION FOR THE SAFETY OF AIR NAVIGATION

Website

Latest news

READ ALL NEWS

Recently, artificial intelligence (AI) algorithms have shown increasable interest in various application domains including in Air Transportation Management (ATM). Different AI in particular Machine Learning (ML) algorithms are used to provide decision support in autonomous decision-making tasks in the ATM domain e.g. predicting air transportation traffic and optimising traffic flows. However, most of the time these automated systems are not accepted or trusted by the intended users as the decisions provided by AI are often opaque, non-intuitive and not understandable by human operators. Safety is the major pillar to air traffic management, and no black box process can be inserted in a decision-making process when human life is involved.

In order to address this challenge related to transparency of the automated system in the ATM domain, ARTIMATION focuses on investigating AI methods in predicting air transportation traffic and optimizing traffic flows based on the domain of Explainable Artificial Intelligence (XAI). Here, AI models’ explainability in terms of understanding a decision i.e., post hoc interpretability and understanding how the model works i.e., transparency can be provided in the air traffic management. In predicting air transportation traffic and optimizing traffic flows systems, ARTIMATION provides a proof-of-concept of transparent AI models that includes visualization, explanation, generalisation with adaptability over time to ensure safe and reliable decision support. 

European Union