TAPAS: Towards an Automated and exPlainable ATM System

Posted Sat, 2020-06-13 13:17 by georgev

TAPAS (Towards an Automated and exPlainable ATM System) addresses explicitly the effectiveness
of introducing AI/ML solutions in order to increase the levels of automation in ATM, considering the need of the operator to trust the system (taken as the ability to understand and explain its behaviour and outcomes).
TAPAS will address the AI/ML models’ transparency challenge, as it is considered to be the highest
priority towards enabling higher levels of automation: beyond aiming to increase situational awareness and reaction capabilities of the operators, transparency is also necessary for the social acceptance and regulatory approval of AI/ML systems, paving the way to the successful deployment of these systems in the ATM domain. It essentially relates to having or losing confidence in a given system, for which no mitigation exists.

In a nutshell, the scope of this research is the systematic exploration of AI/ML solutions towards
increasing levels of automation in specific ATM scenarios, through analysis and experimental activities, with the objective to deliver principles of transparency, enabling the application of AI/ML supported
automation in ATM.

Duration: 
June 2020 - November 2022
Objectives: 

The objective for the project is the exploration of highly automated XAI scenarios through validation
activities and Visual Analytics (VA), in order to identify needs and strategies to address transparency and explainability in the operational cases considered, paving the way for the application of these AI/ML technologies in ATM environments.
The proposed research will advance the state-of-the-art in two main areas:
1. Identification of principles and criteria for AI/ML transparency/explainability1 in ATM domain
scenarios, based on the two operational cases considered and with the target to identify transparency
requirements for AI/ML methods in general, limiting domain-specific results.
2. Selection and development of suitable and explainable AI/ML methods in the operational cases
identified, to fit the needs of transparency as expressed in the explainability criteria developed for each
automation level and according to actors’ needs.

Person Responsible: 
George A. Vouros
Funding Body: 

SESAR JU

Research topic: 

Ai, Reinforcement Learning, Explainable AI/ML