D3.2 Report on the gap analysis including KPIs-KVIs and the development-technical work plan
This document describes the development and technical work plan for the TRUSTY project, based on the strategic planning from Task 3.1, 3.2 and 3.3. “Task 3.1: State of the art (SotA) – AI and XAI support in RDTs” involved a comprehensive evaluation of current AI technologies in Remote Digital Towers (RDTs) against benchmark standards. “Task 3.2: Gap analysis and KPIs/KVIs for trustworthiness”, supported by workshops and interviews with key stakeholders (Workshop #1 on measuring trust and Workshop #2 on tower ATCO tasks and gap analysis), identified operational needs for tower controllers and established Key Performance Indicators (KPIs) essential for trust in Explainable AI (XAI) systems. Building on this, “Task 3.3: Development/technical work plan – Roadmap” created a detailed roadmap addressing the specific needs of Air Traffic Control Officers (ATCOs), outlining the development of transparent, multimodal AI-enhanced, Human-AI Teaming (HAIT) systems. This document builds on the groundwork from the previous deliverable, “D3.1: Report on Definition, Specifications and SotA of Artificial Intelligence in Remote Digital Towers”, which analysed AI applications and Multimodal Machine Learning (MML), emphasizing transparency and explainability. The primary objective is to identify key operational tasks within RDT that can benefit from enhanced XAI support and to present a comprehensive development roadmap for integrating transparency in an AI-driven Decision Support System (DSS) based on the feedback from end-users. This strategic initiative will guide subsequent work in developing reliable, transparent, and explainable AI algorithms, system integration, and scenario validation, aiming to establish a DSS within RDTs for safer and more efficient Air Traffic Management (ATM). The present deliverable is directly linked to the “D6.1 Report on the Validation Plan-Exploratory Research Plan (ERP)” detailing the TRUSTY concept as an AI based tool for assistance in Air Traffic Control Service delivery in the Remote Digital Tower environment.
Institutions
- Mälardalen University (SE)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-06-23
- DOI
- https://doi.org/10.5281/zenodo.15722511
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00