Description du projet
Une IA fiable et transparente pour les tours de contrôle numériques à distance
Les tours de contrôle numériques à distance (TCD), une solution innovante pour améliorer la gestion des données dans les aéroports, sont de plus en plus adoptées par les aéroports du monde entier pour améliorer la sécurité et l’efficacité. Néanmoins, le volume important de données générées exige des efforts et une attention considérables pour une utilisation et une organisation efficaces. Le projet TRUSTY, financé par l’UE, vise à améliorer les TCD en tirant parti de l’intelligence artificielle (IA) pour stimuler leur efficacité, leur capacité de données et leur durabilité globale. En outre, elle vise à garantir des niveaux plus élevés de transparence et de fiabilité dans leurs systèmes d’IA. Pour atteindre ces objectifs, le projet exploitera les découvertes en matière de visualisation interactive des données, différentes technologies récentes et des techniques de visualisation de l’information.
Objectif
Remote digital towers (RDT) are taking place around the world to ensure efficiency and safety. TRUSTY harnesses the power of artificial intelligence (AI) to enhance resilience, capacity, and efficiency in making significant advancements in the deployment of digital towers. The overall goal of TRUSTY is to provide adaptation in the level of transparency and explanation to enhance the trustworthiness of AI-powered decisions in the context of RDT. Through the video transmission data from RDT, TRUSTY considers the following major tasks:
1. Taxiway monitoring (i.e. bird hazard, presence of a drone, autonomous vehicle monitoring, human intrusion, etc.).
2. Runway monitoring (approach and landing) misalignment warning and the corresponding explanation.
To deliver trustworthiness in an AI-powered intelligent system several approaches are considered:
• ‘Self-explainable and Self-learning’ system for critical decision-making
• ‘Transparent ML’ models incorporating interpretability, fairness, and accountability
• ‘Interactive data visualization and HMI dashboard’ for smart and efficient decision support
• ‘Adaptive level of explanation’ regarding the user's cognitive state.
• “Human-centric AI” enhances the trustworthiness of AI-powered systems.
• “Human-AI teaming” to consider users’ feedback to insure some computation flexibility and the users’ acceptability.
To achieve the goal, TRUSTY will rely on the SotA developments in interactive data visualization, and user-centric explanation and on recent technological improvements in accuracy, robustness, interpretability, fairness, and accountability. We will apply information visualization techniques like visual analytics, data-driven storytelling, and immersive analytics in human-machine interactions (HMI). Thus, this project is at the crossroad of trustworthy AI, multi-model machine learning, active learning, and UX for human and AI model interaction.
Champ scientifique
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robotsdrones
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- social scienceseducational sciencespedagogyactive learning
Programme(s)
- HORIZON.2.5 - Climate, Energy and Mobility Main Programme
Régime de financement
HORIZON-JU-RIA - HORIZON JU Research and Innovation ActionsCoordinateur
722 20 VASTERAAS
Suède