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.

Various Air Traffic Flow and Capacity Management (ATFCM) measures are implemented during the pre-tactical and tactical flow management phases to resolve traffic congestion (aka hotspots); however, these are generally based on flight plan data. On the day of operation, an aircraft's actual trajectory may differ significantly from its flight plan and, as a result, hotspots still occur and these have to be resolved by Air Traffic Controllers (ATCOs) without sufficient advance notice. With today's ATFCM tools, tactical Air Traffic Control (ATC) hotspots are only identified up to around 20 minutes in advance. The aim of ASTRA is to bridge the gap between the Flow Management Position (FMP) and the planner Controller Working Position (CWP) by developing a AI-based tool (to TRL2) for FMP personnel which can predict and resolve hotspots earlier than today, before they are within the scope of the sector planner. The objectives of the project are to: (a) develop an FMP function to predict hotspots at least 1 hour in advance, and to propose strategies to resolve them; (b) develop Human Machine Interface (HMI) concepts to allow interaction between operators and the tool; and (c) demonstrate and validate the tool by conducting human-in-the-loop Real-Time Simulations (RTS) in a representative operational environment. The benefits of this tool would include: increased capacity at ATC unit level; better adherence to efficient and green business trajectories; reduced ATCO workload; and more predictable operations. The project will be carried out by a multidisciplinary consortium of 5 partners from 4 countries - Malta, Spain, Italy and Switzerland - including an academic institution, an ANSP, an Air Traffic Management (ATM) technology provider, and two consulting/research entities. The partners are complementary to each other and bring a combination of academic, technical, human factor and operational skills and expertise to the project.

ATM Human Performance research has been traditionally focused on two senses: sight and hearing. Remote tower operations make no exception, with many efforts and resources focused on acquisition of visual images, for instance by means of hi-resolution cameras (SESAR requs here). This situation is often understood by adopting traditional human information processing approaches, where human cognition is described as composed by the three phases of input acquisition-processing-action, with a clear and neat separation among them. MOTO will explore 3 research opportunities. The first one is to consider the role of all the human senses for tower operations. The approach of Embodied Cognition could be applied to achieve a full understanding on the use of other senses for controllers, i.e. one not deprived of important bodily sensations. The second one is that the Embodied Cognition approach also shows how the three phases of human cognition cannot be neatly divided, as decision-making is closely integrated with our perceptual capability and action possibilities. The embodied remote tower could potentially open up new possibilities to study (and reproduce, see point below) advanced forms of naturalistic decision-making, or attentional mechanism like the cocktail party effect. Third, the understanding of embodied aspects of ATM Human Performance is a pre-requisite to design effective multimodal input and output channels, thereby rethinking the current human-system interaction model. The end goal is to enhance human performance, by exploiting other channels than the already overloaded visual channel.

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 optimizing 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 will provide a proof-of-concept of transparent AI models that includes visualization, explanation, generalization with adaptability over time to ensure safe and reliable decision support.