Explainable Artificial Intelligence (XAI) for Air Traffic Management

Machine Learning (ML) and Artificial Intelligence (AI) have matured to the point where they are being used throughout many modern applications. Explainable AI (XAI) – AI in which humans can understand the decisions or predictions made by the AI system – is becoming critical for many applications, including Air Traffic Management (ATM). In contrast, ML-enabled and AI-enabled systems too often resemble “black boxes” that mysteriously convert incoming data into predicted outcomes. At best, such “black box” systems can be explained by inferred explanations where the input/output relationships are analyzed and generalized. Even the designers of such systems cannot explain why the AI or ML system arrived at a specific decision. Outcomes of such “intelligent systems” should resonate with the decision makers’ own expertise, understanding, and intuitions (tacit knowledge). This effort sspecifically merges deep generative models, optimal transport theory along with AI Intent Inference Learning (IIL) to create a vocabulary for XAI that can be used to explain ATM-domain situations.

Supporting NASA's Airspace Operations and Safety Program (ASOP), this technology can be implemented to form a real-time monitoring of system safety, or in terms of analyzing historical data, for data mining, test and evaluation of machine learning an AI systems integrated into ATM, and controller training.

XAI has a wide range of applications where ML and AI are used to provide decision support to process control, manufacturing, airline operational control, and military defense (decision support and training).

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.