Explainable Artificial Intelligence for Aviation Safety Applications

Abstract

NASA's aviation research envisions future concepts for air transportation that will significantly expand the current nature of airspace and vehicle management with an increasing reliance on autonomy technologies. Indeed, increased reliance on autonomy technologies is a key enabler of these future concepts. Artificial Intelligence (AI) algorithms, which are at the heart of emerging autonomy technologies, are generally perceived as black boxes whose decisions are a result of complex rules learned on-the-fly. Unless these decisions are explained in a human understandable form, the end-users are less likely to accept them and certification personnel are less likely to clear these systems for field operation. Explainable AI (XAI) is an AI algorithm whose actions can be easily understood by humans. The research effort described in this paper developed EXplained Process and Logic of Artificial INtelligence Decisions (EXPLAIND)—a prototype tool for verification and validation of AI-based aviation systems. We provided a proof-of-concept for EXPLAIND by applying it to generate reliable, human-understandable explanations for decisions made by a NASA-developed aircraft trajectory anomaly detection AI algorithm. Cognitive walkthroughs of EXPLAIND’s explanation interface with controller subject matter experts demonstrated that EXPLAIND represents an important step towards user acceptance and certification of AI-based decision support tools (DSTs).