Key points are not available for this paper at this time.
View Video Presentation: https://doi.org/10.2514/6.2021-0564.vid Future operational concepts of aerospace missions in both civil and defense domains increasingly demand integration and interoperability of multiple intelligent systems driven by artificial intelligence (AI) technologies such as machine learning and deep learning. AI technologies have become an integral element of the aerospace systems that needs to be coupled with systems engineering practices starting from system concept definition and extending throughout the system life cycle. Although systems engineering has been at the forefront of aerospace system development in the past, the unique challenges of machine learning and deep learning require evolution of systems engineering methodologies for future AI-enabled aerospace systems. The paper proposes the need for systems engineering for acquisition and operationalization of AI and postulates the role of SE as data curator for AI. Additionally, challenges are examined for major SE activities such as Concept and Architecture Development, Model-based Systems Engineering, and Verification and Validation of AI-enabled aerospace systems.
Raz et al. (Mon,) studied this question.