Machine Learning (ML) in aerospace and defense (A&D) industries: a systematic literature review

In recent years, Machine Learning (ML) has made significant technical progress due to increasedavailability of larger data sets, more powerful computing performance, and greater budget allocations. However, ethical, political, and societal implications relate to successful and global implementation of ML in Aerospace and Defense (A&D) environments. Such challenges could result in unpredictability or inexplicability of the ML-enabled operation. This study provides a systematic review of published material on ML methods, limitations, and current and potential applications of ML in A&D. Records from 2012 to 2021 were found using multiple databases and showed ample research in missions changing from manned to semi-autonomous or autonomous; specifically in areas related to surveillance, reconnaissance, logistics, intelligence, and command and control. The results also emphasize the implementation of ML is deemed both threatening and promising.