Artificial Situational Awareness Assessment of a Novel ATC Support System

This paper presents the application of an existing situational awareness framework to a newly developed artificial intelligence system to determine its awareness level. The system incorporates diverse automation techniques - knowledge graph, expert rules, machine learning - for gaining situational awareness and applying it in the field of air traffic control. Since the system was developed to serve as a foundation for exploring automation and artificial situational awareness, the primary result of this work is the system's overall awareness level assessment and the identification of sub-systems that may be improved for additional awareness. The framework used was chosen in the fundamental project documents and its use proved beneficial as it enabled the demonstration of how general guidelines can be interpreted for a specific system. It also informed possible routes for improvement of the process. Highest priority awareness- related improvements are those dealing with robustness, whose implementation would substantiate the current awareness assessment. The system is shown to be on the highest awareness level conditionally, considering its proof-of-concept level. The high level reached by the system is contingent on awareness concept and condition interpretations. With the appropriate assessment of the system, implementation in an operational environment is more feasible.