Multi-agent flight simulation with robust situation generation

Air traffic management systems, on-board aircraft systems, and proposed airspace management structures such as free-flight are often operated with human operators in a simulated environment. This is necessary for effective design and testing of these systems, as well as the training of the operators. For these experiments or training scenarios, success often depends upon human subjects experiencing one-or-more specific situations. Reliably generating these specific situations is often difficult because subjects may not act consistently or as expected; and these variations can affect the system. Generating specific situations in the presence of this uncertainty is referred to as robust situation generation, robust because the situations must occur within a range of possible actions by the subject. A robust situation generation architecture was developed to support flight simulation tests of air transport cockpit systems. Pseudo-aircraft maneuver within reasonable performance constraints, interact in a realistic manner, and make pre-recorded voice radio communications. The achieved robustness of this system to typical variations in the subject's flight path was explored. It was found to successfully generate specific situations within the performance limitations of the subject-aircraft, pseudo-aircraft, and the script used.