Automatic Test and Evaluation of Autonomous Systems

Physical test and evaluation (T&E) of autonomous systems in actual settings is resource intensive time exhaustive. Simulation-based testing, however, can reduce the testing cost time, allowing for whole operation envelope through a massive set scenarios. In this research, novel automatic simulation-based proposed that simultaneously amalgamates knowledge domain experts operating environmental parameters systems. The method employs fuzzy logic to replace exhaustive activities tester leverages tester’s role review root-cause reasoning reports about System Under Test (SUT) focus only on inspection flagged scenarios rather than inspecting all instants uses Type-2 provide more robust handling data uncertainties involved process. An integrated configurable software tool user-friendly Graphical User Interface (GUI) are developed allow single and/or batches large number generate along with analysis. has been successfully applied perception system Unmanned Aerial Systems (UAS) Collaborative Technology Demonstrator (CUSTD).