S.: Toward Verification and Validation of Adaptive Aircraft Controllers

Abstract—Traditional fixed-gain control has proven to be un-successful to deal with complex, strongly nonlinear, uncer-tain, and changing systems such as a damaged aircraft. Con-trol systems with components that can adapt toward changes in the plant, e.g., using a neural network, have been actively investigated as they offer many advantages (e.g., better per-formance, controllability of aircraft despite of a damaged wing). However, neuro-adaptive controllers have not been used in safety-critical applications, because performance and safety guarantees cannot be provided at development time—a major prerequisite for safety certification (e.g., by the FAA or NASA). In this paper, we will describe our approach toward V&V of neuro-adaptive controllers. We have developed tools which dynamically estimate the neural network performance and safety envelope, using a Bayesian approach. We will dis