We interpret several dynamical system verification questions, e.g., region of attraction and reachability analyses, as data classification problems. We discuss some of the tradeoffs between conventional optimization-based certificate constructions with certainty in the outcomes and this new datedriven approach with quantified confidence in the outcomes. The new methodology is aligned with emerging computing paradigms and has the potential to extend systematic verification to systems that do not necessarily admit closed-form models from certain specialized families. We demonstrate its effectiveness on a collection of both conventional and unconventional case studies including model reference adaptive control systems, nonlinear aircraft models, and reinforcement learning problems.

Dynamic soaring extracts energy from naturally occurring wind gradients that can be used to extend aircraft endurance, particularly in small UAVs. Autonomous thermal soaring has already been validated in flight tests with small UAVs, but this level of demonstration has not been performed for dynamic soaring UAVs, partly due to the precise wind measurements required. This paper explores wind vector sensing using flush pressure ports located on the nose of small sailplanes. Single Hidden Layer neural networks are used to generate regression models to calculate the airspeed, angle of attack, and angle of sideslip and are trained with pressure measurements collected during wind tunnel tests. These models are then applied to pressure measurements taken during flight tests of the aircraft and sensing system to judge the viability of the method.

Nonlinear, adaptive, or otherwise complex control techniques are increasingly relied upon to ensure the safety of systems operating in uncertain environments. However, the nonlinearity of the resulting closed-loop system complicates verification that the system does in fact satisfy those requirements at all possible operating conditions. While analytical proof-based techniques and finite abstractions can be used to provably verify the closed-loop system's response at different operating conditions, they often produce conservative approximations due to restrictive assumptions and are difficult to construct in many applications. In contrast, popular statistical verification techniques relax the restrictions and instead rely upon simulations to construct statistical or probabilistic guarantees. This work presents a data-driven statistical verification procedure that instead constructs statistical learning models from simulated training data to separate the set of possible perturbations into "safe" and "unsafe" subsets. Binary evaluations of closed-loop system requirement satisfaction at various realizations of the uncertainties are obtained through temporal logic robustness metrics, which are then used to construct predictive models of requirement satisfaction over the full set of possible uncertainties. As the accuracy of these predictive statistical models is inherently coupled to the quality of the training data, an active learning algorithm selects additional sample points in order to maximize the expected change in the data-driven model and thus, indirectly, minimize the prediction error. Various case studies demonstrate the closed-loop verification procedure and highlight improvements in prediction error over both existing analytical and statistical verification techniques.

No abstract