Risk Verification of Stochastic Systems with Neural Network Controllers
Motivated by the fragility of neural network (NN) controllers in safety-critical applications, we present a data-driven framework for verifying the risk of stochastic dynamical systems with NN controllers. Given a stochastic control system, an NN controller, and a specification equipped with a notio...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Motivated by the fragility of neural network (NN) controllers in
safety-critical applications, we present a data-driven framework for verifying
the risk of stochastic dynamical systems with NN controllers. Given a
stochastic control system, an NN controller, and a specification equipped with
a notion of trace robustness (e.g., constraint functions or signal temporal
logic), we collect trajectories from the system that may or may not satisfy the
specification. In particular, each of the trajectories produces a robustness
value that indicates how well (severely) the specification is satisfied
(violated). We then compute risk metrics over these robustness values to
estimate the risk that the NN controller will not satisfy the specification. We
are further interested in quantifying the difference in risk between two
systems, and we show how the risk estimated from a nominal system can provide
an upper bound the risk of a perturbed version of the system. In particular,
the tightness of this bound depends on the closeness of the systems in terms of
the closeness of their system trajectories. For Lipschitz continuous and
incrementally input-to-state stable systems, we show how to exactly quantify
system closeness with varying degrees of conservatism, while we estimate system
closeness for more general systems from data in our experiments. We demonstrate
our risk verification approach on two case studies, an underwater vehicle and
an F1/10 autonomous car. |
---|---|
DOI: | 10.48550/arxiv.2209.09881 |