Distributionally Robust Policy and Lyapunov-Certificate Learning

arXiv:2404.03017v1 Announce Type: cross
Abstract: This article presents novel methods for synthesizing distributionally robust stabilizing neural controllers and certificates for control systems under model uncertainty. A key challenge in designing controllers with stability guarantees for uncertain systems is the accurate determination of and adaptation to shifts in model parametric uncertainty during online deployment. We tackle this with a novel distributionally robust formulation of the Lyapunov derivative chance constraint ensuring a monotonic decrease of the Lyapunov certificate. To avoid the computational …

abstract article arxiv challenge control control systems cs.lg cs.ro cs.sy deployment designing eess.sy key math.oc novel parametric policy robust stability systems type uncertain uncertainty