English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we propose a construction scheme for a Safe-visor architecturefor sandboxing unverified controllers, e.g., artificial intelligence-based(a.k.a. AI-based) controllers, in two-players non-cooperative stochastic games.Concretely, we leverage abstraction-based approaches to construct a supervisorthat checks and decides whether or not to accept the inputs provided by theunverified controller, and a safety advisor that provides fallback controlinputs to ensure safety whenever the unverified controller is rejected.Moreover, by leveraging an ($\epsilon,\delta$)-approximate probabilisticrelation between the original game and its finite abstraction, we provide aformal safety guarantee with respect to safety specifications modeled bydeterministic finite automata (DFA), while the functionality of the unverifiedcontrollers is still exploited. To show the effectiveness of the proposedresults, we apply them to a control problem of a quadrotor tracking a movingground vehicle, in which an AI-based unverified controller is employed tocontrol the quadrotor.

Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture