Navn
How to ensure Safety in AI-enabled Critical Control Systems using Digital Twins
Beskrivelse
When using AI for control and optimization of critical infrastructure, there is a risk that the underlying (learned) models do not cover all aspects of the given plant, and henceforth the modelled system may enter a potential unstable state.
In this talk, we present the challenges in more detail, and we introduce the notions of shielding and learning under shielding. We couple the notions to the exploitation of digital twins for identifying (stochastic) parameters and for setting up virtual test environments.
Talere
Moderator
Michele Albano, AAU
Dato & Tid
torsdag den 9. november 2023, 11.00 - 11.30
Sal
Sal 5
Temaer
Sikkerhed og Etik i AI, Robotics og Fremtidens Teknologier
