BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Building Certifiably Safe and Correct Large-scale Autonomous Syste
 ms - Chuchu Fan (Massachusetts Institute of Technology)
DTSTART:20220727T143000Z
DTEND:20220727T150000Z
UID:TALK177005@talks.cam.ac.uk
DESCRIPTION:The introduction of machine learning (ML) and artificial intel
 ligence (AI) creates unprecedented opportunities for achieving full autono
 my. However\, learning-based methods in building autonomous systems can be
  extremely brittle in practice and are not designed to be verifiable. In t
 his talk\, I will present several of our recent efforts that combine ML wi
 th formal methods and control theory to enable the design of provably depe
 ndable and safe autonomous systems. I will introduce our techniques to gen
 erate safety certificates and certified decision and control for complex a
 utonomous systems\, even when the systems have a large number of agents an
 d follow nonlinear or unknown dynamics.
LOCATION:Discussion Room\, Newton Institute
END:VEVENT
END:VCALENDAR