BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:0-5855@eng.ufl.edu
DTSTART;TZID=America/New_York:20230919T124500
DTEND;TZID=America/New_York:20230919T134500
DTSTAMP:20251201T210321Z
URL:https://www.eng.ufl.edu/news-events/events/mae-affiliate-seminar-verif
 y-then-monitor-calibration-guarantees-for-safety-confidence/
SUMMARY:MAE Affiliate Seminar - Verify-then-Monitor: Calibration Guarantees
  for Safety Confidence
DESCRIPTION:Verify-then-Monitor: Calibration Guarantees for Safety Confiden
 ce\nTuesday\, September 19\, 2023\, at 12:50 pm\nLocation: In-Person MAE-A
 \, Room 303\nIvan Ruchkin\, PhD\nAssistant Professor\nUF Department of Ele
 ctrical and Computer Engineering\nAbstract\nAutonomous cyber-physical syst
 ems (CPS) are increasingly deployed in complex and safety-critical environ
 ments. To help CPS interact with such environments\, learning-enabled comp
 onents\, typically implemented with neural networks\, perform perception a
 nd control functions. Unfortunately\, the complexity of the environments a
 nd learning components is a major challenge to ensuring the safety of CPS.
  An emerging assurance paradigm prescribes two steps: (i) verifying as muc
 h of the CPS as possible at design time\, and then (ii) monitoring the pro
 bability of safety at run time in case of unexpected situations. But how c
 an we guarantee that the monitor produces a probability that is well-calib
 rated to the true chance of safety? This talk will summarize our recent an
 swers in two settings. The first setting combines Bayesian filtering with 
 probabilistic model checking of Markov decision processes\, instantiated i
 n the context of controlling critical infrastructure. The second setting f
 ocuses on confidence monitoring of formalized assumptions behind closed-lo
 op neural-network verification in the context of an autonomous underwater 
 vehicle.\nBiography\nDr. Ivan Ruchkin is an assistant professor at the Dep
 artment of Electrical and Computer Engineering of the University of Florid
 a\, where he leads the Trustworthy Engineered Autonomy (TEA) Lab. His rese
 arch makes autonomous systems safer and more trustworthy by combining tech
 niques from formal methods and artificial intelligence. Ivan received his 
 Ph.D. degree in Software Engineering from Carnegie Mellon University and c
 ompleted his postdoctoral training at the University of Pennsylvania. His 
 contributions were recognized with multiple Best Paper awards\, a Gold Med
 al in the ACM Student Research Competition\, and the Frank Anger Memorial 
 Award for the crossover of ideas between the software engineering and embe
 dded systems communities. More information can be found at https://ivan.ec
 e.ufl.edu.\nMAE Faculty Host: Yu Wang
CATEGORIES:Seminars
LOCATION:MAE-A Room 303\, 939 Sweetwater Drive\, Gainesville\, FL\, 32611\,
  United States
GEO:29.643814;-82.34865
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=939 Sweetwater Drive\, Gain
 esville\, FL\, 32611\, United States;X-APPLE-RADIUS=100;X-TITLE=MAE-A Room
  303:geo:29.643814,-82.34865
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR