BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T182646Z
UID:1ADDBE03-9209-4E8F-A0EA-5730B97676E8
DTSTART;TZID=America/New_York:20251028T110000
DTEND;TZID=America/New_York:20251028T120000
DESCRIPTION:Abstract: New automated systems with high levels of autonomy\, 
 such as self-driving cars and autonomous robots\, are increasingly enabled
  by machine learning. These applications highlight the safety-critical nat
 ure of control systems technology\, both due to their close proximity to t
 he public and their level of autonomy. Safe control technology aims to pro
 vide guarantees that these systems will not do harm. Interest in safety fi
 lters\, a modular approach to safe control\, has increased in response to 
 safety concerns associated with learning-based control often employed in r
 obotics and autonomous driving. Such safety filters commonly rely on accur
 ate mathematical models\, contradicting the intended use to enhance data-d
 riven learning solutions. This reliance on accurate models also limits the
  use of this technology in uncertain environments and in applications othe
 r than robotics. In this seminar I will highlight some of the challenges e
 ncountered when applying safe control to automated drug delivery. I will p
 resent recent results on data-driven safety filters that can extend the ap
 plicability of safe control technology.\n\nSpeaker(s): Klaske van Heusden\
 , \n\nRoom: SF 2104\, Bldg: SF 2104\, 172 St. George St.\, Toronto\, Ontar
 io\, Canada\, M5R 0A3
LOCATION:Room: SF 2104\, Bldg: SF 2104\, 172 St. George St.\, Toronto\, Ont
 ario\, Canada\, M5R 0A3
ORGANIZER:mehrdad.tirandazian@ieee.org
SEQUENCE:2
SUMMARY:Data-driven methods for safety-critical control
URL;VALUE=URI:https://events.vtools.ieee.org/m/509037
X-ALT-DESC:Description: <br /><blockquote style="color: rgb(34\, 34\, 34)\;
  font-family: Arial\, Helvetica\, sans-serif\; font-size: small\; font-sty
 le: normal\; font-variant-ligatures: normal\; font-variant-caps: normal\; 
 font-weight: 400\; letter-spacing: normal\; orphans: 2\; text-align: start
 \; text-indent: 0px\; text-transform: none\; widows: 2\; word-spacing: 0px
 \; -webkit-text-stroke-width: 0px\; white-space: normal\; background-color
 : rgb(255\, 255\, 255)\; text-decoration-thickness: initial\; text-decorat
 ion-style: initial\; text-decoration-color: initial\;">\n<div>\n<div dir="
 ltr">\n<div>\n<div><span style="font-size: 12pt\;"><strong>Abstract:&nbsp\
 ;</strong>New automated systems with high levels of autonomy\, such as sel
 f-driving cars and autonomous robots\, are increasingly enabled by machine
  learning. These applications highlight the safety-critical nature of cont
 rol systems technology\, both due to their close proximity to the public a
 nd their level of autonomy. Safe control technology aims to provide guaran
 tees that these systems will not do harm. Interest in safety filters\, a m
 odular approach to safe control\, has increased in response to safety conc
 erns associated with learning-based control often employed in robotics and
  autonomous driving. Such safety filters commonly rely on accurate mathema
 tical models\, contradicting the intended use to enhance data-driven learn
 ing solutions. This reliance on accurate models also limits the use of thi
 s technology in uncertain environments and in applications other than robo
 tics. In this seminar I will highlight some of the challenges encountered 
 when applying safe control to automated drug delivery. I will present rece
 nt results on data-driven safety filters that can extend the applicability
  of safe control technology.</span></div>\n</div>\n</div>\n</div>\n</block
 quote>
END:VEVENT
END:VCALENDAR