BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Mountain
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220611T194429Z
UID:DC50CBDB-35C4-4D0F-887D-DF5FBB4D4597
DTSTART;TZID=US/Mountain:20220310T180000
DTEND;TZID=US/Mountain:20220310T190000
DESCRIPTION:As imperfectly designed agents in an uncertain world\, autonomo
 us systems will never work “out of the box” exactly as desired. By tak
 ing on tasks that push the technological limit\, autonomous systems will e
 ncounter unexpected situations that go beyond their immediate capabilities
 . Autonomous systems must therefore be able to continuously and independen
 tly gather\, process\, and act on imperfect information. They must also be
  cognizant of what they can and cannot accomplish on their own and know wh
 en/how to seek help. In aerospace applications and beyond\, scalable human
 -machine and machine-machine interactions will be essential for reinforcin
 g the core perception\, planning\, learning\, and reasoning algorithms tha
 t make machine autonomy on any one platform possible.\n\nThis talk will di
 scuss innovative Bayesian algorithmic approaches developed by the COHRINT 
 Lab at CU Boulder that enable autonomous systems to opportunistically leve
 rage different available kinds of human-machine and machine-machine intera
 ction while performing challenging tasks in the presence of complex uncert
 ainties. I will focus in detail on our group’s work on probabilistic mod
 eling\, inference\, and optimization techniques for augmenting autonomous 
 state estimation and decision-making algorithms running onboard autonomous
  systems with inputs from human teammates\, task assistants and supervisor
 s. I will describe how our approaches connect rigorous statistical modelin
 g and learning techniques with “plug-and-play” semantic interfaces tha
 t can readily adapt to a variety of applications and users. Results from a
 erospace applications such as unmanned air/ground reconnaissance\, missile
  defense\, and space robotics will show how our methods allow human-machin
 e systems to “cut knots and fill in gaps” in fundamentally novel ways 
 for challenging problems.\n\nCo-sponsored by: Christopher Reardon\, James 
 Gowans\, Yvonne Grey\n\nSpeaker(s): Dr. Nisar Ahmed\, \n\n2155 East Wesley
  Avenue\, Denver\, Colorado\, United States\, 80208\, Virtual: https://eve
 nts.vtools.ieee.org/m/296059
LOCATION:2155 East Wesley Avenue\, Denver\, Colorado\, United States\, 8020
 8\, Virtual: https://events.vtools.ieee.org/m/296059
ORGANIZER:christopher.reardon@du.edu
SEQUENCE:4
SUMMARY:IEEE CIR: Cooperative Bayesian Intelligence for Aerospace Autonomy
URL;VALUE=URI:https://events.vtools.ieee.org/m/296059
X-ALT-DESC:Description: <br /><p>As imperfectly designed agents in an uncer
 tain world\, autonomous systems will never work &ldquo\;out of the box&rdq
 uo\; exactly as desired. By taking on tasks that push the technological li
 mit\, autonomous systems will encounter unexpected situations that go beyo
 nd their immediate capabilities. Autonomous systems must therefore be able
  to continuously and independently gather\, process\, and act on imperfect
  information. They must also be cognizant of what they can and cannot acco
 mplish on their own and know when/how to seek help. In aerospace applicati
 ons and beyond\, scalable human-machine and machine-machine interactions w
 ill be essential for reinforcing the core perception\, planning\, learning
 \, and reasoning algorithms that make machine autonomy on any one platform
  possible.</p>\n<p>This talk will discuss innovative Bayesian algorithmic 
 approaches developed by the COHRINT Lab at CU Boulder that enable autonomo
 us systems to opportunistically leverage different available kinds of huma
 n-machine and machine-machine interaction while performing challenging tas
 ks in the presence of complex uncertainties. I will focus in detail on our
  group&rsquo\;s work on probabilistic modeling\, inference\, and optimizat
 ion techniques for augmenting autonomous state estimation and decision-mak
 ing algorithms running onboard autonomous systems with inputs from human t
 eammates\, task assistants and supervisors. I will describe how our approa
 ches connect rigorous statistical modeling and learning techniques with &l
 dquo\;plug-and-play&rdquo\; semantic interfaces that can readily adapt to 
 a variety of applications and users. Results from aerospace applications s
 uch as unmanned air/ground reconnaissance\, missile defense\, and space ro
 botics will show how our methods allow human-machine systems to &ldquo\;cu
 t knots and fill in gaps&rdquo\; in fundamentally novel ways for challengi
 ng problems.&nbsp\;</p>
END:VEVENT
END:VCALENDAR