BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20131027T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20140330T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.6773.field_data.0@diag.uniroma1.it
DTSTAMP:20260421T062336Z
CREATED:20131202T103009Z
DESCRIPTION:Seth Hutchinson:A Hyperbelief Space Approach to Computing Optim
 al Policies for POMDPsThursday\, December 5\, 2013\, at 15:00\, Aula Magna
 AbstractTypically\, the location of a robot is described by a configuratio
 n. If there is uncertainty in the configuration\, one can lift the configu
 ration space into the belief space\, which is essentially the set of possi
 ble probability functions for the robot's position\; in this case\, a beli
 ef is merely an a posteriori pdf for the robot's configuration. If a robot
  system plans into the future\, the future beliefs will depend on future s
 ensor measurements\, which cannot be known at planning time. To deal with 
 this\, we can lift the belief space to the hyperbelief space\, which is me
 rely the set of all possible pdfs on the belief space. In the hyperbelief 
 space\, policies have deterministic effects: for a specific control policy
 \, the transition from one stage of execution to the next is deterministic
 . In this higher-dimensional hyperbelief space\, one need not (explicitly)
  worry about the representation of uncertainty. Thus\, it can be convenien
 t to model partially observed Markov decision processes (POMDPs) in the hy
 perbelief space.  In this talk\, we present results for sampling-based any
 time algorithms that determine nearly optimal policies for POMDPs by repre
 senting the system evolution in the hyperbelief space.BiosketchSeth Hutchi
 nson received his PhD from Purdue University in 1988\, and joined the Univ
 ersity of Illinois in 1990\, where he is currently a Professor in the Depa
 rtment of Electrical and Computer Engineering.  Dr. Hutchinson has served 
 as Editor-in-Chief for the IEEE Trans. on Robotics and was the Founding Ed
 itor-in-Chief of the Conference Editorial Board of the IEEE Robotics and A
 utomation Society.  He has published approximately 200 papers on the topic
 s of robotics and computer vision\, and is coauthor of the books 'Principl
 es of Robot Motion: Theory\, Algorithms\, and Implementations\,' published
  by MIT Press\, and 'Robot Modeling and Control\,' published by Wiley.  Hu
 tchinson is a Fellow of the IEEE. http://www.uiuc.edu/~seth
DTSTART;TZID=Europe/Paris:20131205T150000
DTEND;TZID=Europe/Paris:20131205T150000
LAST-MODIFIED:20210526T101032Z
LOCATION:Aula Magna
SUMMARY:SEMINAR Seth Hutchinson: A Hyperbelief Space Approach to Computing 
 Optimal Policies for POMDPs - Prof. Seth Hutchinson\, University of Illino
 is at Urbana
URL;TYPE=URI:http://diag.uniroma1.it/node/6773
END:VEVENT
END:VCALENDAR