BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240928T002500Z
UID:699E3AC6-CD4A-42E1-9E7A-201F97D0274A
DTSTART;TZID=America/New_York:20240927T130000
DTEND;TZID=America/New_York:20240927T140000
DESCRIPTION:Dr. Mengxue Hou\, an Assistant Professor at the University of N
 otre Dame\, will present on robotic planning at this IEEE CSS seminar. Her
  talk will address the challenge of balancing computational efficiency and
  model fidelity in robotic decision-making for exploring unknown environme
 nts. She will focus on underwater vehicle navigation\, presenting a learni
 ng method to create a non-Markovian reduced-order model that enhances accu
 racy. Additionally\, she will discuss a Large-Language-Model-guided hierar
 chical planner that translates human-specified missions into executable ac
 tions with low computational cost.\n\nSpeaker(s): Prof. Mengxue Hou\n\nRoo
 m: 405\, Bldg: WH\, Cleveland State University\, 2121 Euclid Ave.\, Clevel
 and\, Ohio\, United States\, 44115
LOCATION:Room: 405\, Bldg: WH\, Cleveland State University\, 2121 Euclid Av
 e.\, Cleveland\, Ohio\, United States\, 44115
ORGANIZER:l.dong34@csuohio.edu
SEQUENCE:5
SUMMARY:Assured abstraction for hierarchical robotic planning 
URL;VALUE=URI:https://events.vtools.ieee.org/m/429167
X-ALT-DESC:Description: <br /><p>Dr. Mengxue Hou\, an Assistant Professor a
 t the University of Notre Dame\, will present on robotic planning at this 
 IEEE CSS seminar. Her talk will address the challenge of balancing computa
 tional efficiency and model fidelity in robotic decision-making for explor
 ing unknown environments. She will focus on underwater vehicle navigation\
 , presenting a learning method to create a non-Markovian reduced-order mod
 el that enhances accuracy. Additionally\, she will discuss a Large-Languag
 e-Model-guided hierarchical planner that translates human-specified missio
 ns into executable actions with low computational cost.</p>
END:VEVENT
END:VCALENDAR