BEGIN:VCALENDAR

VERSION:2.0

PRODID:-//wp-events-plugin.com//6.6.4.4//EN

TZID:Asia/Jerusalem

X-WR-TIMEZONE:Asia/Jerusalem
BEGIN:VEVENT

UID:0-294@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20200608T123000

DTEND;TZID=Asia/Jerusalem:20200608T133000

DTSTAMP:20230527T131059Z

URL:https://aerospace.technion.ac.il/events/experience-based-prediction-of
 -unknown-environments-for-enhanced-belief-space-planning/

SUMMARY:Experience-Based Prediction of Unknown Environments for Enhanced Be
 lief Space Planning
DESCRIPTION:Lecturer:Omri Asraf\n Faculty:Department of Aerospace Engineeri
 ng\n Institute:Technion – Israel Institute of Technology\n Location:Zoom
  meeting - https://technion.zoom.us/j/91759816988\n Zoom: \n Abstract: \n 
 Details: \n Autonomous navigation missions require online decision making 
 abilities\, in order to choose from a given set of candidate actions an ac
 tion that will lead to the best outcome. In a partially observable setting
 \, decision making under uncertainty\, also known as belief space planning
  (BSP)\, involves reasoning about belief evolution considering realization
 s of future observations. Yet\, when  candidate actions lead the robot to
  an unknown environment the decision making mission becomes a very challen
 ging problem since without a map it is hard to foresee future observations
 .\nIn this thesis we develop a data-driven approach for predicting a distr
 ibution over an unexplored map\, generating future observations\, and comb
 ining these observations within BSP. We examine our approach and compare i
 t to existing BSP methods in a Gazebo simulation\, and demonstrate it ofte
 n yields improved performance.
CATEGORIES:Seminars
LOCATION:Zoom meeting - https://technion.zoom.us/j/91759816988

END:VEVENT

BEGIN:VTIMEZONE

TZID:Asia/Jerusalem

X-LIC-LOCATION:Asia/Jerusalem

BEGIN:DAYLIGHT

DTSTART:20200327T030000

TZOFFSETFROM:+0200

TZOFFSETTO:+0300

TZNAME:IDT

END:DAYLIGHT

END:VTIMEZONE
END:VCALENDAR