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:0-467@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20160928T163000

DTEND;TZID=Asia/Jerusalem:20160928T173000

DTSTAMP:20230603T191148Z

URL:https://aerospace.technion.ac.il/events/belief-space-planning-for-auto
 nomous-navigation-while-modeling-landmark-identification/

SUMMARY:Belief Space Planning for Autonomous Navigation while Modeling Land
 mark Identification
DESCRIPTION:Lecturer:Shira Har-Nes\n Faculty:Department of Aerospace Engine
 ering\n Institute:Technion – Israel Institute of Technology\n Location:C
 lassroom 165\, ground floor\, Library\, Aerospace Eng.\n Zoom: \n Abstract
 : \n Details: \n We investigate the problem of autonomous navigation in un
 known or uncertain environments\, which is of interest in numerous robotic
 s applications\, such as navigation in GPS-deprived environments\, mapping
  and 3D reconstruction\, and target tracking. In lack of sources of absolu
 te information (e.g. GPS)\, the robot has to infer its own state and to cr
 eate a model of the environment based on sensor observations\, a problem k
 nown as simultaneous localization and mapping (SLAM). Moreover\, it has to
  plan actions\, in order to accomplish given goals while relying on inform
 ation provided by the inference (estimation) process. The inferred state\,
  e.g. robot poses and 3D landmarks\, cannot be assumed perfectly known bec
 ause the observations and dynamics are stochastic\; hence\, planning futur
 e actions has to take into account different sources of uncertainty. The c
 orresponding problem is known as belief space planning (BSP).\nAn essentia
 l ingredient in SLAM and BSP problems is correct association of landmarks 
 observed by robot sensors (e.g. camera)\, as incorrect association might l
 ead to wrong estimation and to catastrophic results. In particular\, the a
 bility to re-identify a previously observed object can be challenging\, es
 pecially considering images taken airborne or on the ground with shallow v
 iewpoints – an object may look completely different when observed from d
 ifferent angles. Yet\, state of the art BSP approaches typically consider 
 perfect ability to re-identify an object. In this work we develop a viewpo
 int aware BSP approach by modeling re-identification aspects within the pl
 anning phase. We study our approach in simulation\, considering the proble
 m of autonomously reaching a goal with highest estimation accuracy in a GP
 S-deprived unknown environment.
CATEGORIES:Seminars
LOCATION:Classroom 165\, ground floor\, Library\, Aerospace Eng.

END:VEVENT

BEGIN:VTIMEZONE

TZID:Asia/Jerusalem

X-LIC-LOCATION:Asia/Jerusalem

BEGIN:DAYLIGHT

DTSTART:20160325T030000

TZOFFSETFROM:+0200

TZOFFSETTO:+0300

TZNAME:IDT

END:DAYLIGHT

END:VTIMEZONE
END:VCALENDAR