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:0-429@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20170726T163000

DTEND;TZID=Asia/Jerusalem:20170726T173000

DTSTAMP:20230530T180901Z

URL:https://aerospace.technion.ac.il/events/cooperative-multi-robot-belief
 -space-planning-for-visual-inertial-navigation-and-online-sensor-calibrati
 on/

SUMMARY:Cooperative Multi-Robot Belief Space Planning for Visual-Inertial N
 avigation and Online Sensor Calibration
DESCRIPTION:Lecturer:Yair Ben-Elisha\n Faculty:Department of Aerospace Engi
 neering\n Institute:Technion – Israel Institute of Technology\n Location
 :Classroom 165\, ground floor\, Library\, Aerospace Eng.\n Zoom: \n Abstra
 ct: \n Details: \n High accuracy navigation in GPS-deprived uncertain envi
 ronments is of prime importance to various robotics applications. In such 
 scenarios\, it has been recently shown that online sensor calibration and 
 multi-robot collaboration\, whereby robots make mutual observations of the
  environment or perform relative observations of each other\, can signific
 antly enhance navigation accuracy. However\, these approaches typically co
 nsider a passive setting\, where robot actions are externally determined. 
 On the other hand\, belief space planning (BSP) approaches account for dif
 ferent sources of uncertainty\, thus identifying actions that improve cert
 ain aspects in inference\, such as accuracy. Yet\, existing BSP approaches
  typically do not consider sensor calibration in the mentioned problem set
 ting\, nor a visual-inertial SLAM setup.\nIn this research\, we contribute
  a multi-robot BSP approach for active sensor calibration considering a vi
 sual-inertial SLAM system. To that end\, we maintain a belief over both ro
 bot's pose and sensor calibration\, and reason how that belief would evolv
 e for different actions while considering partially unknown and uncertain 
 environments. In particular\, we leverage the recently developed concept o
 f IMU pre-integration and develop appropriate factor graph formulation for
  future beliefs to facilitate computationally efficient inference within B
 SP. Another key aspect of our approach are indirect multi-robot observatio
 n updates given the states of different robots are correlated. This concep
 t allows for a subset of robots to carry on their individual (possibly tim
 e-critical) tasks while preserving high accuracy estimation by relying on 
 other expendable robots to make appropriate observations of the environmen
 t. We study our approach in high-fidelity synthetic simulation and show th
 e determined actions can lead to significantly improved estimation accurac
 y.
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:20170324T030000

TZOFFSETFROM:+0200

TZOFFSETTO:+0300

TZNAME:IDT

END:DAYLIGHT

END:VTIMEZONE
END:VCALENDAR