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:0-74@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20221221T133000

DTEND;TZID=Asia/Jerusalem:20221221T143000

DTSTAMP:20221214T080124Z

URL:https://aerospace.technion.ac.il/events/autonomous-scalable-and-robust
 -fusion-for-collaborative-robotic-bayesian-inference/

SUMMARY:Autonomous\, Scalable and Robust Fusion for Collaborative Robotic B
 ayesian Inference
DESCRIPTION:Lecturer:Ofer Dagan\n Faculty:Aerospace Engineering Sciences De
 partment \n Institute:University of Colorado Boulder\n Location:Classroom 
 165\, ground floor\, Library\, Aerospace Eng.\n Zoom: https://cuboulder.zo
 om.us/j/93825793193\n Abstract: The idea of a robotic team cooperating on 
 a joint task can be allegorized to a group of people working together. Oft
 en people have different capabilities\, different knowledge\, and differen
 t worldviews. However\, when collaborating\, people naturally know how to 
 summarize only the relevant information to achieve a joint goal. For a tea
 m of robots that needs to work together\, this human capability is not tri
 vial. The robot's ability to make sense and act in a constantly changing e
 nvironment is much less effective than what the human brain does.\nMy goal
  is to enable teams of robots to collaborate in a robust\, autonomous\, an
 d scalable manner on a variety of complementary tasks. Toward this goal I 
 take a probabilistic approach to robotics\, where a robot models the uncer
 tainty in how it perceives the world using a probability distribution (pdf
 ). In Bayesian decentralized data fusion (DDF) this approach is leveraged 
 to allow any two robots in a network to gain new data by sharing their pos
 terior pdfs\, representing their estimate. However\, DDF methods do not sc
 ale well as the number of robots in the network increase\, since they freq
 uently require all robots to process and communicate the full global pdf. 
 In this talk I will show how the global problem can be “broken” into s
 maller locally relevant problems\, thus significantly improves communicati
 on and computation requirements for each robot. I will present new scalabl
 e algorithms and demonstrate their applicability to collaborative inferenc
 e problems with simulations and hardware experiments on robotic platforms.
 \n Details: \n 
CATEGORIES:Seminars
LOCATION:Classroom 165\, ground floor\, Library\, Aerospace Eng.

END:VEVENT

BEGIN:VTIMEZONE

TZID:Asia/Jerusalem

X-LIC-LOCATION:Asia/Jerusalem

BEGIN:STANDARD

DTSTART:20221030T010000

TZOFFSETFROM:+0300

TZOFFSETTO:+0200

TZNAME:IST

END:STANDARD

END:VTIMEZONE
END:VCALENDAR