BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Dynamic Bayesian Approach to Estimation and Filtering during Conta
 ct Tasks
DTSTART:20130617T110000
DTSTAMP:20260502T113635Z
UID:e0445a21c3be0d1cb0c7db5983337d460ea4659eb0203826993f6c65
CATEGORIES:Conferences - Seminars
DESCRIPTION:Jeff Trinkle\, Rensselaer Polytechnic Institute\, Troy\, NY 12
 180\nIn this work\, we develop a solution to a broad class of grasping and
  manipulation problems that we term as C-SLAM for "contact simultaneous lo
 calization and modeling\," in which robots need to accurately track the mo
 tions of the contacted bodies and the locations of contacts while simultan
 eously estimating important system parameters\, such as body dimensions\, 
 masses and friction coefficients. Our solution is based on a dynamic Bayes
 ian inference framework\, and hence\, we refer to it as Dynamic Bayesian C
 -SLAM (DBC-SLAM). DBC-SLAM combines a model of multibody dyanmics with a d
 ynamic Bayesian network\, and incorporates model parameter estimation as a
 n intrinsic part of the overall inference procedure. We show two prelimina
 ry proof-of-concept examples that demonstrate the use of DBC-SLAM in robot
 ic contact tasks.
LOCATION:ELA2
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR