by RB Rusu
Abstract:
Intelligent sensor equipped environments can be of much greater help if they are capable of recognizing the actions and activities of their users, and inferring their intentions. An intelligent kitchen that recognizes what a person is looking for can highlight the target object. An oven noticing that the cook is on the phone can reduce the heating temperature, in order to avoid the meal getting burnt. In my dissertation research, I investigate the representation of models of everyday activities and study how such models can be learned from sensory data.
Reference:
Acquiring Models of Everyday Activities for Robotic Control in 'Current PhD Research in Pervasive Computing' (RB Rusu), In Technical Reports - University of Munich, Department of Computer Science, Media Informatics Group (A. Ferscha, M. Langheinrich, A. Schmidt, eds.), volume LMU-MI-2005-3, 2006.
Bibtex Entry:
@article{rusu_acquiring_2006,
author = {RB Rusu},
title = {Acquiring Models of Everyday Activities for Robotic Control in {'Current}
{PhD} Research in Pervasive Computing'},
journal = {Technical Reports - University of Munich, Department of Computer
Science, Media Informatics Group},
year = {2006},
volume = {{LMU-MI-2005-3}},
month = {mar},
abstract = {Intelligent sensor equipped environments can be of much greater help
if they are capable of recognizing the actions and activities of
their users, and inferring their intentions. An intelligent kitchen
that recognizes what a person is looking for can highlight the target
object. An oven noticing that the cook is on the phone can reduce
the heating temperature, in order to avoid the meal getting burnt.
In my dissertation research, I investigate the representation of
models of everyday activities and study how such models can be learned
from sensory data.},
editor = {Ferscha, A. and Langheinrich, M. and Schmidt, A.},
issn = {1862-5207},
}