Please consider joining us for the
AAAI 2012 Workshop
on Grounding Language for Physical Systems!
Bio
I'm a graduate student in the University of Washington's
Computer Science and Engineering department, working with professor
Dieter Fox
in the
Robotics and State Estimation lab.
I have also collaborated with CSE's
computer security group
and with Intel Labs Seattle, and am
currently a fellow of the
Intel Science and Technology Center on Pervasive Computing
(ISTC).
Prior to coming to UW, I worked at Cycorp, where my work focused
on using knowledge in the Cyc knowledge base to support machine
learning, as well as security applications of knowledge-based AI.
Research
My main research interests include
robotics, machine learning, and knowledge representation. My current work
focuses on the problem of natural language grounding:
extracting semantically meaningful representations of human
communication, and mapping those representations to aspects of the
physical world in which our robot operates. We use natural language
processing methods to parse human instructions into a formal robot
command language, which can then be executed on a robotic platform
that interacts with the real world.
Videos
My research is
now conducted primarily on the Gambit manipulator arm, which was
developed by a conjunction of UW, Intel, and
Alium Labs.
Our first project was teaching it to play chess robustly in a noisy,
unpredictable environment.
Learning to Parse Natural Language Commands to a Robot Control System.
In Proceedings of the 2012 International Symposium on Experimental Robotics.
In Press.
Cynthia Matuszek, Evan Herbst, Luke Zettlemoyer, Dieter Fox.
Gambit:
A Robust Chess-Playing Robotic System. In Proceedings of the
2011 IEEE International Conference on Robotics and Automation,
Shanghai, China, May 2011. Cynthia Matuszek, Brian Mayton, Roberto Aimi,
Marc Peter Deisenroth, Liefeng Bo,
Robert Chu, Mike Kung, Louis LeGrand, Joshua R. Smith, Dieter Fox.
Common
Sense Reasoning – From Cyc to Intelligent Assistant
In Yang Cai and Julio Abascal (eds.),
Ambient Intelligence in Everyday Life, pp. 1-31, LNAI 3864, Springer,
2006. Kathy Panton, Cynthia Matuszek, Douglas Lenat, David Schneider, Michael Witbrock, Nick Siegel, Blake Shepard.
An Introduction to the Syntax and Content of Cyc. In
Proc. of the 2006 AAAI Spring Symposium on
Formalizing and Compiling Background Knowledge and Its
Applications to Knowledge Representation and Question
Answering, Stanford, CA, March 2006. Cynthia Matuszek, John Cabral, Michael Witbrock, John DeOliveira.
Converting Semantic Meta-Knowledge into Inductive
Bias. In Proc. of the 15th International Conference
on Inductive Logic Programming, Bonn, Germany, August 2005.
John Cabral, Robert C. Kahlert, Cynthia Matuszek, Michael Witbrock, Brett Summers.
Searching for Common Sense: Populating
Cyc from the Web. In Proc. of the Twentieth National
Conference on Artificial Intelligence, Pittsburgh,
Pennsylvania, July 2005.
Cynthia Matuszek, Michael Witbrock, Robert C. Kahlert, John Cabral, David Schneider, Purvesh Shah, Douglas Lenat.
Note: This paper is occasionally mis-attributed to "Cynthia Matuszek Michael".
A Knowledge-Based Approach to
Network Security: Applying Cyc in the Domain of Network Risk
Assessment. In Proc. of the Seventeenth Innovative
Applications of Artificial Intelligence Conference, Pittsburgh,
Pennsylvania, July 2005. Blake Shepard, Cynthia Matuszek, C. Bruce Fraser, William
Wechtenhiser, David Crabbe, Zelal Güngördü, John Jantos,
Todd Hughes, Larry Lefkowitz, Michael Witbrock, Douglas Lenat, Eric Larson.
Gathering and Managing Facts for
Intelligence Analysis. In Proc. of the 2005
International Conference on Intelligence Analysis, McLean,
Virginia, May 2005. David Schneider, Cynthia Matuszek, Purvesh Shah, Robert C. Kahlert,
David Baxter, John Cabral, Michael Witbrock, Douglas Lenat.
Knowledge Begets Knowledge: Steps towards Assisted
Knowledge Acquisition in Cyc. in Papers from the 2005 AAAI
Spring Symposium on Knowledge Collection from Volunteer Contributors
(KCVC), pp. 99-105. Stanford, California, March 2005.
Michael Witbrock, Cynthia Matuszek, Antoine Brusseau, Robert C. Kahlert, C. Bruce Fraser, Douglas Lenat.
Undeadline (nddlnn'), n.
Initially similar to a deadline; however, once presumed over, lurches back
up to resume staggering around eating the brains of the living. Once a
presumed-deadline has become an undeadline, it is likely to require several
more iterations to be put to rest. Related: see extension.