|
|
Background | Objectives | Project
Members | Publications | Related
Links
Background
and Motivation
Cognitive models are models of human performance that represent
human knowledge and internal information management processes.
They provide integrated representations of the knowledge, procedure,
strategies, and problem-solving skills used by humans in domain
or task situations. The execution of the model takes into consideration
the cognitive capabilities and limitations of humans. The key
problem in developing models of human behavior is that there is
no 'standard' cognitive method that is appropriate for all situations.
Usually labor-intensive task analysis is undertaken to make a
detailed mapping of what humans are doing to complete a set of
tasks. Every model is coded as a new set of production rules and
executable procedures (e.g. operators and methods). This approach
is time-consuming, effort- intensive, and does not scale well
for the development of large models.
Research
Objectives
The objective of our research is to provide (1) a methodology,
grounded in computational theory and meeting cognitive requirements
of human performance, to decompose behavior functionality and
map it to a set of software agents and (2) robust computational
methods and software tools that enable increased automation in
reuse and composition of the agents, so that the composite system
reflects the observable behavior of the modeled humans. A key
feature of agent-based development is the encapsulation of knowledge
and processing in autonomous units of behavior/processing. This
distinguishes agents from traditional software components that
are typically passive pieces of code. Current cognitive models
are "monolithic" rather than "compositional" and do not take advantage
of the possibilities of model combination and reuse.
Our overall research hypothesis is that cognitive and behavioral
functionalities can be decomposed in appropriate ways and that
these fragments of behavior can be composed in a semi-automated
fashion similar to the ways that software components can be composed
together. Certain behavior can be treated as modules and composed
to simulate behavior that is more complex. In particular, our
hypothesis is that such reuse and composition will be facilitated
by agent-based software development methods. We propose to enable
cognitive modules to be automatically invoked and composed in
accordance with the task and situation at hand. We have taken
some important steps in this direction with the development of
the RETSINA multiagent infrastructure.
As
computer simulation environments become more complex and as these
environments are increasingly used for training, the need for
increased automation in the construction of these models is becoming
painfully apparent. There are several benefits to being able to
treat portions of models as software components. As in the software
engineering world, modular decomposition of a model minimizes
adverse interactions between the subcomponents. Each portion of
the model can be tested independently, thus contributing to increased
overall reliability of the system. Construction of a new model
requires less time and effort. Therefore increased automation
in model decomposition, reuse and composition of component models
across new applications will allow cognitive models to scale to
complex tasks and simulation environments. Our current work is
in developing composable teamwork models for the MOUT (Military
Operations in Urban Terrain) domain.
Publications
& Presentations
- G. Sukthankar
and K. Sycara, "Automatic
Recognition of Human Team Behaviors," Robotics Institute,
Carnegie Mellon University, in Modeling Others from Observations
(MOO 2005), Workshop at the International Joint Conference
on Artificial Intelligence (IJCAI), Edinburgh, Scotland,
July 2005.
-
- G. Sukthankar,
M. Mandel, K. Sycara, and J. Hodgins, "Modeling
Physical Capabilities of Humanoid Agents Using Motion Capture
Data," in AAMAS'04, July 19-23, 2004, New York, New
York, USA.
- G. Sukthankar, M.
Mandel, K. Sycara, and J.K. Hodgins, "Modeling
Physical Variability for Synthetic MOUT Agents," Proceedings
of 2004 Conference on Behavior Representation in Modeling and
Simulation, May, 2004.
- Agent-based
Composition of Behavior Models
(.ppt)
Related
Links
|
|