Summary
Last Updated: 9 Jul 2020 (added link to PDF Cosy Book)
The CoSy project is a four-year project costing about 7M
Euro, involving 7 European sites (plus one more to be added
after the first year). The project is inspired by the visionary
EC Framework 6 objective for 'Cognitive Systems':
"To construct physically instantiated ... systems that
can perceive, understand ... and interact with their
environment, and evolve in order to achieve human-like
performance in activities requiring context-(situation and
task) specific knowledge"
We assume that this is far beyond the current state of the
art and will remain so for many years. However we have devised
a set of intermediate targets based on that vision. Achieving
these targets will provide a launch pad for further work
towards the long term vision. In particular we aim to advance
the science of cognitive systems through a
multi-disciplinary investigation of requirements,
design options and trade-offs for human-like,
autonomous, integrated, physical (e.g. robot) systems,
including requirements for architectures, for forms of
representation, for perceptual mechanisms, for learning,
planning, reasoning, motivation, action, communication and
self-understanding. The results of the investigation will
provide the basis for a succession of increasingly ambitious
working robot systems to test and demonstrate the ideas in
scenarios that require integration of components that are
normally studied separately in various sub-branches of AI,
Cognitive Science and Psychology.
News: The CogX project, following on from CoSy began in 2008
Details are in
http://www.cs.bham.ac.uk/research/projects/cogx/
Presentation on CoSy by Henrik I Christensen, Oct 2004
(PDF)
Further details are in the following documents: a short summary of the CoSy project
proposal, and the abstract from
the CoSy project proposal (2 pages) (PDF version). Also, as the project
proceeds more information will be provided at the main CoSy web site, e.g.
in
the
'deliverables' section.
Work proposed for CoSy at Birmingham
This is what we proposed in 2004.
The work at Birmingham will address theoretical issues and
test ideas in the context of building a robot that manipulates
3-D objects on a table top, combining conventional robotic
abilities with a wider range of capabilities, including
conversing in natural language and self-understanding. This is
the PlayMate scenario. This will build on research and
teaching experience in the Intelligent
Robotics Lab.
In addition the Birmingham team leads the theoretical
workpackages on architectures for intelligent agents and forms
of representation. (Many of the issues are explored in talks and
papers
in the Birmingham Cognition
and Affect project, as well as in the CoSy
Papers and Presentations directory.)
Because the problems are so difficult, open ended, and long term
we are developing a methodology for trying, iteratively, to identify
the long term problems and then work back through (partially
ordered) stepping stones to tasks that are worth doing in the near
term to further the long term ends. To aid in this task of
requirements analysis, we have developed an experimental
tool to drive the analysis, using a
matrix
of requirements
organised in two dimensions, with long term, intermediate and short
term requirements forming another dimension.
Technical reports, discussion notes, and presentations by members
of the BHAM CoSy Group are available
here. See
the CoSy Book
for more details
