Labyrinth plays the central role in the architecture. It is not only responsible for long term knowledge, but it acts as the central communication facility for Icarus' other modules.
Labyrinth takes after Cobweb in that it stores information in a heirarchy of probabilistic concepts. New events, plans, actions and physical objects are represented as concepts. amd are classified according to their similarity to pre-existing, abstract concept classes. If there are no sufficiently similar classes, the new concept is abstracted and a new class created. Concepts are classified, within a class, according to an abstraction heirarchy, where abstract concepts are the interior nodes and specific concepts are the exterior nodes. This bottom-up method of classification is also Icarus's principle learning method. And because this learning is done automatically, it is reflexive.
The definition of a concept depends upon what type of knowledge is
being represented.
If the knowledge is about a physical object, then the object is parsed into
component parts (i.e. a table may be parsed into four legs and a flat top).
There also then exists composite concepts, where roles within that concepts
represent conposite parts of an object and have associated with them the
probabilitiy that that part is included in the overall object.
So, for example, a composite concepts of the table would include a role for a
leg plus the probability that something was a table also had a leg.
Actions, events and plans, however, are classified as qualitative states.
Qualitative states consist of a set of objects (which are classified as
above) and an interval of time during which the qualitative aspects of the
state changes in a fixed direction.
Labyrinth classifies problems as pairs of qualitative states, representing the
goal and final states, and it classifies plans as a problem, an operator, an
initial subplan, and a final subplan or problem solving trace.
Labyrinth's concept hierarchy may be is extremely flexible.
In particular, it may learn
non-monotonically.
Labyrinth contains an area, known as the active memory, through which
each module can place requests for information from long term memory, and read
and operate on the results.
The flow of information is best described by following some given perception
by Argus through to the resulting reaction by
Maeander, relating how each component is
involved in creating the overall behaviour.
Return to the top of this architecture.