|
Results:
-
Integration of the Modeling Field Theory
algorithm for the classification of objects (Satellite
EOARD workshop)
with a model of the acquisition of language in cognitive
robotics.
we have applied and extended our previous modified version of
the MFT algorithm (ICANN 06) to deal with the scaling up of the
robotic agent’s action repertoire
Description:
-
First agents learn to classify 112 different
actions inspired by an alphabet system (the semaphore flag
signaling system).
-
In the second stage, agents also learn a
lexical item to name each action. At this stage the agents
will start to describe the action as a “word” comprised of
three letters (consonant - vowel - consonant).
-
In the
final stage we are taking a step backwards in the
categorization of actions. We are breaking down the action
into basic gestures in order to generate composite actions
Results:
-
agents are able to acquire a complex set of
actions by building sensorimotor concept-models -
view
results
-
agents are able to learn a lexicon to
describe these objects/actions through a process of cultural
learning - view results
-
agents
learn actions as basic gestures in order to generate
composite actions.
view results
Up -
Back
|
