This study presents experiments on the learning of object handling
behaviors by a
small humanoid robot using a dynamic neural network model, the recurrent
neural net-
work with parametric bias (RNNPB). The first experiment showed that
after the robot
learned different types of ball handling behaviors using human direct
teaching, the robot
was able to generate adequate ball handling motor sequences situated
to the relative po-
sition between the robots hands and the ball. The same scheme was
applied to a block
handling learning task where it was shown that the robot can switch
among learned dif-
ferent block handling sequences, situated to the ways of interaction
by human supporters.
Our analysis showed that entrainment of the internal memory structures
of the RNNPB
through the interactions of the objects and the human supporters are
the essential mech-
anisms for those observed situated behaviors of the robot.
%0 Journal Article
%1 Ito:2006
%A Ito, M.
%A Noda, K.
%A Hoshino, Y.
%A Tani, J.
%D 2006
%J Neural Networks
%K approach, behavior, dynamical handling learning network neural object of recurrent systems
%P 323-337
%T Dynamic and interactive generation of object handling behaviors by
a small humanoid robot using a dynamic neural network model
%V 19
%X This study presents experiments on the learning of object handling
behaviors by a
small humanoid robot using a dynamic neural network model, the recurrent
neural net-
work with parametric bias (RNNPB). The first experiment showed that
after the robot
learned different types of ball handling behaviors using human direct
teaching, the robot
was able to generate adequate ball handling motor sequences situated
to the relative po-
sition between the robots hands and the ball. The same scheme was
applied to a block
handling learning task where it was shown that the robot can switch
among learned dif-
ferent block handling sequences, situated to the ways of interaction
by human supporters.
Our analysis showed that entrainment of the internal memory structures
of the RNNPB
through the interactions of the objects and the human supporters are
the essential mech-
anisms for those observed situated behaviors of the robot.
@article{Ito:2006,
abstract = {This study presents experiments on the learning of object handling
behaviors by a
small humanoid robot using a dynamic neural network model, the recurrent
neural net-
work with parametric bias (RNNPB). The first experiment showed that
after the robot
learned different types of ball handling behaviors using human direct
teaching, the robot
was able to generate adequate ball handling motor sequences situated
to the relative po-
sition between the robots hands and the ball. The same scheme was
applied to a block
handling learning task where it was shown that the robot can switch
among learned dif-
ferent block handling sequences, situated to the ways of interaction
by human supporters.
Our analysis showed that entrainment of the internal memory structures
of the RNNPB
through the interactions of the objects and the human supporters are
the essential mech-
anisms for those observed situated behaviors of the robot.},
added-at = {2009-06-26T15:25:19.000+0200},
author = {Ito, M. and Noda, K. and Hoshino, Y. and Tani, J.},
biburl = {https://www.bibsonomy.org/bibtex/270d45a77b4cd43244bc22d74e2dcd5ad/butz},
description = {diverse cognitive systems bib},
interhash = {72c7bd167c1ee8788150117c25b4606d},
intrahash = {70d45a77b4cd43244bc22d74e2dcd5ad},
journal = {Neural Networks},
keywords = {approach, behavior, dynamical handling learning network neural object of recurrent systems},
owner = {butz},
pages = {323-337},
timestamp = {2009-06-26T15:25:38.000+0200},
title = {Dynamic and interactive generation of object handling behaviors by
a small humanoid robot using a dynamic neural network model},
volume = 19,
year = 2006
}