[1]
|
F. Hesse, G. Martius, R. Der, and J. M. Herrmann.
A sensor-based learning algorithm for the self-organization of robot
behavior.
Algorithms, 2(1):398-409, 2009.
[ bib |
http ]
Ideally, sensory information forms the only source of information to a robot. We consider an algorithm for the self-organization of a controller. At short time scales the controller is merely reactive but the parameter dynamics and the acquisition of knowledge by an internal model lead to seemingly purposeful behavior on longer time scales. As a paradigmatic example, we study the simulation of an underactuated snake-like robot. By interacting with the real physical system formed by the robotic hardware and the environment, the controller achieves a sensitive and body-specific actuation of the robot.
|
[2]
|
F. Hesse, R. Der, and J. M. Herrmann.
Reflexes from self-organizing control in autonomous robots.
In L. Berthouze, C. G. Prince, M. Littman, H. Kozima, and
C. Balkenius, editors, 7th International Conference on Epigenetic
Robotics: Modelling Cognitive Development in Robotic Systems, Rutgers
University, Piscataway, NJ, USA, volume 134 of Cognitive Studies,
pages 37-44. Lund University, 2007.
[ bib |
.pdf ]
Homeokinetic learning provides a route to
the self-organization of elementary behaviors
in autonomous robots by establishing
low-level sensomotoric loops. Strength and
duration of the internal parameter changes
which are caused by the homeokinetic adaptation
provide a natural evaluation of external
states, which can be used to incorporate information
from additional sensory inputs and
to extend the function of the low-level behavior
to more general situations. We illustrate
the approach by two examples, a mobile
robot and a human-like hand which are
driven by the same low-level scheme, but use
the second-order information in different ways
to achieve either risk avoidance and unconstrained
movement or constrained movement.
While the low-level adaptation follows a set of
rigid learning rules, the second-order learning
exerts a modulatory effect to the elementary
behaviors and to the distribution of their inputs.
|
[3]
|
G. Martius, J. M. Herrmann, and R. Der.
Guided self-organisation for autonomous robot development.
In A. e Costa and Francesco, editors, Advances in Artificial
Life 9th European Conference, ECAL 2007, Lisbon, Portugal, volume 4648 of
Lecture Notes in Computer Science, pages 766-775. Springer, 2007.
[ bib |
.pdf ]
The paper presents a method to guide the self-organised development of behaviours
of autonomous robots.
In earlier publications we demonstrated how to use the homeokinesis principle
and dynamical systems theory to obtain self-organised playful but goal-free behaviour.
Now we extend this framework by reinforcement signals.
We validate the mechanisms with two experiment with a spherical robot.
The first experiment aims at fast motion, where the robot reaches on average
about twice the speed of a not reinforcement robot.
In the second experiment spinning motion is rewarded and we demonstrate
that the robot successfully develops
pirouettes and curved motion which
only rarely occur among the natural behaviours of the robot.
|
[4]
|
R. Der, G. Martius, and F. Hesse.
Let it roll - emerging sensorimotor coordination in a spherical
robot.
In L. M. Rocha, L. S. Yaeger, M. A. Bedau, D. Floreano, R. L.
Goldstone, and A. Vespignani, editors, Artificial Life X : Proceedings
of the Tenth International Conference on the Simulation and Synthesis of
Living Systems, pages 192-198. International Society for Artificial Life,
MIT Press, August 2006.
[ bib |
.pdf ]
Self-organization and the phenomenen of emergence play an
essential role in living systems and form a challenge to
artificial life systems. This is not only because systems
become more life like but also since self-organization may
help in reducing the design efforts in creating complex
behavior systems. The present paper exemplifies a general
approach to the self-organization of behavior which has
been developed and tested in various examples in recent
years. We apply this approach to a spherical robot driven
by shifting internal masses. The complex physics of this
robotic object is completely unknown to the controller.
Nevertheless after a short time the robot develops
systematic rolling movements covering large distances with
high velocity. In a hilly landscape it is capable of
manoeuvering out of the basins and in landscapes with a
fixed rotational geometry the robot more or less adatps its
movements to this geometry - the controller so to say
develops a kind of feeling for its environment although
there are no sensors for measuring the positions or the
velocity of the robot. We argue that this behavior is a
result of the spontaneous symmetry breaking effects which
are responsible for the emergence of behavior in our
approach.
|
[5]
|
R. Der and G. Martius.
From motor babbling to purposive actions: Emerging self-exploration
in a dynamical systems approach to early robot development.
In S. Nolfi, G. Baldassarre, R. Calabretta, J. C. T. Hallam,
D. Marocco, J.-A. Meyer, O. Miglino, and D. Parisi, editors, From
Animals to Animats 9, 9th International Conference on Simulation of Adaptive
Behavior, SAB 2006, Rome, Italy, September 25-29, 2006, Proceedings, volume
4095 of Lecture Notes in Computer Science, pages 406-421. Springer,
2006.
[ bib |
.pdf ]
Self-organization and the phenomenon of emergence play an
essential role in living systems and form a challenge to artificial life systems.
This is not only because systems become more lifelike, but also since self-organization
may help in reducing the design efforts in creating complex behavior systems.
The present paper studies self-exploration based on a general approach to the
self-organization of behavior, which has been developed and tested in various
examples in recent years. This is a step towards autonomous early robot development.
We consider agents under the close sensorimotor coupling paradigm with a certain
cognitive ability realized by an internal forward model.
Starting from tabula rasa initial conditions we overcome the bootstrapping problem and
show emerging self-exploration.
Apart from that, we analyze the effect of limited actions,
which lead to deprivation of the world model.
We show that our paradigm explicitly avoids this
by producing purposive actions in a natural way.
Examples are given using a simulated simple wheeled robot and a
spherical robot driven by shifting internal masses.
|
[6]
|
R. Der, F. Hesse, and G. Martius.
Rocking stamper and jumping snake from a dynamical system approach to
artificial life.
Adaptive Behavior, 14(2):105-115, 2006.
[ bib |
DOI |
.pdf ]
Keywords: autonomous robots, self-organization, homeostasis, homeokinesis, dynamical systems, learning
|
[7]
|
R. Der.
Homeokinesis and the moderation of complexity in neural systems.
Neural Computation, to be submitted, 2005.
[ bib |
.pdf ]
|
[8]
|
R. Der, F. Hesse, and G. Martius.
Learning to feel the physics of a body.
In CIMCA '05: Proceedings of the International Conference on
Computational Intelligence for Modelling, Control and Automation and
International Conference on Intelligent Agents, Web Technologies and Internet
Commerce Vol-2 (CIMCA-IAWTIC'06), pages 252-257, Washington, DC, USA, 2005.
IEEE Computer Society.
[ bib |
.pdf ]
Despite the tremendous progress in robotic hardware and in
both sensorial and computing efficiencies the performance
of contemporary autonomous robots is still far below that
of simple animals. This has triggered an intensive search
for alternative approaches to the control of robots. The
present paper exemplifies a general approach to the
self-organization of behavior which has been developed and
tested in various examples in recent years. We apply this
approach to an underactuated snake like artifact with a
complex physical behavior which is not known to the
controller. Due to the weak forces available, the
controller so to say has to develop a kind of feeling for
the body which is seen to emerge from our approach in a
natural way with meandering and rotational collective modes
being observed in computer simulation experiments.
|
[9]
|
R. Der, F. Hesse, and R. Liebscher.
Contingent robot behavior generated by self-referential dynamical
systems.
Autonomous robots, 2005.
submitted.
[ bib |
.pdf ]
|
[10]
|
R. Der.
Videos of self-organised robot behavior.
http://robot.informatik.uni-leipzig.de/Videos, 2005.
[ bib ]
|
[11]
|
R. Der.
Between homeostasis and autopoiesis - theory and practice of
self-referential machines.
Talk given at the Max-Planck Institut for Mathematics in the
Sciences, October 2004.
[ bib ]
|
[12]
|
R. Der.
The homeokinetic neuron in the sensorimotor loop.
Neural computation, 2004.
to be submitted.
[ bib |
.pdf ]
|
[13]
|
M. Herrmann, M. Hoicki, and R. Der.
On ashby's homeostat: A formal model of adaptive regulation.
In S. Schaal, editor, From Animals to Animats, pages 324 -
333. MIT Press, 2004.
[ bib |
.pdf ]
|
[14]
|
R. Der, F. Hesse, and R. Liebscher.
Self-organized exploration and automatic sensor integration from the
homeokinetic principle.
In Proc. 3rd Workshop on Self-Organization of AdaptiVE Behavior
(SOAVE'04), Fortschritt-Berichte VDI, Reihe 10, Nr. 743, pages 220-230.
VDI-Verlag, 2004.
[ bib |
.pdf ]
|
[15]
|
R. Der.
Video of robot in cluttered environment.
http://robot.informatik.uni-leipzig.de/Videos/Pioneer/2004/maze2.wmv,
2004.
[ bib ]
|
[16]
|
R. Der.
Video of robot in cluttered environment.
http://robot.informatik.uni-leipzig.de/Videos/Pioneer/2004/maze4.wmv,
2004.
[ bib ]
|
[17]
|
R. Der.
Basic homeokinetic control.
http://www.informatik.uni-leipzig.de/~der/Forschung/maze1.wmv,
2003.
[ bib ]
|
[18]
|
R. Der.
Basic homeokinetic control II.
http://www.informatik.uni-leipzig.de/~der/Forschung/maze2.wmv,
2003.
[ bib ]
|
[19]
|
R. Der.
Basic homeokinetic control III.
http://www.informatik.uni-leipzig.de/~der/Forschung/maze3.wmv,
2003.
[ bib ]
|
[20]
|
R. Der.
Basic homeokinetic control IV.
http://www.informatik.uni-leipzig.de/~der/Forschung/maze4.wmv,
2003.
[ bib ]
|
[21]
|
R. Der, M. Herrmann, and R. Liebscher.
Homeokinetic approach to autonomous learning in mobile robots.
In R. Dillman, R. D. Schraft, and H. W"orn, editors, Robotik
2002, number 1679 in VDI-Berichte, pages 301-306. 2002.
[ bib ]
|
[22]
|
R. Der, M. Herrmann, and M. Holicki.
Self-organization in sensor-motor loops by the homeokinetic
principle.
Verhandlungen der Deutschen Physikalischen Gesellschaft, page
510, 1 2002.
[ bib ]
|
[23]
|
R. Der and R. Liebscher.
True autonomy from self-organized adaptivity.
In Proc. Workshop Biologically Inspired Robotics, Bristol,
2002.
[ bib |
.pdf ]
|
[24]
|
R. Der.
Self-organized acquisition of situated behavior.
Theory Biosci., 120:179-187, 2001.
[ bib ]
|
[25]
|
R. Der.
Self-organized robot behavior from the principle of homeokinesis.,
1999.
[ bib |
.ps ]
|
[26]
|
R. Der, U. Steinmetz, and F. Pasemann.
Homeokinesis - a new principle to back up evolution with learning.
In Computational Intelligence for Modelling, Control, and
Automation, volume 55 of Concurrent Systems Engineering Series, pages
43-47, Amsterdam, 1999. IOS Press.
[ bib |
.ps ]
|
[27]
|
R. Der, O. Lummer, and T. List.
Incremental nonlinear dynamic data reconciliation.
Technical Report 3/98, Institut für Informatik,
Universität Leipzig, 1997.
[ bib |
.ps ]
|
[28]
|
R. Der and M. Herrmann.
Self-adjusting reinforcement learning.
In Nonlinear Theory and Applications - NOLTA 96, pages
441 - 444, 1996.
[ bib |
.ps.gz ]
|
[29]
|
R. Der and M. Herrmann.
Efficient Q-learning by division of labour.
In Proc. International Conference on Artificial Neural Networks
- ICANN95, pages 129 - 134, 1995.
[ bib |
.ps.gz ]
|
[30]
|
R. Der.
The langevin method in the dynamics of learning.
J. Phys. A: Math. Gen., (23):L763-6, 1990.
[ bib ]
|
[31]
|
R. Der.
Systems under colored noise.
Physica A, 154:421 - 451, 1989.
[ bib ]
|
[32]
|
R. Der.
Systems under colored noise.
Physica A, 154:421-451, 1989.
[ bib ]
|
[33]
|
R. Der.
The time local view of nonequilibrium statistical mechanics I.
J. Stat. Phys., 46:349-390, 1987.
[ bib ]
|
[34]
|
R. Der.
The time local view of nonequilibrium statistical mechanics II.
J. Stat. Phys., 46:391-425, 1987.
[ bib ]
|
[35]
|
R. Der.
The time local view of nonequilibrium statistical mechanics I.
J. Stat. Phys., 46:349-390, 1987.
[ bib ]
|
[36]
|
R. Der.
The time local view of nonequilibrium statistical mechanics II.
J. Stat. Phys., 46:391-425, 1987.
[ bib ]
|
[37]
|
R. Der.
Retarded and instantaneous evolution equations for macroobsevables in
nonequilibrium statistical mechanics.
Physica, 132A:74-93, 1985.
[ bib ]
|