Guided Self-organisation for Autonomous Robot Development

Georg Martius; J. Michael Herrmann; Ralf Der

doi:10.1007/978-3-540-74913-4_77

Guided Self-organisation for Autonomous Robot Development

Georg Martius, J. Michael Herrmann, Ralf Der

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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.

Original language	English
Title of host publication	Advances in Artificial Life
Subtitle of host publication	9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings
Editors	Fernando Almeida e Costa, Luis Mateus Rocha, Ernesto Costa, Inman Harvey, António Coutinho
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	766-775
Number of pages	10
ISBN (Electronic)	978-3-540-74913-4
ISBN (Print)	978-3-540-74912-7
DOIs	https://doi.org/10.1007/978-3-540-74913-4_77
Publication status	Published - 2007

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	4648
ISSN (Print)	0302-9743

Access to Document

10.1007/978-3-540-74913-4_77

http://link.springer.com/chapter/10.1007%2F978-3-540-74913-4_77

Cite this

Martius, G., Herrmann, J. M., & Der, R. (2007). Guided Self-organisation for Autonomous Robot Development. In F. Almeida e Costa, L. M. Rocha, E. Costa, I. Harvey, & A. Coutinho (Eds.), Advances in Artificial Life: 9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings (pp. 766-775). (Lecture Notes in Computer Science; Vol. 4648). Springer. https://doi.org/10.1007/978-3-540-74913-4_77

Martius, Georg ; Herrmann, J. Michael ; Der, Ralf. / Guided Self-organisation for Autonomous Robot Development. Advances in Artificial Life: 9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings. editor / Fernando Almeida e Costa ; Luis Mateus Rocha ; Ernesto Costa ; Inman Harvey ; António Coutinho. Berlin, Heidelberg : Springer, 2007. pp. 766-775 (Lecture Notes in Computer Science).

@inproceedings{4b4aa9e5ecd0424dace73d7005be585e,

title = "Guided Self-organisation for Autonomous Robot Development",

abstract = "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.",

author = "Georg Martius and Herrmann, {J. Michael} and Ralf Der",

year = "2007",

doi = "10.1007/978-3-540-74913-4_77",

language = "English",

isbn = "978-3-540-74912-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "766--775",

editor = "{Almeida e Costa}, Fernando and Rocha, {Luis Mateus} and Ernesto Costa and Inman Harvey and Ant{\'o}nio Coutinho",

booktitle = "Advances in Artificial Life",

address = "United Kingdom",

}

Martius, G, Herrmann, JM & Der, R 2007, Guided Self-organisation for Autonomous Robot Development. in F Almeida e Costa, LM Rocha, E Costa, I Harvey & A Coutinho (eds), Advances in Artificial Life: 9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings. Lecture Notes in Computer Science, vol. 4648, Springer, Berlin, Heidelberg, pp. 766-775. https://doi.org/10.1007/978-3-540-74913-4_77

Guided Self-organisation for Autonomous Robot Development. / Martius, Georg; Herrmann, J. Michael; Der, Ralf.
Advances in Artificial Life: 9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings. ed. / Fernando Almeida e Costa; Luis Mateus Rocha; Ernesto Costa; Inman Harvey; António Coutinho. Berlin, Heidelberg: Springer, 2007. p. 766-775 (Lecture Notes in Computer Science; Vol. 4648).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Guided Self-organisation for Autonomous Robot Development

AU - Martius, Georg

AU - Herrmann, J. Michael

AU - Der, Ralf

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-540-74913-4_77

DO - 10.1007/978-3-540-74913-4_77

M3 - Conference contribution

SN - 978-3-540-74912-7

T3 - Lecture Notes in Computer Science

SP - 766

EP - 775

BT - Advances in Artificial Life

A2 - Almeida e Costa, Fernando

A2 - Rocha, Luis Mateus

A2 - Costa, Ernesto

A2 - Harvey, Inman

A2 - Coutinho, António

PB - Springer

CY - Berlin, Heidelberg

ER -

Martius G, Herrmann JM, Der R. Guided Self-organisation for Autonomous Robot Development. In Almeida e Costa F, Rocha LM, Costa E, Harvey I, Coutinho A, editors, Advances in Artificial Life: 9th European Conference, ECAL 2007, Lisbon, Portugal, September 10-14, 2007. Proceedings. Berlin, Heidelberg: Springer. 2007. p. 766-775. (Lecture Notes in Computer Science). doi: 10.1007/978-3-540-74913-4_77

Guided Self-organisation for Autonomous Robot Development

Abstract

Publication series

Access to Document

Fingerprint

Cite this