Ghent University Academic Bibliography

Advanced

Towards a neural hierarchy of time scales for motor control

Tim Waegeman UGent, Francis wyffels UGent and Benjamin Schrauwen UGent (2012) LECTURE NOTES IN COMPUTER SCIENCE. 7426. p.146-155
abstract
Animals show remarkable rich motion skills which are still far from realizable with robots. Inspired by the neural circuits which generate rhythmic motion patterns in the spinal cord of all vertebrates, one main research direction points towards the use of central pattern generators in robots. On of the key advantages of this, is that the dimensionality of the control problem is reduced. In this work we investigate this further by introducing a multi-timescale control hierarchy with at its core a hierarchy of recurrent neural networks. By means of some robot experiments, we demonstrate that this hierarchy can embed any rhythmic motor signal by imitation learning. Furthermore, the proposed hierarchy allows the tracking of several high level motion properties (e.g.: amplitude and offset), which are usually observed at a slower rate than the generated motion. Although these experiments are preliminary, the results are promising and have the potential to open the door for rich motor skills and advanced control.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
Locomotion Control Hierarchy, Reservoir computing, Adaptive control, Central Pattern Generator, Feedback control
in
LECTURE NOTES IN COMPUTER SCIENCE
Lect. Notes Comput. Sci
editor
Tom Ziemke, Christian Balkenius and John Hallam
volume
7426
issue title
From animals to animals 12
pages
146 - 155
publisher
Springer Berlin
place of publication
Berlin, Germany
conference name
12th International Conference on Simulation of Adaptive Behavior (SAB - 2012)
conference location
Odense, Denmark
conference start
2012-08-27
conference end
2012-08-30
ISSN
0302-9743
ISBN
9783642330926
DOI
10.1007/978-3-642-33093-3_15
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
VABB id
c:vabb:339795
VABB type
VABB-5
id
2976697
handle
http://hdl.handle.net/1854/LU-2976697
alternative location
http://www.springerlink.com/content/j14252t01015/#section=1116200&page=1
date created
2012-08-30 10:24:30
date last changed
2012-08-31 15:48:19
@inproceedings{2976697,
  abstract     = {Animals show remarkable rich motion skills which are still far from realizable with robots. Inspired by the neural circuits which generate rhythmic motion patterns in the spinal cord of all vertebrates, one main research direction points towards the use of central pattern generators in robots. On of the key advantages of this, is that the dimensionality of the control problem is reduced. In this work we investigate this further by introducing a multi-timescale control hierarchy with at its core a hierarchy of recurrent neural networks. By means of some robot experiments, we demonstrate that this hierarchy can embed any rhythmic motor signal by imitation learning. Furthermore, the proposed hierarchy allows the tracking of several high level motion properties (e.g.: amplitude and offset), which are usually observed at a slower rate than the generated motion. Although these experiments are preliminary, the results are promising and have the potential to open the door for rich motor skills and advanced control.},
  author       = {Waegeman, Tim and wyffels, Francis and Schrauwen, Benjamin},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = {Ziemke, Tom and Balkenius, Christian and Hallam, John},
  isbn         = {9783642330926},
  issn         = {0302-9743},
  keyword      = {Locomotion Control Hierarchy,Reservoir computing,Adaptive control,Central Pattern Generator,Feedback control},
  language     = {eng},
  location     = {Odense, Denmark},
  pages        = {146--155},
  publisher    = {Springer Berlin},
  title        = {Towards a neural hierarchy of time scales for motor control},
  url          = {http://dx.doi.org/10.1007/978-3-642-33093-3\_15},
  volume       = {7426},
  year         = {2012},
}

Chicago
Waegeman, Tim, Francis wyffels, and Benjamin Schrauwen. 2012. “Towards a Neural Hierarchy of Time Scales for Motor Control.” In Lecture Notes in Computer Science, ed. Tom Ziemke, Christian Balkenius, and John Hallam, 7426:146–155. Berlin, Germany: Springer Berlin.
APA
Waegeman, T., wyffels, F., & Schrauwen, B. (2012). Towards a neural hierarchy of time scales for motor control. In T. Ziemke, C. Balkenius, & J. Hallam (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 7426, pp. 146–155). Presented at the 12th International Conference on Simulation of Adaptive Behavior (SAB - 2012), Berlin, Germany: Springer Berlin.
Vancouver
1.
Waegeman T, wyffels F, Schrauwen B. Towards a neural hierarchy of time scales for motor control. In: Ziemke T, Balkenius C, Hallam J, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer Berlin; 2012. p. 146–55.
MLA
Waegeman, Tim, Francis wyffels, and Benjamin Schrauwen. “Towards a Neural Hierarchy of Time Scales for Motor Control.” Lecture Notes in Computer Science. Ed. Tom Ziemke, Christian Balkenius, & John Hallam. Vol. 7426. Berlin, Germany: Springer Berlin, 2012. 146–155. Print.