Advanced search
1 file | 431.55 KB

Design of a central pattern generator using reservoir computing for learning human motion

Francis wyffels (UGent) and Benjamin Schrauwen (UGent)
Author
Organization
Abstract
To generate coordinated periodic movements, robot locomotion demands mechanisms which are able to learn and produce stable rhythmic motion in a controllable way. Because systems based on biological central pattern generators (CPGs) can cope with these demands, these kind of systems are gaining in success. In this work we introduce a novel methodology that uses the dynamics of a randomly connected recurrent neural network for the design of CPGs. When a randomly connected recurrent neural network is excited with one or more useful signals, an output can be trained by learning an instantaneous linear mapping of the neuron states. This technique is known as reservoir computing (RC). We will show that RC has the necessary capabilities to be fruitful in designing a CPG that is able to learn human motion which is applicable for imitation learning in humanoid robots.
Keywords
ROBOTS

Downloads

  • 2009 fwyffels lab-rs.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 431.55 KB

Citation

Please use this url to cite or link to this publication:

Chicago
wyffels, Francis, and Benjamin Schrauwen. 2009. “Design of a Central Pattern Generator Using Reservoir Computing for Learning Human Motion.” In AT-EQUAL 2009: 2009 ECSIS SYMPOSIUM ON ADVANCED TECHNOLOGIES FOR ENHANCED QUALITY OF LIFE: LAB-RS AND ARTIPED 2009, ed. Adrian Stoica, 118–122. Los Alamitos, CA, USA: IEEE Computer Society.
APA
wyffels, F., & Schrauwen, B. (2009). Design of a central pattern generator using reservoir computing for learning human motion. In A. Stoica (Ed.), AT-EQUAL 2009: 2009 ECSIS SYMPOSIUM ON ADVANCED TECHNOLOGIES FOR ENHANCED QUALITY OF LIFE: LAB-RS AND ARTIPED 2009 (pp. 118–122). Presented at the ECSIS Symposium on Advanced Technologies for Enhanced Quality of Life (AT-EQUAL 2009), Los Alamitos, CA, USA: IEEE Computer Society.
Vancouver
1.
wyffels F, Schrauwen B. Design of a central pattern generator using reservoir computing for learning human motion. In: Stoica A, editor. AT-EQUAL 2009: 2009 ECSIS SYMPOSIUM ON ADVANCED TECHNOLOGIES FOR ENHANCED QUALITY OF LIFE: LAB-RS AND ARTIPED 2009. Los Alamitos, CA, USA: IEEE Computer Society; 2009. p. 118–22.
MLA
wyffels, Francis, and Benjamin Schrauwen. “Design of a Central Pattern Generator Using Reservoir Computing for Learning Human Motion.” AT-EQUAL 2009: 2009 ECSIS SYMPOSIUM ON ADVANCED TECHNOLOGIES FOR ENHANCED QUALITY OF LIFE: LAB-RS AND ARTIPED 2009. Ed. Adrian Stoica. Los Alamitos, CA, USA: IEEE Computer Society, 2009. 118–122. Print.
@inproceedings{726873,
  abstract     = {To generate coordinated periodic movements, robot locomotion demands mechanisms which are able to learn and produce stable rhythmic motion in a controllable way. Because systems based on biological central pattern generators (CPGs) can cope with these demands, these kind of systems are gaining in success. In this work we introduce a novel methodology that uses the dynamics of a randomly connected recurrent neural network for the design of CPGs. When a randomly connected recurrent neural network is excited with one or more useful signals, an output can be trained by learning an instantaneous linear mapping of the neuron states. This technique is known as reservoir computing (RC). We will show that RC has the necessary capabilities to be fruitful in designing a CPG that is able to learn human motion which is applicable for imitation learning in humanoid robots.},
  author       = {wyffels, Francis and Schrauwen, Benjamin},
  booktitle    = {AT-EQUAL 2009: 2009 ECSIS SYMPOSIUM ON ADVANCED TECHNOLOGIES FOR ENHANCED QUALITY OF LIFE: LAB-RS AND ARTIPED 2009},
  editor       = {Stoica, Adrian},
  isbn         = {9780769537535},
  keyword      = {ROBOTS},
  language     = {eng},
  location     = {Iasi, Roemania},
  pages        = {118--122},
  publisher    = {IEEE Computer Society},
  title        = {Design of a central pattern generator using reservoir computing for learning human motion},
  url          = {http://dx.doi.org/10.1109/AT-EQUAL.2009.32},
  year         = {2009},
}

Altmetric
View in Altmetric
Web of Science
Times cited: