Ghent University Academic Bibliography

Advanced

Modeling multiple autonomous robot behaviors and behavior switching with a single reservoir computing network

Eric Antonelo UGent, Benjamin Schrauwen UGent and Dirk Stroobandt UGent (2008) IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings. p.1843-1848
abstract
Reservoir Computing (RC) uses a randomly created Recurrent Neural Network as a reservoir of rich dynamics which projects the input to a high dimensional space. These projections are mapped to the desired output using a linear output layer, which is the only part being trained by standard linear regression. In this work, RC is used for imitation learning of multiple behaviors which are generated by different controllers using an intelligent navigation system for mobile robots previously published in literature. Target seeking and exploration behaviors are conflicting behaviors which are modeled with a single RC network. The switching between the learned behaviors is implemented by an extra input which is able to change the dynamics of the reservoir, and in this way, change the behavior of the system. Experiments show the capabilities of Reservoir Computing for modeling multiple behaviors and behavior switching.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
imitation learning, autonomous robot navigation, reservoir computing, behavior switching
in
IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings
issue title
2008 IEEE international conference on systems, man and cybernetics (SMC)
pages
1843 - 1848
publisher
IEEE
place of publication
New York, NY, USA
conference name
2008 IEEE International conference on Systems, Man and Cybernetics (SMC 2008)
conference location
Singapore, Singapore
conference start
2008-10-12
conference end
2008-10-15
Web of Science type
Proceedings Paper
Web of Science id
000269197300317
ISSN
1062-922X
ISBN
9781424423835
DOI
10.1109/ICSMC.2008.4811557
language
English
UGent publication?
yes
classification
P1
id
678821
handle
http://hdl.handle.net/1854/LU-678821
date created
2009-06-05 00:21:42
date last changed
2011-07-28 14:16:55
@inproceedings{678821,
  abstract     = {Reservoir Computing (RC) uses a randomly created Recurrent Neural Network as a reservoir of rich dynamics which projects the input to a high dimensional space. These projections are mapped to the desired output using a linear output layer, which is the only part being trained by standard linear regression. In this work, RC is used for imitation learning of multiple behaviors which are generated by different controllers using an intelligent navigation system for mobile robots previously published in literature. Target seeking and exploration behaviors are conflicting behaviors which are modeled with a single RC network. The switching between the learned behaviors is implemented by an extra input which is able to change the dynamics of the reservoir, and in this way, change the behavior of the system. Experiments show the capabilities of Reservoir Computing for modeling multiple behaviors and behavior switching.},
  author       = {Antonelo, Eric and Schrauwen, Benjamin and Stroobandt, Dirk},
  booktitle    = {IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings},
  isbn         = {9781424423835},
  issn         = {1062-922X},
  keyword      = {imitation learning,autonomous robot navigation,reservoir computing,behavior switching},
  language     = {eng},
  location     = {Singapore, Singapore},
  pages        = {1843--1848},
  publisher    = {IEEE},
  title        = {Modeling multiple autonomous robot behaviors and behavior switching with a single reservoir computing network},
  url          = {http://dx.doi.org/10.1109/ICSMC.2008.4811557},
  year         = {2008},
}

Chicago
Antonelo, Eric, Benjamin Schrauwen, and Dirk Stroobandt. 2008. “Modeling Multiple Autonomous Robot Behaviors and Behavior Switching with a Single Reservoir Computing Network.” In IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings, 1843–1848. New York, NY, USA: IEEE.
APA
Antonelo, E., Schrauwen, B., & Stroobandt, D. (2008). Modeling multiple autonomous robot behaviors and behavior switching with a single reservoir computing network. IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings (pp. 1843–1848). Presented at the 2008 IEEE International conference on Systems, Man and Cybernetics (SMC 2008), New York, NY, USA: IEEE.
Vancouver
1.
Antonelo E, Schrauwen B, Stroobandt D. Modeling multiple autonomous robot behaviors and behavior switching with a single reservoir computing network. IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings. New York, NY, USA: IEEE; 2008. p. 1843–8.
MLA
Antonelo, Eric, Benjamin Schrauwen, and Dirk Stroobandt. “Modeling Multiple Autonomous Robot Behaviors and Behavior Switching with a Single Reservoir Computing Network.” IEEE International Conference on Systems, Man and Cybernetics, Conference Proceedings. New York, NY, USA: IEEE, 2008. 1843–1848. Print.