Ghent University Academic Bibliography

Advanced

Mobile Robot Control in the Road Sign Problem using Reservoir Computing Networks

Eric Antonelo UGent, Benjamin Schrauwen UGent and Dirk Stroobandt UGent (2008) IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION. p.911-916
abstract
In this work we tackle the road sign problem with Reservoir Computing (RC) networks. The T-maze task (a particular form of the road sign problem) consists of a robot in a T-shaped environment that must reach the correct goal (left or right arm of the T-maze) depending on a previously received input sign. It is a control task in which the delay period between the sign received and the required response (e.g., turn right or left) is a crucial factor. Delayed response tasks like this one form a temporal problem that can be handled very well by RC networks. Reservoir Computing is a biologically plausible technique which overcomes the problems of previous algorithms such as Backpropagation Through Time - which exhibits slow (or non-) convergence on training. RC is a new concept that includes a fast and efficient training algorithm. We show that this simple approach can solve the T-maze task efficiently.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
t-maze, imitation learning, Reservoir computing, road sign problem
in
IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
pages
6 pages
publisher
IEEE
place of publication
New York
conference name
IEEE International Conference on Robotics and Automation (ICRA)
conference location
Pasadena
conference start
2008-05-19
conference end
2008-05-23
Web of Science type
Proceedings Paper
Web of Science id
000258095000144
ISSN
1050-4729
ISBN
978-1-4244-1646-2
language
English
UGent publication?
yes
classification
P1
copyright statement
I have transferred the copyright for this publication to the publisher
id
680344
handle
http://hdl.handle.net/1854/LU-680344
date created
2009-06-05 14:39:42
date last changed
2009-06-30 15:25:00
@inproceedings{680344,
  abstract     = {In this work we tackle the road sign problem with Reservoir Computing (RC) networks. The T-maze task (a particular form of the road sign problem) consists of a robot in a T-shaped environment that must reach the correct goal (left or right arm of the T-maze) depending on a previously received input sign. It is a control task in which the delay period between the sign received and the required response (e.g., turn right or left) is a crucial factor. Delayed response tasks like this one form a temporal problem that can be handled very well by RC networks. Reservoir Computing is a biologically plausible technique which overcomes the problems of previous algorithms such as Backpropagation Through Time - which exhibits slow (or non-) convergence on training. RC is a new concept that includes a fast and efficient training algorithm. We show that this simple approach can solve the T-maze task efficiently.},
  author       = {Antonelo, Eric and Schrauwen, Benjamin and Stroobandt, Dirk},
  booktitle    = {IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION},
  isbn         = {978-1-4244-1646-2},
  issn         = {1050-4729},
  keyword      = {t-maze,imitation learning,Reservoir computing,road sign problem},
  language     = {eng},
  location     = {Pasadena},
  pages        = {911--916},
  publisher    = {IEEE},
  title        = {Mobile Robot Control in the Road Sign Problem using Reservoir Computing Networks},
  year         = {2008},
}

Chicago
Antonelo, Eric, Benjamin Schrauwen, and Dirk Stroobandt. 2008. “Mobile Robot Control in the Road Sign Problem Using Reservoir Computing Networks.” In Ieee International Conference on Robotics and Automation, 911–916. New York: IEEE.
APA
Antonelo, E., Schrauwen, B., & Stroobandt, D. (2008). Mobile Robot Control in the Road Sign Problem using Reservoir Computing Networks. IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (pp. 911–916). Presented at the IEEE International Conference on Robotics and Automation (ICRA), New York: IEEE.
Vancouver
1.
Antonelo E, Schrauwen B, Stroobandt D. Mobile Robot Control in the Road Sign Problem using Reservoir Computing Networks. IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION. New York: IEEE; 2008. p. 911–6.
MLA
Antonelo, Eric, Benjamin Schrauwen, and Dirk Stroobandt. “Mobile Robot Control in the Road Sign Problem Using Reservoir Computing Networks.” Ieee International Conference on Robotics and Automation. New York: IEEE, 2008. 911–916. Print.