Advanced search

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

Eric Antonelo (UGent) , Benjamin Schrauwen (UGent) and Dirk Stroobandt (UGent)
Author
Organization
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.
Keywords
imitation learning, autonomous robot navigation, reservoir computing, behavior switching

Citation

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

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.
@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},
}

Altmetric
View in Altmetric
Web of Science
Times cited: