Reference : Modeling Multiple Autonomous Robot Behaviors and Behavior Switching with a Single Res...
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/36479
Modeling Multiple Autonomous Robot Behaviors and Behavior Switching with a Single Reservoir Computing Network
English
Antonelo, Eric Aislan mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) >]
Schrauwen, Benjamin [> >]
Stroobandt, Dirk [> >]
2008
Proceedings of the 2008 IEEE International Conference on Systems, Man and Cybernetics
1843-1848
Yes
International
978-1-4244-2383-5
Singapore
IEEE International Conference on Systems, Man and Cybernetics
12-10-2008 to 15-10-2008
[en] 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.
http://hdl.handle.net/10993/36479
10.1109/ICSMC.2008.4811557
https://ieeexplore.ieee.org/document/4811557/

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2008_eric_smc_Modeling Multiple Autonomous Robot Behaviors.pdfAuthor postprint813.18 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.