DocumentCode
1646533
Title
Self-organized modulation of a neural robot controller
Author
Bergfeldt, Nicklas ; Linaker, Fredrik
Author_Institution
Dept. of Comput. Sci., Univ. of Skovde, Sweden
Volume
1
fYear
2002
fDate
6/24/1905 12:00:00 AM
Firstpage
495
Lastpage
500
Abstract
We show how a simple layered system can self-organize into a set of distinct states and qualitatively different behaviors as a result of the learning a robotic delayed response task. Our approach is based on an architecture where higher levels are able to dynamically modulate the lower reactive mapping when needed
Keywords
computerised navigation; mobile robots; modulation; neurocontrollers; self-organising feature maps; unsupervised learning; delayed response task; mobile robot; neurocontrol; recurrent neural network; self-organized modulation; task learning; Computer science; Delay; Mobile robots; Navigation; Neural networks; Robot control; Robot sensing systems; Switches; Testing; Turning;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location
Honolulu, HI
ISSN
1098-7576
Print_ISBN
0-7803-7278-6
Type
conf
DOI
10.1109/IJCNN.2002.1005522
Filename
1005522
Link To Document