[en] Animals such as rats have innate and robust localization capabilities which allow them to navigate to goals in a maze. The rodent’s hippocampus, with the so called place cells, is responsible for such spatial processing. This work seeks to model these place cells using either supervised or unsupervised learning techniques. More specifically, we use a randomly generated recurrent neural network (the reservoir) as a non-linear temporal kernel to expand the input to a rich dynamic space. The reservoir states are linearly combined (using linear regression) or, in the unsupervised case, are used for extracting slowly-varying features from the input to form place cells (the architectures are organized in hierarchical layers). Experiments show that a small mobile robot with cheap and low-range distance sensors can learn to self-localize in its environment with the proposed systems.
Disciplines :
Computer science
Author, co-author :
ANTONELO, Eric Aislan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Schrauwen, Benjamin
External co-authors :
yes
Language :
English
Title :
On Different Learning Approaches with Echo State Networks for Localization of Small Mobile Robots
Publication date :
2009
Event name :
IX Brazilian Conference on Neural Networks (CBRN)
Event date :
25-10-2009 to 28-10-2009
Audience :
International
Main work title :
Proceedings of the IX Brazilian Conference on Neural Networks