Event detection and localization for small mobile robots using reservoir computing

TitleEvent detection and localization for small mobile robots using reservoir computing
Publication TypeJournal Article
Year of Publication2008
AuthorsAntonelo, E. A., B. Schrauwen, and D. Stroobandt
JournalNeural Networks
Volume21
Pagination862–871
Keywordsreservoir computing
Abstract

Reservoir Computing (RC) techniques use a fixed (usually randomly created) recurrent neural network, or more generally any dynamic system, which operates at the edge of stability, where only a linear static readout output layer is trained by standard linear regression methods. In this work, RC is used for detecting complex events in autonomous robot navigation. This can be extended to robot localization tasks which are solely based on a few low-range, high-noise sensory data. The robot thus builds an implicit map of the environment (after learning) that is used for efficient localization by simply processing the stream of distance sensors. These techniques are demonstrated in both a simple simulation environment and in the physically realistic Webots simulation of the commercially available e-puck robot, using several complex and even dynamic environments.

URLhttp://reslab.elis.ugent.be/node/152
DOIdoi:10.1016/j.neunet.2008.06.010
AttachmentSize
robotlocalization_antonelo_nn2008_0.pdf2.68 MB