Presentation 2004/11/20
Navigation of Mobile Robot using Location Map of Place Cells
Toshio TANAKA, Kenji NISHIDA, Takio KURITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Place cells in the rodent hippocampus fire when the rat occupies a restricted portion of an environment. We propose a method of navigating a mobile robot using a location map of place cells and actor-critic reinforcement learning. The location map of place cells is self-organized by neural-gas from position and image data obtained by exploratory movements. The images are captured through Hyper Omni Vision. Then connections between place cells are constructed by Kruskal's algorithm and are used for navigation. The paths to a given goal are learned by actor-critic reinforcement learning algorithm. It is shown by simulation experiments that the mobile robot can reach the given goal by correcting errors even if there are some movement errors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) place cell / neural-gas / mobile robot / navigation / reinforcement learning
Paper # NC2004-104
Date of Issue

Conference Information
Committee NC
Conference Date 2004/11/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Navigation of Mobile Robot using Location Map of Place Cells
Sub Title (in English)
Keyword(1) place cell
Keyword(2) neural-gas
Keyword(3) mobile robot
Keyword(4) navigation
Keyword(5) reinforcement learning
1st Author's Name Toshio TANAKA
1st Author's Affiliation National Institute of Advanced Industrial Science and Technology()
2nd Author's Name Kenji NISHIDA
2nd Author's Affiliation National Institute of Advanced Industrial Science and Technology
3rd Author's Name Takio KURITA
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology
Date 2004/11/20
Paper # NC2004-104
Volume (vol) vol.104
Number (no) 474
Page pp.pp.-
#Pages 6
Date of Issue