Visual homing using an associative memory.


Journal Article

Homing is the process by which an autonomous system guides itself to a particular location on the basis of sensory input. In this paper, a method of visual homing using an associative memory based on a simple pattern classifier is described. Homing is accomplished without the use of an explicit world model by utilizing direct associations between learned visual patterns and system motor commands. The method is analyzed in terms of a pattern space and conditions obtained that allow the system performance to be predicted on the basis of statistical measurements on the environment. Results of experiments utilizing the method to guide a robot-mounted camera in a three-dimensional environment are presented.

Full Text

Cited Authors

  • Nelson, RC

Published Date

  • January 1, 1991

Published In

Volume / Issue

  • 65 / 4

Start / End Page

  • 281 - 291

PubMed ID

  • 1932284

Pubmed Central ID

  • 1932284

Electronic International Standard Serial Number (EISSN)

  • 1432-0770

International Standard Serial Number (ISSN)

  • 0340-1200

Digital Object Identifier (DOI)

  • 10.1007/bf00206225


  • eng