Skip to main content

Real-time sensor data for efficient localisation employing a weightless neural system

McElroy, Ben and Gillham, Michael and Howells, Gareth and Kelly, Stephen W. and Spurgeon, Sarah K. and Pepper, Matthew G. (2012) Real-time sensor data for efficient localisation employing a weightless neural system. In: 2012 1st International Conference on Systems and Computer Science (ICSCS). IEEE, pp. 1-5. ISBN 978-1-4673-0673-7. E-ISBN 978-1-4673-0672-0. (doi:10.1109/IConSCS.2012.6502448)

Abstract

Mobile robotic localisation obtained from simple sensor data potentially offers real-time real-world integration. Computationally highly efficient Weightless Neural Networks, when used for location determination, further enhances performance potential. This paper introduces techniques for the identification of rooms or locations in the absence of complex and succinct information. Using simple floor colour and texture, and room geometrics from ranging data, although inherent uncertainties exist, these limited simple fused real-time sensor data can be easily resolved into a room identification criterion using architectures generated by a Genetic Algorithm technique applied to a Weightless Neural Network Architecture.

Item Type: Book section
DOI/Identification number: 10.1109/IConSCS.2012.6502448
Uncontrolled keywords: genetic algorithms; geometry; mobile robots; neurocontrollers; sensors
Subjects: T Technology > TK Electrical engineering. Electronics. Nuclear engineering > TK7800 Electronics > TK7880 Applications of electronics > TK7882.P3 Pattern recognition systems
Divisions: Faculties > Sciences > School of Engineering and Digital Arts > Image and Information Engineering
Faculties > Sciences > School of Engineering and Digital Arts > Instrumentation, Control and Embedded Systems
Depositing User: M. Gillham
Date Deposited: 01 Feb 2014 20:40 UTC
Last Modified: 24 Sep 2019 11:29 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/38137 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year