Predictive terrain contour mapping for a legged robot

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)22_Publication in policy or professional journal

7 Scopus Citations
View graph of relations

Author(s)

  • S. Galt
  • B. L. Luk

Detail(s)

Original languageEnglish
Pages (from-to)129-133
Journal / PublicationIEE Conference Publication
Issue number440
Publication statusPublished - 1997
Externally publishedYes

Conference

TitleProceedings of the 1997 5th International Conference on Artificial Neural Networks
CityCambridge, UK
Period7 - 9 July 1997

Abstract

Most legged robots have to negotiate unknown environments with little or no descriptive terrain data as autonomous terrain mapping facilities for legged robots are limited. A predictive terrain contour mapping strategy is proposed which considers the use of feed-forward neural networks to predict terrain contours in unstructured environments based on sample data extracted from the walking surface during the locomotion of Robug III - an eight legged, pneumatically powered walking and climbing robot. In simulation, it is shown that the prediction performance is very acceptable; practical tests are conducted on a prototype robot leg and the results are compared with those obtained in simulation.

Citation Format(s)

Predictive terrain contour mapping for a legged robot. / Galt, S.; Luk, B. L.
In: IEE Conference Publication, No. 440, 1997, p. 129-133.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)22_Publication in policy or professional journal