A hybrid architecture for autonomous navigation using a CBR reactive layer

  • Authors:
  • C. Urdiales;E. J. Pérez;F. Sandoval;J. Vázquez-Salceda

  • Affiliations:
  • -;-;-;-

  • Venue:
  • IAT '03 Proceedings of the IEEE/WIC International Conference on Intelligent Agent Technology
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a hybrid architecture for autonomous robotnavigation. It includes a deliberative layer that hierarchicallyextracts a global path from ageometrical-topological model of theenvironment. This path is decomposed into a set of partial goals.Then, anew case-based reasoning based reactive layer capable oflearning new local navigation strategies moves from each partialgoal to the next. The architecture has been successfully tested inreal dynamic environments.