Abstract
Realization of autonomous behavior in mobile robots,
using fuzzy logic control, requires formulation of
rules which are collectively responsible for necessary
levels of intelligence. Such a collection of rules can
be conveniently decomposed and efficiently implemented
as a hierarchy of fuzzy-behaviors. This article
describes how this can be done using a behavior-based
architecture. A behavior hierarchy and mechanisms of
control decision-making are described. In addition, an
approach to behavior coordination is described with
emphasis on evolution of fuzzy coordination rules using
the genetic programming (GP) paradigm. Both
conventional GP and steady-state GP are applied to
evolve a fuzzy-behavior for sensor-based goal-seeking.
The usefulness of the behavior hierarchy, and partial
design by GP, is evident in performance results of
simulated autonomous navigation.
Users
Please
log in to take part in the discussion (add own reviews or comments).