Abstract (EN):
A real autonomous mobile robot should be able to deal with a wide range of tasks and environments and to evolve through the acquisition and adaptation of its own navigation competencies. This is our major concern in the development of ARCoS, an Autonomous mobile Robot Control System, whose main purpose is to transform a mobile robot platform in an autonomous mobile robot. In this paper we are going to focus on the agents' architecture, which are responsible for those navigation competencies. Through the integration of a fuzzy control system together with a neural network, we allow an autonomous mobile robot to acquire as well as to adapt, in a simple way, the needed navigation competencies to perform more complex navigation tasks. These more sophisticated tasks involve the integration and co-operation of several different agents that are responsible for elementary navigation competencies.
Language:
English
Type (Professor's evaluation):
Scientific
No. of pages:
6