A MULTI-AGENT ARCHITECTURE WITH HIERARCHICAL FUZZY CONTROLLER FOR A MOBILE ROBOT

Maïssa Boujelben, Chokri Rekik, and Nabil Derbel

Keywords

Mobile robots, multi-agent architecture, hierarchical fuzzy system, obstacle avoidance

Abstract

The use of multi-agent architecture allows the development of a control system for autonomous navigation of mobile robots. This architecture helps to break the complexity of the task to achieve: the system is composed into different, independent and asynchronous behaviours which are coordinated to obtain the desired results. In this paper, we are interested specifically in controlling the robot to reach the goal position without colliding obstacles. Therefore, we have modelled these two behaviours (reaching the goal position and obstacle avoidance) by two agents. The first agent is based on fuzzy logic control, while, for the other one, a hierarchical fuzzy system have been used. These agents may provide contradictory actions. So that, a coordination approach have been proposed in order to remove conflict situations.

Important Links:

Go Back