Self-Organizing System Forming Strategy of the Global Behavior for Control of an Autonomous Mobile Robot

Abstract

Autonomous mobile robots typically require a preconceived and very detailed navigational model (map) of their intended operating emironment. It requires the presence of a priori information. The creating world model of eironment is a difficult problem requiring a detailed description of all possible routes of the robot motion. Therefore, it is better to describe a behaviour strategy that robot can create the world model of emironment itself during exploration of an unknown territory to achieve efficiently the target from any start position in the future. This strategy assumes fuli self-organization and self-adaptation to the emironment. This paper describes an architecture of such system closely connected with neural network solving the shortest path problem. Such interconnection allows determining the global strategy of the robot behaviour parallel with local strategy formed by reactive navigational system.