A knowledge based fuzzy-probabilistic roadmap method for mobile robot navigation

Abstract

In this paper a novel knowledge based fuzzy control system with Probabilistic Roadmap (PRM) method is proposed for path planning and target seeking behaviour of mobile robot in presence of obstacles. The proposed method runs in two folds, first fold generates the shortest path between the start position to target position in a priori known cluttered environment, wherein the PRM is used to construct straight-lined path by connecting the intermediate nodes. However, the second fold steps help to convert the sharp corners into the smoothen curves throughout the path. The knowledge based fuzzy control system ensures the smooth turns by adjusting the suitable heading angle, there by correcting the position and orientation of the robots to find local/global targets. The presented methodology has been simulated and tested in various environments. Simulation results justify that, the method is not only capable to find an optimal or near-optimal robot path in complex obstacle present environments while avoiding any dead end situation, but also ensures a good control over robot velocity and smooth turning at the turning junctions. In all the simulation experiments it is found that, the method has shorten the path length by more than 5 percent while smoothening and subsequently navigation time was also reduced appreciably.