Intelligent Adaptive RRT^* Path Planning Algorithm for Mobile Robots

Abstract

In this paper a new variant of the widely used Rapidly exploring Random Tree (RRT*) algorithm is proposed. The main goal of this variant is to improve the efficiency of the generated path, in both computation time and the quality of the path. In a previous work by the authors, an improved version RRT*N was proposed, where a normal probability distribution was used to control the generation of the random nodes. The proposed variant utilizes an intelligent fuzzy logic system (FLS) to control the generation of the random nodes and commands the robot to the required target introducing an intelligent fuzzy adaptive RRT*N path planning approach (FA-RRT*N). The proposed approach not only reduced the time required about 29.5 % of the time required by the RRT*, but also generally resulted in shorter path about 63% of the path generated by the traditional RRT <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> .