Memorized Rapidly Exploring Random Tree Optimization (MRRTO): An Enhanced Algorithm for Robot Path Planning

Abstract

With the advancement of the robotics world, many path-planning algorithms have been proposed. One of the important algorithms is the Rapidly Exploring Random Tree (RRT) but with the drawback of not guaranteeing the optimal path. This paper solves this problem by proposing a Memorized RRT Optimization Algorithm (MRRTO Algorithm) using memory as an optimization step. The algorithm obtains a single path from the start point, and another from the target point to store only the last visited new node. The method for computing the nearest node depends on the position, when a new node is added, the RRT function checks if there is another node closer to the new node rather than that is closer to the goal point. Simulation results with different environments show that the MRRTO outperforms the original RRT Algorithm, graph algorithms, and metaheuristic algorithms in terms of reducing time consumption, path length, and number of nodes used.