Ant colony algorithm using endpoint approximation for robot path planning

Abstract

An ant colony algorithm using endpoint approximation is proposed for robot path planning under a unknown and static environment. In this algorithm the model of robot's workspace is established with grid method and fold-back iterating is used to search the aims. A heuristic factor based on the most pheromone in a moving direction range and a goal guiding function is used during the searching process. Meanwhile, two kinds of pheromone are used to guide ants. Furthermore, according to the features of the pheromone strewing in the grids and ants visiting grids, an endpoint approximation method is proposed to make the starting point and the end point gradually move towards each other in the iterative process in order to shorten the distance between the starting point and the end point and accelerate the speed of convergence. The simulation results demonstrate that the proposed algorithm has much high efficiency.