Mobile Robot Path Planning Based on Improved Ant Colony Algorithm

Abstract

Aiming at the problems of traditional ant colony algorithm(ACO) applied to mobile robot path planning, such as easy to fall into local optimization, low search efficiency, poor convergence, and unsmooth path, an improved ant colony algorithm(LACO) is proposed to solve the above problems. In this paper, the angle steering function is introduced into the state transition probability function to make the robot path smoother; The heuristic function is improved to make its weight change dynamically in the state transition probability function, which accelerates the convergence rate of the algorithm; Parameters <tex>$a$</tex> and β are adjusted adaptively to avoid the algorithm falling into local optimization; Set a pheromone concentration range to avoid the stagnation phenomenon. In order to verify the reliability of the improved ant colony algorithm, the comparisons are made in two different environments. The simulation results show that the improved ACO(LACO) applied to the mobile robot path planning has faster convergence speed, stronger searching ability, smoother path, and better stability.