Abstract— Obstacle avoidance methods guarantee the robot’s safety during the tracking of the planned path. Follow the Gap Method known (FGM) is a geometry-based obstacle avoidance method that continuously leads the robot to the goal point by selecting the largest gap existing around the robot. This approach calculates the heading angle by considering the distance to the closest obstacles, the angle to the goal, and the center of the gap. In this paper, a new procedure is developed to improve the gap selection in FGM, where the gaps are selected based on the prediction of gap changes during the time, considering the distance between the robot and obstacles in the future. In order to test the proposed methodology, Monte-Carlo simulations are used and the results are presented for comparison. The results demonstrate that the new procedure leads the robot to safer trajectories in comparison with classical FGM.