Mobile Robot Navigation Techniques Using Potential Field Method in Unknown Environments

摘要

In this paper, a navigation system for autonomous mobile robots that move into unknown environments based on artificial potential field is presented. The robot moves to a predefined target point while detects and maps every encounter object using its artificial monocular vision system based on intrinsic camera parameters. During navigation, every obstacle is associated with a repulsive field depending on the distance and relative position to the robot, while the target point has an attractive field. Combining those values of potential field defines the direction of the next step of the robot. The results reported are showing the behavior of the method in three scenarios, avoiding obstacles, going through a narrow corridor and escaping from a minimum local trap.