Monocular Vision-based Path Identification of a Spherical Robot

With the working environments of the spherical robot become increasingly complex and unstructured, we must improve the autonomy of the robot. As a new mobile robot, the reliable navigation system and accurate sensory ability is very important. The paper presents a monocular vision-based path identification algorithm for a spherical robot moving in an unknown environment. The robot explores the environment with the monocular visual sensor. The close boundaries in the image are obtained by the edge detection and segmentation algorithm based on the mathematical morphology. After the path identification is completed, a safe local path can be planned to navigate the robot. In the end, the feasibility and effectiveness is verified by the experiments.