Vision-based corridor path search of a mobile robot

In this paper, We made an algorithm for a mobile robot to determine direction normal to the wall with two cameras in an indoor environment without any direction-notification marks. Furthermore, with this direction determination ability, made a method with which a mobile robot can navigate and search through an indoor corridor path without any predefined map information is made. the direction determination scheme uses Hough transform and horizontal line search. While the path search algorithm uses SIFT(Scale-Invariant Feature Transformation), 3D reconstruction and binary search tree algorithm. In the direction determination stage, the mobile robot detects lines in the image and detects horizontal lines to determine the normal to the wall direction. After the direction determination stage is completed, the robot determines the corridor path range through SIFT, RANSAC algorithm, and 3D reconstruction, and finally navigates through its pathway. The direction determination and navigation stage constitutes the binary search tree algorithm. After searching through all its pathway in the indoor environment, the robot returns to its original position with various corridor position information.