An Interactive Visual Navigation Method Using a Hand-drawn-Route-Map in an Unknown Dynamic Environment

Abstract

In this paper, a visual navigation method based on Hand-drawn/sketched Route Map is proposed. This navigation method consists in considering the advance Hand-drawn-Route-Map and the effective image matching algorithm. At first, some key boot points are picked up from the hand-drawn route according to the principle of lesser deviation, so that the original route is divided into several segments. Then, in the process of the mobile robot's running along every segment, real-time image information from robot camera is matched with the corresponding one from advance Hand-drawn-Route-Map. In order to speed up image processing, a kind of prediction estimation method is proposed to find the most potential image. SURF algorithm is used to detect image features, where matching points can be found in term of KD-Tree. The projection transform matrix between the reference image and the real-time one is solved by RANSAC algorithm, in order to know the location of the reference image in the real-time one. With reference to the odometer and real-time image information, the robot can be roughly localized. And then, go on next segment, up to the last segment. At last, through a series of experiments, the advantage and efficiency of the new method in navigating and avoiding dynamic obstacles are testified with the imprecise route map.