Monocular vision for robot navigation

The structure and camera pose obtained using multiple view geometry based techniques cannot readily be used for robot localization and mapping. This is due to the fact that the structure and pose obtained relate to the actual environment and motion only up to a transform. In this paper, a method to localize the robot using monocular vision is presented. The assumptions are that the initial pose of the robot is known and that five or more landmarks (true, world points) can be identified. If two or more dissimilar views of at least five non coplanar feature points are initially available, subsequent robot locations with respect to the landmarks in view can be established. The exploration of the environment can then take place incorporating new feature points as the robot moves and successive images are acquired. The feature points which are no longer present in the field of view have to be handled along with the occluded ones. In the presented method, the recovered structure and the knowledge about the intrinsic parameters of the camera are used to obtain the metric structure. Depending on the number of images considered at a time, the structure recovery can be done using the epipolar constraints or using the factorization method. The coordinates of the known landmarks are used to calculate the true 3D world coordinates of the feature points. Current location of the robot is established with respect to these landmarks. The world coordinates of the subsequently observed feature points are obtained using the full camera calibration available following the robot localization. The proposed method avoids cumbersome stereo rig calibration. It naturally uses the new feature information available as the robot moves, for incremental localizations. The performance of the algorithm is verified with simulation and real results.