Visual Map-less Navigation based on Homographies
Keywords: Map-less navigation, homographies, visual relocation
We introduce a method for autonomous robot navigation based on homographies computed between current image and images taken in a previous teaching phase with a monocular vision system. The features used to estimate the homography are vertical lines automatically extracted and matched. From homography, the underlying motion correction between the reference path and the current robot location is computed. The proposed method, which uses a sole calibration parameter, has turned out to be specially useful to correct heading and lateral displacement, which are critical in systems based on odometry. We have tested the proposal in simulation, and with real images. Besides, the visual system has been integrated into an autonomous wheelchair for handicapped, working in real time with robustness and reliability.
Experiment: The wheelchair moves along a square using four reference images
Comparison of the trajectories with and without the visual correction. The image seems to be blurred because the two videos are superimposed.
Comparison between two different turns (second and tenth) of the square with visual correction. The errors in the trajectory are so small that they can not be apreciated in the movie. The image seems to be blurred because the two videos are superimposed.