Using mutual information for appearance-based visual path following

In this paper we propose a new way to achieve a navigation task (visual path following) for a non-holonomic vehicle. We consider an image-based navigation process. We show that it is possible to navigate along a visual path without relying on the extraction, matching and tracking of geometric visual features such as keypoint. The new proposed approach relies directly on the information (entropy) contained in the image signal. We show that it is possible to build a control law directly from the maximization of the shared information between the current image and the next key image in the visual path. The shared information between those two images is obtained using mutual information that is known to be robust to illumination variations and occlusions. Moreover the generally complex task of features extraction and matching is avoided. Both simulations and experiments on a real vehicle are presented and show the possibilities and advantages offered by the proposed method.

► Navigation task along a visual path for a non-holonomic vehicle. ► A new information theoretic approach for appearance-based visual path following. ► The approach does not rely on features extracted from the image. ► The control law is linked to the optimization of the information shared by two images. ► Considering information contained in the images induces a natural robustness to perturbation.