Visual topological map building in self-similar environments

This paper describes a method to automatically build topological maps for robot navigation out of a sequence of visual observations taken from a camera mounted on the robot. This direct non-metrical approach relies completely on the detection of loop closings, i.e. repeated visitations of one particular place. In natural environments, visual loop closing can be very hard, for two reasons. Firstly, the environment at one place can look differently at different time instances due to illumination changes and viewpoint differences. Secondly, there can be different places that look alike, i.e. the environment is self-similar. Here we propose a method that combines state-of-the-art visual comparison techniques and evidence collection based on Dempster-Shafer probability theory to tackle this problem.