Distributed Vision System for Robot Localisation in Indoor Environment

Traditional image-based localisation methods do not work when the robot is moving in an environment whose appearance is changing in time. We propose an extension to the classical image-based localisation that uses a Distributed Vision System (DVS) and can work also in highly dynamic environments. The DVS is composed of omnidirectional cameras installed in the environment and can communicate with the robot. The localisation of the robot is achieved by comparing the current image grabbed by the robot with the images grabbed at the same time by the DVS. Finding the DVS’s image most similar to the robot’s image gives a topological localisation of the robot. In this paper, we analyze requirements and effectiveness of this approach and we present some preliminary experimental results obtained with the Distributed Vision System.