Improving Appearance-based Following Routes with a Probabilistic Approach
This work presents an appearance-based approach to route following in multi-robot systems, using the information captured by a conventional forward-looking camera. In the teaching phase, the most relevant information along the route is stored using incremental Principal Components Analysis (PCA), what means that the follower robot can begin the route while the leader is still recording it. The follower robot makes an auto-localization process, comparing the current view with the information stored in the database, using a probabilistic approach. Then, a fuzzy controller is in charge of calculating the speed and turning to follow the route. Experimental results have shown the robustness of the algorithms in an office environment.