Probabilistic appearance-based navigation of a mobile robot -: Controlling a robot in route following

In this work, a solution to the problem of multi-robot following routes is proposed using an appearance-based method. In this approach, several images are stored along the route to follow, using an uncalibrated forward-looking camera. To extract the most relevant information, an incremental PCA process has been implemented. This incremental process allows adding new locations to the PCA database without necessity of creating it from the scratch. Then, the follower robots can follow the route while a leader one is still recording it. These follower robots, using this database, make first an auto-location process to know their current position and then a control phase to compute the necessary steering speed to tend to the route and follow it till the end. Both speeds are obtained also through the visual information in an appearance-based approach. The problem of 'visual aliasing', typical in office environments, is avoided with a probabilistic approach that, using a Markov-process model, makes the localization more robust. The experimental results have shown how this is a simple but robust and powerful approach for routes in an office environment.