Learning sensor-based navigation of a real mobile robot in unknown worlds

In this paper, we address the problem of navigating an autonomous mobile ro bot in an unknown indoor environment. The parti-game multiresolution learni ng approach [22] is applied for simultaneous and cooperative construction o f a world model, and learning to navigate through an obstacle-free path fro m a starting position to a known goal region. The paper introduces a new ap proach, based on the application of the fuzzy ART neural architecture [7], for on-line map building from actual sensor data. This method is then integ rated, as a complement, on the parti-game world model, allowing the system to make a more efficient use of collected sensor information. Then, a predi ctive on-line trajectory filtering method, is introduced in the learning ap proach. Instead of having a mechanical device moving to search the world, t he idea is to have the system analyzing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only m ore to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results in an overall improved new method fo r goal-oriented navigation. It is assumed that the robot knows its own curr ent world location-a simple dead-reckoning method is used for localization in our experiments. It is also assumed that the robot is able to perform se nsor-based obstacle detection (not avoidance) and straight-line motions. Re sults of experiments with a real Nomad 200 mobile robot will be presented, demonstrating the effectiveness of the discussed methods.