Building geometric certainty maps and application to the navigation of a mobile robot

Autonomous robots must be able to learn and maintain models of their environments. This paper introduces a new approach, based on the fuzzy ART neural architecture, for on-line map building from actual sensor data collected with a mobile robot. This method is then integrated, as a complement, on the parti-game learning approach, allowing the system to make a more efficient use of collected sensor information. Also, a predictive on-line trajectory filtering method, is introduced in the learning approach. Instead of having a mechanical robot moving to search the world, the idea is to have the system analysing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results in an overall new and powerful method for simultaneous and cooperative construction of a world model, and learning to navigate from an initial position to a goal region in an unknown world. It is assumed that the robot knows its own current world location, and is able to perform sensor-based obstacle detection (not avoidance), and straight-line motions. Results of experiments with a real Nomad 200 mobile robot are presented, demonstrating the effectiveness of the proposed methods.