Learning Sensor-Based Navigation of a Real Mobile Robot in Unknown Worlds

Abstract — In this paper we address the problem of navi-gating an autonomous mobile robot on an unknown indoor environment. The parti-game multiresolution learning ap-proach [22] is applied for simultaneous and cooperative con-struction of a world model, and learning to navigate through an obstacle-free path from a starting position, to a known goal region. The paper introduces a new approach, based on the application of the Fuzzy ART neural architecture [7], for on-line map building from actual sensor data. This method is then integrated, as a complement, on the parti-game world model, allowing the system to make a more efficient use of collected sensor information. Then, a predictive on-line tra-jectory filtering method, is introduced on the learning ap-proach. Instead of having a mechanical device moving to search the world, the 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 move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results on an overall improved new method for goal-oriented navigation. It is as-sumed that the robot knows its own current 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 sensor-based obstacle detection (not avoidance), and straight-line motions. Results of experiments with a real Nomad 200 mobile robot will be presented, demonstrat-ing the effectiveness of the discussed methods. I