Sensor-based learning of environment model and path planning with a Nomad 200 mobile robot

This paper addresses the problem of learning sensor-based navigation of a mobile robot on, an indoor environment, where the location, size, and shape of obstacles is assumed to be initially unknown to the robot. We use the parti-game multiresolution approach for simultaneous learning of a world model, and learning to navigate from a start position to a goal region on the world. These two learning abilities are cooperating and enhancing each other in order to improve the overall system performance. It is assumed that the robot knows its own current world location. It is only additionally assumed that the mobile robot is able to perform sensor-based obstacle detection (not avoidance), and that it is able to perform straight-line motions. Results of experiments with a real Nomad 200 mobile robot will be presented