Abstract
This paper presents experiments with a Nomad 200 mobile robot, acquiring a sensor model of a specific environment and using this model to predict robot-environment interaction. Data obtained by operating the real robot in the real target environment is used to train a set of 16 artificial neural networks which can later be used to model robot-environment interaction and predict the behaviour of the real robot in off-line simulation. A number of experimental results are presented, demonstrating that this approach can be used to model sensory perception of a mobile robot, as well as to model the behaviour of a specific robot in its target environment.