In recent years, several approaches for modelling pedestrian dynamics have been proposed. However, so far not much attention has been paid to their quantitative validation. Instead the focus has been on the reproduction of empirically observed collective phenomena like the dynamical formation of lanes. Although this gives an indication of the realism of the model, for practical applications as in safety analysis, reliable quantitative predictions are required. We discuss the experimental situation focusing on the fundamental diagram that is essential for calibration. Furthermore, we present a cellular automaton, the floor field model, which forms the basis for various multi-agent simulations. Apart from the properties of its fundamental diagram, we discuss the role of conflicts and friction effects and their influence on evacuation times.