Interval constraint propagation methods have been shown to be efficient, robust and reliable to solve difficult nonlinear bounded-error state estimation problems. However they are considered as unsuitable in a probabilistic context, where the approximation of a probability density function by a set cannot be accepted as reliable. This paper proposes a new probabilistic approach which makes it possible to use classical set-membership observers which are robust with respect to outliers. The approach is illustrated on a localization of robots in situations where there exist a large number of outliers.