Performing complex assembly task with robots requires fine-motion planners able to cope with uncertainty and contact motions, which is a difficult issue. This report proposes a method to predict the behavior of motions under contact uncertainty in order to check the feasibility of paths generated by gross-motion planning algorithms from a nominal model of environment. This pragmatical approach enables the extension of the gross-motion planning techniques to constrained-motion planning problems, ensuring the feasibility of the task despite the uncertainty. The approach has been implemented for assembly task in the plane with three degrees of freedom.