AbstractRobustness problems due to the substitution of the exact computation on real numbers by the rounded floating point arithmetic are often an obstacle to obtain practical implementation of geometric algorithms. If the adoption of the exact computation paradigm [C.K. Yap, T. Dubé, The exact computation paradigm, in: D.-Z. Du, F.K. Hwang (Eds.), Computing in Euclidean Geometry, in: Lecture Notes Series on Computing, vol. 4, second ed., World Scientific, Singapore, 1995, pp. 452–492, http://cs.nyu.edu/cs/faculty/yap/papers/paradigm.ps] gives a satisfactory solution to this kind of problems for purely combinatorial algorithms, this solution does not allow to solve in practice the case of algorithms that cascade the construction of new geom...