A large number of problems in Artificial Intelligence can be viewed as special cases of constraint-satisfaction problem. Some examples are machine vision, optimization, scheduling and etc. A number of different approaches have been developed for solving these problems. Most powerful of them is model-based nonprocedural approach for Generalized Computational Models. In this paper similar approaches are proposed for the geometrical problems and for the largest domain of problems, that can be interpreted as geometrical. The concept of Generalized Geometrical Models are proposed and used for the data analysis, optimal control etc.