A method of progressive constraints for manipulation planning

We present a method for manipulation planning derived from a systematic approach to constrained motion planning. We call it a method of progressive constraints. It replaces an original problem by a series of progressively constrained ones, and makes a solution of the current problem converge toward a solution of the original problem. The manipulation constraints are analyzed and it is shown how they can be introduced progressively. The progressive constraints framework can thus be used for solving manipulation planning problems. The general algorithm proposed for constrained motion planning can be derived from a standard geometric path planner. We use the variational dynamic programming path planner, in which at every iteration a current path is used to generate a submanifold that is searched for a better path.