Usually, grasp planning can be split up into two phases: In the first phase one tries to find a set of contacts that allow for stable grasping of an object. This phase has been of major research interest, which is also reflected in the (reasonable) definition of a grasp as a set of contact points. In the second phase a feasible hand pose that realizes the grasp with a given hand is calculated. While this point is important for a practical grasp planning system, it has either been considered trivial or been solved by crude heuristics in most cases.
Here we present an approach for calculating a human like hand and finger pose for a given grasp. The problem is formulated as a constraint satisfaction problem and then solved using optimization techniques. The method is applied to two different grasp types: To the well known precision grasp and to the pinch grasp which is the grasp type preferred by men when grasping small objects.