Regrasping objects during manipulation tasks by combining genetic algorithms and finger gaiting

During a manipulation task with a mechanical hand, some particular situations occur frequently. For example, a finger can reach its joint limits or there can be a collision between two or more parts of the hand. In such situations, regrasping must be done without changing the position and the orientation of the object inside the hand. The objective is thus to insure the continuity of the manipulation task. In this work, we propose to compute a new feasible grasp by using genetic algorithms (GAs). The fourth finger enables to reach a new constraint-free grasp using finger gaiting. First we formulate the grasp synthesis problem as an optimization problem that we solve by using genetic algorithms. Once the new optimal grasp is found, a sequence of fingers motions involving the fourth finger is used to reach this new constraint-free grasp. These motions relocate successively the limiting fingers back to their workspace limits. The whole approach is detailed within this paper including the hand kinematics and motion planning. Simulations are shown in order to illustrate the efficiency of the proposed method with a mechanical hand designed in the ROBIOSS team of the PPRIME Institute.