Position-based Visual Servoing to 3D Pose with Feedforward Compensation

This paper deals with position-based 6-DoF visual servoing. With a common sense of feedback control, we stress that improvement of the dynamics of the sensing feedback unit is important for a stable visual servoing system. We propose a method to improve dynamics in visual recognition of model-based matching, with the on-line matching compensating the fictional motion of the target in the hand-eye camera images caused by the ego motion of the manipulator, by extracting the real motion of the target. We named it as hand-eye motion feedforword (MFF) method. The enhanced dynamics of recognition gave further stability and precision to the total visual servoing system, evaluated by full 6-DoF actual manipulator.