Feed forward visual servoing for object exploration

A new visual servoing method is proposed which uses position based visual servoing (PBVS) in combination with an additional image based control layer on the target pose to maintain fixation on an object. The proposed method (denoted feed forward PBVS) does not require trajectory generation but instead uses via-points to explore the object. It exploits the advantages of PBVS without the disadvantages of image based visual servoing (IBVS) as occurs in hybrid approaches. The proposed method is experimentally validated with a redundant 7-DOF manipulator. Comparison with existing visual servoing methods (PBVS and one partitioned approach) shows the effectiveness of the method.