Comparing Position- and Image-Based Visual Servoing for Robotic Assembly of Large Structures

This paper considers image-guided assembly forlarge composite panels. By using fiducial markers on the panelsand robot gripper mounted cameras, we are able to use anindustrial robot to align the panels to sub-millimeter accuracy.We considered two commonly used visual servoing schemes:position-based visual servoing (PBVS) and image-based visualservoing (IBVS). It has been noted that IBVS possesses superiorrobustness with respect to the camera calibration accuracy.However, we have found that in our case, PBVS is both fasterand slightly more accurate than IBVS. This result is due to thefact that the visual servoing target in the image plane is derivedfrom a reference target, which depends on the accuracy of thecamera model. This additional dependency essentially nullifiesthe robustness advantage of IBVS. We also implemented asimple scheme to combine inputs from multiple cameras toimprove the visual servoing accuracy. Both simulation andexperimental results are included to show the effectiveness ofvisual servoing in an industrial setting.