Tracking of moving object by manipulator using estimated image feature and its error correction on image planes

Abstract

This paper proposes a new visual servo system compensating delay time of image processing. To obtain an image feature without delay time, variation of image feature of manipulators during delay time is estimated by a Jacobian matrix from joint velocity to image feature. An image feature of moving object during delay time is estimated from a simple model by using the average velocity/acceleration that are calculated from the past image data. Moreover, its estimation error is reduced by a method based on past estimation error. The effectiveness of the proposed strategy is confirmed by a tracking of a moving object by a manipulator.