Image-based simultaneous control of robot and target object motions by direct-image-interpretation method

This paper deals with the image-based simultaneous motion control of robot-arms mounted with cameras and target objects. Given a goal image, the control achieves to move the robots to the position where the given goal images were taken and, at the same time, target objects to the same position as in the goal images. Their motions are determined to reduce the difference between the goal images and the images taken at their current positions. We use the "eigenspace method" to obtain compact representations of the images. To relate the image differences to the robot-arm and target object motions, we re-arrange the eigenspace so that the representations and their motions become linearly dependent. Experiments to control real robots are shown with good performances.