Abstract
In this paper, we propose an active vision strategy for the construction of a 3D map in a robot brain from its stereo eye images. We show that the combination of the robot action and image change caused by the action improves the accuracy of the map. If the robot stereo cameras have been accurately calibrated, the obtained reconstruction of the static scene stays stationary. If the calibration is not accurate, the reconstructed scene changes according to the robot action. Therefore, we utilize this change to correct the parameters of the stereo cameras and the 3D map so as to obtain stationary scene under the action. We show the feasibility of this idea as an auto-calibration of robot vision with some simulation experiments and implementation on actual robots.
