Active and direct acquisition of 3D map in robot by combining motion and perceived images

摘要

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, by the direct combination of its action and image change caused by the action, the robot can acquires a 3D accurate map in his brain. If the robot stereo cameras and his motion parameters have been calibrated, the obtained reconstruction of the static scene stays stationary. But, if not, the reconstructed scene changes according to the robot action. We utilise this change to correct the robot parameters so as to obtain stationary scene in his 3D map 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.