점 이동 타겟 추적을 위한 가중치 행렬을 사용한 로봇 비젼제어기법 개발

Abstract

Robots introduced for industrial applications in the 1980s were used for simple repetitive tasks. Since then, research on robot vision systems by mounting visual function, which is the most important element of human intelligence, is conducted to cope with various working environments. Thus, this study is to develop the practical robot vision control scheme for the tracking of a point moving target. The vision system model used for this study involves six parameters to actively adjust the change of relative position between the camera and the robot, and the direction and focal length of camera. Based on this vision system model, the robot vision control schemes using the N-R method are presented to efficiently process vision data obtained while the robot tracks the point moving targets. Especially, this study uses the cue to minimize the amount of data without recognizing the whole shape of target. The control schemes are classified into two cases. One is based on the control scheme with weighting matrix while the other is based on the control scheme without the weighting matrix. Finally, the experiments on the tracking of the point moving targets are performed to compare and evaluate the accuracy and efficiency by comparing the results of applying and not applying the weighting matrix.