Motion Control System Via Knowledge Database Using Visual Information

This paper proposes a motion control scheme for robot control system via a knowledge database. Generally speaking, 3D calibration for the position information acquisition is necessary, when we use visual information based on cameras. However, the 3D calibration is a complicated procedure. In addition, especially for hand-eye systems, the process is more difficult. In our research, we used calibration-free robot system via a knowledge database consisted of 3D quantity of deviation of the tip of a robot arm and 2D image data by two cameras. Moreover in order to update the knowledge base, we used the simultaneous perturbation method. We built a system in which the knowledge database is effectively established for every movement with SP method. As a result, the hand-eye robot arm system can move quickly without 3D calibration and chase a moving object