Teach and Playback for Robotic Handling through Object Recognition

In this paper, we develop a teach-and-playback system for object handling. The robot in this system is assumed to be equipped with an RGB-D camera. In the teaching phase, the robot is allowed to record 3D point cloud models of objects and instructed handling motion for the respective object through object recognition. In the playback phase, the position and posture of a target object is estimated through object recognition and 3D point cloud matching. Finally, the instructed motion is modified depending on the object. In the experiment, we discuss the effectiveness of the teach-and-playback system without any prior models for object handling.