Impacting-based Active Detection of Unknown Objects for Picking

Abstract

We study a method for unknown object detection based on impacting and keypoint tracking. In this method, a robot changes object positions by impacting to detect each of the objects individually from camera images before and after impacting. This detection is possible because keypoints of each object always move consistently by impacting, while those of the background do not move. The proposed method is successfully applied to picking up of textured mahjong tiles by an industrial manipulator.