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. A concave hull segmentation method called alpha-shape is used to model the objects. Picking experiments of several objects are demonstrated.
