Robustly Segmenting Cylindrical and Box-like Objects in Cluttered Scenes using Depth Cameras

In this paper, we describe our approach to dealing with cluttered scenes of simple objects in the context of common pickand- place tasks for assistive robots. We consider the case when the robot enters an unknown environment, meaning that it does not know about the shape and size of the objects it should expect. Having no complete model of the objects makes detection through matching impossible, thus we propose an alternative approach to deal with unknown objects. Since many objects are cylindrical or box-like, or at least have such parts, we present a method to locate the best parameters for all such shapes in a cluttered scene. Our generic approach does not get more complex as the number of possible objects increases, and is still able to provide robust results and models that are relevant for grasp planning. We compared our approach to earlier methods and evaluated it on several cluttered tabletop scenes captured by the Microsoft Kinect sensor. Keywords: 3D perception for robots, clutter segmentation, RANSAC, Hough voting, single-view models for grasping