Detection of cylindrical objects in tabletop scenes

Abstract

This paper presents a system with a fixed robot arm and a scanning unit on a table, which is able to detect and grasp given cylindrical objects with cluttered adjacent objects in soft real-time. In the fields of industrial and home robotics, the requirements of complete 3D data, noiselessness, and obstacle-free situations are often not provided. The contribution of this work is a fast and robust method optimised for fitting cylinders in sparse and noisy range data under difficult and changing light conditions recorded from a single view. The improvements focus on the treatment of different objects on the table. The system must distinguish between them, detect, and grasp the given cylindrical object.