Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Object pose detection in industrial environment

: Palzkill, Matthias; Verl, Alexander

Berns, Karsten (Chair); Verl, Alexander (Vice Chair); Hägele, Martin (Session Chair) ; Deutsche Gesellschaft für Robotik; Informationstechnische Gesellschaft im VDE; Fraunhofer-Institut für Produktionstechnik und Automatisierung -IPA-, Stuttgart; TU Kaiserslautern:
ROBOTIK 2012, 7th German Conference on Robotics 2012. Proceedings. CD-ROM : 21-22 May 2012, Munich in Conjunction with Automatica 2012
Berlin: VDE-Verlag, 2012
ISBN: 978-3-8007-3418-4
German Conference on Robotics (ROBOTIK) <7, 2012, Munich>
International Trade Fair on Automation and Mechatronics (AUTOMATICA) <5, 2012, Munich>
Conference Paper
Fraunhofer IPA ()
bin-picking; Griff in die Kiste; object localisation; automatisierte Zuführeinrichtung; Bildverarbeitung; Objekterkennung; Industrieroboter; Roboter; Fertigung; Zuführen

This paper shows a method for object pose detection that is successfully applied to industrial applications running a three-shift system. The industrial applications are fully automated feeding systems, commonly known as bin-picking. The proposed method is a generic approach to detect 6 degrees of freedom of any solid objects with arbitrary geometry. The proposed method is using 3D range data and is based on a hypothesize-and-test approach. In the first step, object poses are hypothesized by means of pose clustering. In the second step, the verification of estimated object poses is realised by an appearance-based template-matching approach. In addition, the method's interfaces are designed to ensure compatibility to 3D sensor systems and handling systems. During long-term operations in different use-cases, the method showed its usability regarding the crucial requirements, such as robustness, accuracy, portability and speed.