Separating Entangled Workpieces in Random Bin Picking using Deep Reinforcement Learning

Procedia CIRP, vol. 104, pp. 881–886

Abstract

Entangled workpiece situations often occur in random bin picking of chaotically stored objects and are a common source of problem in the bin picking process. Previous methods for averting this problem, such as randomly shaking the gripper over the bin, lead to decreasing production efficiency and an increase in cycle time. A promising new strategy uses supervised learning and deep neural networks to learn the separation. However, this approach requires a large amount of labeled data. To overcome this issue, this paper proposes a deep reinforcement learning approach to separate entangled workpieces and to minimize the setup effort.

Authors 8

1. Marius Moosmann corresponding

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

2. Marco Kulig

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

3. Felix Spenrath

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

4. Manuel Mönnig

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

5. Simon Roggendorf Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University, Steinbachstr. 19, 52074 Aachen, Germany

6. Oliver Petrović Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University, Steinbachstr. 19, 52074 Aachen, Germany

7. Richard Bormann

   Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

8. Marco F. Huber

   University of Stuttgart · Fraunhofer Institute for Manufacturing Engineering and Automation

   Affiliation as printed

   Fraunhofer IPA, Nobelstraße 12, 70569 Stuttgart, Germany

   Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Allmandring 35, 70569 Stuttgart, Germany