To main content

Bin Picking of Reflective Steel Parts Using a Dual-Resolution Convolutional Neural Network Trained in a Simulated Environment

Abstract

We consider the case of robotic bin picking of reflective steel parts, using a structured light 3D camera as a depth imaging device. In this paper, we present a new method for bin picking, based on a dual-resolution convolutional neural network trained entirely in a simulated environment. The dual-resolution network consists of a high resolution focus network to compute the grasp and a low resolution context network to avoid local collisions. The reflectivity of the steel parts result in depth images that have a lot of missing data. To take this into account, training of the neural net is done by domain randomization on a large set of synthetic depth images that simulate the missing data problems of the real depth images. We demonstrate both in simulation and in a real-world test that our method can perform bin picking of reflective steel parts.
Read the publication

Category

Academic chapter

Language

English

Affiliation

  • SINTEF Digital / Mathematics and Cybernetics
  • SINTEF Digital / Smart Sensors and Microsystems
  • SINTEF Ocean / Fisheries and New Biomarine Industry
  • Norwegian University of Science and Technology

Year

2018

Publisher

IEEE (Institute of Electrical and Electronics Engineers)

Book

Proceedings of the 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO). Kuala Lumpur, Malaysia, 12-15 Dec. 2018

ISBN

9781728103778

Page(s)

530 - 537

View this publication at Norwegian Research Information Repository