Bin Picking of Reflective Steel Parts Using a Dual-Resolution Convolutional Neural Network Trained in a Simulated Environment
Dyrstad, Jonatan Sjølund; Bakken, Marianne; Grøtli, Esten Ingar; Schulerud, Helene; Mathiassen, John Reidar Bartle
Chapter
Accepted version
Permanent lenke
http://hdl.handle.net/11250/2593595Utgivelsesdato
2019Metadata
Vis full innførselSamlinger
- Publikasjoner fra CRIStin - SINTEF AS [5866]
- SINTEF Digital [2536]
Originalversjon
Proceedings of the 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO). Kuala Lumpur, Malaysia, 12-15 Dec. 2018, 530,537Sammendrag
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. Bin Picking of Reflective Steel Parts Using a Dual-Resolution Convolutional Neural Network Trained in a Simulated Environment