dc.contributor.author | Dyrstad, Jonatan Sjølund | |
dc.contributor.author | Bakken, Marianne | |
dc.contributor.author | Grøtli, Esten Ingar | |
dc.contributor.author | Schulerud, Helene | |
dc.contributor.author | Mathiassen, John Reidar Bartle | |
dc.date.accessioned | 2019-04-02T11:51:03Z | |
dc.date.available | 2019-04-02T11:51:03Z | |
dc.date.created | 2019-01-25T12:51:11Z | |
dc.date.issued | 2018 | |
dc.identifier.issn | 2197-3768 | |
dc.identifier.uri | http://hdl.handle.net/11250/2592926 | |
dc.description.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 dualresolution 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 | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | nb_NO |
dc.title | Bin Picking of Reflective Steel Parts using a Dual-Resolution Convolutional Neural Network Trained in a Simulated Environment | nb_NO |
dc.type | Journal article | nb_NO |
dc.type | Peer reviewed | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.source.journal | Robotics and Biomimetics | nb_NO |
dc.identifier.doi | 10.1109/ROBIO.2018.8664766 | |
dc.identifier.cristin | 1665104 | |
dc.relation.project | Norges forskningsråd: 262900 | nb_NO |
dc.description.localcode | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | nb_NO |
cristin.unitcode | 194,63,25,0 | |
cristin.unitname | Institutt for teknisk kybernetikk | |
cristin.ispublished | false | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |