Til hovedinnhold

John Reidar Mathiassen

Seniorforsker

John Reidar Mathiassen

Seniorforsker

John Reidar Mathiassen
Telefon: 934 53 696
Avdeling: Sjømatteknologi
Kontorsted: Trondheim

Publikasjoner og ansvarsområder

Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/?pubid=CRIStin+1687425

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-r...

År 2018
Type Del av bok/rapport
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/?pubid=CRIStin+1665083

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 dualre...

År 2018
Type Konferansebidrag og faglig presentasjon
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/?pubid=CRIStin+1611909

We teach a real robot to grasp real fish, by training a virtual robot exclusively in virtual reality. Our approach implements robot imitation learning from a human supervisor in virtual reality. A deep 3D convolutional neural network computes grasps from a 3D occupancy grid obtained from depth imagi...

Forfattere Dyrstad Jonatan Sjølund Øye Elling Ruud Stahl Annette Mathiassen John Reidar Bartle
År 2018
Type Tidsskriftspublikasjon
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/?pubid=CRIStin+1572396

We present an approach to robotic deep learning from demonstration in virtual reality, which combines a deep 3D convolutional neural network, for grasp detection from 3D point clouds, with domain randomization to generate a large training data set. The use of virtual reality (VR) enables robot learn...

Forfattere Dyrstad Jonatan Sjølund Mathiassen John Reidar Bartle
År 2018
Type Tidsskriftspublikasjon
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/?pubid=CRIStin+1561519

Despite advances in computer vision and segmentation techniques, the segmentation of food defects such as blood spots, exhibiting a high degree of randomness and biological variation in size and coloration degree, has proven to be extremely challenging and it is not successfully resolved. Therefore,...

År 2017
Type Tidsskriftspublikasjon