Bin picking describes a robot system that picks unsorted objects from a bin based on sensor data. The object recognition is one of the main difficulties when calculating the grasping pose. In the worst case, a faulty object recognition leads to a system standstill. This work introduces a framework concept for improving the object recognition by predicting the configuration of all the objects in the bin based on an initial scan in form of a point cloud. This is done by taking advantage of an online simulation, with the goal of reducing the total number of scan cycles, which leads to a reduced risk of failure and improves the overall performance of a bin picking system.
%0 Journal Article
%1 FUR202054
%A Fur, Shan
%A Boughattas, Bilel
%A Verl, Alexander
%A Pott, Andreas
%D 2020
%J Procedia CIRP
%K bin-picking myown network simulation
%P 54 - 59
%R https://doi.org/10.1016/j.procir.2020.05.010
%T Prediction of the configuration of objects in a bin based on synthetic sensor data
%U http://www.sciencedirect.com/science/article/pii/S2212827120303255
%V 88
%X Bin picking describes a robot system that picks unsorted objects from a bin based on sensor data. The object recognition is one of the main difficulties when calculating the grasping pose. In the worst case, a faulty object recognition leads to a system standstill. This work introduces a framework concept for improving the object recognition by predicting the configuration of all the objects in the bin based on an initial scan in form of a point cloud. This is done by taking advantage of an online simulation, with the goal of reducing the total number of scan cycles, which leads to a reduced risk of failure and improves the overall performance of a bin picking system.
@article{FUR202054,
abstract = {Bin picking describes a robot system that picks unsorted objects from a bin based on sensor data. The object recognition is one of the main difficulties when calculating the grasping pose. In the worst case, a faulty object recognition leads to a system standstill. This work introduces a framework concept for improving the object recognition by predicting the configuration of all the objects in the bin based on an initial scan in form of a point cloud. This is done by taking advantage of an online simulation, with the goal of reducing the total number of scan cycles, which leads to a reduced risk of failure and improves the overall performance of a bin picking system.},
added-at = {2020-08-19T13:23:40.000+0200},
author = {Fur, Shan and Boughattas, Bilel and Verl, Alexander and Pott, Andreas},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24dca775811aff39fed6945b7d6390c16/isw-bibliothek},
doi = {https://doi.org/10.1016/j.procir.2020.05.010},
interhash = {b15db43837812b4e9a4ebd57771a8bb8},
intrahash = {4dca775811aff39fed6945b7d6390c16},
issn = {2212-8271},
journal = {Procedia CIRP},
keywords = {bin-picking myown network simulation},
note = {13th CIRP Conference on Intelligent Computation in Manufacturing Engineering, 17-19 July 2019, Gulf of Naples, Italy},
pages = {54 - 59},
timestamp = {2020-08-19T14:38:05.000+0200},
title = {Prediction of the configuration of objects in a bin based on synthetic sensor data},
url = {http://www.sciencedirect.com/science/article/pii/S2212827120303255},
volume = 88,
year = 2020
}