Authors:
Lukáš Gajdošech
1
;
2
;
Viktor Kocur
3
;
1
;
Martin Stuchlík
2
;
Lukáš Hudec
4
and
Martin Madaras
1
;
2
Affiliations:
1
Faculty of Mathematics, Physics and Informatics, Comenius University Bratislava, Slovakia
;
2
Skeletex Research, Slovakia
;
3
Faculty of Information Technology, Brno University of Technology, Czech Republic
;
4
Faculty of Informatics and Information Technologies, Slovak Technical University Bratislava, Slovakia
Keyword(s):
Computer Vision, Bin Pose Estimation, 6D Pose Estimation, Deep Learning, Point Clouds.
Abstract:
An automated robotic system needs to be as robust as possible and fail-safe in general while having relatively high precision and repeatability. Although deep learning-based methods are becoming research standard on how to approach 3D scan and image processing tasks, the industry standard for processing this data is still analytically-based. Our paper claims that analytical methods are less robust and harder for testing, updating, and maintaining. This paper focuses on a specific task of 6D pose estimation of a bin in 3D scans. Therefore, we present a high-quality dataset composed of synthetic data and real scans captured by a structured-light scanner with precise annotations.
Additionally, we propose two different methods for 6D bin pose estimation, an analytical method as the industrial standard and a baseline data-driven method. Both approaches are cross-evaluated, and our experiments show that augmenting the training on real scans with synthetic data improves our proposed data-d
riven neural model. This position paper is preliminary, as proposed methods are trained and evaluated on a relatively small initial dataset which we plan to extend in the future.
(More)