Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting

Kenneth Korsgaard Meyer, Adam Wolniakowski, Frederik Hagelskjær, Lilita Kiforenko, Anders Glent Buch, Norbert Krüger, Jimmy Alison Jørgensen, Leon Bodenhagen

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Resumé

We introduce a vision system that is able to on-line learn spatial constraints to improve pose estimation in terms of correct recognition as well as computational speed. By making use of a simulated industrial robot system performing various pick and place tasks, we show the effect of model building when making use of visual knowledge in terms of visually extracted pose hypotheses as well as action knowledge in terms of pose hypotheses verified by action execution. We show that the use of action knowledge significantly improves the pose estimation process.
OriginalsprogEngelsk
TitelMechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing
RedaktørerDan Zhang, Bin Wei
Vol/bind1
ForlagSpringer
Publikationsdato2017
Sider123-133
ISBN (Trykt)978-3-319-33580-3
ISBN (Elektronisk)978-3-319-33581-0
DOI
StatusUdgivet - 2017
Begivenhed2nd International Conference on Mechatronics and Robotics Engineering - Nice, Frankrig
Varighed: 18. feb. 201622. feb. 2016

Konference

Konference2nd International Conference on Mechatronics and Robotics Engineering
LandFrankrig
ByNice
Periode18/02/201622/02/2016
NavnLecture Notes in Mechanical Engineering
ISSN2195-4356

Emneord

  • Pose estimation
  • Online modelling
  • Pick and place
  • Stable pose

Citer dette

Meyer, K. K., Wolniakowski, A., Hagelskjær, F., Kiforenko, L., Buch, A. G., Krüger, N., ... Bodenhagen, L. (2017). Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting. I D. Zhang, & B. Wei (red.), Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing (Bind 1, s. 123-133). Springer. Lecture Notes in Mechanical Engineering https://doi.org/10.1007/978-3-319-33581-0_10
Meyer, Kenneth Korsgaard ; Wolniakowski, Adam ; Hagelskjær, Frederik ; Kiforenko, Lilita ; Buch, Anders Glent ; Krüger, Norbert ; Jørgensen, Jimmy Alison ; Bodenhagen, Leon. / Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting. Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing. red. / Dan Zhang ; Bin Wei. Bind 1 Springer, 2017. s. 123-133 (Lecture Notes in Mechanical Engineering).
@inproceedings{2558c4ccf5dd4eec83a416844bcf3ce2,
title = "Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting",
abstract = "We introduce a vision system that is able to on-line learn spatial constraints to improve pose estimation in terms of correct recognition as well as computational speed. By making use of a simulated industrial robot system performing various pick and place tasks, we show the effect of model building when making use of visual knowledge in terms of visually extracted pose hypotheses as well as action knowledge in terms of pose hypotheses verified by action execution. We show that the use of action knowledge significantly improves the pose estimation process.",
keywords = "Pose estimation, Online modelling, Pick and place, Stable pose",
author = "Meyer, {Kenneth Korsgaard} and Adam Wolniakowski and Frederik Hagelskj{\ae}r and Lilita Kiforenko and Buch, {Anders Glent} and Norbert Kr{\"u}ger and J{\o}rgensen, {Jimmy Alison} and Leon Bodenhagen",
year = "2017",
doi = "10.1007/978-3-319-33581-0_10",
language = "English",
isbn = "978-3-319-33580-3",
volume = "1",
pages = "123--133",
editor = "Dan Zhang and Bin Wei",
booktitle = "Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing",
publisher = "Springer",
address = "Germany",

}

Meyer, KK, Wolniakowski, A, Hagelskjær, F, Kiforenko, L, Buch, AG, Krüger, N, Jørgensen, JA & Bodenhagen, L 2017, Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting. i D Zhang & B Wei (red), Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing. bind 1, Springer, Lecture Notes in Mechanical Engineering, s. 123-133, 2nd International Conference on Mechatronics and Robotics Engineering, Nice, Frankrig, 18/02/2016. https://doi.org/10.1007/978-3-319-33581-0_10

Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting. / Meyer, Kenneth Korsgaard; Wolniakowski, Adam; Hagelskjær, Frederik; Kiforenko, Lilita; Buch, Anders Glent; Krüger, Norbert; Jørgensen, Jimmy Alison; Bodenhagen, Leon.

Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing. red. / Dan Zhang; Bin Wei. Bind 1 Springer, 2017. s. 123-133 (Lecture Notes in Mechanical Engineering).

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

TY - GEN

T1 - Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting

AU - Meyer, Kenneth Korsgaard

AU - Wolniakowski, Adam

AU - Hagelskjær, Frederik

AU - Kiforenko, Lilita

AU - Buch, Anders Glent

AU - Krüger, Norbert

AU - Jørgensen, Jimmy Alison

AU - Bodenhagen, Leon

PY - 2017

Y1 - 2017

N2 - We introduce a vision system that is able to on-line learn spatial constraints to improve pose estimation in terms of correct recognition as well as computational speed. By making use of a simulated industrial robot system performing various pick and place tasks, we show the effect of model building when making use of visual knowledge in terms of visually extracted pose hypotheses as well as action knowledge in terms of pose hypotheses verified by action execution. We show that the use of action knowledge significantly improves the pose estimation process.

AB - We introduce a vision system that is able to on-line learn spatial constraints to improve pose estimation in terms of correct recognition as well as computational speed. By making use of a simulated industrial robot system performing various pick and place tasks, we show the effect of model building when making use of visual knowledge in terms of visually extracted pose hypotheses as well as action knowledge in terms of pose hypotheses verified by action execution. We show that the use of action knowledge significantly improves the pose estimation process.

KW - Pose estimation

KW - Online modelling

KW - Pick and place

KW - Stable pose

U2 - 10.1007/978-3-319-33581-0_10

DO - 10.1007/978-3-319-33581-0_10

M3 - Article in proceedings

SN - 978-3-319-33580-3

VL - 1

SP - 123

EP - 133

BT - Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing

A2 - Zhang, Dan

A2 - Wei, Bin

PB - Springer

ER -

Meyer KK, Wolniakowski A, Hagelskjær F, Kiforenko L, Buch AG, Krüger N et al. Using Online Modelled Spatial Constraints for Pose Estimation in an Industrial Setting. I Zhang D, Wei B, red., Mechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing. Bind 1. Springer. 2017. s. 123-133. (Lecture Notes in Mechanical Engineering). https://doi.org/10.1007/978-3-319-33581-0_10