Loading…
Using spatial constraints for fast set-up of precise pose estimation in an industrial setting
This paper presents a method for high precision visual pose estimation along with a simple setup procedure. Robotics for industrial solutions is a rapidly growing field and these robots require very precise position information to perform manipulations. This is usually accomplished using e.g. fixtur...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Citations: | Items that cite this one |
Online Access: | Request full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c268t-fd91c750e387f2959f3fe507c767dfe00936770f1c1de1b67594c56ae6bede5f3 |
---|---|
cites | |
container_end_page | 1314 |
container_issue | |
container_start_page | 1308 |
container_title | |
container_volume | |
creator | Hagelskjar, Frederik Savarimuthu, Thiusius Rajeeth Kruger, Norbert Buch, Anders Glent |
description | This paper presents a method for high precision visual pose estimation along with a simple setup procedure. Robotics for industrial solutions is a rapidly growing field and these robots require very precise position information to perform manipulations. This is usually accomplished using e.g. fixtures or feeders, both expensive hardware solutions. To enable fast changes in production, more flexible solutions are required, one possibility being visual pose estimation. Although many current pose estimation algorithms show increased performance in terms of recognition rates on public datasets, they do not focus on actual applications, neither in setup complexity or high accuracy during object localization. In contrast, our method focuses on solving a number of specific pose estimation problems in a seamless manner with a simple setup procedure. Our method relies on a number of workcell constraints and employs a novel method for automatically finding stable object poses. In addition, we use an active rendering method for refining the estimated object poses, giving a very fine localization, suitable for robotic manipulation. Experiments with current state-of-the-art 2D algorithms and our method show an average improvement from 9 mm to 0.95 mm uncertainty. The method was also used by the winning team at the 2018 World Robot Summit Assembly Challenge. |
doi_str_mv | 10.1109/COASE.2019.8842876 |
format | conference_proceeding |
fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8842876</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8842876</ieee_id><sourcerecordid>8842876</sourcerecordid><originalsourceid>FETCH-LOGICAL-c268t-fd91c750e387f2959f3fe507c767dfe00936770f1c1de1b67594c56ae6bede5f3</originalsourceid><addsrcrecordid>eNotkM1KAzEUhaMgWGtfQDd5gRnvnTR_yzLUHyh0oV1KSTM3EqkzwyRd-Pam2M05q-_jcBh7QKgRwT6129X7um4AbW3MsjFaXbGF1QZ1YxCEVOKazRpUWBkw9pbdpfQNoMAgztjnLsX-i6fR5eiO3A99ypOLfU48DBMPLmWeKFenkQ-BjxP5mIiPQwlKOf4UbOh57Lk7Z3cq9NlTkFy89-wmuGOixaXnbPe8_mhfq8325a1dbSrfKJOr0Fn0WgIJo0NjpQ0ikATttdJdIAArlNYQ0GNHeFBa2qWXypE6UEcyiDl7_PdGItqPU9k1_e4vb4g_E15Vcw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Using spatial constraints for fast set-up of precise pose estimation in an industrial setting</title><source>IEEE Xplore All Conference Series</source><creator>Hagelskjar, Frederik ; Savarimuthu, Thiusius Rajeeth ; Kruger, Norbert ; Buch, Anders Glent</creator><creatorcontrib>Hagelskjar, Frederik ; Savarimuthu, Thiusius Rajeeth ; Kruger, Norbert ; Buch, Anders Glent</creatorcontrib><description>This paper presents a method for high precision visual pose estimation along with a simple setup procedure. Robotics for industrial solutions is a rapidly growing field and these robots require very precise position information to perform manipulations. This is usually accomplished using e.g. fixtures or feeders, both expensive hardware solutions. To enable fast changes in production, more flexible solutions are required, one possibility being visual pose estimation. Although many current pose estimation algorithms show increased performance in terms of recognition rates on public datasets, they do not focus on actual applications, neither in setup complexity or high accuracy during object localization. In contrast, our method focuses on solving a number of specific pose estimation problems in a seamless manner with a simple setup procedure. Our method relies on a number of workcell constraints and employs a novel method for automatically finding stable object poses. In addition, we use an active rendering method for refining the estimated object poses, giving a very fine localization, suitable for robotic manipulation. Experiments with current state-of-the-art 2D algorithms and our method show an average improvement from 9 mm to 0.95 mm uncertainty. The method was also used by the winning team at the 2018 World Robot Summit Assembly Challenge.</description><identifier>EISSN: 2161-8089</identifier><identifier>EISBN: 9781728103563</identifier><identifier>EISBN: 1728103568</identifier><identifier>DOI: 10.1109/COASE.2019.8842876</identifier><language>eng</language><publisher>IEEE</publisher><subject>Image edge detection ; Pose estimation ; Service robots ; Solid modeling ; Three-dimensional displays ; Two dimensional displays</subject><ispartof>2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019, p.1308-1314</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c268t-fd91c750e387f2959f3fe507c767dfe00936770f1c1de1b67594c56ae6bede5f3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8842876$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8842876$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hagelskjar, Frederik</creatorcontrib><creatorcontrib>Savarimuthu, Thiusius Rajeeth</creatorcontrib><creatorcontrib>Kruger, Norbert</creatorcontrib><creatorcontrib>Buch, Anders Glent</creatorcontrib><title>Using spatial constraints for fast set-up of precise pose estimation in an industrial setting</title><title>2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)</title><addtitle>COASE</addtitle><description>This paper presents a method for high precision visual pose estimation along with a simple setup procedure. Robotics for industrial solutions is a rapidly growing field and these robots require very precise position information to perform manipulations. This is usually accomplished using e.g. fixtures or feeders, both expensive hardware solutions. To enable fast changes in production, more flexible solutions are required, one possibility being visual pose estimation. Although many current pose estimation algorithms show increased performance in terms of recognition rates on public datasets, they do not focus on actual applications, neither in setup complexity or high accuracy during object localization. In contrast, our method focuses on solving a number of specific pose estimation problems in a seamless manner with a simple setup procedure. Our method relies on a number of workcell constraints and employs a novel method for automatically finding stable object poses. In addition, we use an active rendering method for refining the estimated object poses, giving a very fine localization, suitable for robotic manipulation. Experiments with current state-of-the-art 2D algorithms and our method show an average improvement from 9 mm to 0.95 mm uncertainty. The method was also used by the winning team at the 2018 World Robot Summit Assembly Challenge.</description><subject>Image edge detection</subject><subject>Pose estimation</subject><subject>Service robots</subject><subject>Solid modeling</subject><subject>Three-dimensional displays</subject><subject>Two dimensional displays</subject><issn>2161-8089</issn><isbn>9781728103563</isbn><isbn>1728103568</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkM1KAzEUhaMgWGtfQDd5gRnvnTR_yzLUHyh0oV1KSTM3EqkzwyRd-Pam2M05q-_jcBh7QKgRwT6129X7um4AbW3MsjFaXbGF1QZ1YxCEVOKazRpUWBkw9pbdpfQNoMAgztjnLsX-i6fR5eiO3A99ypOLfU48DBMPLmWeKFenkQ-BjxP5mIiPQwlKOf4UbOh57Lk7Z3cq9NlTkFy89-wmuGOixaXnbPe8_mhfq8325a1dbSrfKJOr0Fn0WgIJo0NjpQ0ikATttdJdIAArlNYQ0GNHeFBa2qWXypE6UEcyiDl7_PdGItqPU9k1_e4vb4g_E15Vcw</recordid><startdate>201908</startdate><enddate>201908</enddate><creator>Hagelskjar, Frederik</creator><creator>Savarimuthu, Thiusius Rajeeth</creator><creator>Kruger, Norbert</creator><creator>Buch, Anders Glent</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201908</creationdate><title>Using spatial constraints for fast set-up of precise pose estimation in an industrial setting</title><author>Hagelskjar, Frederik ; Savarimuthu, Thiusius Rajeeth ; Kruger, Norbert ; Buch, Anders Glent</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c268t-fd91c750e387f2959f3fe507c767dfe00936770f1c1de1b67594c56ae6bede5f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Image edge detection</topic><topic>Pose estimation</topic><topic>Service robots</topic><topic>Solid modeling</topic><topic>Three-dimensional displays</topic><topic>Two dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Hagelskjar, Frederik</creatorcontrib><creatorcontrib>Savarimuthu, Thiusius Rajeeth</creatorcontrib><creatorcontrib>Kruger, Norbert</creatorcontrib><creatorcontrib>Buch, Anders Glent</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hagelskjar, Frederik</au><au>Savarimuthu, Thiusius Rajeeth</au><au>Kruger, Norbert</au><au>Buch, Anders Glent</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Using spatial constraints for fast set-up of precise pose estimation in an industrial setting</atitle><btitle>2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)</btitle><stitle>COASE</stitle><date>2019-08</date><risdate>2019</risdate><spage>1308</spage><epage>1314</epage><pages>1308-1314</pages><eissn>2161-8089</eissn><eisbn>9781728103563</eisbn><eisbn>1728103568</eisbn><abstract>This paper presents a method for high precision visual pose estimation along with a simple setup procedure. Robotics for industrial solutions is a rapidly growing field and these robots require very precise position information to perform manipulations. This is usually accomplished using e.g. fixtures or feeders, both expensive hardware solutions. To enable fast changes in production, more flexible solutions are required, one possibility being visual pose estimation. Although many current pose estimation algorithms show increased performance in terms of recognition rates on public datasets, they do not focus on actual applications, neither in setup complexity or high accuracy during object localization. In contrast, our method focuses on solving a number of specific pose estimation problems in a seamless manner with a simple setup procedure. Our method relies on a number of workcell constraints and employs a novel method for automatically finding stable object poses. In addition, we use an active rendering method for refining the estimated object poses, giving a very fine localization, suitable for robotic manipulation. Experiments with current state-of-the-art 2D algorithms and our method show an average improvement from 9 mm to 0.95 mm uncertainty. The method was also used by the winning team at the 2018 World Robot Summit Assembly Challenge.</abstract><pub>IEEE</pub><doi>10.1109/COASE.2019.8842876</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | EISSN: 2161-8089 |
ispartof | 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019, p.1308-1314 |
issn | 2161-8089 |
language | eng |
recordid | cdi_ieee_primary_8842876 |
source | IEEE Xplore All Conference Series |
subjects | Image edge detection Pose estimation Service robots Solid modeling Three-dimensional displays Two dimensional displays |
title | Using spatial constraints for fast set-up of precise pose estimation in an industrial setting |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A02%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Using%20spatial%20constraints%20for%20fast%20set-up%20of%20precise%20pose%20estimation%20in%20an%20industrial%20setting&rft.btitle=2019%20IEEE%2015th%20International%20Conference%20on%20Automation%20Science%20and%20Engineering%20(CASE)&rft.au=Hagelskjar,%20Frederik&rft.date=2019-08&rft.spage=1308&rft.epage=1314&rft.pages=1308-1314&rft.eissn=2161-8089&rft_id=info:doi/10.1109/COASE.2019.8842876&rft.eisbn=9781728103563&rft.eisbn_list=1728103568&rft_dat=%3Cieee_CHZPO%3E8842876%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c268t-fd91c750e387f2959f3fe507c767dfe00936770f1c1de1b67594c56ae6bede5f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8842876&rfr_iscdi=true |