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

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationMechatronics and Robotics Engineering for Advanced and Intelligent Manufacturing
EditorsDan Zhang, Bin Wei
Volume1
PublisherSpringer
Publication date2017
Pages123-133
ISBN (Print)978-3-319-33580-3
ISBN (Electronic)978-3-319-33581-0
DOIs
Publication statusPublished - 2017
Event2nd International Conference on Mechatronics and Robotics Engineering - Nice, France
Duration: 18. Feb 201622. Feb 2016

Conference

Conference2nd International Conference on Mechatronics and Robotics Engineering
Country/TerritoryFrance
CityNice
Period18/02/201622/02/2016
SeriesLecture Notes in Mechanical Engineering
ISSN2195-4356

Cite this