A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly

Jacob P. Buch, Henrik G. Petersen

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

Abstract

Automated assembly operations have traditionally been carried out using 'hard automation', where all parts to be handled during the operation are located at known positions with very high accuracy. Such automation solutions are often mechanically very expensive to implement and also the programming time can be substantial. Hence, hard automation is only suitable for large batch sizes. However, with the upcoming programming paradigms based on joining preprogrammed subtasks (skills) to a complete solution, the programming time can be shortened significantly. Skills are subtasks with well defined interfaces in terms of pre- and postconditions. However, skills still rely on high accuracy as there is no methodology for handling the propagation of inaccuracies when combining the skills. Therefore, skills are typically only useful for hard automation situations. In cases with smaller batch sizes, the high accuracy property will have to be loosened to lower the costs on the hardware side. In this paper, we extend the skill interfaces with a unified formalism for how the skill propagates inaccuracies. The formalism includes how the inaccuracy propagation for a skill can be learned and how the learned propagations can be used to join the skills while also predicting how inaccuracies will propagate through the entire skill chain. We also briefly discuss the perspectives using the formalism to offline search for the most robust combinations of skills for the entire task.

Original languageEnglish
Title of host publicationIROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems
Volume2017-September
PublisherIEEE
Publication date2017
Pages3848-3854
Article number8206236
ISBN (Electronic)9781538626825
DOIs
Publication statusPublished - 2017
Event2017 IEEE/RSJ International Conference on Intelligent Robots and Systems - Vancouver, Canada
Duration: 24. Sep 201728. Sep 2017

Conference

Conference2017 IEEE/RSJ International Conference on Intelligent Robots and Systems
CountryCanada
CityVancouver
Period24/09/201728/09/2017
SponsorAIRA, Amazon, Bosch, Clearpath, et al., Guangdong University of Technology

Fingerprint

Automation
Robots
Joining
Hardware
Costs

Cite this

Buch, J. P., & Petersen, H. G. (2017). A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly. In IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems (Vol. 2017-September, pp. 3848-3854). [8206236] IEEE. https://doi.org/10.1109/IROS.2017.8206236
Buch, Jacob P. ; Petersen, Henrik G. / A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly. IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Vol. 2017-September IEEE, 2017. pp. 3848-3854
@inproceedings{ff418b1ffcaf46f2a96539989bc1705b,
title = "A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly",
abstract = "Automated assembly operations have traditionally been carried out using 'hard automation', where all parts to be handled during the operation are located at known positions with very high accuracy. Such automation solutions are often mechanically very expensive to implement and also the programming time can be substantial. Hence, hard automation is only suitable for large batch sizes. However, with the upcoming programming paradigms based on joining preprogrammed subtasks (skills) to a complete solution, the programming time can be shortened significantly. Skills are subtasks with well defined interfaces in terms of pre- and postconditions. However, skills still rely on high accuracy as there is no methodology for handling the propagation of inaccuracies when combining the skills. Therefore, skills are typically only useful for hard automation situations. In cases with smaller batch sizes, the high accuracy property will have to be loosened to lower the costs on the hardware side. In this paper, we extend the skill interfaces with a unified formalism for how the skill propagates inaccuracies. The formalism includes how the inaccuracy propagation for a skill can be learned and how the learned propagations can be used to join the skills while also predicting how inaccuracies will propagate through the entire skill chain. We also briefly discuss the perspectives using the formalism to offline search for the most robust combinations of skills for the entire task.",
author = "Buch, {Jacob P.} and Petersen, {Henrik G.}",
year = "2017",
doi = "10.1109/IROS.2017.8206236",
language = "English",
volume = "2017-September",
pages = "3848--3854",
booktitle = "IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems",
publisher = "IEEE",
address = "United States",

}

Buch, JP & Petersen, HG 2017, A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly. in IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. vol. 2017-September, 8206236, IEEE, pp. 3848-3854, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vancouver, Canada, 24/09/2017. https://doi.org/10.1109/IROS.2017.8206236

A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly. / Buch, Jacob P.; Petersen, Henrik G.

IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Vol. 2017-September IEEE, 2017. p. 3848-3854 8206236.

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

TY - GEN

T1 - A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly

AU - Buch, Jacob P.

AU - Petersen, Henrik G.

PY - 2017

Y1 - 2017

N2 - Automated assembly operations have traditionally been carried out using 'hard automation', where all parts to be handled during the operation are located at known positions with very high accuracy. Such automation solutions are often mechanically very expensive to implement and also the programming time can be substantial. Hence, hard automation is only suitable for large batch sizes. However, with the upcoming programming paradigms based on joining preprogrammed subtasks (skills) to a complete solution, the programming time can be shortened significantly. Skills are subtasks with well defined interfaces in terms of pre- and postconditions. However, skills still rely on high accuracy as there is no methodology for handling the propagation of inaccuracies when combining the skills. Therefore, skills are typically only useful for hard automation situations. In cases with smaller batch sizes, the high accuracy property will have to be loosened to lower the costs on the hardware side. In this paper, we extend the skill interfaces with a unified formalism for how the skill propagates inaccuracies. The formalism includes how the inaccuracy propagation for a skill can be learned and how the learned propagations can be used to join the skills while also predicting how inaccuracies will propagate through the entire skill chain. We also briefly discuss the perspectives using the formalism to offline search for the most robust combinations of skills for the entire task.

AB - Automated assembly operations have traditionally been carried out using 'hard automation', where all parts to be handled during the operation are located at known positions with very high accuracy. Such automation solutions are often mechanically very expensive to implement and also the programming time can be substantial. Hence, hard automation is only suitable for large batch sizes. However, with the upcoming programming paradigms based on joining preprogrammed subtasks (skills) to a complete solution, the programming time can be shortened significantly. Skills are subtasks with well defined interfaces in terms of pre- and postconditions. However, skills still rely on high accuracy as there is no methodology for handling the propagation of inaccuracies when combining the skills. Therefore, skills are typically only useful for hard automation situations. In cases with smaller batch sizes, the high accuracy property will have to be loosened to lower the costs on the hardware side. In this paper, we extend the skill interfaces with a unified formalism for how the skill propagates inaccuracies. The formalism includes how the inaccuracy propagation for a skill can be learned and how the learned propagations can be used to join the skills while also predicting how inaccuracies will propagate through the entire skill chain. We also briefly discuss the perspectives using the formalism to offline search for the most robust combinations of skills for the entire task.

U2 - 10.1109/IROS.2017.8206236

DO - 10.1109/IROS.2017.8206236

M3 - Article in proceedings

AN - SCOPUS:85041944020

VL - 2017-September

SP - 3848

EP - 3854

BT - IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - IEEE

ER -

Buch JP, Petersen HG. A framework for handling and combining inaccuracy propagation in robot subtasks for industrial assembly. In IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Vol. 2017-September. IEEE. 2017. p. 3848-3854. 8206236 https://doi.org/10.1109/IROS.2017.8206236