Measuring and modelling delays in robot manipulators for temporally precise control using machine learning

Thomas Timm Andersen, Hani Ben Amor, Nils Axel Andersen, Ole Ravn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Latencies and delays play an important role in temporally precise robot control. During dynamic tasks in particular, a robot has to account for inherent delays to reach manipulated objects in time. The different types of occurring delays are typically convoluted and thereby hard to measure and separate. In this paper, we present a data-driven methodology for separating and modelling inherent delays during robot control. We show how both actuation and response delays can be modelled using modern machine learning methods. The resulting models can be used to predict the delays as well as the uncertainty of the prediction. Experiments on two widely used robot platforms show significant actuation and response delays in standard control loops. Predictive models can, therefore, be used to reason about expected delays and improve temporal accuracy during control. The approach can easily be used on different robot platforms.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages168-175
Number of pages8
ISBN (Print)9781509002870
DOIs
StatePublished - Mar 2 2016
Externally publishedYes
EventIEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015 - Miami, United States
Duration: Dec 9 2015Dec 11 2015

Other

OtherIEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
CountryUnited States
CityMiami
Period12/9/1512/11/15

Fingerprint

Manipulators
Learning systems
Robots
Experiments

Keywords

  • Automation
  • Machine learning algorithms
  • Robot control

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Andersen, T. T., Ben Amor, H., Andersen, N. A., & Ravn, O. (2016). Measuring and modelling delays in robot manipulators for temporally precise control using machine learning. In Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015 (pp. 168-175). [7424304] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2015.98

Measuring and modelling delays in robot manipulators for temporally precise control using machine learning. / Andersen, Thomas Timm; Ben Amor, Hani; Andersen, Nils Axel; Ravn, Ole.

Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 168-175 7424304.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Andersen, TT, Ben Amor, H, Andersen, NA & Ravn, O 2016, Measuring and modelling delays in robot manipulators for temporally precise control using machine learning. in Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015., 7424304, Institute of Electrical and Electronics Engineers Inc., pp. 168-175, IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015, Miami, United States, 12/9/15. https://doi.org/10.1109/ICMLA.2015.98
Andersen TT, Ben Amor H, Andersen NA, Ravn O. Measuring and modelling delays in robot manipulators for temporally precise control using machine learning. In Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 168-175. 7424304 https://doi.org/10.1109/ICMLA.2015.98
Andersen, Thomas Timm ; Ben Amor, Hani ; Andersen, Nils Axel ; Ravn, Ole. / Measuring and modelling delays in robot manipulators for temporally precise control using machine learning. Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 168-175
@inproceedings{032393e472fd404691d4b758c63d0634,
title = "Measuring and modelling delays in robot manipulators for temporally precise control using machine learning",
abstract = "Latencies and delays play an important role in temporally precise robot control. During dynamic tasks in particular, a robot has to account for inherent delays to reach manipulated objects in time. The different types of occurring delays are typically convoluted and thereby hard to measure and separate. In this paper, we present a data-driven methodology for separating and modelling inherent delays during robot control. We show how both actuation and response delays can be modelled using modern machine learning methods. The resulting models can be used to predict the delays as well as the uncertainty of the prediction. Experiments on two widely used robot platforms show significant actuation and response delays in standard control loops. Predictive models can, therefore, be used to reason about expected delays and improve temporal accuracy during control. The approach can easily be used on different robot platforms.",
keywords = "Automation, Machine learning algorithms, Robot control",
author = "Andersen, {Thomas Timm} and {Ben Amor}, Hani and Andersen, {Nils Axel} and Ole Ravn",
year = "2016",
month = "3",
day = "2",
doi = "10.1109/ICMLA.2015.98",
language = "English (US)",
isbn = "9781509002870",
pages = "168--175",
booktitle = "Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Measuring and modelling delays in robot manipulators for temporally precise control using machine learning

AU - Andersen, Thomas Timm

AU - Ben Amor, Hani

AU - Andersen, Nils Axel

AU - Ravn, Ole

PY - 2016/3/2

Y1 - 2016/3/2

N2 - Latencies and delays play an important role in temporally precise robot control. During dynamic tasks in particular, a robot has to account for inherent delays to reach manipulated objects in time. The different types of occurring delays are typically convoluted and thereby hard to measure and separate. In this paper, we present a data-driven methodology for separating and modelling inherent delays during robot control. We show how both actuation and response delays can be modelled using modern machine learning methods. The resulting models can be used to predict the delays as well as the uncertainty of the prediction. Experiments on two widely used robot platforms show significant actuation and response delays in standard control loops. Predictive models can, therefore, be used to reason about expected delays and improve temporal accuracy during control. The approach can easily be used on different robot platforms.

AB - Latencies and delays play an important role in temporally precise robot control. During dynamic tasks in particular, a robot has to account for inherent delays to reach manipulated objects in time. The different types of occurring delays are typically convoluted and thereby hard to measure and separate. In this paper, we present a data-driven methodology for separating and modelling inherent delays during robot control. We show how both actuation and response delays can be modelled using modern machine learning methods. The resulting models can be used to predict the delays as well as the uncertainty of the prediction. Experiments on two widely used robot platforms show significant actuation and response delays in standard control loops. Predictive models can, therefore, be used to reason about expected delays and improve temporal accuracy during control. The approach can easily be used on different robot platforms.

KW - Automation

KW - Machine learning algorithms

KW - Robot control

UR - http://www.scopus.com/inward/record.url?scp=84969716644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969716644&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2015.98

DO - 10.1109/ICMLA.2015.98

M3 - Conference contribution

SN - 9781509002870

SP - 168

EP - 175

BT - Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -