Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior

A.J. Veale, Sheng Quan Xie, Iain Alexander Anderson

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Wearable exoskeletons and soft robots require actuators with muscle-like compliance. These actuators can benefit from the robust and effective interaction that biological muscles' compliance enables them to have in the uncertainty of the real world. Fluidic muscles are compliant but difficult to control due to their nonlinear behavior. Precise control of these actuators needs accurate models that readily capture this behavior. Here we present the multivariable arbitrary piecewise model regression (MAPMORE) algorithm for automatically creating accurate data-driven, behavior-based models for fluidic muscles. MAPMORE integrates an arbitrary term dictionary based orthogonal forward regression algorithm with piecewise function fusion. We modeled the static and hysteresis force components of a McKibben pneumatic artificial muscle (PAM) and a Peano muscle with MAPMORE, Sárosi's empirical model, and a polynomial model. In all cases, MAPMORE's models had the best mean accuracy of below 15N. This shows it to be an easy to use, accurate, and versatile soft fluidic actuator modeling tool.
Original languageEnglish
Title of host publication2017 IEEE International Conference on Mechatronics (ICM)
PublisherIEEE
Pages254-259
Number of pages6
ISBN (Electronic)978-1-5090-4538-9
DOIs
Publication statusPublished - 8 May 2017
Event2017 IEEE International Conference on Mechatronics, IEEE-ICM 2017 - Federation University Australia Gippsland Campus, Gippsland, Australia
Duration: 13 Feb 201715 Feb 2017
http://ieee-icm2017.org/

Conference

Conference2017 IEEE International Conference on Mechatronics, IEEE-ICM 2017
Abbreviated titleIEEE-ICM
CountryAustralia
CityGippsland
Period13/02/1715/02/17
Internet address

Fingerprint

Fluidics
Muscle
Actuators
Glossaries
Pneumatics
Hysteresis
Fusion reactions
Robots

Keywords

  • fluidic muscle
  • McKibben PAM
  • Peano muscle
  • MAPMORE
  • soft actuator
  • nonlinear behavior
  • modeling

Cite this

Veale, A. J., Xie, S. Q., & Anderson, I. A. (2017). Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior. In 2017 IEEE International Conference on Mechatronics (ICM) (pp. 254-259). IEEE. https://doi.org/10.1109/ICMECH.2017.7921113
Veale, A.J. ; Xie, Sheng Quan ; Anderson, Iain Alexander. / Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior. 2017 IEEE International Conference on Mechatronics (ICM). IEEE, 2017. pp. 254-259
@inproceedings{63ef7416c40e467ca65e483f55c74704,
title = "Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior",
abstract = "Wearable exoskeletons and soft robots require actuators with muscle-like compliance. These actuators can benefit from the robust and effective interaction that biological muscles' compliance enables them to have in the uncertainty of the real world. Fluidic muscles are compliant but difficult to control due to their nonlinear behavior. Precise control of these actuators needs accurate models that readily capture this behavior. Here we present the multivariable arbitrary piecewise model regression (MAPMORE) algorithm for automatically creating accurate data-driven, behavior-based models for fluidic muscles. MAPMORE integrates an arbitrary term dictionary based orthogonal forward regression algorithm with piecewise function fusion. We modeled the static and hysteresis force components of a McKibben pneumatic artificial muscle (PAM) and a Peano muscle with MAPMORE, Sárosi's empirical model, and a polynomial model. In all cases, MAPMORE's models had the best mean accuracy of below 15N. This shows it to be an easy to use, accurate, and versatile soft fluidic actuator modeling tool.",
keywords = "fluidic muscle, McKibben PAM, Peano muscle, MAPMORE, soft actuator, nonlinear behavior, modeling",
author = "A.J. Veale and Xie, {Sheng Quan} and Anderson, {Iain Alexander}",
year = "2017",
month = "5",
day = "8",
doi = "10.1109/ICMECH.2017.7921113",
language = "English",
pages = "254--259",
booktitle = "2017 IEEE International Conference on Mechatronics (ICM)",
publisher = "IEEE",
address = "United States",

}

Veale, AJ, Xie, SQ & Anderson, IA 2017, Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior. in 2017 IEEE International Conference on Mechatronics (ICM). IEEE, pp. 254-259, 2017 IEEE International Conference on Mechatronics, IEEE-ICM 2017, Gippsland, Australia, 13/02/17. https://doi.org/10.1109/ICMECH.2017.7921113

Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior. / Veale, A.J.; Xie, Sheng Quan; Anderson, Iain Alexander.

2017 IEEE International Conference on Mechatronics (ICM). IEEE, 2017. p. 254-259.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior

AU - Veale, A.J.

AU - Xie, Sheng Quan

AU - Anderson, Iain Alexander

PY - 2017/5/8

Y1 - 2017/5/8

N2 - Wearable exoskeletons and soft robots require actuators with muscle-like compliance. These actuators can benefit from the robust and effective interaction that biological muscles' compliance enables them to have in the uncertainty of the real world. Fluidic muscles are compliant but difficult to control due to their nonlinear behavior. Precise control of these actuators needs accurate models that readily capture this behavior. Here we present the multivariable arbitrary piecewise model regression (MAPMORE) algorithm for automatically creating accurate data-driven, behavior-based models for fluidic muscles. MAPMORE integrates an arbitrary term dictionary based orthogonal forward regression algorithm with piecewise function fusion. We modeled the static and hysteresis force components of a McKibben pneumatic artificial muscle (PAM) and a Peano muscle with MAPMORE, Sárosi's empirical model, and a polynomial model. In all cases, MAPMORE's models had the best mean accuracy of below 15N. This shows it to be an easy to use, accurate, and versatile soft fluidic actuator modeling tool.

AB - Wearable exoskeletons and soft robots require actuators with muscle-like compliance. These actuators can benefit from the robust and effective interaction that biological muscles' compliance enables them to have in the uncertainty of the real world. Fluidic muscles are compliant but difficult to control due to their nonlinear behavior. Precise control of these actuators needs accurate models that readily capture this behavior. Here we present the multivariable arbitrary piecewise model regression (MAPMORE) algorithm for automatically creating accurate data-driven, behavior-based models for fluidic muscles. MAPMORE integrates an arbitrary term dictionary based orthogonal forward regression algorithm with piecewise function fusion. We modeled the static and hysteresis force components of a McKibben pneumatic artificial muscle (PAM) and a Peano muscle with MAPMORE, Sárosi's empirical model, and a polynomial model. In all cases, MAPMORE's models had the best mean accuracy of below 15N. This shows it to be an easy to use, accurate, and versatile soft fluidic actuator modeling tool.

KW - fluidic muscle

KW - McKibben PAM

KW - Peano muscle

KW - MAPMORE

KW - soft actuator

KW - nonlinear behavior

KW - modeling

U2 - 10.1109/ICMECH.2017.7921113

DO - 10.1109/ICMECH.2017.7921113

M3 - Conference contribution

SP - 254

EP - 259

BT - 2017 IEEE International Conference on Mechatronics (ICM)

PB - IEEE

ER -

Veale AJ, Xie SQ, Anderson IA. Accurate and versatile multivariable arbitrary piecewise model regression of nonlinear fluidic muscle behavior. In 2017 IEEE International Conference on Mechatronics (ICM). IEEE. 2017. p. 254-259 https://doi.org/10.1109/ICMECH.2017.7921113