Comparing parallel and sequential control parameter tuning for a powered knee prosthesis

Yue Wen, Andrea Brandt, Ming Liu, He Huang, Jennie Si

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

3 Citations (Scopus)

Abstract

Powered knee prostheses, compared to traditional energetically-passive knee prostheses, greatly enhance the mobility of transfemoral amputees. However, powered prostheses have a large number of control parameters that must be adjusted for individual amputee users, which presents a great challenge for clinical use. To address this challenge, we proposed and compared 2 automatic tuning strategies (i.e. parallel and sequential) using our newly developed optimal adaptive dynamic programming (ADP) tuner that objectively tuned the control parameters of an experimental powered knee prosthesis to mimic the knee profile of an able-bodied person (i.e. reference profile). With the parallel tuning strategy, we tuned all control parameters during the stance and the swing phases simultaneously. With the sequential tuning strategy, we alternately tuned stance or swing phase control parameters while fixing the remaining parameters. One able-bodied subject with a prosthesis adapter and one transfemoral amputee subject walked with the experimental powered knee prosthesis under both tuning strategies. Results show that with both tuning strategies, the ADP tuner successfully tuned the impedance parameters to match the prosthetic knee profile to the reference profile. Additionally, the parallel strategy outperformed the sequential strategy with better convergence to the reference profile. Interestingly, with the sequential tuning strategy, tuning during the swing phase greatly impacted the subsequent stance phase profile, but the impact was not as great when the order of tuning was switched. The ability to simultaneously adjust all control parameters with ADP using a parallel strategy may be a preferred solution for the current high-dimension control challenge, which may lead to more advanced, adaptive powered knee prostheses.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1716-1721
Number of pages6
Volume2017-January
ISBN (Electronic)9781538616451
DOIs
StatePublished - Nov 27 2017
Event2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 - Banff, Canada
Duration: Oct 5 2017Oct 8 2017

Other

Other2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
CountryCanada
CityBanff
Period10/5/1710/8/17

Fingerprint

Knee prostheses
Parameter Tuning
Control Parameter
Tuning
Adaptive Dynamics
Dynamic programming
Dynamic Programming
Prosthetics
Phase control
Strategy
Impedance
Higher Dimensions
Profile
Person

Keywords

  • Control Parameter Tuning
  • Gait
  • Impedance Control
  • Machine Learning
  • Reinforcement Learning Finite State Machine
  • Transfemoral Amputee

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Control and Optimization

Cite this

Wen, Y., Brandt, A., Liu, M., Huang, H., & Si, J. (2017). Comparing parallel and sequential control parameter tuning for a powered knee prosthesis. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 (Vol. 2017-January, pp. 1716-1721). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2017.8122863

Comparing parallel and sequential control parameter tuning for a powered knee prosthesis. / Wen, Yue; Brandt, Andrea; Liu, Ming; Huang, He; Si, Jennie.

2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 1716-1721.

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

Wen, Y, Brandt, A, Liu, M, Huang, H & Si, J 2017, Comparing parallel and sequential control parameter tuning for a powered knee prosthesis. in 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1716-1721, 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, Banff, Canada, 10/5/17. https://doi.org/10.1109/SMC.2017.8122863
Wen Y, Brandt A, Liu M, Huang H, Si J. Comparing parallel and sequential control parameter tuning for a powered knee prosthesis. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1716-1721 https://doi.org/10.1109/SMC.2017.8122863
Wen, Yue ; Brandt, Andrea ; Liu, Ming ; Huang, He ; Si, Jennie. / Comparing parallel and sequential control parameter tuning for a powered knee prosthesis. 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1716-1721
@inproceedings{b5eeb10d63654f9c847c4f8526c6b5f1,
title = "Comparing parallel and sequential control parameter tuning for a powered knee prosthesis",
abstract = "Powered knee prostheses, compared to traditional energetically-passive knee prostheses, greatly enhance the mobility of transfemoral amputees. However, powered prostheses have a large number of control parameters that must be adjusted for individual amputee users, which presents a great challenge for clinical use. To address this challenge, we proposed and compared 2 automatic tuning strategies (i.e. parallel and sequential) using our newly developed optimal adaptive dynamic programming (ADP) tuner that objectively tuned the control parameters of an experimental powered knee prosthesis to mimic the knee profile of an able-bodied person (i.e. reference profile). With the parallel tuning strategy, we tuned all control parameters during the stance and the swing phases simultaneously. With the sequential tuning strategy, we alternately tuned stance or swing phase control parameters while fixing the remaining parameters. One able-bodied subject with a prosthesis adapter and one transfemoral amputee subject walked with the experimental powered knee prosthesis under both tuning strategies. Results show that with both tuning strategies, the ADP tuner successfully tuned the impedance parameters to match the prosthetic knee profile to the reference profile. Additionally, the parallel strategy outperformed the sequential strategy with better convergence to the reference profile. Interestingly, with the sequential tuning strategy, tuning during the swing phase greatly impacted the subsequent stance phase profile, but the impact was not as great when the order of tuning was switched. The ability to simultaneously adjust all control parameters with ADP using a parallel strategy may be a preferred solution for the current high-dimension control challenge, which may lead to more advanced, adaptive powered knee prostheses.",
keywords = "Control Parameter Tuning, Gait, Impedance Control, Machine Learning, Reinforcement Learning Finite State Machine, Transfemoral Amputee",
author = "Yue Wen and Andrea Brandt and Ming Liu and He Huang and Jennie Si",
year = "2017",
month = "11",
day = "27",
doi = "10.1109/SMC.2017.8122863",
language = "English (US)",
volume = "2017-January",
pages = "1716--1721",
booktitle = "2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Comparing parallel and sequential control parameter tuning for a powered knee prosthesis

AU - Wen, Yue

AU - Brandt, Andrea

AU - Liu, Ming

AU - Huang, He

AU - Si, Jennie

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Powered knee prostheses, compared to traditional energetically-passive knee prostheses, greatly enhance the mobility of transfemoral amputees. However, powered prostheses have a large number of control parameters that must be adjusted for individual amputee users, which presents a great challenge for clinical use. To address this challenge, we proposed and compared 2 automatic tuning strategies (i.e. parallel and sequential) using our newly developed optimal adaptive dynamic programming (ADP) tuner that objectively tuned the control parameters of an experimental powered knee prosthesis to mimic the knee profile of an able-bodied person (i.e. reference profile). With the parallel tuning strategy, we tuned all control parameters during the stance and the swing phases simultaneously. With the sequential tuning strategy, we alternately tuned stance or swing phase control parameters while fixing the remaining parameters. One able-bodied subject with a prosthesis adapter and one transfemoral amputee subject walked with the experimental powered knee prosthesis under both tuning strategies. Results show that with both tuning strategies, the ADP tuner successfully tuned the impedance parameters to match the prosthetic knee profile to the reference profile. Additionally, the parallel strategy outperformed the sequential strategy with better convergence to the reference profile. Interestingly, with the sequential tuning strategy, tuning during the swing phase greatly impacted the subsequent stance phase profile, but the impact was not as great when the order of tuning was switched. The ability to simultaneously adjust all control parameters with ADP using a parallel strategy may be a preferred solution for the current high-dimension control challenge, which may lead to more advanced, adaptive powered knee prostheses.

AB - Powered knee prostheses, compared to traditional energetically-passive knee prostheses, greatly enhance the mobility of transfemoral amputees. However, powered prostheses have a large number of control parameters that must be adjusted for individual amputee users, which presents a great challenge for clinical use. To address this challenge, we proposed and compared 2 automatic tuning strategies (i.e. parallel and sequential) using our newly developed optimal adaptive dynamic programming (ADP) tuner that objectively tuned the control parameters of an experimental powered knee prosthesis to mimic the knee profile of an able-bodied person (i.e. reference profile). With the parallel tuning strategy, we tuned all control parameters during the stance and the swing phases simultaneously. With the sequential tuning strategy, we alternately tuned stance or swing phase control parameters while fixing the remaining parameters. One able-bodied subject with a prosthesis adapter and one transfemoral amputee subject walked with the experimental powered knee prosthesis under both tuning strategies. Results show that with both tuning strategies, the ADP tuner successfully tuned the impedance parameters to match the prosthetic knee profile to the reference profile. Additionally, the parallel strategy outperformed the sequential strategy with better convergence to the reference profile. Interestingly, with the sequential tuning strategy, tuning during the swing phase greatly impacted the subsequent stance phase profile, but the impact was not as great when the order of tuning was switched. The ability to simultaneously adjust all control parameters with ADP using a parallel strategy may be a preferred solution for the current high-dimension control challenge, which may lead to more advanced, adaptive powered knee prostheses.

KW - Control Parameter Tuning

KW - Gait

KW - Impedance Control

KW - Machine Learning

KW - Reinforcement Learning Finite State Machine

KW - Transfemoral Amputee

UR - http://www.scopus.com/inward/record.url?scp=85044116431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044116431&partnerID=8YFLogxK

U2 - 10.1109/SMC.2017.8122863

DO - 10.1109/SMC.2017.8122863

M3 - Conference contribution

AN - SCOPUS:85044116431

VL - 2017-January

SP - 1716

EP - 1721

BT - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -