Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming

Yue Wen, Andrea Brandt, Jennie Si, He Helen Huang

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

Abstract

In this study, we validated a human-in-the-loop auto-tuner using machine learning to automatically customize powered knee prosthesis control parameters for an amputee subject in real time. The experimental powered knee prosthesis was controlled by a finite state impedance controller, which had 12 configurable impedance control parameters. Using adaptive dynamic programming with reinforcement learning while one transfemoral amputee subject walked with the powered knee prosthesis, the auto-tuner would interact with the human-prosthesis system and learn to configure the high dimension of control parameters. We tested 4 different initial conditions with one unilateral transfemoral amputee subject. The results showed that the auto-tuner discovered the control parameters that allowed amputee subject to generate normative knee kinematics in 3 out of 4 tuning sessions. For all test sessions, the averaged root-mean-square error of the knee kinematics relative to the normative knee kinematics decreased from 6.6 degrees to 4.6 degrees after tuning procedure.

Original languageEnglish (US)
Title of host publication2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-2
Number of pages2
ISBN (Electronic)9781538643778
DOIs
StatePublished - Jun 12 2018
Event2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017 - Houston, United States
Duration: Nov 5 2017Nov 8 2017

Other

Other2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017
CountryUnited States
CityHouston
Period11/5/1711/8/17

Fingerprint

Knee prostheses
Knee Prosthesis
Amputees
Adaptive Dynamics
Dynamic programming
Control Parameter
Dynamic Programming
Biomechanical Phenomena
Kinematics
Knee
Electric Impedance
Tuning
Impedance Control
Reinforcement learning
Reinforcement Learning
Mean square error
Impedance
Higher Dimensions
Prostheses and Implants
Learning systems

ASJC Scopus subject areas

  • Rehabilitation
  • Artificial Intelligence
  • Biomedical Engineering
  • Control and Optimization
  • Clinical Neurology

Cite this

Wen, Y., Brandt, A., Si, J., & Huang, H. H. (2018). Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming. In 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017 (pp. 1-2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WEROB.2017.8383835

Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming. / Wen, Yue; Brandt, Andrea; Si, Jennie; Huang, He Helen.

2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-2.

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

Wen, Y, Brandt, A, Si, J & Huang, HH 2018, Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming. in 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017. Institute of Electrical and Electronics Engineers Inc., pp. 1-2, 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017, Houston, United States, 11/5/17. https://doi.org/10.1109/WEROB.2017.8383835
Wen Y, Brandt A, Si J, Huang HH. Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming. In 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-2 https://doi.org/10.1109/WEROB.2017.8383835
Wen, Yue ; Brandt, Andrea ; Si, Jennie ; Huang, He Helen. / Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming. 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-2
@inproceedings{b61860d4c8eb479e820cc3c70a88fe15,
title = "Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming",
abstract = "In this study, we validated a human-in-the-loop auto-tuner using machine learning to automatically customize powered knee prosthesis control parameters for an amputee subject in real time. The experimental powered knee prosthesis was controlled by a finite state impedance controller, which had 12 configurable impedance control parameters. Using adaptive dynamic programming with reinforcement learning while one transfemoral amputee subject walked with the powered knee prosthesis, the auto-tuner would interact with the human-prosthesis system and learn to configure the high dimension of control parameters. We tested 4 different initial conditions with one unilateral transfemoral amputee subject. The results showed that the auto-tuner discovered the control parameters that allowed amputee subject to generate normative knee kinematics in 3 out of 4 tuning sessions. For all test sessions, the averaged root-mean-square error of the knee kinematics relative to the normative knee kinematics decreased from 6.6 degrees to 4.6 degrees after tuning procedure.",
author = "Yue Wen and Andrea Brandt and Jennie Si and Huang, {He Helen}",
year = "2018",
month = "6",
day = "12",
doi = "10.1109/WEROB.2017.8383835",
language = "English (US)",
pages = "1--2",
booktitle = "2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatically customizing a powered knee prosthesis with human in the loop using adaptive dynamic programming

AU - Wen, Yue

AU - Brandt, Andrea

AU - Si, Jennie

AU - Huang, He Helen

PY - 2018/6/12

Y1 - 2018/6/12

N2 - In this study, we validated a human-in-the-loop auto-tuner using machine learning to automatically customize powered knee prosthesis control parameters for an amputee subject in real time. The experimental powered knee prosthesis was controlled by a finite state impedance controller, which had 12 configurable impedance control parameters. Using adaptive dynamic programming with reinforcement learning while one transfemoral amputee subject walked with the powered knee prosthesis, the auto-tuner would interact with the human-prosthesis system and learn to configure the high dimension of control parameters. We tested 4 different initial conditions with one unilateral transfemoral amputee subject. The results showed that the auto-tuner discovered the control parameters that allowed amputee subject to generate normative knee kinematics in 3 out of 4 tuning sessions. For all test sessions, the averaged root-mean-square error of the knee kinematics relative to the normative knee kinematics decreased from 6.6 degrees to 4.6 degrees after tuning procedure.

AB - In this study, we validated a human-in-the-loop auto-tuner using machine learning to automatically customize powered knee prosthesis control parameters for an amputee subject in real time. The experimental powered knee prosthesis was controlled by a finite state impedance controller, which had 12 configurable impedance control parameters. Using adaptive dynamic programming with reinforcement learning while one transfemoral amputee subject walked with the powered knee prosthesis, the auto-tuner would interact with the human-prosthesis system and learn to configure the high dimension of control parameters. We tested 4 different initial conditions with one unilateral transfemoral amputee subject. The results showed that the auto-tuner discovered the control parameters that allowed amputee subject to generate normative knee kinematics in 3 out of 4 tuning sessions. For all test sessions, the averaged root-mean-square error of the knee kinematics relative to the normative knee kinematics decreased from 6.6 degrees to 4.6 degrees after tuning procedure.

UR - http://www.scopus.com/inward/record.url?scp=85049991814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049991814&partnerID=8YFLogxK

U2 - 10.1109/WEROB.2017.8383835

DO - 10.1109/WEROB.2017.8383835

M3 - Conference contribution

AN - SCOPUS:85049991814

SP - 1

EP - 2

BT - 2017 International Symposium on Wearable Robotics and Rehabilitation, WeRob 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -