Real-time intent recognition for a powered knee and ankle transfemoral prosthesis

Huseyin Atakan Varol, Michael Goldfarb

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

21 Citations (Scopus)

Abstract

This paper describes a real-time gait intent recognition approach for use in controlling a fully powered transfemoral prosthesis. Rather than utilize an "echo control" as proposed by others, which requires instrumentation of the sound-side leg, the proposed approach infers user intent based on the characteristic shape of the force and moment vector of interaction between the user and prosthesis. The real-time intent recognition approach utilizes a K-nearest neighbor algorithm with majority voting and threshold biasing schemes to increase its robustness. The ability of the approach to recognize in real time a person's intent to stand or walk at one of three different speeds is demonstrated on measured biomechanics data.

Original languageEnglish
Title of host publication2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07
Pages16-23
Number of pages8
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07 - Noordwijk, Netherlands
Duration: Jun 12 2007Jun 15 2007

Other

Other2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07
CountryNetherlands
CityNoordwijk
Period6/12/076/15/07

Fingerprint

Biomechanics
Acoustic waves
Prostheses and Implants

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Varol, H. A., & Goldfarb, M. (2007). Real-time intent recognition for a powered knee and ankle transfemoral prosthesis. In 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07 (pp. 16-23). [4428400] https://doi.org/10.1109/ICORR.2007.4428400

Real-time intent recognition for a powered knee and ankle transfemoral prosthesis. / Varol, Huseyin Atakan; Goldfarb, Michael.

2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07. 2007. p. 16-23 4428400.

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

Varol, HA & Goldfarb, M 2007, Real-time intent recognition for a powered knee and ankle transfemoral prosthesis. in 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07., 4428400, pp. 16-23, 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07, Noordwijk, Netherlands, 6/12/07. https://doi.org/10.1109/ICORR.2007.4428400
Varol HA, Goldfarb M. Real-time intent recognition for a powered knee and ankle transfemoral prosthesis. In 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07. 2007. p. 16-23. 4428400 https://doi.org/10.1109/ICORR.2007.4428400
Varol, Huseyin Atakan ; Goldfarb, Michael. / Real-time intent recognition for a powered knee and ankle transfemoral prosthesis. 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07. 2007. pp. 16-23
@inproceedings{c5118547bf4f4e23af78dab8161dd4a4,
title = "Real-time intent recognition for a powered knee and ankle transfemoral prosthesis",
abstract = "This paper describes a real-time gait intent recognition approach for use in controlling a fully powered transfemoral prosthesis. Rather than utilize an {"}echo control{"} as proposed by others, which requires instrumentation of the sound-side leg, the proposed approach infers user intent based on the characteristic shape of the force and moment vector of interaction between the user and prosthesis. The real-time intent recognition approach utilizes a K-nearest neighbor algorithm with majority voting and threshold biasing schemes to increase its robustness. The ability of the approach to recognize in real time a person's intent to stand or walk at one of three different speeds is demonstrated on measured biomechanics data.",
author = "Varol, {Huseyin Atakan} and Michael Goldfarb",
year = "2007",
doi = "10.1109/ICORR.2007.4428400",
language = "English",
isbn = "1424413206",
pages = "16--23",
booktitle = "2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07",

}

TY - GEN

T1 - Real-time intent recognition for a powered knee and ankle transfemoral prosthesis

AU - Varol, Huseyin Atakan

AU - Goldfarb, Michael

PY - 2007

Y1 - 2007

N2 - This paper describes a real-time gait intent recognition approach for use in controlling a fully powered transfemoral prosthesis. Rather than utilize an "echo control" as proposed by others, which requires instrumentation of the sound-side leg, the proposed approach infers user intent based on the characteristic shape of the force and moment vector of interaction between the user and prosthesis. The real-time intent recognition approach utilizes a K-nearest neighbor algorithm with majority voting and threshold biasing schemes to increase its robustness. The ability of the approach to recognize in real time a person's intent to stand or walk at one of three different speeds is demonstrated on measured biomechanics data.

AB - This paper describes a real-time gait intent recognition approach for use in controlling a fully powered transfemoral prosthesis. Rather than utilize an "echo control" as proposed by others, which requires instrumentation of the sound-side leg, the proposed approach infers user intent based on the characteristic shape of the force and moment vector of interaction between the user and prosthesis. The real-time intent recognition approach utilizes a K-nearest neighbor algorithm with majority voting and threshold biasing schemes to increase its robustness. The ability of the approach to recognize in real time a person's intent to stand or walk at one of three different speeds is demonstrated on measured biomechanics data.

UR - http://www.scopus.com/inward/record.url?scp=48349121261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48349121261&partnerID=8YFLogxK

U2 - 10.1109/ICORR.2007.4428400

DO - 10.1109/ICORR.2007.4428400

M3 - Conference contribution

SN - 1424413206

SN - 9781424413201

SP - 16

EP - 23

BT - 2007 IEEE 10th International Conference on Rehabilitation Robotics, ICORR'07

ER -