Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters

Anirban Dutta; Konrad Koerding; Eric Perreault; Levi Hargrove

doi:10.1109/IEMBS.2011.6090626

Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters

Anirban Dutta^*, Konrad Koerding, Eric Perreault, Levi Hargrove

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Scopus citations

Abstract

Machine learning methods for interfacing humans with machines is an emerging area. Here we propose a novel algorithm for interfacing humans with powered lower limb prostheses for restoring control of naturalistic gait following amputation. Unlike most previous neural machine interfaces, our approach fuses control information from the user with sensor information from the prosthesis to approximate the closed loop behavior of the unimpaired sensorimotor system. We present a Bayesian framework to control an artificial knee by probabilistically mixing of process state estimates from different Kalman filters, each addressing separate regimes of locomotion such as level ground walking, walking up a ramp, and walking down a ramp. We show its utility as a mode classifier that is tolerant to temporary sensor faults which are frequently experienced in practical applications.

Original language	English (US)
Title of host publication	33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Pages	3696-3699
Number of pages	4
DOIs	https://doi.org/10.1109/IEMBS.2011.6090626
State	Published - Dec 26 2011
Event	33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States Duration: Aug 30 2011 → Sep 3 2011

Other

Other	33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Country	United States
City	Boston, MA
Period	8/30/11 → 9/3/11

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/IEMBS.2011.6090626

Fingerprint Dive into the research topics of 'Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters'. Together they form a unique fingerprint.

Cite this

@inproceedings{d6eac40c3bbb4c7c9c712e19f9a89657,

title = "Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters",

abstract = "Machine learning methods for interfacing humans with machines is an emerging area. Here we propose a novel algorithm for interfacing humans with powered lower limb prostheses for restoring control of naturalistic gait following amputation. Unlike most previous neural machine interfaces, our approach fuses control information from the user with sensor information from the prosthesis to approximate the closed loop behavior of the unimpaired sensorimotor system. We present a Bayesian framework to control an artificial knee by probabilistically mixing of process state estimates from different Kalman filters, each addressing separate regimes of locomotion such as level ground walking, walking up a ramp, and walking down a ramp. We show its utility as a mode classifier that is tolerant to temporary sensor faults which are frequently experienced in practical applications.",

author = "Anirban Dutta and Konrad Koerding and Eric Perreault and Levi Hargrove",

year = "2011",

month = dec,

day = "26",

doi = "10.1109/IEMBS.2011.6090626",

language = "English (US)",

isbn = "9781424441211",

pages = "3696--3699",

booktitle = "33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011",

note = "33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 ; Conference date: 30-08-2011 Through 03-09-2011",

}

Dutta, A, Koerding, K, Perreault, E & Hargrove, L 2011, Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters. in 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011., 6090626, pp. 3696-3699, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011, Boston, MA, United States, 8/30/11. https://doi.org/10.1109/IEMBS.2011.6090626

Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters. / Dutta, Anirban; Koerding, Konrad; Perreault, Eric ; Hargrove, Levi.

33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. p. 3696-3699 6090626.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters

AU - Dutta, Anirban

AU - Koerding, Konrad

AU - Perreault, Eric

AU - Hargrove, Levi

PY - 2011/12/26

Y1 - 2011/12/26

N2 - Machine learning methods for interfacing humans with machines is an emerging area. Here we propose a novel algorithm for interfacing humans with powered lower limb prostheses for restoring control of naturalistic gait following amputation. Unlike most previous neural machine interfaces, our approach fuses control information from the user with sensor information from the prosthesis to approximate the closed loop behavior of the unimpaired sensorimotor system. We present a Bayesian framework to control an artificial knee by probabilistically mixing of process state estimates from different Kalman filters, each addressing separate regimes of locomotion such as level ground walking, walking up a ramp, and walking down a ramp. We show its utility as a mode classifier that is tolerant to temporary sensor faults which are frequently experienced in practical applications.

AB - Machine learning methods for interfacing humans with machines is an emerging area. Here we propose a novel algorithm for interfacing humans with powered lower limb prostheses for restoring control of naturalistic gait following amputation. Unlike most previous neural machine interfaces, our approach fuses control information from the user with sensor information from the prosthesis to approximate the closed loop behavior of the unimpaired sensorimotor system. We present a Bayesian framework to control an artificial knee by probabilistically mixing of process state estimates from different Kalman filters, each addressing separate regimes of locomotion such as level ground walking, walking up a ramp, and walking down a ramp. We show its utility as a mode classifier that is tolerant to temporary sensor faults which are frequently experienced in practical applications.

UR - http://www.scopus.com/inward/record.url?scp=84055192572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84055192572&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2011.6090626

DO - 10.1109/IEMBS.2011.6090626

M3 - Conference contribution

C2 - 22255142

AN - SCOPUS:84055192572

SN - 9781424441211

SP - 3696

EP - 3699

BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011

T2 - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011

Y2 - 30 August 2011 through 3 September 2011

ER -