Skip to Main content Skip to Navigation
Conference papers

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

Anirban Dutta 1, 2 Konrad Koerding 1 Eric Perreault 1 Levi Hargrove 1
1 Department of Clinical Neurophysiology [Göttingen]
2 DEMAR - Artificial movement and gait restoration
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
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.
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-01062434
Contributor : Anirban Dutta <>
Submitted on : Tuesday, September 9, 2014 - 5:32:00 PM
Last modification on : Monday, December 14, 2020 - 3:46:13 PM

Identifiers

Collections

CNRS | INRIA | DEMAR | LIRMM | MIPS | UNIV-MONTPELLIER

Citation

Anirban Dutta, Konrad Koerding, Eric Perreault, Levi Hargrove. Sensor-fault tolerant control of a powered lower limb prosthesis by mixing mode-specific adaptive Kalman filters. EMBC: Engineering in Medicine and Biology Conference, Aug 2011, Boston, United States. pp.3696-3699, ⟨10.1109/IEMBS.2011.6090626⟩. ⟨hal-01062434⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

364

 

Contact                    Legal Notice                    Personal Data