Across-user adaptation for a powered lower limb prosthesis

John A. Spanias*, Ann M. Simon, Levi J. Hargrove

*Corresponding author for this work

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

3 Scopus citations

Abstract

Pattern recognition algorithms have been used to control powered lower limb prostheses because they are capable of identifying the intent of the amputee user and therefore can provide a method for seamlessly transitioning between the different locomotion modes of the prosthesis. However, one major limitation of current algorithms is that they require subject-specific data from the individual user. These data are difficult and time-consuming to collect and consequently these algorithms do not generalize well across users. We have developed an adaptive pattern recognition algorithm that automatically learns new subject-specific data acquired from a novel user during ambulation. We tested this adaptive algorithm with one transfemoral amputee subject walking on a powered knee-ankle prosthesis. Before adaptation, the algorithm, which was initially trained with data from two other transfemoral amputee subjects, made critical errors that prevented continuous ambulation. With adaptation, error rates dropped from 4.21% before adaptation to 1.25% after adaptation, and allowed the novel amputee user to complete all mode transitions. This study demonstrates that adaptation can decrease error rates over time and can allow pattern recognition algorithms to generalize to novel users.

Original languageEnglish (US)
Title of host publication2017 International Conference on Rehabilitation Robotics, ICORR 2017
EditorsArash Ajoudani, Panagiotis Artemiadis, Philipp Beckerle, Giorgio Grioli, Olivier Lambercy, Katja Mombaur, Domen Novak, Georg Rauter, Carlos Rodriguez Guerrero, Gionata Salvietti, Farshid Amirabdollahian, Sivakumar Balasubramanian, Claudio Castellini, Giovanni Di Pino, Zhao Guo, Charmayne Hughes, Fumiya Iida, Tommaso Lenzi, Emanuele Ruffaldi, Fabrizio Sergi, Gim Song Soh, Marco Caimmi, Leonardo Cappello, Raffaella Carloni, Tom Carlson, Maura Casadio, Martina Coscia, Dalia De Santis, Arturo Forner-Cordero, Matthew Howard, Davide Piovesan, Adriano Siqueira, Frank Sup, Masia Lorenzo, Manuel Giuseppe Catalano, Hyunglae Lee, Carlo Menon, Stanisa Raspopovic, Mo Rastgaar, Renaud Ronsse, Edwin van Asseldonk, Bram Vanderborght, Madhusudhan Venkadesan, Matteo Bianchi, David Braun, Sasha Blue Godfrey, Fulvio Mastrogiovanni, Andrew McDaid, Stefano Rossi, Jacopo Zenzeri, Domenico Formica, Nikolaos Karavas, Laura Marchal-Crespo, Kyle B. Reed, Nevio Luigi Tagliamonte, Etienne Burdet, Angelo Basteris, Domenico Campolo, Ashish Deshpande, Venketesh Dubey, Asif Hussain, Vittorio Sanguineti, Ramazan Unal, Glauco Augusto de Paula Caurin, Yasuharu Koike, Stefano Mazzoleni, Hyung-Soon Park, C. David Remy, Ludovic Saint-Bauzel, Nikos Tsagarakis, Jan Veneman, Wenlong Zhang
PublisherIEEE Computer Society
Pages1580-1583
Number of pages4
ISBN (Electronic)9781538622964
DOIs
StatePublished - Aug 11 2017
Event2017 International Conference on Rehabilitation Robotics, ICORR 2017 - London, United Kingdom
Duration: Jul 17 2017Jul 20 2017

Other

Other2017 International Conference on Rehabilitation Robotics, ICORR 2017
CountryUnited Kingdom
CityLondon
Period7/17/177/20/17

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Rehabilitation
  • Medicine(all)

Fingerprint Dive into the research topics of 'Across-user adaptation for a powered lower limb prosthesis'. Together they form a unique fingerprint.

Cite this