Movement prediction for a lower limb exoskeleton using a conditional restricted Boltzmann machine

We propose a novel class of unsupervised learning-based algorithms that extend the conditional restricted Boltzmann machine to predict, in real-time, a lower limb exoskeleton wearer's intended movement type and future trajectory. During training, our algorithm automatically clusters unlabeled e...

Full description

Saved in:
Bibliographic Details
Published in:Robotica 2017-11, Vol.35 (11), p.2177-2200
Main Authors: Chong, Eunsuk, Park, F. C.
Format: Article
Language:English
Subjects:
Exoskeletons
Machine learning
Real time
Time series
Trajectories
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel class of unsupervised learning-based algorithms that extend the conditional restricted Boltzmann machine to predict, in real-time, a lower limb exoskeleton wearer's intended movement type and future trajectory. During training, our algorithm automatically clusters unlabeled exoskeletal measurement data into movement types. Our predictor then takes as input a short time series of measurements, and outputs in real-time both the movement type and the forward trajectory time series. Physical experiments with a prototype exoskeleton demonstrate that our method more accurately and stably predicts both movement type and the forward trajectory compared to existing methods.
ISSN:0263-5747
1469-8668
DOI:10.1017/S0263574716000795