Novel Soft Smart Shoes for Motion Intent Learning of Lower Limbs Using LSTM With a Convolutional Autoencoder

Estimating the joint torques of lower limbs in human gait, known as motion intent understanding, is of great significance in the control of lower limb exoskeletons. This study presents novel soft smart shoes designed for motion intent learning at unspecified walking speeds using long short-term memo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors journal Jg. 21; H. 2; S. 1906 - 1917
Hauptverfasser: Yang, Jiantao, Yin, Yuehong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 15.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Convolution
Convolutional autoencoder
Data structures
Exoskeletons
Feature extraction
Foot
Footwear
Gait
Human motion
Image sensors
Intelligent sensors
Learning
Limbs
long short-term memory
motion intent learning
Motion sensors
Shoes
Short term
soft smart shoes
Three dimensional motion
Torque
Walking
ISSN:1530-437X, 1558-1748
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Estimating the joint torques of lower limbs in human gait, known as motion intent understanding, is of great significance in the control of lower limb exoskeletons. This study presents novel soft smart shoes designed for motion intent learning at unspecified walking speeds using long short-term memory with a convolutional autoencoder. The smart shoes serve as a wearable sensing system consisting of a soft instrumented sole and two 3D motion sensors that are nonintrusive to the human gait and comfortable for the wearers. A novel data structure is developed as a "sensor image" for the measured ground reaction force and foot motion. A convolutional autoencoder is established to fuse multisensor datasets and extract the hidden features of the sensor images, which represent the spatial and temporal correlations among the data. Then, long short-term memory is exploited to learn the multiscale, highly nonlinear input-output relationships between the acquired features and joint torques. Experiments were conducted on five subjects at three walking speeds (0.8 m/s, 1.2 m/s, and 1.6 m/s). Results showed that 98% of the <inline-formula> <tex-math notation="LaTeX">{r}^{2} </tex-math></inline-formula> values were acceptable in individual testing and 75% of the <inline-formula> <tex-math notation="LaTeX">{r}^{2} </tex-math></inline-formula> values were acceptable in interindividual testing. The proposed method is able to learn the join torques in human gait and has satisfactory generalization properties.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2020.3019053