Efficient Multiaxial Shoulder-Motion Tracking Based on Flexible Resistive Sensors Applied to Exosuits

Abstract

This article describes the performance of a flexible resistive sensor network to track shoulder motion. This system monitors every gesture of the human shoulder in its range of motion except rotations around the longitudinal axis of the arm. In this regard, the design considers the movement of the glenohumeral, acromioclavicular, sternoclavicular, and scapulothoracic joints. The solution presented in this work considers several sensor configurations and compares its performance with a set of inertial measurement units (IMUs). These devices have been put together in a shoulder suit with Optitrack visual markers in order to be used as pose ground truth. Optimal configurations of flexible resistive sensors, in terms of accuracy requirements and number of sensors, have been obtained by applying principal component analysis techniques. The data provided by each configuration are then mapped onto the shoulder pose by using neural network algorithms. According to the results shown in this article, a set of flexible resistive sensors can be an adequate alternative to IMUs for multiaxial shoulder pose tracking in open spaces. Furthermore, the system presented can be easily embedded in fabric or wearable devices without obstructing the user's motion.

Textile Technology for Soft Robotic and Autonomous Garments

“…Others have sought to optimize sensor integration by investigating the minimal number of distributed sensors required to track multi‐DOF motion of the body, comparing to video‐based motion tracking system results as ground truths. [ 15,511 ] In a shirt that uses textile sensors to estimate shoulder kinematics, machine learning algorithms helped the researchers down‐select from eight to four sensors for motion tracking. [ 15 ] Regardless of the sensor architecture and underlying mechanism, choice of location of integration and sensor network design could benefit from experiment‐based studies when implemented into wearable robots.…”

Soft-Wearable Device for the Estimation of Shoulder Orientation and Gesture

“…Using a configuration of seven one-axis sensors, as in previous work [21], it is possible to obtain 95% of the variance of the principal components for the shoulder gestures. The configuration proposed in this paper places only an array of four flexion sensors in the intermediate positions due to the fact that they provide flexion measurements in two axes.…”

Efficient Upper Limb Position Estimation Based on Angular Displacement Sensors for Wearable Devices

“…It was proved that it is possible to obtain 95% of the variance of the main components for shoulder gestures with an array of seven single-axis resistive sensors [ 19 ]. Other results showed that it is possible to estimate the gestures of the shoulder with a performance 95.4% using an array of four WFSs and EMG signals [ 28 ].…”

“…Initially, four sADS were placed in the intermediate positions of the seven single-axis resistive sensors configuration recommended by [ 19 ]. Replicating the proposed 20-layer hidden neural network method, with a configuration for the acquired data from the four sADS of [70%, 15%, 15%] for training, cross-validation and test stages, respectively, an overfitting was identified.…”

“…It has been proved that it is possible to estimate the angles of the arm with respect to the trunk by placing sensors on the body [ 14 , 15 , 16 , 17 ]. Additionally, the use of compression jackets, combined with soft sensor arrays, makes it possible to accurately estimate the position of the limb [ 18 , 19 ], as well as to place the sensors onto the skin without the use of adhesives or other preparations such as invasive intrusions in the user’s body. However, a disadvantage of compression garments is that sweat can cause damage when it comes into contact with electronic devices.…”