Grasp Prediction Toward Naturalistic Exoskeleton Glove Control

Abstract

This paper presents accurate grasp prediction algorithms that can be used for naturalistic, synergistic control of exoskeleton gloves with minimal user input. Recent research in exoskeleton systems has focused mainly on the development of novel soft or hard mechanical designs and actuation systems for rehabilitative and assistive applications. On the other hand, estimating user intent for intelligent grasp assistance is a problem that has remained largely unaddressed. As demonstrated by existing studies, the complex motions of human hand can be mapped to a latent space, thereby reducing perceived noise in individual joint angles as well as the number of variables upon which the prediction must be performed. To this extent, we present two latent space grasp prediction algorithms for intelligent exoskeleton glove control. The first presented algorithm is based on a linear regression to determine the slope and prediction horizon. The second algorithm is based on a Gaussian process trajectory matching where the trajectory of the grasping motion is probabilistically compared to existing data in order to form a prediction. Both algorithms were tested on published motion data collected from healthy subjects. In addition, the experimental validation of the algorithms was done using the RML glove (Robotics and Mechatronics Lab), which yielded similar prediction accuracy as compared to the simulation results. The proposed prediction algorithm can act as the backbone for a shifting authority controller that simultaneously amplifies the user's motion while guiding them toward their desired grasp. Preliminary work in this direction is also described in the paper, with directions for future research.

A New Intelligent Approach for Deaf/Dumb People based on Deep Learning

“…The use of convolutional neural networks on 6 grasp classifications using a piezoresistive data glove was proposed by Ayodele et al [20], and the average classification accuracy of the convolutional neural networks (CNN) algorithm was 88.27 percent in the object-seen and 75.73 percent in the object-unseen scenarios, respectively. Chauhan et al [21] reported grab prediction algorithms for 5 activities that can be employed for naturalistic, synergistic control of exoskeleton gloves, with an average accuracy of about 75%. Convolution Neural Networks was used to translate a video clip of ASL signals into text.…”

Dynamic Analysis and Experimental Study of Lasso Transmission for Hand Rehabilitation Robot

“…By moving the remote host to a more convenient position, maintaining a rigid structure, or combined with a flexible fabric structure, this method frees the remote from the heavy driving unit and electronic equipment, thus increasing the portability, comfort, and usability of the equipment [22][23][24][25]. Although the development of this drive system aims to improve usability, reduce weight, and maximize compliance, the inevitable cost is the decrease in strength and accuracy compared with the traditional rigid exoskeleton [26][27][28][29]. As shown in Figure 1a, Dario Marconi designed a new index finger-thumb exoskeleton named HX-β for hand rehabilitation by lasso transmission, which allowed the thumb to flex/extend and rotate independently, thus realizing various natural and functional grasping configurations [30].…”

Data-efficient human walking speed intent identification

“…Autonomous mobile robots may navigate around moving humans (Aoude et al, 2013 ), whereas robotic lower-limb prostheses (Wentink et al, 2013 ; Yuan et al, 2022 ) and exoskeletons (Jung et al, 2012 ; Zhang et al, 2022b ) support stable, efficient gait in coordination with the user. These applications all require the ability to reason about what the human aims to accomplish (Malmi, 2013 ; Abbink et al, 2018 ; Chauhan et al, 2019 ; Khalin et al, 2021 ; Kalinowska et al, 2023 ). Robots assisting locomotion rely on a variety of sensors to glean information related to the human’s intentions.…”