Dataset Information

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices.

ABSTRACT: Within the field of robotics and autonomous systems where there is a human in the loop, intent recognition plays an important role. This is especially true for wearable assistive devices used for rehabilitation, particularly post-stroke recovery. This paper reports results on the use of tactile patterns to detect weak muscle contractions in the forearm while at the same time associating these patterns with the muscle synergies during different grips. To investigate this concept, a series of experiments with healthy participants were carried out using a tactile arm brace (TAB) on the forearm while performing four different types of grip. The expected force patterns were established by analysing the muscle synergies of the four grip types and the forearm physiology. The results showed that the tactile signatures of the forearm recorded on the TAB align with the anticipated force patterns. Furthermore, a linear separability of the data across all four grip types was identified. Using the TAB data, machine learning algorithms achieved a 99% classification accuracy. The TAB results were highly comparable to a similar commercial intent recognition system based on a surface electromyography (sEMG) sensing.

SUBMITTER: Stefanou T

PROVIDER: S-EPMC7805773 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices.

Stefanou Thekla T Chance Greg G Assaf Tareq T Dogramadzi Sanja S

Frontiers in robotics and AI 20191121

Within the field of robotics and autonomous systems where there is a human in the loop, intent recognition plays an important role. This is especially true for wearable assistive devices used for rehabilitation, particularly post-stroke recovery. This paper reports results on the use of tactile patterns to detect weak muscle contractions in the forearm while at the same time associating these patterns with the muscle synergies during different grips. To investigate this concept, a series of expe ...[more]

PMID: 33501139

Similar Datasets

Project description:BackgroundRobotic hand orthoses (RHO) aim to provide grasp assistance for people with sensorimotor hand impairment during daily tasks. Many of such devices have been shown to bring a functional benefit to the user. However, assessing functional benefit is not sufficient to evaluate the usability of such technologies for daily life application. A comprehensive and structured evaluation of device usability not only focusing on effectiveness but also efficiency and satisfaction is required, yet often falls short in existing literature. Mixed methods evaluations, i.e., assessing a combination of quantitative and qualitative measures, allow to obtain a more holistic picture of all relevant aspects of device usability. Considering these aspects already in early development stages allows to identify design issues and generate generalizable benchmarks for future developments.MethodsWe evaluated the short-term usability of the RELab tenoexo, a RHO for hand function assistance, in 15 users with tetraplegia after a spinal cord injury through a comprehensive mixed methods approach. We collected quantitative data using the Action Research Arm Test (ARAT), the System Usability Scale (SUS), and timed tasks such as the donning process. In addition, qualitative data were collected through semi-structured interviews and user observations, and analyzed with a thematic analysis to enhance the usability evaluation. All insights were attributed and discussed in relation to specifically defined usability attributes such as comfort, ease of use, functional benefit, and safety.ResultsThe RELab tenoexo provided an immediate functional benefit to the users, resulting in a mean improvement of the ARAT score by 5.8 points and peaking at 15 points improvement for one user (clinically important difference: 5.7 points). The mean SUS rating of 60.6 represents an adequate usability, however, indicating that especially the RHO donning (average task time = 295 s) was perceived as too long and cumbersome. The participants were generally very satisfied with the ergonomics (size, dimensions, fit) of the RHO. Enhancing the ease of use, specifically in donning, increasing the provided grasping force, as well as the availability of tailoring options and customization were identified as main improvement areas to promote RHO usability.ConclusionThe short-term usability of the RELab tenoexo was thoroughly evaluated with a mixed methods approach, which generated valuable data to improve the RHO in future iterations. In addition, learnings that might be transferable to the evaluation and design of other RHO were generated, which have the potential to increase the daily life applicability and acceptance of similar technologies.

Dataset Information

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices.

Publications

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets