CiteScore 3.36
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Robot. AI | doi: 10.3389/frobt.2019.00124

Tactile Signatures and Hand Motion Intent Recognition for Wearable Assistive Devices

 Thekla Stefanou1, 2, 3*,  Greg Chance1, 2, Tareq Assaf4 and Sanja Dogramadzi1, 3
  • 1Bristol Robotics Laboratory, United Kingdom
  • 2University of Bristol, United Kingdom
  • 3University of the West of England, United Kingdom
  • 4University of Bath, United Kingdom

Within the field of robotics and autonomous systems, intent recognition is crucial when human and robot workspaces overlap. This is especially true with wearable devices and in particular those used for assistive or rehabilitative purposes. 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 gripping. To investigate this concept a series of experiments with healthy participants were carried out using a tactile arm brace (TAB) on the forearm to perform 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 on the TAB aligned with the anticipated force patterns. Furthermore, there was a linear separability of the data across the four grip types. 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.

Keywords: Motion intent, Wearabe sensors, upper-limb, tactile sensing, assistive devices

Received: 22 Apr 2019; Accepted: 04 Nov 2019.

Copyright: © 2019 Stefanou, Chance, Assaf and Dogramadzi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Ms. Thekla Stefanou, Bristol Robotics Laboratory, Bristol, United Kingdom, thekla.stefanou@bristol.ac.uk