Magbagbeola, Morenike;
(2022)
An AI Driven Approach to Autonomous Sensory Feedback for Upper Limb Prosthesis.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Morenike_Magbagbeola_Thesis Final.pdf - Accepted Version Download (16MB) | Preview |
Abstract
Sensory feedback in prosthesis can provide proprioceptive information on grasping, texture, and shape to individuals with limb differences. The most common non-invasive feedback mechanism is vibrational feedback, and recent research has investigated its incorporation into myoelectrically controlled prosthesis. Its presence has been found to help with control of prosthesis, increase embodiment of the device, and reduce instances of neuropathic pain. Despite this, many users do not utilize the feedback and end up rejecting the prosthesis entirely. This is partly due to the physical factors of individuals such as weight, hair and sweat which vary daily and can result in a subjective perception of the feedback for each individual. As a result, daily fine-tuning of sensory parameters before use is required to maintain accurate and intuitive feedback. This prevents long term adoption of sensory feedback into prosthesis. This work aims to address this issue by providing a novel method of autonomously maintaining perception of texture for individual users via vibrational feedback. Experiments were conducted to validate the use of EMG sensors as a means of measuring vibrations. The results show an increased accuracy in identifying vibrations in comparison to standard piezoelectric sensors and provide more information about the muscle state. The results also show a difference in dissipation patterns between individuals but similar patterns for the same individual over multiple days. Algorithms were developed to identify textures from vibration dissipation patterns in electromyography data, to correlate dissipation patterns to perceptions of texture, and finally, to control feedback parameters to maintain the perception.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | An AI Driven Approach to Autonomous Sensory Feedback for Upper Limb Prosthesis |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2022. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10152190 |
Archive Staff Only
 |
View Item |
