Design and Evaluation of a 3d-Printed Multimodal Neuromorphic Prosthetic Limb
Naoki Aoyama
m5251101
1
Outline
2
Background
Hands play an important role in human life. For example most of people use their hands to do day-to-day tasks.
However, unfortunately, there are those who lose their hands or arms due to accidents or diseases.
It is estimated that at least 1.5 million people are living with an absence of upper limbs and prosthetic arms are still having limitations.
By using multimodal we aim to build a reliable prosthetic hand system.
3
Research Goal
To create neuromorphic prosthetic limb using image recognition and waveform recognition
4
Prosthetic hand
Creating a prosthetic hand for a child.
-> 86% of adult hands size
5
Age ＼ Average size | Height | Hand size |
12 years old | 150 cm | 16 cm |
Adults | 170 cm | 18.5 cm |
Adult
Child
Schedule
6
| 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 |
Add motors to move the fingers | | | | | | | | | |
Use image and waveform recognition control with CNN and RNN | | | | | | | | | |
Use image recognition control with SNN | | | | | | | | | |
Implement CNN and SNN control on Raspberry Pi | | | | | | | | | |
Compare performance and power consumption of SNN and CNN control on Raspberry Pi | | | | | | | | | |
Write thesis | | | | | | | | | |