Fernández-Martos, Juan (2024) Development of an intention detection system for the EduExo Pro exoskeleton. Bachelor's Thesis, Biomedical Engineering.
|
Text
BT-Juan-FernndezMartos-Fernndez-S4686004.pdf Download (1MB) | Preview |
|
Text
toestemming_ Juan Fernández-Martos _ degree programme_ Biomedical Engineering.pdf Restricted to Registered users only Download (136kB) |
Abstract
Exoskeletons are tools used for movement amplification or medical rehabilitation. However, these exoskeletons try to understand what the user wants to do through an intent detection system. Most intention detection systems rely on residual muscle function, making them difficult to use for certain subgroups of patients who lack these abilities. The development of systems that do not rely on residual function would be beneficial for the users. For this purpose, an intention detection system was developed for a one-degree-of-freedom upper limb exoskeleton focused on users with muscle weakness. Two MPU6050 sensors were used to determine the position of the head relative to the body. Two Grove-EMG sensors were used to perform vertical and horizontal electrooculography to detect the movement of the user's eyes. The sensors were connected to two Arduino Uno R3 boards and combined via Python. The developed algorithm was tested on a user without vision problems and in a static position. Obtaining an average accuracy of 56% in the detection of eye movement directions. However, being unable to compute the head and shoulder movement in the yaw axis, a limitation that compromises an essential function of the system. Further research focused on improving yaw axis motion measurement, the blinking detection capacity, and the detection of more complex eye movement patterns, might enhance the user experience.
Item Type: | Thesis (Bachelor's Thesis) |
---|---|
Supervisor name: | Wilhelm, E. and Roossien, C.C. |
Degree programme: | Biomedical Engineering |
Thesis type: | Bachelor's Thesis |
Language: | English |
Date Deposited: | 16 Jul 2024 11:56 |
Last Modified: | 16 Jul 2024 11:56 |
URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/33422 |
Actions (login required)
View Item |