Erik D. Engeberg

Individuals who have suffered neurotrauma like a stroke or brachial plexus injury
often experience reduced limb functionality. Soft robotic exoskeletons have
been successful in assisting rehabilitative treatment and improving activities of
daily life but restoring dexterity for tasks such as playing musical instruments
has proven challenging. This research presents a soft robotic hand exoskeleton
coupled with machine learning algorithms to aid in relearning how to play the
piano by ‘feeling’ the difference between correct and incorrect versions of the
same song. The exoskeleton features piezoresistive sensor arrays with 16 taxels
integrated into each fingertip. The hand exoskeleton was created as a single unit,
with polyvinyl acid (PVA) used as a stent and later dissolved to construct the
internal pressure chambers for the five individually actuated digits. Ten variations
of a song were produced, one that was correct and nine containing rhythmic
errors. To classify these song variations, Random Forest (RF), K-Nearest Neighbor
(KNN), and Artificial Neural Network (ANN) algorithms were trained with data
from the 80 taxels combined from the tactile sensors in the fingertips. Feeling the
differences between correct and incorrect versions of the song was done with
the exoskeleton independently and while the exoskeleton was worn by a person.
Results demonstrated that the ANN algorithm had the highest classification
accuracy of 97.13% ± 2.00% with the human subject and 94.60% ± 1.26% without.
These findings highlight the potential of the smart exoskeleton to aid disabled
individuals in relearning dexterous tasks like playing musical instruments.

Current research in prosthetic device design aims to mimic natural movements using a feedback
system that connects to the patient's own nerves to control the device. The first step in
using neurons to control motion is to make and maintain contact between neurons and the
feedback sensors. Therefore, the goal of this project was to determine if changes in electrode
resistance could be detected when a neuron extended a neurite to contact a sensor.
Dorsal root ganglia (DRG) were harvested from chick embryos and cultured on a collagencoated
carbon nanotube microelectrode array for two days. The DRG were seeded along
one side of the array so the processes extended across the array, contacting about half of
the electrodes. Electrode resistance was measured both prior to culture and after the two
day culture period. Phase contrast images of the microelectrode array were taken after two
days to visually determine which electrodes were in contact with one or more DRG neurite
or tissue. Electrodes in contact with DRG neurites had an average change in resistance of
0.15 MΩ compared with the electrodes without DRG neurites. Using this method, we determined
that resistance values can be used as a criterion for identifying electrodes in contact
with a DRG neurite. These data are the foundation for future development of an autonomous
feedback resistance measurement system to continuously monitor DRG neurite outgrowth
at specific spatial locations.