Evaluation of an adaptive hybrid tongue-brain control framework by
individuals with amyotrophic lateral sclerosis
Abstract
Preprint submitted to IOP Journal of Neural Engineering
Objective. Individuals with Amyotrophic lateral sclerosis (ALS)
progressively lose muscle functionality and therefore experience both an
increased need for assistive robot technologies and a reduced ability to
control such robots. While these individuals may use high-performing
control systems, such as tongue control, at the beginning of their
disease progression, they will eventually be restricted to a
lower-performing control system, such as brain control. However, an
adaptive multimodal control interface framework consisting of
combinations of tongue control and noninvasive brain control can utilize
the residual tongue functionality to optimize the control performance
throughout the disease progression.
Approach. To investigate this concept, a new adaptive tongue-brain
multimodal control framework for manual and continuous control of a
7-degree-of-freedom robot arm is developed, based on a prior validation
study. The new framework focuses on improved visual feedback, as
individuals with ALS specifically requested this in a previous
validation study, and consists of four subsystems: the first uses full
tongue control; the second and third use hybrid tongue and noninvasive
brain control, with a decreasing need for tongue functionality; and the
fourth uses noninvasive brain control only. The framework was evaluated
with three participants with ALS.
Main results. All participants were succesful with all subsystems. One
user could no longer efficiently use the full tongue control interface
but achieved good results with the third and fourth subsystems. The
second participant achieved significantly better results with the
subsystems that included some tongue control, thereby showing the
advantage of including some tongue control. The third participant
performed well with all subsystems showing the ideal performance
progression between each subsystem. Moreover, all participants,
including the two with good tongue control, chose a multimodal control
interface as their favorite.
Significance. The results indicate that individuals with ALS prefer
interfaces that combine multiple control modalities.