Brain Machine Interface Enables Mind-Controlled Wheelchairs

Source: Geralt/Pixabay

A new study published in iScience, a Cell Press journal, reveals how the severely paralyzed can drive wheelchairs with thoughts in a realistic environment after non-invasively training an artificial intelligence (AI)-enabled brain-machine interface (BMI) algorithm.

“The primary objective of this study is to probe the hypothesis that BMI skill acquisition by end-users is fundamental to control a non-invasive brain-actuated intelligent wheelchair in real-world settings,” wrote The University of Texas at Austin research study authors.

Brain-machine interfaces, also known as brain-computer interfaces (BCIs), are neurotechnology devices that enable the decoding of human brain activity into commands that may operate devices such as smartphones, computers, robotic limbs, and wheelchairs.

“In this work, we demonstrate that three individuals affected by severe tetraplegia after spinal cord injury (SCI) learned to operate a self-paced sensorimotor rhythm (SMR)-based BMI to drive an intelligent robotic wheelchair in real-world scenarios with different degrees of proficiency,” the researchers wrote.

The three male quadriplegic, also known as tetraplegic, participants in the study were existing wheelchair users due to spinal cord injuries. The neural activity of the participants was recorded noninvasively via an electroencephalography (EEG) skullcap while seated in a wheelchair training three times per week over a specific period of either two, three, or five months.

The technology used for the study includes Matlab, OpenGL, Robotic Operating System (ROS), eego™sport by ANT Neuro, TDX SP2 by Invacare, and Hokuyo URG-04LX-UG01.

To train the brain-machine interface, the participants were asked to think about specific movements with visual prompts. After training the brain-machine interface, the participants were tasked with operating the wheelchair with their thoughts in a cluttered, real-world environment.

“Our work shows that the participants’ ability to navigate in a natural, cluttered clinical environment is directly proportional to the acquired BMI skills,” the scientists reported.

Two out of the three participants had notable changes in neural activity patterns as their accuracy in operating the brain-machine interface device improved. The remaining participant had relatively consistent neural activity during the period. Aside from a small boost in accuracy in the initial training, his performance plateaued and didn’t vary much subsequently.

The power of AI and human learning

Based on the participants’ individual performances, the researchers learned that the machine learning algorithm’s ability to distinguish and decode the brain activity for different movement commands was a function of both the AI and human learning of the participants.

The researchers discovered that shared control with robotic artificial intelligence and subject learning are both critical components for translational noninvasive brain-machine interfaces.

With these new insights, the researchers suggest that future studies should explore ways to “couple machine learning and subject learning” and that “larger studies are needed to determine the exact translational potential of BMI assistive robotic technology.”

“The results achieved in this work allow us to highlight how shared-control—and, in general, human-robot interaction approaches and collaborative robotics—may support the user to achieve safety, efficiency, and usability of the brain-controlled wheelchair, especially in the case of mediocre BMI performance,” concluded the scientists.

Copyright © 2022 Cami Rosso All rights reserved.