Achieved! Humans are trained to control objects with their "minds."

By translating the user's mind into mechanical commands, a mind-controlled wheelchair can help paralyzed people gain new mobility
.
Researchers have shown that after a long period of training, quadriplegic patients can control wheelchairs
with their minds in a natural, cluttered environment.

"We show that mutual learning by both the user and the brain-computer interface algorithm is important for the user to successfully operate the wheelchair," said José del R.
Millán, corresponding author of the study from the University of Texas at
Austin.
"Our study highlights potential avenues
for improving clinical translation of noninvasive brain-computer interface technologies.
"

Millán and his colleagues recruited three quadriplegic people for a longitudinal study
.
Each participant received training three times a week for 2 to 5 months
.
Participants wore a beanie that detected their brain activity by electroencephalogram (EEG) and converted it into mechanical instructions
for wheelchairs via a brain-computer interface device.
Participants were asked to control the direction of
the wheelchair by thinking about moving body parts.
Specifically, they need to consider moving their hands to turn left and their feet to turn to
the right.

In the first training, when the device's response was consistent with the user's thoughts, the three participants had similar accuracy rates of about 43 to 55 percent
.
During the training, the Brain-Computer Interface Devices team found a significant improvement in Participant 1's accuracy, reaching more than
95% accuracy at the end of the training.
The team also observed that halfway through participant 3's training, the accuracy improved to 98 percent
before the team updated his device with the new algorithm.

The improvements in participants 1 and 3 correlated with improvements in feature discrimination, the ability of the algorithm to
distinguish between patterns of brain activity that "walk left" and "walk right.
" The team found that better feature recognition was not only the result of machine learning on the device, but also of brain learning in the participants
.
EEGs from participants 1 and 3 showed a noticeable change
in brainwave patterns as they improved the accuracy of their mind control devices.

Millán said: "We see from the EEG results that the subjects have consolidated the skill of regulating different parts of the brain to generate different patterns
of 'walking left' and 'walking right'.
We believe that the cerebral cortex reorganized
as a result of the participants' learning process.
”

Compared to participants 1 and 3, participant 2 did not have a significant change
in brain activity patterns throughout the training.
His accuracy improved only slightly over the first few training sessions, but remained stable
in subsequent training sessions.
Millán says this suggests that machine learning alone is not enough to successfully manipulate such a mind-controlled device

At the end of the training, all participants were asked to drive wheelchairs through the messy wards
.
They must bypass obstacles such as room dividers and hospital beds, which are set up to simulate real-world environments
.
Participants 1 and 3 both completed the task, but participant 2 did not
.

"It seems that for a person to have good brain-computer interface control that allows them to perform relatively complex daily activities, such as driving a wheelchair in a natural environment, this requires some neuroplasticity reorganization
in our cortex," Millán said.

The study also highlighted the role of
long-term training for users.
Millán said that although Participant 1 performed exceptionally well at the end, he also struggled
in the first few training sessions.
This longitudinal study is the first to
evaluate the clinical translation of noninvasive brain-computer interface technology in patients with total paralysis.

Next, the research team wanted to figure out why participant 2 did not experience the learning effect
.
They hope to conduct a more detailed analysis of brain signals from all participants to understand their differences and provide possible interventions
for future people who experience difficulties in the learning process.

Learning to control a BMI-driven wheelchair for people with severe tetraplegia