Summary: New brain-machine interface technology allows those who are immobile to control their wheelchairs through mind control. The BMI allows users to traverse natural and messy environments after training.
Font: cell press
A mind-controlled wheelchair can help a paralyzed person gain new mobility by translating users’ thoughts into mechanical commands.
On November 18 in the newspaper iScienceResearchers show that quadriplegic users can operate mind-controlled wheelchairs in a natural and messy environment after training for a long period.
“We show that mutual learning of both the user and the brain-machine interface algorithm is important for users to successfully operate this type of wheelchair,” says José del R. Millán, corresponding author of the study at the University of Texas in Austin. “Our research highlights a potential pathway to improve the clinical translation of non-invasive brain-machine interface technology.”
Millán and his colleagues recruited three quadriplegics for the longitudinal study. Each of the participants underwent training sessions three times a week for 2 to 5 months.
The participants wore a cap that detected their brain activities via electroencephalography (EEG), which would be converted into mechanical commands for the wheelchairs via a brain-machine interface device.
Participants were asked to control the direction of the wheelchair by thinking about moving their body parts. Specifically, they needed to think about moving both hands to turn left and both feet to turn right.
In the first training session, three participants had similar levels of accuracy (when device responses aligned with users’ thoughts) of around 43% to 55%. Over the course of the training, the brain-machine interface device team saw a significant improvement in accuracy for Participant 1, who achieved over 95% accuracy by the end of his training.
The team also observed an increase in participant 3’s accuracy to 98% halfway through their training before the team updated their device with a new algorithm.
The improvement seen in participants 1 and 3 correlates with the improvement in feature discrimination, which is the algorithm’s ability to discriminate the pattern of brain activity encoded for “go left” thoughts from “go left” thoughts. the right”.
The team found that the better feature discrimination is not just the result of machine learning on the device, but also learning in the brains of the participants. The EEGs of participants 1 and 3 showed clear changes in brain wave patterns as the precision of mind control of the device improved.
“We see from the EEG results that the subject has consolidated the ability to modulate different parts of his brain to generate a pattern to ‘go left’ and a different pattern to ‘go right’”, says Millán. “We believe that a cortical reorganization occurred as a result of the learning process of the participants.”
Compared to participants 1 and 3, participant 2 had no significant changes in brain activity patterns during training. Her accuracy increased only slightly during the first few sessions, which remained stable for the rest of the training period. It suggests that machine learning alone is insufficient to successfully maneuver a mind-controlled device, Millán says.
At the end of the training, all the participants were asked to steer their wheelchairs through a crowded hospital room. They had to navigate obstacles like a room divider and hospital beds, which are set up to simulate the real world environment. Both participant 1 and 3 finished the task, while participant 2 was unable to complete it.
“It seems that for someone to acquire good control of the brain-machine interface that allows them to perform relatively complex daily activities such as driving a wheelchair in a natural environment, it requires some neuroplastic reorganization in our cortex,” says Millán.
The study also emphasized the role of long-term training in users. Although participant 1 performed exceptionally at the end, he too had problems in the first training sessions, says Millán. The longitudinal study is one of the first to assess the clinical translation of noninvasive brain-machine interface technology in quadriplegics.
Next, the team wants to find out why participant 2 did not experience the learning effect. They hope to carry out a more detailed analysis of the brain signals of all the participants to understand their differences and possible interventions for people who struggle with the learning process in the future.
About this neurotechnology research news
original research: Open access.
“Learning to control a BMI powered wheelchair for people with severe quadriplegia” by José del R. Millán et al. iScience
Learning to control a BMI powered wheelchair for people with severe quadriplegia
- Three participants learned to drive a non-invasive BMI-powered wheelchair
- Direct transfer of learned BMI skills to wheelchair control
- Subject learning and robotic intelligence are key to BMI-powered translational robots
Mind-controlled wheelchairs are an intriguing assisted mobility solution applicable in total paralysis. Despite progress in brain-machine interface (BMI) technology, its translation remains elusive.
The primary objective of this study is to test the hypothesis that end-users’ acquisition of BMI skills is critical to control a brain-powered non-invasive smart wheelchair in real-world settings.
We demonstrate that three quadriplegic spinal cord injury users could be trained to operate a noninvasive thought-controlled wheelchair, at their own pace, and perform complex navigation tasks. However, only the two users who exhibited increased feature discrimination and decoding performance, significant changes in neuroplasticity, and improved BMI command latency, achieved high browsing performance.
Furthermore, we show that dexterous and continuous control of robots is possible through discrete and uncertain low-degree-of-freedom control channels, such as a motor imaging BMI, by combining human and artificial intelligence through control methodologies. shared.
We postulate that subject learning and shared control are the key components that pave the way for translational non-invasive BMI.