Researchers Incorporate Machine Learning Into Brain-Computer Interface

Researchers Incorporate Machine Learning Into Brain-Computer Interface
Researchers incorporated machine learning into the brain-computer interface. This solution can understand the needs of a subject and self-calibrate.
Technology Briefing


A real-world interface developed by engineers at The University of Texas at Austin let’s people play racing games like Mario Kart, using only their brains to execute the complex series of turns in a lap. It was created as part of research intended to help improve the lives of people with motor disabilities. Most importantly, the researchers incorporated machine learning capabilities into the brain-computer interface, making it a one size-fits-all solution.

Typically, such technology requires extensive calibration for each user because every brain is different and that has been a major hurdle to mainstream adoption. On the contrary, this new solution can quickly understand the needs of an individual subject and self-calibrate through repetition. That means multiple patients could use the device without needing to fine tune it to work with each individual user.

In a clinical setting, this technology eliminates the need for a specialized team to do a long and tedious calibration process. As described in the journal PNAS Nexus, the subject wears a cap packed with electrodes that is hooked up to a computer. The electrodes gather data by measuring electrical signals from the brain, and a decoder interprets that information and translates it into game action.

This work on brain-computer interfaces helps users guide and strengthen the ability of the brain to change, grow and reorganize over time. The process improves brain function for patients while using the devices controlled by the brain-computer interfaces to make their lives easier. The researchers describe this work as foundational, in that it sets the stage for further brain-computer interface innovation.

This first phase of the project used 18 subjects with no motor impairments. Later the researchers plan to test this interface on people with motor impairments and apply it to larger groups in clinical settings. In addition to this application, the researchers are working on a wheelchair that users can drive with the brain-computer interface.

At the most recent South by Southwest Conference and Festival, the researchers showed off another potential use of the technology: controlling two rehabilitation robots for the hand and arm. Several people volunteered and succeeded in operating the brain-controlled robots within minutes.


No comments have been submitted to date.

Submit A Comment

Comments are reviewed prior to posting. You must include your full name to have your comments posted. We will not post your email address.

Your Name

Your Company
Your E-mail

Your Country
Your Comments