A team of researchers from Carnegie Mellon University in Pittsburgh USA, in collaboration with the University of Minnesota, has achieved a breakthrough that could mainly benefit patients with some type of paralysis and those with movement disorders.

Using a non-invasive brain-computer interface (BCI), scientists have developed the first mind-controlled robotic arm that exhibits the ability to continuously track and follow a computer’s cursor.

BCIs have been shown to effectively control robotic devices using only the signals detected in non-invasive brain implants.. When the devices can be controlled with high precision, they can be used to complete a variety of daily tasks.

However, at present, successful BCIs to control robotic arms have required invasive brain implants (placed via brain surgery). These implants require a great deal of medical and surgical expertise to install and operate correctly, not to mention the potential costs and risks to the subjects, and as such their use has been limited to a few clinical cases. Play

A major challenge in BCI research is developing a less invasive or even totally non-invasive technology that allows paralyzed patients to control their surroundings or robotic limbs using their own “thoughts.”

Such non-invasive BCI technology, if successful, would bring new hope to numerous patients and potentially even the general population.

However,ICBs that use non-invasive external sensors, rather than brain implants, they receive “dirtier” signals, leading to lower resolution and less precise control.

Bin He, the professor and head of the Department of Biomedical Engineering at Carnegie Mellon University, is achieving that goal, one key step at a time.

“There have been major advances in mind-controlled robotic devices, but non-invasiveness is the end goal.

This device can have various practical applications in medicine, engineering among many other areas Photo: Video screen printing Carnegie Mellon University
This device can have various practical applications in medicine, engineering among many other areas Photo: Video screen printing Carnegie Mellon University

Using new detection techniques and machine learning, éHe and his lab have been able to access signals deep in the brain, achieving a high resolution in terms of control over a robotic arm.

With a non-invasive neuroimaging and a novel continuous search paradigm,he is overcoming the noisy electroencephalogram (EEG) signals that lead to significantly improved neural decoding based on EEG and facilitating the control of continuous 2D robotic devices in real time.

Their study, published in Science Robotics, the team has shown en human subjects that a robotic arm can now follow a computer cursor in a smooth, continuous path, something that had not been achieved.

Su técnica no solo mejora el aprendizaje BCI en casi un 60% para las tareas tradicionales de centrado, sino que también mejora el seguimiento continuo de un cursor de computadora por encima del 500%.

La tecnología, hasta la fecha, ha sido probada en 68 sujetos humanos (hasta 10 sesiones para cada sujeto), incluido el control de dispositivos virtuales y el control de un brazo robótico para la búsqueda continua. Técnica que es directamente aplicable a los pacientes, y el equipo planea realizar ensayos clínicos en un futuro próximo.

Fuente: https://www.infobae.com