PRACTICAL APPS: Controlling robotic devices with the mind alone will benefit the lives of paralyzed patients and those with movement disorders.

SOURCE: CARNEGIE MELLON UNIVERSITY

A team of researchers from Carnegie Mellon University, in collaboration with the University of Minnesota, has made a breakthrough in the field of noninvasive robotic device control. Using a noninvasive brain-computer interface (BCI), researchers have developed the first-ever successful mind-controlled robotic arm exhibiting the ability to continuously track and follow a computer cursor.

Being able to noninvasively control robotic devices using only thoughts will have broad applications, in particular benefiting the lives of paralyzed patients and those with movement disorders.

BCIs have been shown to achieve good performance for controlling robotic devices using only the signals sensed from brain implants. When robotic devices can be controlled with high precision, they can be used to complete a variety of daily tasks. Until now, however, BCIs successful in controlling robotic arms have used invasive brain implants. These implants require a substantial amount of medical and surgical expertise to correctly install and operate, not to mention the cost and potential risks to subjects, and as such, their use has been limited to just a few clinical cases.

A grand challenge in BCI research is to develop less invasive or even totally noninvasive technology that would allow paralyzed patients to control their environment or robotic limbs using their own "thoughts." Such noninvasive BCI technology, if successful, would bring such much-needed technology to numerous patients and even potentially to the general population.

However, BCIs that use noninvasive external sensing, rather than brain implants, receive "dirtier" signals, leading to current lower resolution and less precise control. Thus, when using only the brain to control a robotic arm, a noninvasive BCI doesn't stand up to using implanted devices. Despite this, BCI researchers have forged ahead, their eye on the prize of a less- or non-invasive technology that could help patients everywhere on a daily basis.

Bin He, Trustee Professor and Department Head of Biomedical Engineering at Carnegie Mellon University, is achieving that goal, one key discovery at a time.

"There have been major advances in mind-controlled robotic devices using brain implants. It's excellent science," says He. "But noninvasive is the ultimate goal. Advances in neural decod ing and the practical utility of noninvasive robotic arm control will have major implications on the eventual development of noninvasive neurorobotics."

Using novel sensing and machine learning techniques, He and his lab have been able to access signals deep within the brain, achieving a high resolution of control over a robotic arm. With noninvasive neuroimaging and a novel continuous pursuit paradigm, He is overcoming the noisy EEG signals leading to significantly improve EEGbased neural decoding, and facilitating realtime continuous 2D robotic device control. The technology is directly applicable to patients, and the team plans to conduct clinical trials in the near future. The image is credited to College of Engineering, Carnegie Mellon University.

Using a noninvasive BCI to control a robotic arm that's tracking a cursor on a computer screen, for the first time ever, He has shown in human subjects that a robotic arm can now follow the cursor continuously. Whereas robotic arms controlled by humans noninvasively had previously followed a moving cursor in jerky, discrete motions–as though the robotic arm was trying to "catch up" to the brain's commands– now, the arm follows the cursor in a smooth, continuous path.

In a paper published in Science Robotics, the team established a new framework that addresses and improves upon the "brain" and "computer" components of BCI by increasing user engagement and training, as well as spatial resolution of noninvasive neural data through EEG source imaging.

The paper, "Noninvasive neuroimaging enhances continuous neural tracking for robotic device control," shows that the team's unique approach to solving this problem not enhanced BCI learning by nearly 60% for traditional center-out tasks, it also enhanced continuous tracking of a computer cursor by over 500%.

The technology also has applications that could help a variety of people, by offering safe, noninvasive "mind control" of devices that can allow people to interact with and control their environments. The technology has, to date, been tested in 68 able-bodied human subjects (up to 10 sessions for each subject), including virtual device control and controlling of a robotic arm for continuous pursuit. The technology is directly applicable to patients, and the team plans to conduct clinical trials in the near future.

"Despite technical challenges using noninvasive signals, we are fully committed to bringing this safe and economic technology to people who can benefit from it," says He. "This work represents an important step in noninvasive brain-computer interfaces, a technology which someday may become a pervasive assistive technology aiding everyone, like smartphones."•

ABOUT THIS NEUROSCIENCE RESEARCH ARTICLE:

Source: Carnegie Mellon University

Image Source: The image is credited to College of Engineering, Carnegie Mellon University.

Funding: This work was supported in part by the National Center for Complementary and Integrative Health, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, and National Institute of Mental Health.

Original Research: Open access; "Noninvasive neuroimaging enhances continuous neural tracking for robotic device control". B. J. Edelman, J. Meng, D. Suma, C. Zurn, E. Nagarajan, B. S. Baxter, C. C. Cline and B. He. Science Robotics. doi:10.1126/scirobotics.aaw6844

Abstract: Noninvasive neuroimaging enhances continuous neural tracking for robotic device control Brain-computer interfaces (BCIs) using signals acquired with intracortical implants have achieved successful high-dimensional robotic device control useful for completing daily tasks. However, the substantial amount of medical and surgical expertise required to correctly implant and operate these systems greatly limits their use beyond a few clinical cases. A noninvasive counterpart requiring less intervention that can provide high-quality control would profoundly improve the integration of BCIs into the clinical and home setting. Here, we present and validate a noninvasive framework using electroencephalography (EEG) to achieve the neural control of a robotic device for continuous random target tracking. This framework addresses and improves upon both the "brain" and "computer" components by increasing, respectively, user engagement through a continuous pursuit task and associated training paradigm and the spatial resolution of noninvasive neural data through EEG source imaging. In all, our unique framework enhanced BCI learning by nearly 60% for traditional center-out tasks and by more than 500% in the more realistic continuous pursuit task. We further demonstrated an additional enhancement in BCI control of almost 10% by using online noninvasive neuroimaging. Last, this framework was deployed in a physical task, demonstrating a near-seamless transition from the control of an unconstrained virtual cursor to the real-time control of a robotic arm. Such combined advances in the quality of neural decoding and the practical utility of noninvasive robotic arm control will have major implications for the eventual development and implementation of neurorobotics by means of noninvasive BCI.