9:00 a.m.
Poster Session by McNair Scholars and McNair M.D./Ph.D. Students
7th Floor Lounge, Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital
10:00 a.m.
Keynote by Dr. Thomas Reardon
Auditorium, Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital
11:00 a.m.
McNair Scholar Oral Presentation
Trey Westbrook, Ph.D.
Founder & Executive Director, Therapeutic Innovation Center
McNair Scholar
Robert A. Welch Chair in Chemistry
McNair M.D./Ph.D. Scholar Oral Presentation
Thomas Gebert, M.D./Ph.D. candidate
7th Floor Lounge, Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital
Since the advent of computing, humans have sought interfaces for computer input that are expressive, intuitive and universal. While diverse modalities have been developed – including keyboards, mice, and touchscreens – each requires interaction with an intermediary device that poses constraints, especially in mobile scenarios. Gesture-based interaction systems using cameras or inertial sensors support more natural interaction schemes but constrain users with cumbersome head-mounted camera systems or a confined field of view.
Brain-computer interfaces (BCIs) have been imagined for decades to solve the interface problem by allowing for input to computing devices at the speed of thought. However, high-bandwidth communication has been demonstrated using only invasive BCIs with interaction models designed for single individuals, an approach that cannot scale to the general public. Here we describe the development of a noninvasive neuromotor interface that allows for computer input using surface electromyography (sEMG).
We developed a highly sensitive and robust hardware platform that is easily donned to sense myoelectric activity at the wrist and transform intentional neuromotor commands into computer input. We paired this device with an infrastructure optimized to collect training data from thousands of consenting participants. This allowed us to develop generic sEMG neural network decoding models that work across many people without the need for per-person calibration. Users not included in the training set demonstrate closed-loop median performance of gesture decoding at 0.5 target acquisitions per second in a continuous navigation task, 0.9 gesture detections per second in a discrete gesture task, and handwriting at 19.6 words per minute. We demonstrate that input bandwidth can be further improved up to 30% by personalizing sEMG decoding models to the individual, anticipating a future in which humans and machines co-adapt to provide seamless translation of human intent into digital interactions.
To our knowledge, this is the first high-bandwidth neuromotor interface that directly leverages biosignals with performant out-of-the-box generalization across people.
Thomas Reardon, Ph.D., is a neuroscientist and entrepreneur and serves as vice president of Research and head of Neural Interfaces at Meta. His company, CTRL-Labs, was acquired by Meta in 2019.
Dr. Reardon trained under Tom Jessell, Ph.D., the former Claire Tow Professor of Biochemistry and Molecular Biophysics at Columbia University. Dr. Reardon’s studies focused on the neural circuits of volitional movement. Before pursuing his Ph.D. research, Reardon had a storied career in software development and is best known as the creator of the Internet Explorer project at Microsoft. He was a founding board member of the World Wide Web Consortium and contributed widely to the early architecture of the Web, its protocols and standards.
Today, alongside a team of computational neuroscientists and biotech engineers at CTRL-Labs, Dr. Reardon is developing novel non-invasive neural controls of wearable computers for consumers.
Among other awards, Dr. Reardon was recognized in the MIT Technology Review’s 2003 Innovators Under 35 list. He sits on the board of visitors of Columbia University School of General Studies as well as the board of directors of the Zuckerman Institute at Columbia and at Transportation Alternatives.
With special thanks to the McNair Medical Institute.
