Brain-computer interface with adaptations for high-speed, accurate, and intuitive user interactions

Inventors

ALCAIDE, Ramses • Padden, Dereck • JANTZ, Jay • HAMET, James • MORRIS, Jr., Jeffrey • Pereira, Arnaldo

Assignees

Neurable Inc

Abstract

Embodiments described herein relate to systems, devices, and methods for use in the implementation of a brain-computer interface that tracks brain activity, with or without additional sensors providing additional sources of information, while presenting and updating a User Interface/User Experience that is strategically designed for high speed and accuracy of human-machine interaction. Embodiments described herein also relate to the implementation of a hardware agnostic brain-computer interface that uses neural signals to mediate user manipulation of machines and devices.

Core Innovation

The invention provides a hardware-agnostic hybrid brain-computer interface that presents a control interface including a plurality of control items each associated with an action and presented at predetermined locations. A neural recording device records neural signals associated with a stimulus presented via the control interface, and an interfacing device uses memory and a processor to present the stimulus, receive the set of neural signals after presenting the stimulus, and classify the set of neural signals to identify a control signal indicative of a user's intent.

For each control item included in the stimulus, the processor calculates a probability metric indicating a probability that the control signal was evoked by that control item. The processor determines a first score for each control item based on the probability metric and a second score for each control item based on the predetermined location of that control item with respect to the predetermined location of at least one other control item from the remaining control items.

Using the first score and the second score associated with each control item, the processor determines a point of focus of the user associated with at least one control item. The disclosure also describes embodiments that determine scores using predetermined presentation locations and, in some cases, use a weighted combination of first and second scores, as well as classification strategies that include selecting classifiers and using an ensemble classifier to classify the set of neural signals.

Claims Coverage

The partial document includes three independent claim sets covering an apparatus, a non-transitory processor-readable medium, and a method. The claims share four inventive features: presenting a control interface and stimulus with control items at predetermined locations, recording and classifying neural signals to identify a control signal indicative of intent, computing a probability metric per control item with first and second scores, and determining a point of focus from the scores; the method claim further determines a predicted action intended by the user based on the point of focus.

Across the independent claims, the core claimed coverage is the combination of neural-signal classification to identify an intent-associated control signal, probability metric calculation per control item, dual scoring where the first score is neural-probability based and the second score is derived from predetermined spatial relationships among control items, and point-of-focus determination that is used to predict an intended action.

Stated Advantages

Documented Applications