Brain-computer interface with high-speed eye tracking features
Inventors
ALCAIDE, Ramses • Padden, Dereck • JANTZ, Jay • HAMET, James • MORRIS, Jr., Jeffrey • Pereira, Arnaldo
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12455625-B2
Publication Date
2025-10-28
Expiration Date
Abstract
Embodiments described herein relate to systems, devices, and methods for use in the implementation of a brain-computer interface that integrates real-time eye-movement tracking with brain activity tracking to present and update a user interface 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 real-time eye tracking and online analysis of neural signals to mediate user manipulation of machines.
Core Innovation
The invention provides an apparatus with an interactive environment presented via a display. The apparatus includes an eye-tracker configured to record eye-movement signals generated by a user and a neural recording device configured to record neural signals generated by the user. An interfacing device is operatively coupled to the display, the eye-tracker, and the neural recording device, and includes memory and a processor configured to receive the eye-movement signals and the neural signals.
The processor filters the eye-movement signals using a gaze kinematics model of a set of eye-movements of a simulated user to obtain gaze data. The processor generates and presents a stimulus via the interactive environment, and processes the gaze data to detect a saccade and to determine a point of focus of the user, wherein a machine learning classifier is used to detect the saccade based on the gaze data. The processor processes the neural signals to determine an action corresponding to the point of focus that is intended by the user.
The processor implements the intended action and updates the presentation of the interactive environment. The disclosed architecture supports integration of gaze kinematics and neural recording, with ensemble processing of oculomotor and neural signals and processing adaptations including missing-data handling using the gaze kinematics model and artifact/event-driven processing. Further features include control tied to hold-release, dynamic stimulus tagging for moving objects, and adaptive stimulus presentation based on saccades.
Claims Coverage
The independent claims (clm-00001, clm-00009, clm-00017) cover a hardware-agnostic hybrid brain-computer interface for interactive control by detecting a user's point of focus from filtered eye-movement signals and a neural-intent action from recorded neural signals, using a machine learning classifier for saccade detection.
Hybrid interactive environment apparatus with gaze-kinesmatics and neural intent processing
An apparatus with a display, an eye-tracker recording eye-movement signals, a neural recording device recording neural signals, and an interfacing device that receives both signals, filters the eye-movement signals using a gaze kinematics model to obtain gaze data, generates and presents a stimulus, detects a saccade and determines a point of focus using a machine learning classifier based on the gaze data, determines an intended action from the neural signals corresponding to the point of focus, and implements the intended action to update the interactive environment.
Hybrid interactive environment method with gaze-kinesmatics and neural intent processing
A method that receives eye-movement signals from an eye-tracker and neural signals from a neural recording device, filters the eye-movement signals using a gaze kinematics model to obtain gaze data, generates and presents a stimulus via an interactive environment, processes the gaze data to detect a saccade and determine a point of focus using a machine learning classifier, processes the neural signals to determine an action corresponding to the intended point of focus, implements the intended action, and updates the presentation of the interactive environment.
Non-transitory computer-readable medium with hybrid interactive environment gaze-kinesmatics and neural intent processing
A non-transitory computer-readable medium storing code that causes a processor to receive eye-movement signals and neural signals, filter the eye-movement signals using a gaze kinematics model to obtain gaze data, generate and present a stimulus via an interactive environment, process gaze data to detect a saccade and determine a point of focus using a machine learning classifier, process neural signals to determine an intended action corresponding to the point of focus, and implement the intended action and update the presentation of the interactive environment.
Across independent claims, the inventive core is the combination of gaze-data derivation from eye-movement signals filtered using a gaze kinematics model, saccade/point-of-focus detection using a machine learning classifier, neural-signal processing to determine an intended action corresponding to the point of focus, and updating an interactive environment presentation based on the intended action.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?