Abstract: In particular embodiments, a computing system may capture a first image of a scene using a first camera of an artificial reality device. The system may capture a second image of the scene using a second camera and one or more optical elements of the artificial reality device. The second image may include an overlapping portion of multiple shifted copies of the scene. The system may generate an upsampled first image by applying a particular sampling technique to the first image. The system may generate a tiled image comprising a plurality of repeated second images by applying a tiling process to the second image. The system may generate an initial output image by processing the upsampled first image and the tiled image using a machine learning model. The system may generate a final output image by normalizing the initial output image using the upsampled first image.

Abstract: A distributed imaging system for augmented reality devices is disclosed. The system includes a computing module in communication with a plurality of spatially distributed sensing devices. The computing module is configured to process input images from the sensing devices based on performing a local feature matching computation to generate corresponding first output images. The computing module is further configured to process the input images based on performing an optical flow correspondence computation to generate corresponding second output images. The computing module is further configured to computationally combine first and second output images to generate third output images.

Abstract: An apparatus and method for a feature extraction network based brain machine interface is disclosed. A set of neural sensors sense neural signals from the brain. A feature extraction module is coupled to the set of neural sensors to extract a set of features from the sensed neural signals. Each feature is extracted via a feature engineering module having a convolutional filter and an activation function. The feature engineering modules are each trained to extract the corresponding feature. A decoder is coupled to the feature extraction module. The decoder is trained to determine a kinematics output from a pattern of the plurality of features. An output interface provides control signals based on the kinematics output from the decoder.

Abstract: Methods and systems are provided for decoding movement intentions using functional ultrasound (fUS) imaging of the brain. In one example, decoding movement intentions include determining a memory phase of a cognitive state of the brain, the memory phase between a gaze fixation phase and movement execution phase, and determining one or more movement intentions including one or more of intended effector (e.g., hand, eye) and intended direction (e.g., right, left) according to a machine learning algorithm trained to classify one or more movement intentions simultaneously.

Abstract: In an embodiment, the invention relates to neural prosthetic devices in which control signals are based on the cognitive activity of the prosthetic user. The control signals may be used to control an array of external devices, such as prosthetics, computer systems, and speech synthesizers. Data obtained from a 4×4 mm patch of the posterial parietal cortex illustrated that a single neural recording array could decoded movements of a large extent of the body. Cognitive activity is functionally segregated between body parts.

Abstract: In an embodiment, the invention relates to neural prosthetic devices in which control signals are based on the cognitive activity of the prosthetic user. The control signals may be used to control an array of external devices, such as prosthetics, computer systems, and speech synthesizers. Data obtained from a 4×4 mm patch of the posterial parietal cortex illustrated that a single neural recording array could decoded movements of a large extent of the body. Cognitive activity is functionally segregated between body parts.

Abstract: A method and system of compensating for a damaged brain node is disclosed. The damaged node is determined by techniques such as fMRI or neural recording. A healthy node that can compensate for the function of the damaged node is determined. A stimulating electrode is placed on at least one functioning node to bypass the activity from the damaged node to compensate for a missing node. The functioning node is then stimulated to compensate for the damaged node.

Abstract: Prosthetic devices, methods and systems are disclosed. Eye position and/or neural activity of a primate are recorded and combined. The combination signal is compared with a predetermined signal. The result of the comparison step is used to actuate the prosthetic device.

Abstract: A method and system of compensating for a damaged brain node is disclosed. The damaged node is determined by techniques such as fMRI or neural recording. A healthy node that can compensate for the function of the damaged node is determined. A stimulating electrode is placed on at least one functioning node to bypass the activity from the damaged node to compensate for a missing node. The functioning node is then stimulated to compensate for the damaged node.

Abstract: The present invention relates to systems and methods for controlling neural prosthetic devices and electrophysiological recording equipment, and for using the same in clinical operation. Various embodiments of the invention are directed to an algorithm for autonomously isolating and maintaining neural action potential recordings. The algorithm may be used in connection with a neural interface microdrive capable of positioning electrodes to record signals from active neurons.

Abstract: Prosthetic devices, methods and systems are disclosed. Eye position and/or neural activity of a primate are recorded and combined. The combination signal is compared with a predetermined signal. The result of the comparison step is used to actuate the prosthetic device.

Abstract: In an embodiment, the invention relates to neural prosthetic devices in which control signals are based on the cognitive activity of the prosthetic user. The control signals may be used to control an array of external devices, such as prosthetics, computer systems, and speech synthesizers. Data obtained from monkeys' movement intentions were recorded, decoded with a computer algorithm, and used to position cursors on a computer screen. Not only the intended goals, but also the value of the reward the animals expected to receive at the end of each trial, were decoded from the recordings. The results indicate that brain activity related to cognitive variables can be a viable source of signals for the control of a cognitive-based neural prosthetic.

Abstract: Prosthetic devices, methods and systems are disclosed. Eye position and/or neural activity of a primate are recorded and combined. The combination signal is compared with a predetermined signal. The result of the comparison step is used to actuate the prosthetic device.

Abstract: The present invention relates to systems and methods for controlling neural prosthetic devices and electrophysiological recording equipment, and for using the same in clinical operation. Various embodiments of the invention are directed to an algorithm for autonomously isolating and maintaining neural action potential recordings. The algorithm may be used in connection with a neural interface microdrive capable of positioning electrodes to record signals from active neurons.

Abstract: Prosthetic devices, methods and systems are disclosed. Eye position and/or neural activity of a primate are recorded and combined. The combination signal is compared with a predetermined signal. The result of the comparison step is used to actuate the prosthetic device.

Abstract: In an embodiment, the invention relates to neural prosthetic devices in which control signals are based on the cognitive activity of the prosthetic user. The control signals may be used to control an array of external devices, such as prosthetics, computer systems, and speech synthesizers. Data obtained from monkeys' movement intentions were recorded, decoded with a computer algorithm, and used to position cursors on a computer screen. Not only the intended goals, but also the value of the reward the animals expected to receive at the end of each trial, were decoded from the recordings. The results indicate that brain activity related to cognitive variables can be a viable source of signals for the control of a cognitive-based neural prosthetic.

Abstract: A prosthetic system may use a decoder to predict an intended action, such as a reach, from processed signals generated from measured neural activity. The decoder may included a cognitive state machine, which transitions between cognitive states based on transition rules.

Abstract: In an embodiment, neural activity of a subject may be measured with an implant in the sensory motor cortex of the subject and used to predict an intended movement. The measured neural activity may be the local field potential (LFP) at an electrode or single unit (SU) activity. The spectral structure of the LFP and the SU activity may be estimated using spectral analysis techniques. The estimated LFP and SU responses may be used to predict and intended movement by the subject.

Abstract: A prosthetic system may use a decoder to predict an intended action, such as a reach, from processed signals generated from measured neural activity. The decoder may included a cognitive state machine, which transitions between cognitive states based on transition rules.

Abstract: The present invention provides a processed neural signal that encodes a reach plan, comprising the target location of the planned reach encoded relative to an eye-centered reference frame. The present invention also provides methods for generating and decoding the processed neural signal.