Abstract: In one embodiment, a device may extract, from one or more bodies of text, a data usage restriction for a particular type of data. The device may send, to a user interface, the data usage restriction extracted from the one or more bodies of text for presentation for a user. The device may receive, via the user interface, feedback from the user regarding the data usage restriction. The device may generate a data compliance constraint that controls how an application service handles the particular type of data, based on the data usage restriction and the feedback from the user.

Abstract: Digitized audio command is decoded to generate audio features. An in-domain confidence score is calculated for a model trained by a limited set of peripheral device commands. An out-domain confidence score is calculated for a model trained without the peripheral device commands. The best score determines whether to process the audio locally or at a remote server. In some embodiments, a likelihood ratio (LR) is calculated of the in-domain and out-domain confidence scores. Based on the likelihood ratio, a locally decoded audio command is performed, or the audio features are sent to a remote server for processing to determine the audio command.

Abstract: Digitized audio command is decoded to generate audio features. An in-domain confidence score is calculated for a model trained by a limited set of peripheral device commands. An out-domain confidence score is calculated for a model trained without the peripheral device commands. The best score determines whether to process the audio locally or at a remote server. In some embodiments, a likelihood ratio (LR) is calculated of the in-domain and out-domain confidence scores. Based on the likelihood ratio, a locally decoded audio command is performed, or the audio features are sent to a remote server for processing to determine the audio command.

Abstract: An AR/VR input device include a processor(s), an internal measurement unit (IMU), and a plurality of sensors configured to detect emissions received from a plurality of remote emitters. The processor(s) can be configured to: determine a time-of-flight (TOF) of the detected emissions, determine a first estimate of a position and orientation of the input device based on the TOF of a subset of the detected emissions and the particular locations of each of the plurality of sensors on the input device that are detecting the detected emissions, determine a second estimate of the position and orientation of the input device based on the measured acceleration and velocity from the IMU, and continuously update a calculated position and orientation of the input device within the AR/VR environment in real-time based on a Beyesian estimation (e.g., Extended Kalman filter) that utilizes the first estimate and second estimate.

Abstract: An AR/VR input device include a processor(s), an internal measurement unit (IMU), and a plurality of sensors configured to detect emissions received from a plurality of remote emitters. The processor(s) can be configured to: determine a time-of-flight (TOF) of the detected emissions, determine a first estimate of a position and orientation of the input device based on the TOF of a subset of the detected emissions and the particular locations of each of the plurality of sensors on the input device that are detecting the detected emissions, determine a second estimate of the position and orientation of the input device based on the measured acceleration and velocity from the IMU, and continuously update a calculated position and orientation of the input device within the AR/VR environment in real-time based on a Beyesian estimation (e.g., Extended Kalman filter) that utilizes the first estimate and second estimate.

Abstract: An AR/VR input device include a processor(s), an internal measurement unit (IMU), and a plurality of sensors configured to detect emissions received from a plurality of remote emitters. The processor(s) can be configured to: determine a time-of-flight (TOF) of the detected emissions, determine a first estimate of a position and orientation of the input device based on the TOF of a subset of the detected emissions and the particular locations of each of the plurality of sensors on the input device that are detecting the detected emissions, determine a second estimate of the position and orientation of the input device based on the measured acceleration and velocity from the IMU, and continuously update a calculated position and orientation of the input device within the AR/VR environment in real-time based on a Beyesian estimation (e.g., Extended Kalman filter) that utilizes the first estimate and second estimate.

Abstract: The present disclosure is directed to retinal display projection device comprising a projection component arranged for projecting an image directly onto the retina of a user wearing the device. The projection device further comprises an eye gaze detection module arranged to take an eye image of a user's eyes and to activate the projection component if a pupil of the user is in a predetermined position in said eye image.

Abstract: Embodiments of the invention are directed to input devices configured for use with computing devices. The present invention relates to input devices configured with a plurality of sensors configured to determine the displacement and position of the input device. Tracking of the input device may be switched from an optical sensor to an inertial sensor based on the speed of movement of the input device or based on the input device detecting that loss of tracking has occurred. In some embodiments, a gyroscope may be configured to modify data from the inertial sensor module to correct for fictitious accelerations generated when the input device is rotated.

Abstract: The present disclosure is directed to retinal display projection device comprising a projection component arranged for projecting an image directly onto the retina of a user wearing the device. The projection device further comprises an eye gaze detection module arranged to take an eye image of a user's eyes and to activate the projection component if a pupil of the user is in a predetermined position in said eye image.

Abstract: Embodiments of the invention are directed to input devices configured for use with computing devices. The present invention relates to input devices configured with a plurality of sensors configured to determine the displacement and position of the input device. Tracking of the input device may be switched from an optical sensor to an inertial sensor based on the speed of movement of the input device or based on the input device detecting that loss of tracking has occurred. In some embodiments, a gyroscope may be configured to modify data from the inertial sensor module to correct for fictitious accelerations generated when the input device is rotated.

Abstract: According to one embodiment of the present invention, the system for clinical assessment of movement disorders (iTUG) is comprised of a) a protocol to assess gait, balance, and mobility; b) a plurality of wearable sensors including accelerometers, gyroscopes, magnetometers, optical sensors, and goniometers to record kinematics data obtained from a patient during said protocol; c) means for wirelessly transmitting said kinematics data to a storage and data processing server; and d) a plurality of statistical and biomedical signal processing methods to analyze said kinematic data and derive a plurality of metrics (outcomes) to objectively quantify movement disorders. A specially important outcome for the assessment of movement disorders is described, namely, the quantification of the onset and offset parameters during turning.

Abstract: According to one embodiment of the present invention, the system for clinical assessment of movement disorders (iTUG) is comprised of a) a protocol to assess gait, balance, and mobility; b) a plurality of wearable sensors including accelerometers, gyroscopes, magnetometers, optical sensors, and goniometers to record kinematics data obtained from a patient during said protocol; c) means for wirelessly transmitting said kinematics data to a storage and data processing server; and d) a plurality of statistical and biomedical signal processing methods to analyze said kinematic data and derive a plurality of metrics (outcomes) to objectively quantify movement disorders. A specially important outcome for the assessment of movement disorders is described, namely, the quantification of the onset and offset parameters during turning.