Abstract: Systems and methods are disclosed for calibrating a sensor. A recursive least squares estimation may be performed to update a mean and a covariance matrix for samples of data from a motion sensor and a bias estimate for the motion sensor may be derived from the mean and covariance matrix. The motion sensor may be an gyroscope, an accelerometer or a magnetometer.

Abstract: Systems and methods are disclosed for refining a coarse location determination by detecting patterns of motion sensor data that may be associated with predetermined locations. One or more geofeatures may be identified that cause a mobile device associated with a user to detect a distinguishable pattern of sensor data when the user interacts with the object. Accordingly, a coarse location may be refined using information associated with the geofeature, such as the location of the geofeature.

Abstract: Systems and methods are disclosed for providing sensor based authentication of a user's identification and may be used to control access. In this manner, a user's identity may be used to control access to any suitable location, space or resource, either locally or remotely. A combination of functions involved in authenticating a user's identification may be performed by one or more discrete devices and include obtaining sensor data from at least one sensor that is physically associated with a user, monitoring to determine that the sensor remains physically associated with the user, authenticating the user's identity using the sensor data and communicating information regarding the user's identification.

Abstract: Systems and methods are disclosed for calibrating a sensor. A recursive least squares estimation may be performed to update a mean and a covariance matrix for samples of data from a motion sensor and a bias estimate for the motion sensor may be derived from the mean and covariance matrix. The motion sensor may be an gyroscope, an accelerometer or a magnetometer.

Abstract: This disclosure provides techniques for guiding a user through a calibration operation of a mobile device having a motion sensor. The user may receive one or more visual cues to aid the user in positioning the device in one or more desired orientations or patterns of motion. The visual cues may be with respect to a virtual three dimensional environment that is responsive to a determined orientation of the device.

Abstract: A state machine may be implemented in hardware by representing each state with one operational code (opcode) such that each opcode may be read from memory in sequential order. The state machine includes a plurality of states linked by at least one transition triggered by data input. The data input may be motion sensor data such that the state machine is configured to recognize a pattern of motion corresponding to a gesture or an activity.

Abstract: A device having a sensor may be calibrated by obtaining a condition of a device incorporating the sensor and initiating a calibration operation for the sensor based, at least in part, on the condition of the device. The condition may be a motion state, a charging state, a pattern of motion, an orientation, a location, a surrounding environment measurement, sensor usage, an age of calibration, a quality of calibration, or any combination. Further, the sensor may be an accelerometer, a gyroscope, a magnetometer or a pressure sensor.

Abstract: Systems and methods are disclosed for classifying an activity. A sensor tracks motion by a user and a classifier recognizes data output sensor as corresponding to an activity. The classifier may be trained or otherwise modified using received information, which may include data from the sensor or information from an external source, such as a remotely maintained database. The device may update a local or remote database using sensor data when in a training mode. The training mode may be implemented automatically when there is sufficient confidence in the activity identification or manually in response to a user input.