Qualcomm Incorporated

Faraz Mohammad Mirzaei

Saumitra Mohan Das

Hui Chao

Vinay Sridhara

Ayman Fawzy Naguib

Behrooz Khorashadi

Sameera Poduri

Ravi Palanki

Lionel Jacques Garin

Raghuraman Krishnamoorthi

Ju-Yong Do

Nayeem Islam

Yanghai Tsin

Methods, devices, systems, and non-transitory process-readable storage media for a computing device to use machine learning to dynamically configure an application and/or complex algorithms associated with the application. An aspect method performed by a processor of the computing device may include operations for performing an application that calls a library function associated with a complex algorithm, obtaining signals indicating user responses to performance of the application, determining whether a user tolerates the performance of the application based on the obtained signals indicating the user responses, adjusting a configuration of the application to improve a subsequent performance of the application in response to determining the user does not tolerate the performance of the application, and storing data indicating the user responses to the performance of the application and other external variables for use in subsequent evaluations of user inputs.

Application characterization for machine learning on heterogeneous core devices

Various methods, apparatuses and articles of manufacture are provided which may be used in determining an altitude of a mobile device. For example, an electronic device may select a subset of reporting mobile devices located within a particular environment, estimate a reference parameter that is indicative, at least in part, of a reference altitude within the particular region, e.g., based, at least in part, on one or more altitude measurements for one or more of the reporting mobile devices, and initiate transmission of the reference parameter to at least a target mobile device. In another example, a mobile device may obtain such a reference parameter, and estimate its altitude based, at least in part, on the reference parameter.

Methods and apparatuses for use in determining an altitude of a mobile device

Methods, apparatuses, and non-transitory processor-readable media of the present disclosure are presented for efficiently executing applications based on pressure sensor data. In some embodiments, a method includes monitoring pressure, and determining a rate of change in the pressure over time exceeds a predetermined rate-of-pressure-change threshold. The method further includes subsequently determining that the rate of change in the pressure over time no longer exceeds the predetermined rate-of-pressure-change threshold. The method further includes determining a change in pressure has exceeded a predetermined pressure-change threshold, and performing floor disambiguation.

Method and apparatus for positioning with always on barometer

Methods, systems, computer-readable media, and apparatuses for labeling crowd sourced data are presented. In some embodiments, a method for labeling crowd sourced data may include: receiving an atmospheric pressure signal from a mobile device associated with a venue, the mobile device comprising an atmospheric pressure sensor; clustering a plurality of atmospheric pressure signals from a plurality of mobile devices associated with the venue into a plurality of clusters; assigning a label to each of the plurality of clusters; receiving signal measurements from one or more of the plurality of mobile devices; and applying the label to the signal measurement.

Systems and methods for labeling crowd sourced data

Systems, apparatus and methods for determining a location of a mobile device are presented. Often a mobile device requests assistance data from a location server. If the mobile device expects a significant delayed response in receiving the assistance data, the mobile device may determine a seed location or rough location estimate from a server. The mobile device may also request a map to display and/or a data structure for its estimator. The mobile device may preload the estimator with the rough location estimate and/or the data structure. After preloading, the estimator determines a location of the mobile device. Also, the mobile device may show the map to a user via a display.

Seeding an estimator when receiving assistance data on a slow link

Disclosed are systems, apparatus, devices, method, computer program products, and other implementations, including a method that includes capturing an image of a scene by an image capturing unit of a device that includes at least one sensor, determining relative device orientation of the device based, at least in part, on determined location of at least one vanishing point in the captured image of the scene, and performing one or more calibration operations for the at least one sensor based, at least in part, on the determined relative device orientation.

Sensor calibration and position estimation based on vanishing point determination

Example methods, apparatuses, or articles of manufacture are disclosed herein that may be utilized, in whole or in part, to facilitate or support one or more operations or techniques for detecting location changes and monitoring assistance data via scanning for use in or with a mobile device. Briefly, in accordance with at least one implementation, a method may include obtaining, at a mobile device, a rough estimate of a location of the mobile device; identifying a plurality of transmitters within a signal acquisition range of the roughly estimated location; transmitting probe requests addressed to at least some of the transmitters; and selectively initiating a passive scan at a receiver of the mobile device if a number of responses to the probe requests received from the transmitters is less than a threshold number.

Method and apparatus for detecting location changes and monitoring assistance data via scanning

A method for template matching is described. In one implementation, an image including a target object is captured by a camera. A pose of the camera is estimated based, at least in part, on peripheral information from the image. Pre-selecting is performed on a set of pose templates by matching the pose of the camera to poses associated with pose templates to identify a set of matching pose templates. The template matching for the target object is then performed using the set of matching pose templates.

Speed-up template matching using peripheral information

Techniques for determining a position of a mobile device in an indoor environment are provided. An example method includes receiving a request for the position of the mobile device within the indoor environment from an application running on the mobile device, estimating the position of the mobile device within the indoor environment based on signals received from a plurality of wireless access points responsive to receiving the request for the position of the mobile device, identifying an ambiguity in estimating the position of the mobile device, identifying disambiguation information for resolving the ambiguity in the position, requesting disambiguation information for resolving the ambiguity associated with the position, receiving the disambiguation information for resolving the ambiguity associated with the position; resolving the ambiguity in estimating the position using the disambiguation information; and determining the position of the mobile device in the indoor environment.

User-in-the-loop architecture for indoor positioning

A method for estimating camera pose includes: obtaining an image of a location captured via a camera, where the image includes a target object and edge line features outside of the target object; and calculating a pose of the camera with respect to the target object based on the edge line features.

Pose estimation based on peripheral information

Disclosed are systems, apparatus, devices, methods, computer program products, and other implementations, including a method that includes capturing an image of a scene by an image capturing unit of a device that includes an accelerometer, and determining orientation of the device based, at least in part, on determined location of a vanishing point (e.g., a single vanishing point) in the captured image of the scene and at least one measurement obtained from the accelerometer.

Orientation determination based on vanishing point computation

A method and system for sharing indoor location information with one or more application program modules within a portable computing device ('PCD') includes receiving an indoor location data request and determining if a location service is currently being executed by the PCD. If the location service is not being executed, it is determined if a location engine of the PCD has been installed. If the location engine of the portable computing device has not been installed, then the code for the location engine is downloaded from a communications network. Next, the location service may be executed once the location engine has been installed. It is determined if the indoor location data being requested is present in a memory element of the PCD. If the indoor location data being requested is not present in the memory element of the PCD, then the indoor location data is downloaded from the communications network.

System and method for sharing indoor location information with one or more application program modules within a portable computing device

Disclosed are systems, methods and techniques for obtaining round trip time (RTT) measurements from acquisition of signals at one or more mobile devices, the signals being transmitted by one or more transmitters; approximating locations of the one or more mobile devices while obtaining the RTT measurements; and combining the measurements to determine expected RTT signature values at discrete positions in the area based, at least in part, on the obtained RTT measurements and the approximated locations.

Growing community of inventors

San Jose, CA, United States of America

Faraz Mohammad Mirzaei