Magnetic fingerprint neural network training for mobile device indoor navigation

    公开(公告)号:US11473915B2

    公开(公告)日:2022-10-18

    申请号:US16503555

    申请日:2019-07-04

    申请人: MAPSTED CORP.

    发明人: Sean Huberman

    摘要: A method and system of magnetic fingerprint based neural network training for mobile device indoor navigation and positioning. The method, executed in a processor of a server computing device, comprises determining, in the processor, at a plurality of locations, a set of magnetic input parameters in accordance with a magnetic infrastructure profile of at least a portion of an indoor area, the processor implementing an input layer of a neural network, the set of magnetic input parameters providing a magnetic feature input to the input layer of the neural network; receiving, from a mobile device positioned at the first location, a set of measured magnetic parameters at respective ones of the plurality of locations; computing, at an output layer of the neural network implemented by the processor, an error matrix based on comparing an initial matrix of weights associated with the at least a first neural network layer representing the magnetic feature input to a magnetic feature output in accordance with the magnetic measured parameters of the mobile device; and recursively adjusting the initial weights matrix by backpropogation to diminish the error matrix until the generated magnetic feature output matches the magnetic measured parameters.

    METHOD AND SYSTEM FOR DEPLOYING CROWD-SOURCED MAGNETIC DISTORTION REJECTION MAP

    公开(公告)号:US20200240789A1

    公开(公告)日:2020-07-30

    申请号:US16257456

    申请日:2019-01-25

    申请人: MAPSTED CORP.

    发明人: Sean Huberman

    摘要: A method and system for deploying a magnetic distortion rejection map of an indoor area. The method comprises generating, using a processor, (i) a first distribution of magnetic fingerprint data that includes magnetic distortion data points based at least in part on a set of positions traversed by a plurality of mobile devices within the indoor area, and (ii) based on accessing a position correction factor, a second distribution of magnetic fingerprint data that includes true position data points corresponding to the magnetic distortion data points, receiving, at the memory, a set of magnetic fingerprint data that includes a second set of magnetic distortion data points based on an additional set of positions traversed by at least one additional mobile device within the indoor area, processing the second set of magnetic distortion data points, the first distribution and the second distribution to generate an updated distribution of magnetic distortion data points, and if the updated distribution exceeds a threshold density of magnetic distortion data points, deploying the updated distribution as the magnetic distortion rejection map of the area.

    Deployment of trained neural network based RSS fingerprint dataset

    公开(公告)号:US10716089B1

    公开(公告)日:2020-07-14

    申请号:US16429551

    申请日:2019-06-03

    申请人: Mapsted Corp.

    摘要: A method and system of deploying a trained neural network-based RSS fingerprint dataset for mobile device indoor navigation and positioning. The method comprises: based on RSS parameters acquired from a plurality of mobile devices acquired at a set of positions within an indoor area, accumulating the RSS parameters as a trained neural network-based RSS fingerprint dataset in a fingerprint database of the indoor area; and when a density of points represented by the set of positions having accumulated RSS parameters exceeds a deployment threshold density, deploying the RSS fingerprint dataset within a fingerprint map for mobile device navigation of the indoor area, the fingerprint map encompassing the set of positions.

    Maintaining a trained neural network for mobile device RSS fingerprint based indoor navigation

    公开(公告)号:US10655971B1

    公开(公告)日:2020-05-19

    申请号:US16400819

    申请日:2019-05-01

    申请人: MAPSTED CORP.

    IPC分类号: G01C21/20 G06N3/04 G06N3/08

    摘要: A method and system of maintaining a trained neural network for mobile device indoor navigation and positioning. The method comprises: determining, in the processor, at a first location relative to a wireless signal source at a second location, a set of received signal strength (RSS) input parameters in accordance with a postulated RSS model, the processor implementing an input layer of a neural network, the set of RSS input parameters providing an RSS input feature to the input layer of the neural network; receiving a set of RSS measured parameters acquired at a mobile device positioned at the first location from the wireless signal source at the second location; computing, at an output layer of the trained neural network, an output error based on comparing the RSS input feature to an RSS output feature generated at the output layer, the RSS output feature being generated at least in part based on a matrix of weights associated with at least a first neural network layer; and if the output error exceeds a threshold value, re-training the neural network based at least in part upon re-initializing the matrix of weights associated with the at least a first neural network layer.

    METHOD AND SYSTEM FOR CROWD-SOURCED TRUSTED-GPS REGION FOR MOBILE DEVICE LOCALIZATION

    公开(公告)号:US20200142076A1

    公开(公告)日:2020-05-07

    申请号:US16180306

    申请日:2018-11-05

    申请人: MAPSTED CORP.

    摘要: A method and system for deploying a trusted-global positioning system (trusted-GPS) positioning map. The method comprises receiving, at a memory of the server computing device, at least a first set of fingerprint data and at least a first set of GPS position data for a sequence of positions traversed within an indoor area by at least a first mobile device, generating, using the processor, a distribution of positioning data points of the indoor area for which a correlation between the at least a first set of fingerprint data and the at least a first set of GPS position data for respective ones of the sequence of positions exceeds a threshold correlation value, and when the distribution exceeds at least one of a predetermined and a dynamically updated threshold density of positioning data points, deploying the distribution as the trusted-GPS positioning map of the indoor area.

    METHOD AND SYSTEM FOR CROWD- SOURCED MAP FEATURE UPDATING

    公开(公告)号:US20200068349A1

    公开(公告)日:2020-02-27

    申请号:US16113044

    申请日:2018-08-27

    申请人: MAPSTED CORP.

    摘要: A method and system of updating a map feature. The method, executed in a processor of a server computing device, comprises receiving, from a mobile device, a request for update of a map feature, generating a request for localizing the mobile device, validating the request for update based on a threshold confidence level associated with the localizing, and upon the validating, updating the map feature in a memory of the server computing device.

    Method and system for localizing tracking devices indoors and outdoors

    公开(公告)号:US10423926B1

    公开(公告)日:2019-09-24

    申请号:US16101816

    申请日:2018-08-13

    申请人: MAPSTED CORP.

    摘要: A method and a device for tracking an item using a tracking device associated with the item are described. The method, executed in a processor of the tracking device, comprises identifying a location state of the tracking device as one of an indoor location and an outdoor location relative to an indoor facility, based on at least one of satellite based data and connectivity to an access point in the indoor facility. Upon identifying the location state as the indoor location, a wireless transceiver and one or more sensor devices may be activated. The sensor devices may include at least one of a wireless signal strength sensor, a wireless signal connectivity sensor, an inertial sensor, a magnetic field sensor, a barometric sensor, and an ambient light sensor. Further, indoor localization data gathered by the sensor devices may be provided for localization.

    Method and system for mobile device localization-based access

    公开(公告)号:US10249116B1

    公开(公告)日:2019-04-02

    申请号:US15944407

    申请日:2018-04-03

    申请人: MAPSTED CORP.

    IPC分类号: G07C9/00 H04L29/06 H04W4/80

    摘要: A method and system for facilitating an access request. The method may be executed in the processor of a server computing device and comprises receiving, at a memory of the server computing device, the request for access, the request for access performed using a security device at an access point device communicatively coupled to the server computing device, localizing a mobile computing device having a preestablished association with the security device, and enabling the request for access when a position of the mobile computing device as determined from the localizing is within a predetermined threshold distance from a location of the access point device.

    Method and system of pedestrian localization

    公开(公告)号:US10145689B1

    公开(公告)日:2018-12-04

    申请号:US15910080

    申请日:2018-03-02

    申请人: MAPSTED CORP.

    摘要: A method and system localizing a mobile device along a pedestrian route traversed in an indoor area, the mobile device including a processor and a memory. The method executed in the processor and comprises localizing the mobile device to an estimated first position within the indoor area based on accessing, from a first memory tier of the memory, a first portion fingerprint data that includes fingerprint data of a first subset area of the indoor area, the first subset area at least partly surrounding the estimated first position, detecting a traversal of the mobile device along the route to an estimated second position within the indoor area, and when a difference between the estimated first and second positions exceeds a threshold distance, replacing the first portion fingerprint data of the first memory tier upon pre-fetching a second portion fingerprint data, the second portion fingerprint data including fingerprint data of a second subset area of the indoor area, the second subset area at least partly surrounding the estimated second position.

    Crowd sourced multi-stage mobile device fingerprint based navigation

    公开(公告)号:US11525686B2

    公开(公告)日:2022-12-13

    申请号:US16587362

    申请日:2019-09-30

    申请人: MAPSTED CORP.

    摘要: A method and system for deploying a calibrated positioning map of an area. The method, executed in a processor of a server computing device, comprises deploying a crowd sourced magnetic fingerprint map for mobile device localization during traversal of the indoor area, accumulating received signal strength (RSS) measurements in forming a RSS fingerprint map using crowd sourced RSS measurements during the deploying, and switching, responsive to identifying desirability of a change in the mobile device localization within the indoor area, from the crowd sourced magnetic fingerprint map to the RSS fingerprint map as basis for localizing the mobile device.