Self-learning localization data repository

• US 10,425,772 B2
• Filed: 02/19/2019
• Issued: 09/24/2019
• Est. Priority Date: 11/30/2017
• Status: Active Grant

• Current Assignee: Mapsted Corp.
• Original Assignee: Mapsted Corp.
• Inventors: Gulo, Eros, Huberman, Sean
• Primary Examiner(s): Manoharan, Muthuswamy G
• Application Number:
  US16/279,164
• Publication Number:
  US 20190182628A1
• Time in Patent Office: 217 Days
• CPC Class Codes: G01C 21/005 with correlation of navigation data from several sources, e.g. map or contour matching G01C21/30 takes precedence
• CPC Class Codes: G01C 21/08 involving use of the magnetic field of the earth
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01S 5/02522 The radio-map containing measured values of non-radio values
• CPC Class Codes: G01S 5/02524 Creating or updating the radio-map
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/025 using location based information parameters
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/33 for indoor environments, e.g. buildings
• CPC Class Codes: H04W 4/40 for vehicles, e.g. vehicle-to-pedestrians [V2P]

Abstract

A method and system for automatically updating a self-learning data repository. The method is executed in a processor of a server computing device to store a fingerprint map of an area in the self-learning data repository, the fingerprint map having positioning fingerprint data that includes magnetic spatial derivative fingerprint data, receive, at the self-learning data repository, at least one of mobile device signal data and mobile device sensor data correlated with a sequence of positions along a trajectory describing a movement of a mobile device relative to the area, the sensor data including mobile device magnetic spatial derivative data, and automatically update, using the processor, the self-learning data repository by adding the at least one of mobile device signal data and mobile device sensor data to the positioning fingerprint data.

Claims

1. A method of updating a self-learning data repository, the method executed in a processor of a server computing device and comprising:

storing, in a memory of the server computing device that constitutes the self-learning data repository, a fingerprint map of an indoor facility, the fingerprint map having positioning fingerprint data that includes magnetic spatial derivative fingerprint data;

receiving, from a mobile device, at the self-learning data repository, mobile device sensor data correlated with a sequence of positions describing a movement of the mobile device along a trajectory within the indoor facility, the mobile device sensor data including mobile device magnetic spatial derivative data indicative of relative changes in a magnetic field as the mobile device traverses the sequence of positions;

performing, using the processor, a spatial shifting of at least one of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data of the self-learning data repository for at least a segment of the trajectory within the indoor facility to create updated mobile device sensor data, wherein the spatial shifting narrows a spatial phase difference between the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data; and

updating, using the processor, the self-learning data repository by adding the updated mobile device sensor data to the positioning fingerprint data.

2. The method of claim 1 wherein the mobile device spatial derivative magnetic data is derived from a set of magnetic field measurements correlated with the sequence of positions.

3. The method of claim 1 wherein the mobile device spatial derivative magnetic data is derived in accordance with a magnetic spatial gradient based on differences in absolute magnetic field measurements and a spatial separation existing across at least a pair of contiguous positions that indicate the relative changes as the mobile device traverses the sequence of positions.

4. The method of claim 3 wherein performing the spatial shifting comprises compensating for variations in the absolute magnetic measurements of the mobile device by narrowing a spatial gap between corresponding data points of respective mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data.

5. The method of claim 4 wherein the compensating results in an increase in a coincidence in overlay of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data.

6. The method of claim 1 wherein the spatial shifting is based on identifying a pattern match between the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data of the self-learning data repository.

7. The method of claim 1 further comprising localizing a position of the mobile device based on the updating.

8. The method of claim 1 wherein the magnetic spatial derivative data of the self-learning data repository includes at least one of a horizontal and a vertical magnetic field component data.

9. The method of claim 1 further comprising deploying the updated self-learning data repository for localization of mobile devices relative to the area.

10. The method of claim 1 wherein the mobile device is a first mobile device, and further comprising at least a second mobile device, wherein the sensor data including magnetic spatial derivative data of the at least a second mobile device data is accorded one of a higher and a lower weighting compared to a weighting accorded the first mobile device during the updating.

11. A self-learning data repository comprising:

a processor; and

a memory storing a set of instructions, the instructions executable in the processor to;

store, in the memory, a fingerprint map of an indoor facility, the fingerprint map having positioning fingerprint data that includes magnetic spatial derivative fingerprint data;

receive, from a mobile device, at the self-learning data repository, mobile device sensor data correlated with a sequence of positions describing a movement of the mobile device along a trajectory within the indoor facility, the mobile device sensor data including mobile device magnetic spatial derivative data indicative of relative changes in a magnetic field as the mobile device traverses the sequence of positions;

perform, using the processor, a spatial shifting of at least one of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data of the self-learning data repository for at least a segment of the trajectory within the indoor facility to create updated mobile device sensor data, wherein the spatial shifting narrows a spatial phase difference between the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data; and

update, using the processor, the self-learning data repository by adding the updated mobile device sensor data to the positioning fingerprint data.

12. The self-learning data repository of claim 11 wherein the mobile device spatial derivative magnetic data is derived from a set of magnetic field measurements correlated with the sequence of positions.

13. The self-learning data repository of claim 11 wherein the mobile device spatial derivative magnetic data is derived in accordance with a magnetic spatial gradient based on differences in absolute magnetic field measurements and a spatial separation existing across at least a pair of contiguous positions that indicate the relative changes as the mobile device traverses the sequence of positions.

14. The self-learning data repository of claim 13 wherein performing the spatial shifting comprises compensating for variations in the absolute magnetic measurements of the mobile device by narrowing a spatial gap between corresponding data points of respective mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data.

15. The self-learning data repository of claim 14 wherein compensating for the variations in the absolute magnetic measurements results in an increase in a coincidence in overlay of the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data.

16. The self-learning data repository of claim 11 wherein the spatial shifting is based on identifying a pattern match between the mobile device magnetic spatial derivative data and the magnetic spatial derivative fingerprint data of the self-learning data repository.

17. The self-learning data repository of claim 11 further comprising instructions executable in the processor to localize a position of the mobile device based on the updating.

18. The self-learning data repository of claim 11 wherein the magnetic spatial derivative data of the self-learning data repository includes at least one of a horizontal and a vertical magnetic field component data.

19. The self-learning data repository of claim 11 further comprising instructions executable in the processor to deploy the updated self-learning data repository for localization of mobile devices relative to the area.

20. The self-learning data repository of claim 11 wherein the mobile device is a first mobile device, and further comprising at least a second mobile device, wherein the sensor data including magnetic spatial derivative data of the at least a second mobile device data is accorded one of a higher and a lower weighting compared to a weighting accorded the first mobile device during the updating.