CROWD SOURCED MAPPING WITH ROBUST STRUCTURAL FEATURES

• US 20180274932A1
• Filed: 05/23/2018
• Published: 09/27/2018
• Est. Priority Date: 06/12/2012
• Status: Active Grant

• Current Assignee: TRX Systems, Inc.
• Original Assignee: TRX Systems, Inc.
• Inventors: YOUNG, Travis, KORDARI, Kamiar, FUNK, Benjamin, TEOLIS, Carole
• Granted Patent: US 10,852,145 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/1652 with ranging devices, e.g. LIDAR or RADAR
• CPC Class Codes: G01C 21/1654 with electromagnetic compass
• CPC Class Codes: G01C 21/1656 with passive imaging devices, e.g. cameras
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/383 Indoor data
• CPC Class Codes: G01C 21/3841 Data obtained from two or more sources, e.g. probe vehicles
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• CPC Class Codes: G01C 21/3856 Data obtained from user input
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G01S 5/02526 using non-dedicated equipment, e.g. user equipment or crowd-sourcing

Abstract

A location and mapping service is described that creates a global database of indoor navigation maps through crowd-sourcing and data fusion technologies. The navigation maps consist of a database of geo-referenced, uniquely described features in the multi-dimensional sensor space (e.g., including structural, RF, magnetic, image, acoustic, or other data) that are collected automatically as a tracked mobile device is moved through a building (e.g. a person with a mobile phone or a robot). The feature information can be used to create building models as one or more tracked devices traverse a building.

Claims

1. A method for determining a position of a mobile device traversing a structure, the method comprising:

sampling signal data associated with an environment of a structure using a mobile device traversing the structure;

utilizing the sample of signal data to generate a path of the mobile device through the structure, wherein each sample of the signal data among a plurality of samples of the signal data is uniquely identified in the path of the mobile device, wherein the path indicates physical features of the structure;

comparing the plurality of samples of the signal data to previously collected samples of the signal data from the structure and updating the path of the mobile device based on matches between the plurality of samples of the signal data to previously collected samples of the signal data; and

determining a position of the mobile device relative to the path based on signal data associated with a current position of the mobile device and the updated path of the mobile device.

2. The method of claim 1, further comprising:

inferring a map of the structure based on the path of the mobile device.

3. The method of claim 1, further comprising:

receiving a known map of the structure; and

superimposing the path of the mobile device onto the known map.

4. The method of claim 1, wherein the signal data is uniquely identified by symbols indicating a characteristic of the signal data.

5. The method of claim 4, wherein the characteristic of the signal data is signal strength.

6. The method of claim 1, wherein the physical features of the structure are inferred from the plurality of samples of the signal data.

7. The method of claim 1, further comprising:

prior to determining, adding at least one constraint to the path of the mobile device, the at least one constraint including one or more of a known location of the mobile device relative to a first location on the path of the mobile device and a known location of a physical feature relative to a second location on the path of the mobile device.

8. The method of claim 1, wherein the sample of signal data is only utilized to generate the path of the mobile device when the mobile device has access to high sample rate sensor data.

9. The method of claim 1, further comprising:

generating feature messages during or after utilizing the sample of signal data to generate the path, wherein feature messages include a start of one or more physical features being indicated, a stop of one or more physical features being indicated, and a physical feature construction parameter.

10. The method of claim 1, wherein the sample of signal data includes low level signal data and high level signal data, and wherein the high level signal data is only collected in response to a trigger associated with the low level signal data.

11. The method of claim 1, wherein the sample of signal data includes a signal signature, and wherein comparing includes comparing a signal signature for each location along the path of the mobile device with previously collected signal signatures within the structure.

12. The method of claim 11, wherein a match exists between a signal signature and a previously collected signal signature if a match confidence between the signal signature and the previously collected signal signature exceeds a threshold.

13. The method of claim 11, wherein the signal signature and the previously collected signal signature are magnetic signatures, WiFi signatures, or radiofrequency signatures.

14. The method of claim 1, wherein sampling signal data comprises:

ranging to a signal source; and

estimating a location of the signal source,

wherein the signal source is at least one of;

a radiofrequency (RF) source, a Bluetooth low energy (BLE) source, a magnetic source, and a WiFi source.

15. The method of claim 1, further comprising:

inferring a map of the structure, based on the path of the mobile device; and

displaying the inferred map on a user interface associated with the mobile device, wherein the map includes an icon indicating at least one of an estimated location of a signal source and an estimated location of a physical feature.

16. The method of claim 1, wherein the physical features include one or more of a stairway, a hallway, a ramp, an elevator, an entrance, and an exit.

17. A computing system for determining a position of a mobile device traversing a structure, the computing system comprising:

at least one processor; and

a memory communicatively coupled to the one or more processors, the memory bearing instructions that, when executed on the one or more processors, cause the computing system to at least;

sample signal data associated with an environment of a structure from one or more mobile devices traversing the structure;

utilize the sample of signal data to generate a path through the structure of at least one mobile device among the one or more mobile devices, wherein each sample of the signal data among a plurality of samples of the signal data is uniquely identified in the path of the at least one mobile device, wherein the path indicates physical features of the structure;

compare the plurality of samples of the signal data to previously collected samples of the signal data from the structure and updating the path of the at least one mobile device based on matches between the plurality of samples of the signal data to previously collected samples of the signal data; and

determine a position of the at least one mobile device relative to the path based on signal data associated with a current position of the at least one mobile device and the updated path of the at least one mobile device.

18. The computing system of claim 17, wherein the instructions that cause the computing system to sample signal data comprise:

ranging to a signal source; and

estimating a location of the signal source,

wherein the signal source is at least one of;

a radiofrequency (RF) source, a Bluetooth low energy (BLE) source, a magnetic source, and a WiFi source.

19. The computing system of claim 17, wherein the path indicates a three-dimensional localization of the indicated physical features of the structure.

20. The computing system of claim 17, further comprising instructions that cause the computing to at least:

infer a three-dimensional map of the structure based on the generated path, wherein the map includes an estimated location of physical features indicated by the path; and

display the inferred three-dimensional map on a user interface associated with the mobile device, the display including at least one icon indicating one or more of an estimated location of a signal source and an estimated location of a physical feature.

21. The computing system of claim 20, further comprising instructions that cause the computing system to at least:

receive a previously generated path from a mobile device traversing the structure; and

update the inferred three-dimensional map, based on the indicated physical features in the previously generated path.

22. The computing system of claim 17, further comprising instructions that cause the computing system to at least:

receive a known map of the structure; and

superimpose the path onto the known map.

23. The computing system of claim 17, further comprising instructions that cause the computing system to at least:

identify a signal source and an estimated location of the signal source relative to the path based on at least one sample of signal data.

24. The computing system of claim 17, wherein in matches between the plurality of samples and previously collected samples are based on one or more of a signal signature, a signal strength, a type of signal, and an estimated location of a signal source.

25. The computing system of claim 17, wherein the physical features of the structure are inferred from the plurality of samples of the signal data, and the physical features include one or more of a radiofrequency (RF) source, a magnetic source, a Bluetooth low energy source, a WiFi source, and a structural feature.

26. The computing system of claim 17, further comprising instructions that cause the computing system to at least:

generate feature messages during or after utilizing the sample of signal data to generate the path, wherein feature messages include a start of one or more physical features being indicated, a stop of one or more physical features being indicated, and a physical feature construction parameter.

27. The computing system of claim 17, further comprising instructions that cause the computing system to at least:

prior to determining, add at least one constraint to the path of the at least one mobile device, the at least one constraint including one or more of a known location of the at least one mobile device relative to a first location on the path of the at least one mobile device and a known location of a physical feature relative to a second location on the path of the at least one mobile device.