Collaborative creation of indoor maps

• US 9,733,091 B2
• Filed: 02/12/2014
• Issued: 08/15/2017
• Est. Priority Date: 05/31/2007
• Status: Active Grant

• Current Assignee: TRX Systems, Inc.
• Original Assignee: TRX Systems, Inc.
• Inventors: Teolis, Carole, Napora, Jared, Karvounis, John, Hakim, Dan, Giles, Christopher, Politi, Carol, Kordari, Kamiar, Funk, Benjamin
• Primary Examiner(s): Cass, Jean-Paul
• Application Number:
  US14/178,605
• Publication Number:
  US 20140278060A1
• Time in Patent Office: 1,280 Days
• Field of Search: None
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/383 Indoor data

Abstract

This disclosure provides techniques for the creation of maps of indoor spaces. In these techniques, an individual or a team with no mapping or cartography expertise can contribute to the creation of maps of buildings, campuses or cities. An indoor location system can track the location of contributors in the building. As they walk through indoor spaces, an application may automatically create a map based on data from motion sensors by both tracking the location of the contributors and also inferring building features such as hallways, stairways, and elevators based on the tracked contributors'"'"' motions as they move through a structure. With these techniques, the process of mapping buildings can be crowd sourced to a large number of contributors, making the indoor mapping process efficient and easy to scale up.

Claims

1. A computer-implemented method for generating a building map of an indoor space, the method comprising:

collecting sensor data, including inertial sensor data, via an electronic network from each computing device among a plurality of computing devices;

using the sensor data to generate location data corresponding to an estimate of a location of each computing device;

using the sensor data to generate motion data corresponding to motions of each computing device;

using the location data and the motion data associated with each device to generate a three dimensional feature graph of building features associated with the indoor space comprising;

assigning one or more motions to be associated with a building feature; and

inferring building features by using the motion data from each computing device by identifying the one or more motions associated with each building feature;

creating a graphical map from each three dimensional feature graph, representing a temporal sequence of events, comprising;

generating a node for each inferred building feature;

estimating a location of each node using the location data;

establishing location error bounds for each node; and

generating links between nodes to represent spatial connections using the location of each node and a time of discovery for each inferred building feature;

correcting one or more of the estimates of node location and error bounds to compensate for drift of the estimate of location for one or more of the computing devices to create a plurality of corrected graphical maps; and

merging a plurality of the nodes of the corrected graphical maps to generate the building map, the merging being based at least on a node type and a node location.

2. The method of claim 1, wherein each computing device among the plurality of computing devices is connected to a user among a plurality of users moving about the indoor space, and wherein the building map is updated based on the location and the motions of each user among the plurality of users.

3. The method of claim 1, wherein the inferred building features are based on a history of location information and motion information associated with each computing device.

4. The method of claim 1, wherein the inferred building features are based on a confidence level based on the location of each computing device and prior information about the indoor space.

5. The method of claim 1, wherein correcting is further based on received corrected location data for a corresponding computing device.

6. The method of claim 1, wherein the inferred corrected location data corrects for angular drift associated with the motions.

7. The method of claim 1, wherein one or more of the plurality of computing devices is a smartphone.

8. The method of claim 1, wherein at least two or more nodes are merged if each of the two or more nodes are associated with two events.

9. The method of claim 8, wherein merging is further based on a node error bound, and wherein the two events include the location and node error bound associated with each computing device at a time of discovery of the building features associated with the two or more nodes.

10. The method of claim 1, wherein two locations in the three dimensional feature graph are connected by an edge if the inferred building features connect two estimated locations of the computing device.

11. The method of claim 1, wherein the motion data corresponds to a path of each computing device and wherein using the motion data includes segmenting the path and inferring building features from the segmented path.

12. The method of claim 1, wherein merging the plurality of the nodes is further based on a weighted average of the node locations of the plurality of the nodes.

13. The method of claim 12, wherein merging is further based on a node error bound, and wherein the weighted average is weighted based on an occupancy of each node of the plurality of the nodes and inversely weighted based on the node error bound for each node of the plurality of the nodes.

14. The method of claim 12, wherein merging the plurality of the nodes further includes removing nodes with a low occupancy number.

15. The method of claim 12, wherein merging the plurality of the nodes further includes determining a role of each node among the plurality of the nodes, the role including one of a decision point node, an articulation point node, a corner point node, a leaf node, and a redundant node.

34. The method of claim 1, wherein correcting one or more of the estimates of location includes correcting the one or more of the estimates of location based on location information obtained by a user of the computing device.

35. The method of claim 1, wherein correcting one or more of the estimates of location includes correcting the one or more of the estimates of location based on a location error bound of the computing device.

16. A computing system for generating a map of an indoor space, the computing system comprising:

a processor; and

a memory communicatively coupled to the processor, the memory bearing instructions that, when executed on the processor, cause the computing system to at least;

receive sensor data, including inertial sensor data, at the processor via an electronic network from each computing device among a plurality of computing devices;

use the sensor data to generate location data indicative of a location of each computing device in the indoor space;

use the sensor data to generate motion data indicative of motions of each computing device in the indoor space, wherein the motion data corresponds to a path of each computing device;

generate a three dimensional feature graph of building features of the indoor space based on the motion data, the path and the location data of each computing device comprising;

assigning one or motions to be associated with a building feature; and

identifying the one or more motions associated with each building feature;

create a graphical map from each three dimensional feature graph, representing a temporal sequence of events, comprising;

generating a node for each inferred building feature;

estimating a location of each node using the location data;

establishing location error bounds for each node; and

generating links between nodes to represent spatial connections using the location of each node and a time of discovery for each inferred building feature; and

merge a plurality of the nodes of the graphical maps to generate the map, the merging being based at least on a node type and a node location.

17. The system of claim 16, wherein each computing device is connected to a user among a plurality of users moving about the indoor space.

18. The system of claim 16, wherein the inferred building features are based on a history of location data and motion data associated with each computing device.

19. The system of claim 16, wherein the inferred building features are based on a confidence level based on the location of each computing device and prior information about the indoor space.

20. The system of claim 16, wherein a location of an inferred building feature may be corrected based on one or more constraints imposed on the path of each computing device.

21. The system of claim 20, wherein the one or more constraints correct for angular drift associated with the path of each computing device.

22. The system of claim 16, wherein two nodes in a graphical map are connected by a link if the two nodes are associated with two consecutive events corresponding to an activity of one of the computing devices.

23. The system of claim 22, wherein merging is further based on a node error bound, and wherein the two consecutive events are based on the node location and the node error bound of one of the computing devices at a time of discovery of the two consecutive events.

24. The system of claim 16, wherein two locations in the three dimensional feature graph are connected by an edge if the inferred building features connect two estimated locations of computing device.

25. A computer-implemented method for generating a map of an indoor space, the method comprising:

receiving sensor data, including inertial sensor data, at the processor via an electronic network from each computing device among a plurality of computing devices;

using the sensor data to generate location data indicative of a location of each computing device in the indoor space;

using the sensor data to generate motion data indicative of motions of each computing device in the indoor space, wherein the motion data corresponds to a path of each computing device;

generating a three dimensional feature graph of building features of the indoor space based on the motion data, the path and the location data of each computing device comprising;

assigning one or motions to be associated with a building feature; and

identifying the one or more motions associated with each building feature;

create a graphical map from each three dimensional feature graph, representing a temporal sequence of events, comprising;

generating a node for each inferred building feature;

estimating a location of each node using the location data;

establishing location error bounds for each node; and

generating links between nodes to represent spatial connections using the location of each node and a time of discovery for each inferred building feature; and

merging a plurality of the nodes of the graphical maps to generate the map, the merging being based at least on a node type and a node location.

26. The medium of claim 25, wherein each computing device is connected to a user among a plurality of users moving about the indoor space.

27. The medium of claim 25, wherein the inferred building features are based on a history of location data and motion data associated with each computing device.

28. The medium of claim 25, wherein the inferred building features are based on a confidence level based on the location of each computing device and prior information about the indoor space.

29. The medium of claim 25, wherein a location of an inferred building feature may be corrected based on one or more constraints imposed on the path of each computing device.

30. The medium of claim 29, wherein the one or more constraints correct for angular drift associated with the path of each computing device.

31. The medium of claim 25, wherein two nodes in a graphical map are connected by a link if the two nodes are associated with two consecutive events corresponding to an activity of one of the computing devices.

32. The medium of claim 31, wherein merging is further based on a node error bound, and wherein the two consecutive events are based on the node location and the node error bound of one of the computing devices at a time of discovery of the two consecutive events.

33. The medium of claim 25, wherein two locations in the three dimensional feature graph are connected by an edge if the inferred building features connect two estimated locations of computing device.