Crowd sourced mapping with robust structural features
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.
1. A computer-implemented method for localizing a mobile device traversing a structure, the method comprising:
generate feature descriptor data corresponding to a sequence of features associated with the structure that are detected by the mobile device while traversing the structure, the sequence of features being detected using sensor data associated with the mobile device;
communicate the feature descriptor data to a server communicatively coupled to a dataset comprised of previously received feature descriptor data corresponding to previously detected features associated with the structure submitted by other mobile devices, the previously detected features being detected using sensor data associated with the other mobile devices while traversing the structure; and
receive from the server feature map data associated with a global map of the structure generated in part using the previously received feature descriptors, the feature map data usable to correct the mobile device's location on a mobile structure map by matching two or more features among the sequence of features to corresponding features on the global map.
2. The computer-implemented method of claim 1 , wherein the sequence of features includes a structural feature associated with the structure.
3. The computer-implemented method of claim 1 , wherein the sequence of features includes a signal feature associated with the structure.
4. The computer-implemented method of claim 1 , wherein the mobile structure map is received from the server and is based on the global map of the structure.
5. The computer-implemented method of claim 1 , wherein the mobile structure map is generated by the mobile device using the sensor data associated with the mobile device.
6. The computer-implemented method of claim 1 , wherein the sensor data describes physical information about the detected structural feature and includes inertial sensor data, pressure sensor data, location data, or a combination thereof.
7. The computer-implemented method of claim 1 , wherein the sensor data includes radio frequency signal data, magnetic field data, vibration data, acoustic signature data, image data, light data, or a combination thereof.
8. The computer-implemented method of claim 1 , wherein the method further comprises:
refine one or more path parameters describing an intended path followed by the mobile device while traversing the structure, the one or more path parameters including heading, scale, drift, mobile device location, or a combination thereof.
9. A computing system for localizing a mobile device traversing a structure, the computing system comprising:
one or more processors; 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:
receive feature descriptor data corresponding to an ordered sequence of features associated with the structure that are detected by the mobile device while traversing the structure, the ordered sequence of features being detected using sensor data associated with the mobile device;
provide feature map data associated with a global map of the structure generated in part using previously received feature descriptors corresponding to previously detected features submitted by other mobile devices while traversing the structure,
the feature map data usable by the mobile device to correct the mobile device's location on a mobile structure map.
10. The computing system of claim 9 , wherein the instructions further cause the computing system to receive routing data from the mobile device, the routing data including one or more path parameters describing an intended path to be followed by the mobile device while traversing the structure.
11. The computing system of claim 10 , wherein the instructions further cause the computing system to analyze a reduced search space based on the routing data when identifying the feature map data, the reduced search space representing a subset of the global map corresponding to the intended route.
12. The computing system of claim 10 , wherein the instructions further cause the computing system analyze features of the global map that are external to the intended route upon determining that at least a subset of the feature descriptor data does not correspond to features of the global map along the intended route.
13. The computing system of claim 9 , wherein the ordered sequence of features includes a plurality of adjacent structural features.
14. The computing system of claim 9 , wherein the ordered sequence of features includes a plurality of concurrent signal features.
15. A non-transitory computer-readable storage medium comprising instructions tangibly embodied thereon that, when executed by a computing device adapted to localize a mobile device traversing a structure, cause the computing device to at least:
receive route data comprising one or more path parameters describing an intended path followed by the mobile device while traversing the structure;
generate feature descriptor data corresponding to an ordered sequence of features associated with the structure that are detected by the mobile device while traversing an intended route through structure, the sequence of features being detected using sensor data associated with the mobile device;
communicate the route data and the feature descriptor data to a server communicatively coupled to a dataset comprised of previously received feature descriptor data corresponding to previously detected features associated with the structure submitted by other mobile devices, the previously detected features being detected using sensor data associated with the other mobile devices while traversing the structure;
receive from the server feature map data associated with a global map of the structure generated in part using the previously received feature descriptors, the feature map data usable to correct the mobile device's location on a mobile structure map by matching two or more features among the ordered sequence of features to corresponding features on the global map.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the computing device to generate updated routing information upon correcting the mobile device's location on the mobile structure map.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the updated routing information is used to update the one or more path parameters to conform with the intended path.
18. The non-transitory computer-readable storage medium of claim 15 , wherein a first feature of the ordered sequence of features is a structural feature detected by the mobile device using inertial data associated with the mobile device.
19. The non-transitory computer-readable storage medium of claim 18 , wherein a second feature of the ordered sequence of features is a signal feature associated with the first feature.
20. The non-transitory computer-readable storage medium of claim 18 , wherein a second feature of the ordered sequence of features is an adjacent structural feature detected by the mobile device.