System and method for mobile device locationing

1. A method of determining a location of a mobile device in a system having a plurality of fixed transmitters, the method comprising:

obtaining, at a location generator device, inference model data defining a plurality of node operations;

collecting, at the mobile device, respective proximity indicators corresponding to a subset of the fixed transmitters, each proximity indicator representing a proximity of the mobile device to the respective fixed transmitter;

at the location generator device, generating a location according to the proximity indicators and the node operations; and

presenting the location,

wherein the method further comprises, prior to obtaining the inference model data:

collecting training proximity indicators,

labelling the training proximity indicators based on captured data, and

transmitting the labelled training proximity indicators to a server for use in generation of the inference model data.

2. The method of claim 1 , wherein obtaining the inference model comprises receiving the inference model from the server.

3. The method of claim 1 , wherein the plurality of node operations define a deep neural network.

4. The method of claim 1 , wherein each proximity indicator includes an identifier of the corresponding fixed transmitter and an indication of at least one of signal strength for the corresponding fixed transmitter and a round trip time (RTT) for the corresponding fixed transmitter.

5. The method of claim 4 , wherein the fixed transmitters include wireless access points, and wherein the indication of signal strength includes one of (i) a received signal strength indicator (RSSI) for the corresponding wireless access point and (ii) a path loss measurement for the corresponding wireless access point.

6. The method of claim 1 , wherein presenting the location includes:

presenting a map of the system on a display of the mobile device with an overlay corresponding to the generated location.

7. The method of claim 1 , further comprising:

obtaining, at the mobile device, secondary inference model data defining a second plurality of node operations;

collecting, with the proximity indicators, motion data from a motion sensor of the mobile device;

generating an initial location according to the proximity indicators and the node operations; and

generating a final location according to the initial location, the motion data and the second plurality of node operations;

wherein presenting the location comprises presenting the final location.

8. The method of claim 7 , wherein the second plurality of node operations define a recurrent neural network.

9. The method of claim 7 , wherein the motion data includes one or more of accelerometer data, gyroscope data and magnetometer data.

10. The method of claim 1 , wherein the location generator device is one of the mobile device and a server.

11. The method of claim 1 , wherein the labelling the training proximity indicators comprises capturing a barcode, and labelling the training proximity indicators with data decoded from the barcode.

12. The method of claim 1 , wherein the labelling the training proximity indicators includes:

presenting a map on a display of the mobile device;

receiving a selection of a position on the map; and

labelling the training proximity indicators with a location corresponding to the position selected on the map.

13. The method of claim 1 , wherein the labeling the training proximity indicators based on captured data includes correlating first sensor data with second sensor data to determine one or more reference points in an environment of the mobile device and inferring one or more labels of the training proximity indicators based on the one or more reference points.

14. The method of claim 13 , wherein the first sensor data includes image sensor data and the second sensor data includes inertial sensor data of the mobile device.

15. The method of claim 1 , wherein the processor is configured to label the training proximity indicators based on captured data by correlating first sensor data with second sensor data to determine one or more reference points in an environment of the mobile device and inferring one or more labels of the training proximity indicators based on the one or more reference points.

16. The method of claim 15 , wherein the first sensor data includes image sensor data and the second sensor data includes inertial sensor data of the mobile device.

17. A mobile device, comprising:

a memory;

a sensor configured to detect a plurality of fixed transmitters;

a processor interconnected with the memory and the sensor, the processor configured to:

obtain inference model data defining a plurality of node operations;

collect respective proximity indicators corresponding to a subset of the fixed transmitters, each proximity indicator representing a proximity of the mobile device to the respective fixed transmitter;

generate a location according to the proximity indicators and the node operations; and

present the location,

wherein the processor is further configured, prior to obtaining the inference model data, to:

collect training proximity indicators,

label the training proximity indicators based on captured data, and

transmit the labelled training proximity indicators to a server for use in generation of the inference model data.

18. The mobile device of claim 17 , wherein the plurality of node operations define a deep neural network.

19. The mobile device of claim 17 , wherein each proximity indicator includes an identifier of the corresponding fixed transmitter and an indication of signal strength for the corresponding fixed transmitter.

20. The mobile device of claim 19 , wherein the fixed transmitters include wireless access points, and wherein the indication of signal strength includes one of (i) a received signal strength indicator (RSSI) for the corresponding wireless access point and (ii) a path loss measurement for the corresponding wireless access point.

21. The mobile device of claim 17 , further comprising a display; wherein the processor is further configured to present the location by presenting a map on the display with an overlay corresponding to the generated location.

22. The mobile device of claim 17 , further comprising a motion sensor; wherein the processor is further configured to:

obtain secondary inference model data defining a second plurality of node operations;

collect, with the proximity indicators, motion data from the motion sensor;

generate an initial location according to the proximity indicators and the node operations; and

generate a final location according to the initial location, the motion data and the second plurality of node operations; and

present the final location.

23. The mobile device of claim 22 , wherein the second plurality of node operations define a recurrent neural network.

24. The mobile device of claim 22 , wherein the motion sensor includes one or more of an accelerometer, a gyroscope and a magnetometer.

25. The mobile device of claim 17 , wherein the processor is configured to obtain the inference model by receiving the inference model from a server.

26. The mobile device of claim 16 , wherein the processor is further configured to label the training proximity indicators by capturing a barcode, and labelling the training proximity indicators with data decoded from the barcode.

27. The mobile device of claim 16 , further comprising a display; wherein the processor is further configured to label the training proximity indicators by:

presenting a map on the display;

receiving a selection of a position on the map; and

labelling the training proximity indicators with a location corresponding to the position selected on the map.

28. A server, comprising:

a memory;

a communications interface; and

a processor interconnected with the memory and the communications interface, the processor configured to:

obtain inference model data defining a plurality of node operations;

receive, from a mobile device, respective proximity indicators corresponding to a subset of a plurality of fixed transmitters, each proximity indicator representing a proximity of the mobile device to the respective fixed transmitter as detected by a sensor of the mobile device;

generate a location of the mobile device according to the proximity indicators and the node operations; and

present the location,

wherein the processor is further configured, prior to obtaining the inference model data, to receive labelled training proximity indicators based on captured data from the mobile device for use in generation of the inference model data.