Indoor tag location detection system

1. A method of location detection of a wireless tag comprising:

receiving, by a localization system, an identifier of the wireless tag and sensor data generated for one or more augmented localization devices;

determining, by the localization system, an approximate location of the wireless tag based on known locations of the one or more augmented localization devices;

identifying one or more fingerprints based on the approximate location of the wireless tag, wherein each fingerprint indicates time-dependent expected sensor readings in a corresponding room; and

identifying a room in which the wireless tag is located by comparing the sensor data to the expected sensor readings of the one or more fingerprints.

2. The method of claim 1 , further comprising receiving, by the localization system, a RoomID that was received by the wireless tag in a signal from a transceiver, wherein the signal is an IR signal that is received by multiple wireless tags and the localization system receives tracking packets from the multiple wireless tags via an access point, each tracking packet including an identifier of a corresponding tag and the RoomID.

3. The method of claim 2 , wherein the wireless tags additionally record a signal strength of the IR signal and the tracking packet includes an indication of the signal strength.

4. The method of claim 3 , further comprising determining the location of the multiple wireless tags using weighted probabilities for the multiple wireless tags, the weighted probabilities based on indications of signal strengths corresponding to the multiple wireless tags.

5. The method of claim 2 , wherein RoomID is locally unique and the localization system identifies the approximate location of the wireless tag by looking up, in a database, a room closest to the access point with a matching RoomID.

6. The method of claim 1 , wherein the wireless tag is wearable by a human.

7. The method of claim 1 , wherein the wireless tag broadcasts tracking packets including the identifier of the wireless tag periodically.

8. The method of claim 1 , wherein the wireless tag broadcasts a tracking packet including the identifier of the wireless tag responsive to detecting motion of the wireless tag.

9. The method of claim 1 , wherein the identifier of the wireless tag is included in a tracking packet that also includes motion sensor data.

10. The method of claim 1 , further comprising receiving, from the wireless tag:

a second RoomID identifying a second room corresponding to a second transceiver that generated a second signal; and

location data indicating a location of the wireless tag relative to the transceiver and the second transceiver.

11. The method of claim 10 , wherein the location data comprises Received Signal Strength Indication (RSSI) data indicating signal strengths of the signal and the second signal.

12. The method of claim 10 , wherein the location data comprises Time of Flight data indicating amounts of time it took the signal and the second signal to reach the wireless tag.

13. The method of claim 1 , wherein each of the one or more fingerprints was generated by applying a machine-learning model to sensor data collected in the corresponding room.

14. A non-transitory computer readable medium storing instructions that, when executed by a localization system, cause the localization system to perform operations comprising:

receiving, by the localization system, an identifier of the wireless tag and sensor data generated for one or more augmented localization devices;

determining, by the localization system, an approximate location of the wireless tag based on known locations of the one or more augmented localization devices;

identifying one or more fingerprints based on the approximate location of the wireless tag, wherein each fingerprint indicates time-dependent expected sensor readings in a corresponding room; and

identifying a room in which the wireless tag is located by comparing the sensor data to the expected sensor readings of the one or more fingerprints.

15. The non-transitory computer readable medium of claim 14 , wherein the operations further comprise receiving, by the localization system, a RoomID that was received by the wireless tag in a signal from a transceiver, wherein the signal is an IR signal that is received by multiple wireless tags and the localization system receives tracking packets from the multiple wireless tags via an access point, each tracking packet including an identifier of a corresponding tag and the RoomID.

16. The method of claim 15 , wherein the wireless tags additionally record a signal strength of the IR signal and the tracking packet includes an indication of the signal strength.

17. The method of claim 16 , further comprising determining the location of the multiple wireless tags using weighted probabilities for the multiple wireless tags, the weighted probabilities based on indications of signal strengths corresponding to the multiple wireless tags.

18. The non-transitory computer readable medium of claim 14 , wherein the operations further comprise receiving, from the wireless tag:

a second RoomID identifying a second room corresponding to a second transceiver that generated a second signal; and

location data indicating a location of the wireless tag relative to the transceiver and the second transceiver.

19. The non-transitory computer readable medium of claim 14 , wherein each of the one or more fingerprints was generated by applying a machine-learning model to sensor data collected in the corresponding room.

20. The non-transitory computer readable medium of claim 18 , wherein the location data comprises at least one of Received Signal Strength Indication (RSSI) data indicating signal strengths of the signal and the second signal or Time of Flight data indicating amounts of time it took the signal and the second signal to reach the wireless tag.