Location fingerprinting for a transit system
Methods, program products, and systems for using multiple sensors to determine a location fingerprint are described. A sampling device can measure RF signals detected at a train station of a transit system or a route of the transit system. The sampling device, or a location server receiving the measurements, can filter RF signal measurements using one or more readings from sensors coupled to the sampling device and that are different from RF receivers. The readings can be taken concurrently with the RF signal measurements. These readings, designated as motion cues, can include motion sensor readings, barometer readings, or magnetometer readings. Using the motion cues, the sampling device or location server can distinguish different platforms of a station of the transit system and different levels of the station, or filter out RF signal measurements that may have been inaccurate, e.g., as caused by disturbances from a train entering or leaving a station.
1. A method comprising:
obtaining, by a mobile device, a map of a transit system, the map indicating a plurality of stations of the transit system and respective platforms at each station;
obtaining, by the mobile device, a location fingerprint associated with a platform of a station of the plurality of stations, the location fingerprint indicating a probability distribution of crowdsourced or surveyed received signal strength measurements of radio frequency (RF) signals;
obtaining, by the mobile device while operating at the station, received signal strength measurements of radio frequency (RF) signals;
receiving, from one or more sensors of the mobile device, sensor measurements indicating a first motion state of the mobile device at the station;
determining that the mobile device is located at the platform of the station based on the received signal strength measurements, the first motion state, the location fingerprint and the map;
determining, based at least upon the first motion state, that the mobile device is onboard a transit vehicle that is stopped at the platform;
predicting a next station that the mobile device will reach from the platform based at least upon the map and a determination that the mobile device is onboard the transit vehicle; and
providing a representation of the next station for presentation by the mobile device.
2. The method of claim 1 , wherein:
the transit system is a subway system where signals from a global positioning satellite system are undetectable,
the RF signals are from one or more signal sources that include at least one of a cell site of a cellular communications network, a wireless access point, or a wireless beacon, and
each measurement is associated with an identifier of a corresponding signal source.
3. The method of claim 1 , wherein:
the location fingerprint is determined based on one or more surveys by a sampling device.
4. The method of claim 1 , wherein predicting the next station comprises:
determining a respective likelihood that the mobile device will move from the platform to another location in the transit system; and
predicting the next station based on the respective likelihood.
5. The method of claim 1 , wherein providing the representation of the next station for presentation by the mobile device comprises: displaying a moving marker indicating that the mobile device is moving towards the next station upon determining, based at least in part on a second motion state that is different than the first motion state, that the mobile device is leaving the platform in the transit vehicle.
6. The method of claim 1 , wherein determining the platform on which the mobile device is located and predicting the next station that the mobile device will reach from the platform includes estimating a level of the platform using a barometric sensor reading.
7. The method of claim 1 , further comprising:
estimating a location and direction of travel of the mobile device on a route of the transit system.
8. A mobile device comprising:
one or more computer processors;
a non-transitory computer-readable medium storing instructions operable to cause the one or more computer processors to perform operations comprising:
obtaining, by the mobile device, a map of a transit system, the map indicating a plurality of stations of the transit system and respective platforms at each station;
obtaining, by the mobile device, a location fingerprint associated with a platform of a station of the plurality of stations, the location fingerprint indicating a probability distribution of crowdsourced or surveyed received signal strength measurements of radio frequency (RF) signals;
obtaining, by the mobile device while operating at the station, received signal strength measurements of radio frequency (RF) signals;
receiving, from one or more sensors of the mobile device, sensor measurements indicating a first motion state of the mobile device at the station;
determining that the mobile device is located at the platform of the station based on the received signal strength measurements, the first motion state, the location fingerprint and the map;
determining, based at least upon the first motion state, that the mobile device is onboard a transit vehicle that is stopped at the platform;
predicting a next station that the mobile device will reach from the platform based at least upon the map and a determination that the mobile device is onboard the transit vehicle; and
providing a representation of the next station for presentation by the mobile device.
9. The mobile device of claim 8 , wherein:
the transit system is a subway system where signals from a global positioning satellite system are undetectable,
the RF signals are from one or more signal sources that include at least one of a cell site of a cellular communications network, a wireless access point, or a wireless beacon, and
each measurement is associated with an identifier of a corresponding signal source.
10. The mobile device of claim 8 , wherein:
the location fingerprint is determined based on one or more surveys by a sampling device.
11. The mobile device of claim 8 , wherein predicting the next station comprises:
determining a respective likelihood that the mobile device will move from the platform to another location in the transit system; and
predicting the next station based on the respective likelihood.
12. The mobile device of claim 8 , wherein providing the representation of the next station from the platform for presentation by the mobile device comprises:
displaying a moving marker indicating that the mobile device is moving towards the next station upon determining, based at least in part on a second motion state that is different than the first motion state, that the mobile device is leaving the platform in a the transit vehicle.
13. The system of claim 8 , wherein determining the platform on which the mobile device is located and predicting the next station that the mobile device will reach from the platform includes estimating a level of the platform using a barometric sensor reading.
14. The system of claim 8 , the operations further comprising:
estimating a location and direction of travel of the mobile device on a route of the transit system.
15. A non-transitory computer-readable medium storing instructions operable to cause one or more computer processors to perform operations comprising:
obtaining, by a mobile device, a map of a transit system, the map indicating a plurality of stations of the transit system and respective platforms at each station;
obtaining, by the mobile device, a location fingerprint associated with a platform of a station of the plurality of stations, the location fingerprint indicating a probability distribution of crowdsourced or surveyed received signal strength measurements of radio frequency (RF) signals;
obtaining, by the mobile device while operating at the station, received signal strength measurements of radio frequency (RF) signals;
receiving, from one or more sensors of the mobile device, sensor measurements indicating a first motion state of the mobile device at the station;
determining that the mobile device is located at the platform of the station based on the received signal strength measurements, the first motion state, the location fingerprint and the map;
determining, based at least upon the first motion state, that the mobile device is onboard a transit vehicle that is stopped at the platform;
predicting a next station that the mobile device will reach from the platform based at least upon the map and a determination that the mobile device is onboard the transit vehicle; and
providing a representation of the next station for presentation by the mobile device.
16. The non-transitory computer-readable medium of claim 15 , wherein:
the transit system is a subway system where signals from a global positioning satellite system are undetectable,
the RF signals are from one or more signal sources that include at least one of a cell site of a cellular communications network, a wireless access point, or a wireless beacon, and
each measurement is associated with an identifier of a corresponding signal source.
17. The non-transitory computer-readable medium of claim 15 , wherein:
the location fingerprint is determined based on one or more surveys by a sampling device.
18. The non-transitory computer-readable medium of claim 15 , wherein predicting the next station comprises:
determining a respective likelihood that the mobile device will move from the platform to another location in the transit system; and
predicting the next station based on the respective likelihood.
19. The non-transitory computer-readable medium of claim 15 , wherein providing the representation of the next station from the platform for presentation by the mobile device comprises:
displaying a moving marker indicating that the mobile device is moving towards the next station upon determining, based at least in part on a second motion state that is different than the first motion state, that the mobile device is leaving the platform in the transit vehicle.
20. The non-transitory computer-readable medium of claim 15 , wherein determining the platform on which the mobile device is located and predicting the next station that the mobile device will reach from the platform includes estimating a level of the platform using a barometric sensor reading.