Methods and apparatus for using received signal strength information in a wireless system
Methods and apparatus for processing and using signals transmitted by a device, e.g., a low cost beacon transmitter device, to facilitate making location determinations with regard to the transmitting device and/or making a decision of when or how to use location information generated based on received signals are described. In accordance with some features the processing performed on the received signal strength measurements is based on whether or not the device from which the signals are received is in motion. The size of a sample period used as a processing window when determining device location is based, in some embodiments, on the rate of motion. When and/or how to use location determinations are performed is also based on motion in some embodiments. Machine learning updates of location determination parameters, based on received signals, are disabled when the signals are from devices determined to be in motion.
1. A method comprising:
determining a rate of motion of a first wireless device;
conditionally updating a machine learning model based on the determined rate of motion being below a first motion rate threshold indicative of the first wireless device is not in motion;
deriving path loss parameters from the machine learning model;
estimating a location of the first wireless device based on the derived path loss parameters; and
outputting an indication of the estimated location of the first wireless device.
2. The method of claim 1 , wherein the rate of motion is a first rate of motion, and further comprising:
measure a rate of variability of RSSI values of signals from the first wireless device;
determining a second rate of motion when the rate of variability is above a predefined first threshold and below a predefined second threshold; and
determining a third rate of motion when the rate of variability is above said second threshold.
3. The method of claim 1 , wherein the conditional updating of the machine learning model further comprises inhibiting an update to the machine learning model in response to a second determined rate of motion being above said first motion rate threshold.
4. The method of claim 1 , further comprising determining a frequency of location estimates of the first wireless device based on the rate of motion, wherein the estimation of the location of the first wireless device is based on the frequency of location estimates.
5. The method of claim 4 , wherein the determination of the frequency is based on whether the rate of motion is above a predefined threshold.
6. The method of claim 5 , wherein the rate of motion is a first rate of motion, and further comprising: determining a first location estimate of the first wireless device based on a first number of RSSI measurements when a second rate of motion is below the predefined threshold and determining a second location estimate of the first wireless device based on a second number of RSSI measurements when a third rate of motion is above the predefined threshold.
7. A system comprising:
hardware processing circuitry;
one or more hardware memories storing instructions that when executed configure the hardware processing circuitry to perform operations comprising:
determining a rate of motion of a first wireless device;
conditionally updating a machine learning model based on the determined rate of motion being below a first motion rate threshold indicative of the first wireless device is not in motion;
deriving path loss parameters from the machine learning model;
estimating a location of the first wireless device based on the derived path loss parameters; and
outputting an indication of the estimated location of the first wireless device.
8. The system of claim 7 , wherein the rate of motion is a first rate of motion, and the operations further comprising:
measure a rate of variability of RSSI values of signals from the first wireless device;
determining a second rate of motion when the rate of variability is above a predefined first threshold and below a predefined second threshold; and
determining a third rate of motion when the rate of variability is above said second threshold.
9. The system of claim 8 , wherein the conditional updating of the machine learning model further comprises inhibiting an update to the machine learning model in response to a second determined rate of motion being above said first motion rate threshold.
10. The system of claim 7 , the operations further comprising determining a frequency of location estimates of the first wireless device based on the rate of motion, wherein the estimation of the location of the first wireless device is based on the frequency of location estimates.
11. The system of claim 10 , wherein the determination of the frequency is based on whether the rate of motion is above a predefined threshold.
12. The system of claim 11 , wherein the rate of motion is a first rate of motion, and the operations further comprising: determining a first location estimate of the first wireless device based on a first number of RSSI measurements when a second rate of motion is below the predefined threshold and determining a second location estimate of the first wireless device based on a second number of RSSI measurements when a third rate of motion is above the predefined threshold.
13. A non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations comprising:
determining a rate of motion of a first wireless device;
conditionally updating a machine learning model based on the determined rate of motion being below a first motion rate threshold indicative of the first wireless device is not in motion;
deriving path loss parameters from the machine learning model;
estimating a location of the first wireless device based on the derived path loss parameters; and
outputting an indication of the estimated location of the first wireless device.
14. The non-transitory computer readable storage medium of claim 13 , wherein the rate of motion is a first rate of motion, and the operations further comprising:
measure a rate of variability of RSSI values of signals from the first wireless device;
determining a second rate of motion when the rate of variability is above a predefined first threshold and below a predefined second threshold; and
determining a third rate of motion when the rate of variability is above said second threshold.
15. The non-transitory computer readable storage medium of claim 13 , wherein the conditional updating of the machine learning model further comprises inhibiting an update to the machine learning model in response to a second determined rate of motion being above said first motion rate threshold.
16. The non-transitory computer readable storage medium of claim 15 , the operations further comprising determining a frequency of location estimates of the first wireless device based on the rate of motion, wherein the estimation of the location of the first wireless device is based on the frequency of location estimates.
17. The non-transitory computer readable storage medium of claim 16 , wherein the rate of motion is a first rate of motion, and the operations further comprising: determining a first location estimate of the first wireless device based on a first number of RSSI measurements when a second rate of motion is below a predefined threshold and determining a second location estimate of the first wireless device based on a second number of RSSI measurements when a third rate of motion is above the predefined threshold.