Correcting for antennae spatial distortions in radio frequency (RF) localizations
Correcting for antennae spatial distortions in Radio Frequency (RF) localization may be provided. A plurality of actual locations associated with a plurality of Access Point (APs) may be received. Then a plurality of signal strengths associated with the plurality of APs may be received. Based on the plurality of signal strengths, a model may be created that models a plurality of inference errors respectively corresponding to the plurality of APs between a plurality of inferred locations respectively corresponding to the plurality of APs and the plurality of actual locations. The model may then be used in determining a location of a device.
1. A method comprising:
receiving a plurality of actual locations associated with a plurality of radios;
receiving a plurality of signal strengths associated with the plurality of radios;
creating, based on the plurality of signal strengths, a model that models a plurality of inference errors respectively corresponding to the plurality of radios between a plurality of inferred locations respectively corresponding to the plurality of radios and the plurality of actual locations, wherein the model models the plurality of inference errors as a convolution of a partial individual error contribution by each of the plurality of radios; and
using the model in determining a location of a device.
2. The method of claim 1 , wherein creating the model comprises using a Machine Learning (ML) process to create the model.
3. The method of claim 1 , wherein the plurality of signal strengths comprise Received Signal Strength Indicators (RSSI).
4. The method of claim 1 , wherein the plurality of signal strengths are obtained from Channel State Information (CSI).
5. The method of claim 1 , wherein the plurality of signal strengths are associated with beacons.
6. The method of claim 1 , wherein the plurality of signal strengths are obtained using Neighbor Discovery Protocol (NDP).
7. A system comprising:
a memory storage; and
a processing unit coupled to the memory storage, wherein the processing unit is operative to:
receive a plurality of actual locations associated with a plurality of Access Point (APs);
receive a plurality of signal strengths associated with the plurality of APs;
create, based on the plurality of signal strengths, a model that models a plurality of inference errors respectively corresponding to the plurality of APs between a plurality of inferred locations respectively corresponding to the plurality of APs and the plurality of actual locations, wherein the model models the plurality of inference errors as a convolution of a partial individual error contribution by each of the plurality of APs; and
use the model in determining a location of a device.
8. The system of claim 7 , wherein the processing unit being operative to create the model is operative to use a Machine Learning (ML) process to create the model.
9. The system of claim 7 , wherein the plurality of signal strengths comprise Received Signal Strength Indicators (RSSI).
10. The system of claim 7 , wherein the plurality of signal strengths are obtained from Channel State Information (CSI).
11. The system of claim 7 , wherein the plurality of signal strengths are associated with beacons.
12. The system of claim 7 , wherein the plurality of signal strengths are obtained using Neighbor Discovery Protocol (NDP).
13. A computer-readable medium that stores a set of instructions which when executed perform a method executed by the set of instructions comprising:
receiving a plurality of actual locations associated with a plurality of Access Point (APs);
receiving a plurality of signal strengths associated with the plurality of APs;
creating, based on the plurality of signal strengths, a model that models a plurality of inference errors respectively corresponding to the plurality of APs between a plurality of inferred locations respectively corresponding to the plurality of APs and the plurality of actual locations, wherein the model models the plurality of inference errors as a convolution of a partial individual error contribution by each of the plurality of APs; and
using the model in determining a location of a device.
14. The computer-readable medium of claim 13 , wherein creating the model comprises using a Machine Learning (ML) process to create the model.
15. The computer-readable medium of claim 13 , wherein the plurality of signal strengths comprise Received Signal Strength Indicators (RSSI).
16. The computer-readable medium of claim 13 , wherein the plurality of signal strengths are obtained from Channel State Information (CSI).
17. The computer-readable medium of claim 13 , wherein the plurality of signal strengths are associated with beacons.