Stable and accurate indoor localization based on predictive hyperbolic location fingerprinting

A method for indoor location comprising the steps of:

• (a) fixedly-positioning a first sensor device in a first known location in an environment and fixedly-positioning a second sensor device in a second known location in the environment;
• (b) causing the first sensor device to transmit a first radio signal to the second sensor device, and causing the second sensor device to transmit a second radio signal to the first sensor device;
• (c) at the first sensor device, measuring a received signal strength indicator (RSSI) value of the second radio signal, and at the second sensor device, measuring a received RSSI value of the first radio signal;
• (d) generating at least one Friis equation for each of the first radio signal and the second radio signal;
• (e) generating a fusion RSSI fingerprint based on a raw RSSI fingerprint and a log-ratio RSSI fingerprint, the fusion RSSI fingerprint comprising a level of accuracy based on a number (N) of sensor devices within the environment;
• and
• (f) repeating steps (a) to (e) at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment;
• and
• wherein the first known location and the second known location comprise permanent geo-coordinates.

A system for predicting cell fingerprints comprising:

• a computing system comprising a processor and a memory storing instructions executable by the processor to cause the processor to at least:
• receive measured RSSI values associated with a plurality of fixedly-positioned sensor devices, wherein the plurality of fixedly-positioned sensor devices are stationary in known locations in an environment and caused to transit radio signals to each other and measure characteristics of the received radio signals;
• generate at least one Friis equation for each of the received radio signals, to generate a raw RSSI fingerprint for each sensor device;
• generate a log-ratio RSSI fingerprint between a pair of sensor devices;
• normalize the raw RSSI fingerprint and normalize the log-ratio RSSI fingerprint;
• combine the normalized raw RSSI fingerprint and the normalized log-ratio RSSI fingerprint to form a fusion RSSI fingerprint comprising a level of accuracy based on a number (N) of sensor devices within the environment;
• and
• receive updated measured RSSI values at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment;
• wherein the plurality of fixedly-positioned sensor devices comprise fixed geo-coordinates.