Energy-efficient localization of wireless devices in contained environments
Aspects of the present invention provide systems and methods for distributed signal processing of indoor localization signals wherein statistical algorithms and machine learning are used in place of a fingerprint map. The disclosure relates to calculation of angle and distance based on measurements of an indoor localization signal, followed by energy-efficient distribution of signal processing. Local signal processing is performed using any of multiple eigen structure algorithms or a linear probabilistic inference, before cloud-based signal processing is performed using a nonlinear probabilistic inference and machine learning that's been trained with historical data transmitted by the base stations and time-of-day location patterns. Without having to generate and constantly update an energy-exorbitant fingerprint map, the disclosed system reduces localization error to merely 50 cm with 95% probability without compromising energy-efficiency to rival the accuracy of indoor localization systems that utilize fingerprinting.
1. An energy-efficient method ( 100 ) of distributed signal processing for radiofrequency (RF) localization, wherein statistical algorithms and machine learning are used in place of a fingerprint map, the method comprising:
A. announcing, by an RF beacon ( 901 ), a location of said RF beacon ( 901 ) through a plurality of transmissions ( 903 ) to a plurality of base stations;
B. receiving ( 101 ), by each base station ( 902 ) of the plurality of base stations, the plurality of transmissions ( 903 ) from the RF beacon ( 901 );
C. measuring ( 102 ), by each base station ( 902 ) of the plurality of base stations, each transmission of the plurality of transmissions;
D. calculating ( 102 ) for each transmission ( 903 ), by each base station ( 902 ), at least one of: an angle of arrival (AOA) data point ( 904 ), a received signal strength indication (RSSI) distance data point ( 905 ), and a Time Difference of Arrival (TDOA) distance data point ( 906 );
E. filtering ( 103 ), by each base station ( 902 ), any AOA data points, any RSSI distance data points, and any TDOA distance data points, wherein filtering comprises:
i. filtering ( 103 ), by each base station ( 902 ), any AOA data points ( 904 ) into a smaller plurality of frequency estimates ( 909 ),
ii. filtering ( 103 ), by each base station ( 902 ), any RSSI distance data points ( 905 ) into a smaller plurality of first distance estimates ( 910 ), and
iii. filtering ( 103 ), by each base station ( 902 ), any TDOA distance data points ( 906 ) into a smaller plurality of second distance estimates ( 911 );
F. receiving ( 104 ), by a cloud server ( 912 ) from each base station ( 902 ), any transmitted frequency estimates ( 909 ), any transmitted first distance estimates ( 910 ), and any transmitted second distance estimates ( 911 ); and
G. processing ( 105 ), by the cloud server ( 912 ), a sensor fusion of: a statistical inference ( 913 ), machine learning ( 914 ), any received frequency estimates ( 909 ), any received first distance estimates ( 910 ), and any received second distance estimates ( 911 ) into a location estimate ( 915 ) of the RF beacon ( 901 ).
2. The method of claim 1 , wherein the AOA data points ( 904 ) are filtered into a smaller plurality of frequency estimates ( 909 ) using one or more statistical algorithms ( 907 ).
3. The method of claim 2 , wherein the RSSI distance data points ( 905 ) and the TDOA distance data points ( 906 ) are filtered into a smaller plurality of first distance estimates ( 910 ) and a smaller plurality of second distance estimates ( 911 ), respectively, each using a linear quadratic estimation ( 908 ).
4. The method of claim 1 , wherein the statistical inference is a Bayesian inference ( 913 ) comprising a Sequential Monte Carlo algorithm ( 913 ).
5. The method of claim 2 , wherein the statistical algorithms ( 907 ) are eigen structure algorithms comprising MUltiple Signal Classification (MUSIC), beamscan, and cross-correlation.
6. The method of claim 5 , wherein each base station ( 902 ) uses a deep forward error correction (FEC) code technique to transmit ( 308 ) the smaller plurality of frequency estimates ( 909 ), the smaller plurality of first distance estimates ( 910 ), and the smaller plurality of second distance estimates ( 911 ) to the cloud server ( 912 ).
7. The method of claim 6 , wherein the AOA data point ( 904 ) of each transmission ( 903 ) calculated by each base station ( 902 ) comprises an azimuth and a bearing.
8. The method of claim 7 , wherein the machine learning ( 914 ) is a deep neural network trained with previous data transmitted by the plurality of base stations ( 902 ) and time-of-day location patterns.
9. The method of claim 8 , wherein the linear quadratic estimation ( 908 ) is implemented with a multiplication algorithm based on Homer's method.
10. The method of claim 9 , wherein the RF modulation scheme is a close approximation of Gaussian minimum-shift keying (GMSK).
11. An energy-efficient system of distributed signal processing for radiofrequency (RF) localization, wherein statistical algorithms and machine learning are used in place of a fingerprint map, the system comprising:
A. an RF beacon ( 901 ):
i. a first processor ( 1001 ) capable of executing computer-executable instructions,
ii. a first antenna ( 1002 ), and
iii. a first memory device ( 1004 ) comprising computer-executable instructions for:
a. announcing a location of the RF beacon ( 901 ) by transmitting ( 101 ) a plurality of transmissions ( 903 );
B. a base station ( 902 ):
i. a second processor ( 1005 ) capable of executing computer-executable instructions,
ii. a second antenna ( 1006 ), and
iii. a second memory device ( 1008 ) comprising computer-executable instructions for:
a. receiving ( 101 ) a plurality of transmissions ( 903 ) from an RF beacon ( 901 ),
b. measuring ( 102 ) a transmission;
c. calculating, for each transmission ( 903 ) at least one of: an angle of arrival (AOA) data point ( 904 ), a received signal strength indication (RSSI) distance data point ( 905 ), and a Time Difference of Arrival (TDOA) distance data point ( 906 ), and
d. filtering ( 103 ) any AOA data points ( 904 ) into a smaller plurality of frequency estimates ( 909 ), any RSSI distance data points ( 905 ) into a smaller plurality of first distance estimates ( 910 ), and any TDOA distance data points ( 906 ) into a smaller plurality of second distance estimates ( 911 ); and
C. a cloud server ( 912 ):
i. a third processor ( 1009 ) capable of executing computer-executable instructions,
ii. a third antenna ( 1010 ), and
iii. a third memory device ( 1012 ) comprising computer-executable instructions for:
a. receiving ( 104 ) any transmitted any transmitted frequency estimates ( 909 ), first distance estimates ( 910 ), and any transmitted second distance estimates ( 911 ), and
b. processing ( 105 ), by the cloud server ( 912 ), a sensor fusion of: a statistical inference ( 913 ), machine learning ( 914 ), any received frequency estimates ( 909 ), any received first distance estimates ( 910 ), and any received second distance estimates ( 911 ) into a location estimate ( 915 ) of the RF beacon ( 901 ).
12. The system of claim 11 , wherein the AOA data points ( 904 ) are filtered into a smaller plurality of frequency estimates ( 909 ) using one or more statistical algorithms ( 907 ).
13. The system of claim 12 , wherein the RSSI distance data points ( 905 ) and the TDOA distance data points ( 906 ) are filtered into a smaller plurality of first distance estimates ( 910 ) and a smaller plurality of second distance estimates ( 911 ), respectively, each using a linear quadratic estimation ( 908 ).
14. The system of claim 13 , wherein the statistical inference is a Bayesian inference ( 913 ) comprising a Sequential Monte Carlo algorithm ( 913 ).
15. The system of claim 14 , wherein the statistical algorithms ( 907 ) are eigen structure algorithms comprising MUSIC, beamscan, and cross-correlation.
16. The system of claim 15 , wherein each base station ( 902 ) uses a deep FEC to transmit ( 308 ) the smaller plurality of frequency estimates ( 909 ), the smaller plurality of first distance estimates ( 910 ), and the smaller plurality of second distance estimates ( 911 ) to the cloud server ( 912 ).
17. The system of claim 16 , wherein the AOA data point ( 904 ) of each transmission ( 903 ) calculated by each base station ( 902 ) comprises an azimuth and a bearing.
18. The system of claim 17 , wherein the machine learning ( 914 ) is a deep neural network trained with previous data transmitted by the plurality of base stations ( 902 ) and time-of-day location patterns.
19. The system of claim 18 , wherein the linear quadratic estimation ( 908 ) is implemented with a multiplication algorithm based on Homer's system.
20. The system of claim 19 , wherein the RF modulation scheme is a close approximation of GMSK.