REAL-TIME LOCATION DETECTION USING EXCLUSION ZONES

• US 20150248797A1
• Filed: 03/03/2015
• Published: 09/03/2015
• Est. Priority Date: 03/03/2014
• Status: Active Grant

• Current Assignee: Consortium P Incorporated
• Original Assignee: Consortium P Incorporated
• Inventors: Duggan, Robert J., Vidacic, Dragan, Nevish, Keith A.
• Granted Patent: US 9,443,363 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01S 5/0278 involving statistical or probabilistic considerations G01S5/0252, G01S5/0294 take precedence
• CPC Class Codes: G06K 7/00 Methods or arrangements for sensing record carriers, e.g. for reading patterns methods or arrangements for marking the record carrier in digital fashion G06K1/00; pattern recognition G06F18/00; arrangements for image or video recognition or understanding G06V10/00; character recognition, recognising digital ink or document-oriented image-based pattern recognition G06V30/00
• CPC Class Codes: G07C 9/28 the pass enabling tracking or indicating presence

Abstract

A system and method for real-time location detection consists of a scalable real time location system (RTLS). It provides revised real time object location determinations. It includes a tag within a location environment, a processor to calculate a location of the tag, and at least one exclusion zone in the environment. Processing includes an original location determination of the tag and a revised location determination of the tag. The revised location determination is calculated by applying attributes of at least one exclusion zone to the original location determination of the tag. Some exclusion zones are defined by no-fly exclusion zones. The revised location determination improves the operation of the RTLS by correcting for impossible and improbable original location determinations. For embodiments, system deployment consists of three phases: collection of training and testing data, network training and testing, and network adaptive maintenance.

Claims

1. A real time location system (RTLS) for revised real time location determination of at least one object comprising:

a location environment;

at least one tag located within said location environment;

a processor to calculate a location of said at least one tag located within said location environment;

at least one exclusion zone in said location environment;

an original location determination of said tag in said location environment;

a revised location determination of said tag in said location environment,

said revised location determination calculated by said processor by applying attributes of said at least one exclusion zone to said original location determination of said at least one tag if it is determined that said original location determination is cospatial with said at least one exclusion zone, and

said revised location determination modifying operation of said RTLS by modifying original location determinations.

2. The system of claim 1, wherein said revised location determination comprises calculation by a neural network by applying attributes of said at least one exclusion zone to said original location determination of said at least one tag.

3. The system of claim 2, wherein said calculation by said neural network comprises setup and training of said neural network.

4. The system of claim 3, wherein said training comprises blurring of said at least one exclusion zone.

5. The system of claim 4, wherein said blurring comprises Gaussian distribution.

6. The system of claim 1, wherein said revised location determination comprises gradient descent.

7. The system of claim 3, wherein said training comprises diverted output.

8. The system of claim 1, wherein said at least one exclusion zone comprises locations in which it would be improbable for tags to be found.

9. The system of claim 1, wherein said at least one exclusion zone comprises locations in which it would be impossible for tags to be found.

10. The system of claim 1, wherein said original location determination comprises noise.

11. The system of claim 1, wherein said original location determination comprises at least one missed reading of signals from said at least one tag.

12. The system of claim 1, wherein said revised real time location determination comprises an input map of said location environment.

13. The system of claim 1, wherein said revised real time location determination comprises receiving wireless RF transmissions from said at least one tag at at least one transceiver.

14. A method for revised real time location determination of at least one object by a real time location system (RTLS) comprising the steps of:

designating a location environment;

obtaining a map of said location environment;

defining at least one exclusion zone in said location environment;

providing at least one tag located within said location environment;

obtaining an original location determination;

producing a revised location determination of said tag in said location environment,

said revised location determination calculated by applying attributes of said at least one exclusion zone to said original location determination of said at least one tag, and

said revised location determination modifying operation of said RTLS by correcting for impossible and improbable original location determinations.

15. The method of claim 14, wherein said step of producing a revised location comprises training a neural network;

and

said revised location determination is calculated by said neural network.

16. The method of claim 15, wherein the step of training comprises measured data from said at least one tag.

17. The method of claim 16, wherein said measured data comprises at least one physically measurable property associated with a position in three-dimensional space.

18. The method of claim 15, wherein the step of training comprises modeled data.

19. The method of claim 15, further comprising:

mathematically defining a no-fly exclusion zone polyhedron;

inputting a location estimate;

comparing said location estimate with a four dimensional space-time region of said no-fly exclusion zone polyhedron;

determining if said location estimate is within said no fly exclusion zone polyhedron region;

locating a boundary of said no-fly exclusion zone polyhedron closest to said location estimate;

defining allowed locations in said closest boundary;

revising said estimated location to said defined allowed locations; and

creating a revised virtual path from said estimated location to said revised location.

20. A neural network real time location system (RTLS) for revised real time location determination of at least one object comprising:

a map representing a location environment;

at least one tag located within said location environment;

a neural network to process a location of said at least one tag located within said location environment, said neural network trained with wireless RF data from said at least one tag and corresponding locations of said at least one tag;

at least one exclusion zone in said location environment, said map processed by Gaussian blurring of said at least one exclusion zone;

an original location determination of said tag in said location environment;

a revised location determination of said tag in said location environment,

said revised location determination calculated by said neural network by applying attributes of said at least one exclusion zone to said original location determination of said at least one tag including gradient descent algorithms, and

said revised location determination modifying operation of said RTLS by correcting for impossible and improbable original location determinations.