Systems and Methods for Radio Frequency Identification (RFID) Localization

Patent metadata

Field	Value
Publication number	US-2015186693-A1
Application number	US-201314145395-A
Country	US
Kind code	A1
Filing date	Dec 31, 2013
Priority date	Dec 31, 2013
Publication date	Jul 2, 2015
Grant date	—

Abstract

A system for radio frequency identification localization. The system may include a modeling engine that employs one or more machine learning algorithms for receiving information associated with a plurality of reference tags; training, using one of the one or more machine learning algorithms, a prediction engine based upon the received information associated with the plurality of reference tags to output predicted tag locations; receiving information associated with the unknown tag; inputting the information associated with the unknown tag to the prediction engine; and determining a location of the unknown tag based upon an output of the prediction engine.

First claim

What is claimed is:

1 . A radio frequency identification (RFID) localization system for determining location of unknown tags, comprising:
a RFID reader, the RFID reader being within an office device; a plurality of reference tags positioned within a surrounding space of the RFID reader, the RFID reader operative to receive one or more signals from one or more reference tags of the plurality of reference tags and a signal from an unknown tag within the surrounding space; and a processing device associated with the RFID reader, the processing device operative to:
obtain information associated with the one or more reference tags based at least upon the one or more signals received therefrom by the RFID reader;
train a prediction engine based upon the obtained information associated with the one or more reference tags to output predicted tag locations;
obtain information associated with the unknown tag based upon the signal received therefrom by the RFID reader;
provide the information associated with the unknown tag as input to the prediction engine; and
determine a location of the unknown tag in the surrounding space based on an output of the prediction engine.

2 . The localization system of claim 1 , wherein the one or more reference tags are fixedly positioned within the surrounding space.

3 . The localization system of claim 1 , wherein for each reference tag, the information associated therewith includes location information of the reference tag and at least one of a signal strength and phase shift of the signal received therefrom.

4 . The localization system of claim 3 , wherein the location information of each of the one or more reference tags is obtained by the processing device from a system user.

5 . The localization system of claim 1 , wherein the RFID reader is configured to receive from the one or more reference tags a first set of signals at a first time period and a second set of signals at a second time period after the first time period, and the processing device is further operative to:
obtain a first set and a second set of information associated with the one or more reference tags based upon the first and second sets of signals, respectively; determine a difference between the first and second sets of information; and redefine the prediction engine based at least upon the determined difference.

6 . The localization system of claim 1 , wherein the information associated with the unknown tag provided to the prediction engine includes at least one of a signal strength and phase shift of the signal received by the RFID reader from the unknown tag.

7 . The localization system of claim 1 , wherein the unknown tag is attachable to an object, and the processing device is further operative to determine whether the object is in use based on the signal received by the RFID reader from the unknown tag, and to provide to a user both the location of the object and an indication of whether the object is in use.

8 . The localization system of claim 1 , further comprising a plurality of RFID readers and a plurality of office devices deployed in an environment, wherein each office device is integrated with a corresponding RFID reader.

9 . The localization system of claim 8 , wherein at least one of the plurality of office devices comprises an imaging device.

10 . A device for determining location of unknown tags, comprising:
a radio frequency identification (RFID) reader configured to receive signals from a plurality of reference tags fixedly positioned within a surrounding space of the device, and from an unknown tag within the surrounding space; and a modeling engine that employs one or more machine learning algorithms to determine a location of the unknown tag, the modeling engine communicatively coupled to the RFID reader and operative to:
obtain location information associated with each of the plurality of reference tags;
determine one or more features associated with the plurality of reference tags based upon the signals received therefrom;
based upon the one or more features associated with the plurality of reference tags and the location information associated therewith, defining a function to output predicted tag locations;
determine one or more features associated with the unknown tag based upon the signal received therefrom;
provide the one or more features associated with the unknown tag to the function; and
determine a location of the unknown tag based upon an output of the function.

11 . The device of claim 10 , wherein the one or more features associated with the plurality of reference tags include at least one of corresponding signal strengths and signal phase shifts of the signals from each of the plurality of reference tags.

12 . The device of claim 10 , further comprising a user interface for receiving from a user the location information associated with each of the plurality of reference tags.

13 . The device of claim 10 , wherein the RFID reader is configured to receive from the plurality of reference tags a first set of signals at a first time period and a second set of signals at a second time period, and the modeling engine is further operative to:
determine one or more additional features associated with the plurality of reference tags based upon a difference between the first set of signals and the second set of signals; and redefine the function based at least upon the one or more additional features.

14 . The device of claim 10 , wherein the device includes a single RFID reader.

15 . A non-transitory computer readable storage medium having stored thereon instructions that when executed by a machine result in the following operations:
receiving information associated with a plurality of reference tags; training, using one or more machine learning algorithms, a prediction engine based upon the received information associated with the plurality of reference tags to output predicted tag locations; receiving information associated with the unknown tag; inputting the information associated with the unknown tag to the prediction engine; and determining a location of the unknown tag based upon an output of the prediction engine.

16 . The computer readable storage medium of claim 15 , wherein the information associated with the plurality of reference tags includes location information thereof and at least one of corresponding signal strengths and phase shifts of signals transmitted by the plurality of reference tags.

17 . The computer readable storage medium of claim 15 , wherein the information associated with the unknown tag includes at least one of a signal strength and a phase shift of a signal transmitted by the unknown tag.

18 . The computer readable storage medium of claim 15 , further having instructions that when executed by the machine result in the following operations:
during a first time period, receiving a first set of information associated with the plurality of reference tags; during a second time period after the first time period, receiving a second set of information associated with the plurality of reference tags; determining a difference between the first set of information and the second set of information; and redefining the prediction engine based at least upon the determined difference.

19 . The computer readable storage medium of claim 18 , wherein the receiving the first set of information includes receiving at least one of signal strengths and phase shifts of signals transmitted by each of the plurality of reference

Assignees

• Lexmark Int Inc

Inventors

• Blair Bryan Michael
• Fessler John Thomas
• Whitney Julie Ann Gordon

Classifications

• G06K7/10366 Primary

  the interrogation device being adapted for miscellaneous applications · CPC title

• G06Q10/0877

  by inventory control or reporting using inventory tracking or counting · CPC title

• G01S13/74

  Systems using reradiation of radio waves, e.g. secondary radar systems; Analogous systems · CPC title

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G16H40/20

  for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms · CPC title