System and method for locating, tracking, and/or monitoring the status of personnel and/or assets both indoors and outdoors

• US 8,712,686 B2
• Filed: 11/21/2011
• Issued: 04/29/2014
• Est. Priority Date: 08/06/2007
• Status: Active Grant

• Current Assignee: TRX Systems, Inc.
• Original Assignee: TRX Systems, Inc.
• Inventors: Bandyopadhyay, Amrit, Hakim, Daniel, Funk, Benjamin E., Kohn, Eric Asher, Teolis, Carole A., Blankenship, Gilmer
• Primary Examiner(s): Tran, Khoi
• Assistant Examiner(s): MOYER, DALE S
• Application Number:
  US13/301,491
• Publication Number:
  US 20120130632A1
• Time in Patent Office: 890 Days
• Field of Search: 701400-526, 901 1- 50, 700245-264
• US Class Current: 701/446
• CPC Class Codes: G01C 17/38 Testing, calibrating, or compensating of compasses
• CPC Class Codes: G01C 21/1652 with ranging devices, e.g. LIDAR or RADAR
• CPC Class Codes: G01C 21/1654 with electromagnetic compass
• CPC Class Codes: G01C 21/188 for accumulated errors, e.g. by coupling inertial systems with absolute positioning systems
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/3438 Rendez-vous, i.e. searching a destination where several users can meet, and the routes to this destination for these users; Ride sharing, i.e. searching a route such that at least two users can share a vehicle for at least part of the route
• CPC Class Codes: G01C 21/3626 Details of the output of route guidance instructions traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G01S 19/48 by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
• CPC Class Codes: G01S 19/49 whereby the further system is an inertial position system, e.g. loosely-coupled
• CPC Class Codes: G01S 5/015 between indoor and outdoor environments
• CPC Class Codes: G01S 5/0294 Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/33 for indoor environments, e.g. buildings
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

A system and method for locating, tracking, and/or monitoring the status of personnel and/or assets (“trackees”), both indoors and outdoors, is provided. Tracking data obtained from various sources utilizing any number of tracking methods may be provided as input to a mapping application. The mapping application generates position estimates for trackees using a suite of mapping tools to make corrections to the tracking data. The mapping application further uses information from building data, when available, to enhance position estimates. Indoor tracking methods including sensor fusion methods, map matching methods, and map building methods may be implemented to take tracking data from one or more trackees and compute a more accurate tracking estimate for each trackee. Outdoor tracking methods may be implemented to enhance outdoor tracking data by combining tracking estimates such as inertial tracks with magnetic data, compass data, and/or with GPS, if and when available.

Claims

1. A computer-implemented method of tracking a trackee both indoors and outdoors, comprising:

receiving as input, at a computer, tracking data for a tracking path being followed by a trackee, wherein the tracking data includes tracking points, and wherein each tracking point includes at least two-dimensional location coordinates;

when building data is available for part or all of one or more buildings, receiving as input at the computer, the building data and utilizing the building data to develop a first set of mathematical constraints on a tracking path solution based on the tracking data that improves the accuracy of the tracking data;

when the building data is not available, generating building features of part or all of the one or more buildings based on one or more of segmentation of the tracking path and classification of the trackee'"'"'s motion based on the tracking data as the trackee traverses a building and utilizing the building features to develop a second set of mathematical constraints on the tracking path solution that improves the accuracy of the tracking data; and

generating and displaying, via a graphical user interface associated with the computer, position estimates generated based on the improved tracking data.

2. The method of claim 1, wherein the computer comprises at least one of a portable laptop computer, a mobile phone, or a personal digital assistant.

3. The method of claim 1, wherein the computer is incorporated in a component of a portable tracking system associated with the trackee.

4. The method of claim 1, wherein the tracking data received as input comprises previously-acquired, stored tracking data.

5. The method of claim 1, wherein the tracking data includes data obtained from inertial sensors and signal-based location sensors, and wherein the position estimates are generated by fusing data from the inertial sensors and the signal-based location sensors.

6. The method of claim 1, wherein the tracking data includes inertial tracking data obtained from inertial sensors, and wherein the building data and the building features are used to correct for angular drift and scaling errors of the inertial sensors.

7. The method of claim 1, wherein the tracking data includes data obtained from signal-based location systems, and wherein the building data and the building features are used to identify and correct or remove tracking point outliers.

8. The method of claim 1, wherein the tracking data includes received signal strength indication (RSSI) data acquired when the trackee is at a given location.

9. The method of claim 8, method further comprising:

determining, based on the RSSI data, in which region of an established grid of regions for the building the trackee is located, wherein the RSSI data is based on transmissions received, at a portable unit associated with the trackee, from radios located at a predetermined number of reference points outside of the building that are used to establish the grid; and

determining the heading of the trackee based on variances in the RSSI data.

10. The method of claim 8, method further comprising:

averaging and filtering the received RSSI data to smoothen the RSSI data;

storing the smoothed RSSI data for the given location as a location signature; and

using matches between current location signatures to stored location signatures to increase a probability of matching the trackee to a previously-visited location.

11. The method of claim 1, wherein the building data includes a building outline polygon for the building, the method further comprising:

determining grid angles for the building, the grid angles comprising the angles at which long straight edges of the building outline polygon are oriented; and

utilizing the grid angles to achieve heading corrections.

12. The method of claim 11, further comprising:

dividing the building outline polygon into partitions based on the determined grid angles, wherein each partition is associated with an expected hallway orientation or angle; and

utilizing the partitions to achieve the heading corrections.

13. The method of claim 1, wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

dividing the tracking path into segments of tracking points, wherein each segment includes a group of tracking points contained within a bounding box having a threshold maximum width; and

determining whether one or more of the segments can be matched to the building features or the building data.

14. The method of claim 1, wherein the tracking data includes inertial tracking data obtained from inertial sensors, the method further comprising:

determining inertial tracking error estimates for one or more tracking points based on error accumulated by the inertial sensors;

determining bounds on corrections to be made for the one or more tracking points based on the determined inertial tracking error estimates; and

making corrections to the one or more tracking points if the corrections fall within the determined bounds.

15. The method of claim 1, wherein the tracking data includes inertial tracking data obtained from inertial sensors, and wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

dividing the tracking path into segments of tracking points;

identifying segments, having a length that exceeds a predetermined threshold, that are approximately parallel or perpendicular to one another as being on a path grid;

correcting the identified segments to a relative grid to eliminate error accumulated by the inertial sensors; and

matching the path grid to the building features or the building data.

16. The method of claim 1, wherein the tracking data includes tracking data obtained from a gyroscope and a compass, the method further comprising:

selecting segments, each segment comprising a series of tracking points;

determining a compass prediction for a heading of a selected segment, using each tracking point in the series of tracking points, by rotating a compass angle at each tracking point by a difference between the segment heading and a gyroscope angle for the tracking point;

clustering each of the compass predictions for the segments; and

determining a highest probability compass heading for each segment heading using cluster densities from the clustering and, in so doing, filtering out outliers in lower density clusters.

17. The method of claim 1, wherein the tracking data includes compass data, and wherein building grid angles are determined from the building data, the method further comprising:

clustering compass angles of tracking points around grid angle headings to determine a highest probability grid heading for one or more segments of tracking points.

18. The method of claim 1, wherein grid angles and partitions for the building are determined from the building data, and wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

dividing the tracking path into segments of tracking points; and

for each segment;

(i) identifying a building partition the segment crosses and/or lies within; and

(ii) rotating the segment to a probable heading based on a grid angle associated with the identified partition if the correction is within determined correction bounds.

19. The method of claim 1, wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

determining when a defined mathematical constraint is violated by one or more features of a tracking path solution; and

performing required corrections to the tracking path solution to restore the violated mathematical constraint while propagating the effect of the corrections to all tracking points in the tracking path by enforcing mathematical constraints on the tracking path solution to remove any path discontinuity created by the corrections.

20. The method of claim 1, the method further comprising:

matching a collection of tracking points to possible location estimates, wherein the possible location estimates are defined as mathematical constraints for a constraint solver; and

utilizing the constraint solver to satisfy one or more of the defined mathematical constraints for the collection of tracking points.

21. The method of claim 20, further comprising:

ranking each tracking solution, from among multiple feasible tracking solutions generated by the constraint solver, according to the degree to which defined mathematical constraints are satisfied by the tracking solution, and the change required to satisfy the defined mathematical constraints; and

selecting the best tracking solution, based on the rankings.

22. The method of claim 20, further comprising:

executing the constraint solver to constrain indoor tracking points of the trackee'"'"'s tracking path within a building outline.

23. The method of claim 20, further comprising:

executing the constraint solver to constrain outdoor tracking points of the trackee'"'"'s tracking path outside of a building outline.

24. The method of claim 1, further comprising:

determining a route that represents a shortest path between a plurality of trackees being tracked using a combination of tracking points; and

displaying the determined route on the graphical user interface associated with the computer.

25. The method of claim 1, wherein the tracking data includes magnetic data acquired when the trackee is at an unknown location, the method further comprising:

defining a magnetic signature at the unknown location as a series of numbers representing a total magnetic field strength of a series of tracking points around the unknown location;

comparing the magnetic signature data to stored magnetic signatures for known locations; and

correcting the trackee'"'"'s position estimate to the known location when a signature match is detected between the magnetic signature data and the magnetic signature for the known location.

26. The method of claim 1, wherein the tracking data includes short-range radio received signal strength indication (RSSI) data relating to the trackee'"'"'s proximity to other trackees, the method further comprising:

determining a distance range between the trackee and at least one other trackee based on the received RSSI data;

defining a length constraint between tracking points associated with the trackee and the at least one other trackee based on the determined distance range; and

utilizing a constraint solver to satisfy the defined length constraint while solving all other constraints to improve inter-trackee and overall tracking accuracy.

27. The method of claim 1, further comprising:

determining, based on the received tracking data, when the trackee has transitioned from an outdoor location to an indoor location, wherein the determination is based on one or more of an increase in GPS horizontal dilution of precision (HDOP), a reduction in satellite strength, the absence of GPS, a decrease in signal strength from an outdoor reference point, or an increase in magnetic field variance.

28. The method of claim 1, wherein the received building data includes a building outline for the building, the method further comprising:

determining, based on the received tracking data, that the trackee has transitioned from an outdoor location to an indoor location when an outdoor trajectory of the trackee overlaps the building outline.

29. The method of claim 1, wherein grid angles and partitions for the building are determined from the building data, the tracking data includes compass data, and wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

dividing the tracking path into segments of tracking points, and detecting path grids;

associating the segments and the path grids with compass angles and grid angles by clustering and building partition testing; and

aligning the segments and path grids to the grid angles.

30. The method of claim 1, wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

dividing the tracking path into segments of tracking points; and

correlating a segment to a building feature if it is determined that the segment matches the building feature.

31. The method of claim 1, further comprising:

triggering a hallway event, indicating movement of the trackee in a hallway of the building, when a group of tracking points are contained within a rectangle having a threshold maximum width, and wherein a length of the rectangle exceeds a predetermined threshold.

32. The method of claim 1, further comprising:

determining an event based on the received tracking data, wherein the event corresponds to one of a path type, or a motion type; and

generating a new building feature based on the event if the event cannot be matched to an existing building feature.

33. The method of claim 1, further comprising:

generating multiple feasible tracking solutions for the position estimates while matching segments of tracking points to choices of building grid angles from building data or building features;

utilizing a constraint solver to satisfy one or more defined mathematical constraints on the tracking points; and

removing tracking solutions, from among the multiple feasible tracking solutions, that violate certain of the one or more defined mathematical constraints by more than a predetermined threshold.

34. The method of claim 1, wherein the tracking data includes elevation change data, the method further comprising:

calculating floor heights of the building using the elevation change data; and

resolving the elevation change data into floor numbers for the building using the calculated floor heights.

35. The method of claim 1, further comprising:

triggering an elevation change event, indicating an elevation transition of the trackee, based on the received tracking data; and

determining whether the elevation change event can be correlated to an existing elevation type feature on a floor plan included with the building data.

36. The method of claim 1, wherein the tracking data includes inertial tracking data obtained from inertial sensors and GPS data, the method further comprising:

comparing and matching a shape between an inertial tracking path and a GPS tracking path;

improving position estimates when the trackee is outdoors by fusing an inertial tracking path estimate of inertial tracking points and a GPS tracking path estimate of GPS position estimates into a single tracking path estimate;

correlating the single tracking path estimate with at least one building outline among the building data.

37. The method of claim 1, wherein a collection of tracking points for the trackee comprises a tracking path, the method further comprising:

determining whether the tracking path of the trackee matches a building feature or a second trackee'"'"'s tracking path by;

i) dividing the trackee'"'"'s tracking path into segments with associated segment lines, the associated segment lines comprising an input set of lines; and

ii) testing a shape fit, an overlap, and/or a match of the input set of lines into one or more base sets of lines stored for the building feature or the second trackee'"'"'s tracking path to determine whether the shape fit, the overlap and/or the match quality qualifies as a location match.