Pathway matching

• US 9,998,877 B2
• Filed: 12/28/2015
• Issued: 06/12/2018
• Est. Priority Date: 11/21/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Marti, Lukas M., Ma, Shannon M.
• Primary Examiner(s): MAPA, MICHAEL Y
• Application Number:
  US14/981,633
• Publication Number:
  US 20160198308A1
• Time in Patent Office: 897 Days
• Field of Search: 4554042, 4554142, 4554561-457
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01S 5/02521 using a radio-map
• CPC Class Codes: G01S 5/0263 by combining or switching between positions derived from two or more separate positioning systems
• CPC Class Codes: G01S 5/0269 Inferred or constrained positioning, e.g. employing knowledge of the physical or electromagnetic environment, state of motion or other contextual information to infer or constrain a position
• CPC Class Codes: G01S 5/0278 involving statistical or probabilistic considerations G01S5/0252, G01S5/0294 take precedence
• 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

Abstract

Methods, program products, and systems for estimating a location of a mobile device in a venue are provided. The venue can have pathways represented by a path network that includes segments connected by junctions. Estimating the location can include determining a first set of candidate locations for the mobile device, and mapping some of the candidate locations to updated candidate locations that are on or closer to one or more segments of the path network based on distances between the candidate locations and respective segments, resulting in a second set of candidate locations for the mobile device. The location of the mobile device can be derived from the second set of candidate locations.

Claims

1. A computer-implemented method, comprising:

estimating a location of a mobile device relative to pathways represented by a path network that includes segments connected by junctions, the estimating including

determining a first set of candidate locations for the mobile device,

shifting one or more of the candidate locations to updated candidate locations that are closer to, but not on, a corresponding segment or segments of the network path when the distances between the candidate locations and the corresponding segment or segments are larger than a threshold, wherein the shifting of the one or more candidate locations results in a second set of candidate locations for the mobile device, and

deriving the location of the mobile device from the second set of candidate locations.

2. The method of claim 1, comprising

receiving a sensor reading from a sensor that senses an environment variable,

propagating the second set of candidate locations based on the sensor reading, resulting in a third set of candidate locations, in which the third set of candidate locations is not constrained to the path network for at least a portion of the path network, and

estimating the location of the mobile device based on the third set of candidate locations.

3. The method of claim 2, wherein the propagating of the second set of candidate locations comprises using a state space estimator to explore possible candidate locations at a next time point given the second set of candidate locations at a previous time point.

4. The method of claim 3, wherein the state space estimator takes into account directions of the segments when exploring the possible candidate locations at the next time point.

5. The method of claim 2, wherein when propagating the second set of candidate locations to derive the third set of candidate locations, the third set of candidate locations is constrained to the path network for at least a portion of the path network.

6. The method of claim 1, wherein the shifting comprises shifting one or more of the candidate locations to updated locations that are on the corresponding segment or segments when the distances between the candidate locations and the corresponding segment or segments are less than a threshold.

7. The method of claim 6, wherein the shifting one or more of the candidate locations to updated candidate locations comprises for each of the one or more of the candidate locations, identifying a segment having an orthogonal distance from the candidate location that is smallest among the segments in the path network, and shifting the candidate location to the corresponding updated candidate location that is on or closer to the segment.

8. The method of claim 1, wherein the pathways represent routes that may be traveled by a pedestrian carrying the mobile device.

9. The method of claim 1, comprising determining that no constraint of movement of the mobile device is located between the candidate locations and the corresponding segment or segments prior to shifting the candidate locations to the updated candidate locations.

10. A computer-implemented method, comprising:

estimating a location of a mobile device relative to pathways represented by a path network that includes segments connected by junctions, the estimating including

determining a first set of candidate locations for the mobile device,

shifting one or more of the candidate locations to updated candidate locations that are on or closer to one or more segments of the path network based on distances between the candidate locations and respective segments, wherein the shifting

comprises determining a weight value based on a probability distribution function and a distance between a candidate location from the first set of candidate locations and a corresponding segment, and determining a position of the updated candidate location based on the weight value, and

results in a second set of candidate locations for the mobile device, and

deriving the location of the mobile device from the second set of candidate locations.

11. The method of claim 10, wherein when a segment represents a path in a hallway, the probability distribution function associated with the segment is dependent on a width of the hallway.

12. The method of claim 10, wherein the probability distribution function associated with the segment is dependent on a density of pathways in a vicinity of the segment.

13. The method of claim 10, comprising determining whether there is any constraint of movement of the movable body between the one or more candidate locations and a corresponding segment, and shifting the one or more candidate locations to the updated candidate locations only when there is no constraint of movement of the movable body between the one or more candidate locations and the corresponding segment.

14. A mobile device comprising:

a sensor to sense an environment variable;

a storage configured to store information about a path network representing pathways accessible by a movable body carrying the mobile device, the path network including segments connected by junctions; and

a processor configured to

determine a first estimated location of the mobile device;

when the first estimated location is not on the path network, identify a first segment in the path network, and when a distance between the first estimated location and the first segment is greater than a threshold, shift the first estimated location to a second estimated location that is closer to, but not on, the first segment; and

determine a current location of the mobile device based on the second estimated location and a sensor reading from the sensor.

15. The mobile device of claim 14, wherein when the distance between the first estimated location and the first segment is less than a threshold, shift the first estimated location to a second estimated location that is on the first segment.

16. A mobile device comprising:

a sensor to sense an environment variable;

a storage configured to store information about a path network representing pathways accessible by a movable body carrying the mobile device, the path network including segments connected by junctions; and

a processor configured to

determine a first estimated location of the mobile device;

when the first estimated location is not on the path network,

identify a first segment in the path network,

shift the first estimated location to a second estimated location that is on or closer to the first segment based on a distance between the first estimated location and the first segment,

determine a weight value based on a probability distribution function and the distance between the first estimated location and the corresponding segment, and

determine a position of the second estimated location based on the weight value; and

determine a current location of the mobile device based on the second estimated location and a sensor reading from the sensor.

17. The mobile device of claim 16, wherein the processor is configured to determine whether there is any constraint of movement of the movable body between the first estimated location and the first segment, and shift the first estimated location to the second estimated location only when there is no constraint of movement of the movable body between the first estimated location and the first segment.