Methods and systems for mobile-agent navigation

• US 9,625,912 B2
• Filed: 05/03/2016
• Issued: 04/18/2017
• Est. Priority Date: 09/03/2014
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Liao, Miao, Xu, Xinyu, van Beek, Petrus J. L.
• Primary Examiner(s): Dager, Jonathan M
• Application Number:
  US15/145,700
• Publication Number:
  US 20160246302A1
• Time in Patent Office: 350 Days
• Field of Search: None
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G05D 1/0234 using optical markers or beacons optical beacons per se G01S1/70
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means

Abstract

Aspects of the present invention are related to methods and systems for autonomous navigation using visual-landmark recognition. One method may include scanning a captured image to detect a machine-readable marker and extracting encoded data therefrom. The data may include an identifying key usable to access a database to retrieve physical attributes associated with the marker. The method may include using the physical attributes to compute a position and an orientation of a mobile agent relative to a landmark object associated with the marker. The method may further include determining a path toward a next route location based on the position of the next route location and the computed position and orientation of the mobile agent and controlling the mobile agent to drive along the path toward the next route location.

Claims

1. A method for autonomous navigation, said method comprising:

receiving a captured image;

scanning said captured image to detect a machine-readable marker;

when a machine-readable marker is detected;

extracting an encoded data from said detected machine-readable marker, wherein said extracted encoded data comprises an identifying key;

using said identifying key, accessing a database to retrieve a plurality of physical attributes associated with said detected machine-readable marker;

using said plurality of physical attributes, computing a world coordinate for each locating point in a plurality of locating points associated with said detected, machine-readable marker;

determining a corresponding image coordinate for said each locating point in said plurality of locating points; and

using said world coordinate for said each locating point in said plurality of locating points and said corresponding image coordinate for said each locating point in said plurality of locating points, computing a position and an orientation of a mobile agent relative to a landmark object associated with said detected machine-readable marker.

2. The method of claim 1, further comprising:

obtaining a position of a next route location;

determining a path toward said next route location based on said position of said next route location and said position and said orientation of said mobile agent relative to said landmark object associated with said detected machine-readable marker;

controlling said mobile agent to drive along said path toward said next route location.

3. The method of claim 2, wherein said obtaining a position of a next route location comprises accessing a stored route comprising a plurality of landmark-object identifiers.

4. The method of claim 2, wherein said obtaining a position of a next route location comprises accessing a stored route comprising a plurality of route-location identifiers.

5. The method of claim 2, further comprising:

taking repeated motion measurements during said controlling; and

determining driving instructions based on said motion measurements and said path.

6. The method of claim 1, wherein said computing a position and an orientation of a mobile agent relative to a landmark object associated with said detected machine-readable marker comprises a Perspective-n-Point method.

7. The method of claim 1, wherein said machine-readable marker is a code selected from the group consisting of a barcode, a QR code, an Aztec code, and a Data Matrix code.

8. The method of claim 1, wherein:

said machine-readable marker is a two-dimensional machine-readable code; and

said plurality of physical attributes comprises a length of a side of said two-dimensional machine-readable code, a world coordinate associated with a center of said two-dimensional machine-readable code, and a normal vector associated with said two-dimensional machine-readable code.

9. The method of claim 1, wherein said database is on said mobile agent.

10. The method of claim 1, wherein said database is on a server.

11. The method of claim 1, wherein said plurality of physical attributes comprises three non-co-linear points on said machine-readable code.

12. A mobile agent comprising:

a camera for capturing an image;

a control component; and

a processor configured to;

scan said captured image to detect a machine-readable marker;

when a machine-readable marker is detected;

extract an encoded data from said detected machine-readable marker, wherein said extracted encoded data comprises an identifying key;

using said identifying key, access a database to retrieve a plurality of physical attributes associated with said detected machine-readable marker;

using said plurality of physical attributes, compute a world coordinate for each locating point in a plurality of locating points associated with said detected machine-readable marker;

determine a corresponding image coordinate for said each locating point in said plurality of locating points; and

using said world coordinate for said each locating point in said plurality of locating points and said corresponding image coordinate for said each locating point in said plurality of locating points, compute a position and an orientation of the mobile agent relative to a landmark object associated with said detected machine-readable marker.

13. The mobile agent of claim 12, wherein said processor is further configured to:

obtain a position of a next route location; and

determine a path toward said next route location based on said position of said next route location and said position and said orientation of said mobile agent relative to said landmark object associated with said detected machine-readable marker; and

said control portion is configured to control said mobile agent to drive along said path toward said next route location.

14. The mobile agent of claim 13, wherein said processor is configured to obtain a position of a next route location by accessing a stored route comprising a plurality of landmark-object identifiers.

15. The mobile agent of claim 13, wherein said processor is configured to obtain a position of a next route location by accessing a stored route comprising a plurality of route-location identifiers.

16. The mobile agent of claim 13, wherein said processor is further configured to:

take repeated motion measurements during said controlling; and

determine driving instructions based on said motion measurements and said path.

17. The mobile agent of claim 12, wherein said database is on said mobile agent.

18. The mobile agent of claim 12, wherein said database is on a server.

19. The mobile agent of claim 12, wherein

said machine-readable marker is a code selected from the group consisting of a barcode, a QR code, an Aztec code, and a Data Matrix code.

20. The mobile agent of claim 12, wherein said plurality of physical attributes comprises three non-co-linear points on said machine-readable marker.