USE OF MULTI-SCALE FIDUCIALS BY AUTONOMOUSLY CONTROLLED AERIAL VEHICLES

• US 20170371351A1
• Filed: 09/11/2017
• Published: 12/28/2017
• Est. Priority Date: 10/29/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: KELSO, CARL RYAN, SCHOENBERG, YVES CHRISTIAN ALBERS, YANG, JAMES
• Granted Patent: US 10,613,551 B2
• Time in Patent Office: Days
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64U 10/13 Flying platforms
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• CPC Class Codes: G05D 1/0808 specially adapted for aircraft
• CPC Class Codes: G05D 1/102 specially adapted for vertical take-off of aircraft
• CPC Class Codes: G06K 19/06009 with optically detectable marking G06K19/063, G06K19/08 take precedence
• CPC Class Codes: G06K 19/06037 multi-dimensional coding
• CPC Class Codes: G06K 19/06056 the marking comprising a further embedded marking, e.g. a 1D bar code with the black bars containing a smaller sized coding
• CPC Class Codes: G06K 19/06131 the marking comprising a target pattern, e.g. for indicating the center of the bar code or for helping a bar code reader to properly orient the scanner or to retrieve the bar code inside of an image
• CPC Class Codes: G06K 19/06168 the marking being a concentric barcode
• CPC Class Codes: G06K 2019/06243 concentric-code
• CPC Class Codes: G06K 2019/06262 with target- or other orientation-indicating feature
• CPC Class Codes: G06K 7/1426 Multi-level bar codes
• CPC Class Codes: G06T 2207/30208 Marker matrix

Abstract

Disclosed are various embodiments involving use of a multi-scale fiducial by an autonomously controlled aerial vehicle. A first image at a first location is captured, and a first fiducial at a first scale of a multi-scale fiducial is recognized within the first image. The autonomously controlled aerial vehicle is piloted relative to the multi-scale fiducial based at least in part on information contained within the first fiducial. A second image at a second location is captured, and a second fiducial at a second scale of the multi-scale fiducial is recognized within the second image. An action is then performed based at least in part on information contained within the second fiducial.

Claims

1. A system, comprising:

an autonomously controlled aerial vehicle; and

control logic implemented in the autonomously controlled aerial vehicle configured to perform a method comprising;

capturing, via an imaging device of the autonomously controlled aerial vehicle, a first image at a first location;

recognizing a first fiducial at a first scale of a multi-scale fiducial depicted within the first image, the first fiducial encoding data indicating a position of a second fiducial relative to the first fiducial;

piloting the autonomously controlled aerial vehicle relative to the multi-scale fiducial based at least in part on the data indicating the position of the second fiducial relative to the first fiducial, the second fiducial being located outside of an outer boundary of the first fiducial;

capturing, via the imaging device, a second image at a second location;

recognizing the second fiducial at a second scale of the multi-scale fiducial, the second fiducial being depicted within the second image; and

piloting the autonomously controlled aerial vehicle relative to the multi-scale fiducial based at least in part on information contained in the second fiducial.

2. The system of claim 1, wherein the first fiducial and the second fiducial employ at least one of:

different colors, textures, or patterns.

3. The system of claim 1, wherein recognizing the second fiducial further comprises recognizing the second fiducial using a scale-variant algorithm.

4. A system, comprising:

an autonomously controlled aerial vehicle; and

control logic implemented in the autonomously controlled aerial vehicle configured to perform a method comprising;

capturing, via an imaging device of the autonomously controlled aerial vehicle, a first image at a first location;

recognizing a first fiducial at a first scale of a multi-scale fiducial depicted within the first image;

piloting the autonomously controlled aerial vehicle relative to the multi-scale fiducial based at least in part on information contained within the first fiducial;

capturing, via the imaging device, a second image at a second location;

recognizing a second fiducial at a second scale of the multi-scale fiducial, the second fiducial being depicted within the second image; and

performing an action based at least in part on information contained in the second fiducial.

5. The system of claim 4, wherein each scale of the multi-scale fiducial can be used independently to determine a relative position of a respective parent fiducial.

6. The system of claim 4, wherein each scale of the multi-scale fiducial can be used independently to determine a relative position of a respective child fiducial.

7. The system of claim 4, wherein at least a portion of the first fiducial is clipped in the second image.

8. The system of claim 4, wherein the second fiducial is unresolvable from the first image by the control logic.

9. The system of claim 4, wherein recognizing the first fiducial further comprises actively ignoring data from the first image corresponding to an expected location of the second fiducial.

10. The system of claim 4, wherein the control logic is configured to recognize the first fiducial and the second fiducial without using a scale-invariant algorithm.

11. The system of claim 4, wherein the action comprises piloting the autonomously controlled aerial vehicle relative to multi-scale fiducial based at least in part on the information contained in the second fiducial.

12. The system of claim 4, wherein the multi-scale fiducial is affixed to an object that has moved between when the first image was captured and when the second image was captured.

13. A method, comprising:

capturing, via an imaging device of an autonomously controlled aerial vehicle, a first image at a first location;

recognizing, via control logic of the autonomously controlled aerial vehicle, a first fiducial at a first scale of a multi-scale fiducial depicted within the first image;

piloting the autonomously controlled aerial vehicle relative to the multi-scale fiducial based at least in part on information contained within the first fiducial;

capturing, via the imaging device, a second image at a second location;

recognizing, via the control logic, a second fiducial at a second scale of the multi-scale fiducial, the second fiducial being depicted within the second image; and

performing, via the control logic, an action based at least in part on information contained in the second fiducial.

14. The method of claim 13, wherein each scale of the multi-scale fiducial can be used independently to determine a relative position of a respective parent fiducial or a respective child fiducial.

15. The method of claim 13, wherein at least a portion of the first fiducial is clipped in the second image.

16. The method of claim 13, wherein the second fiducial is unresolvable from the first image by the control logic.

17. The method of claim 13, wherein recognizing the first fiducial further comprises actively ignoring data from the first image corresponding to an expected location of the second fiducial.

18. The method of claim 13, wherein the control logic is configured to recognize the first fiducial and the second fiducial without using a scale-invariant algorithm.

19. The method of claim 13, wherein the action comprises piloting the autonomously controlled aerial vehicle relative to multi-scale fiducial based at least in part on the information contained in the second fiducial.

20. The method of claim 13, wherein the multi-scale fiducial is affixed to an object that has moved between when the first image was captured and when the second image was captured.