Autonomous aircraft navigation

• US 10,401,874 B1
• Filed: 11/10/2018
• Issued: 09/03/2019
• Est. Priority Date: 11/10/2018
• Status: Active Grant

• Current Assignee: Skyways Air Transportation, Inc.
• Original Assignee: Skyways Air Transportation, Inc.
• Inventors: Acknin, Charles, Muller, Jonathan Plinio
• Primary Examiner(s): Dager, Jonathan M
• Assistant Examiner(s): Evans, Garrett F
• Application Number:
  US16/186,528
• Time in Patent Office: 297 Days
• Field of Search: None
• CPC Class Codes: B64D 1/22 Taking-up articles from earth's surface
• CPC Class Codes: B64U 2101/30 for imaging, photography or videography
• CPC Class Codes: B64U 2101/60 for transporting passengers; for transporting goods other than weapons
• 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 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0676 specially adapted for landing
• CPC Class Codes: G05D 1/101 specially adapted for aircraft
• CPC Class Codes: G05D 1/12 Target-seeking control
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

Systems and methods for autonomous aircraft navigation are disclosed. Embodiments relate to autonomously navigating an aircraft to a payload by locating a payload target attached to the payload. In some embodiments, the payload target is comprised of a plurality of concentric shapes of retroreflective material. These retroreflective shapes may be quickly identified in images to locate the payload. The retroreflective shapes may be illuminated by a light source on the aircraft so that the payload and the payload target do not requires a power source of their own. Some embodiments use band-filtered light and image acquisition techniques to facilitate locating of the payload target.

Claims

1. An unmanned aerial vehicle (UAV) navigation system, comprising:

a camera attached to the UAV positioned to have a downward view;

an illumination system attached to the UAV positioned to illuminate the view of the camera;

a payload having a retroreflective payload target on its top side; and

a targeting system configured to receive images from the camera, locate the payload target in the field of vision of the camera, and transmit navigational instructions to a navigation system,

wherein the navigation system receives the navigational instructions and navigates the UAV to the payload;

wherein the payload target is retroreflective;

wherein the payload target comprises a plurality of concentric squares of retroreflective material;

wherein to locate the payload target in the field of vision of the camera the targeting system is configured to;

identify a plurality of edges in an image;

identify a quadrilateral shape formed by four edges of the plurality of edges; and

find the geometric center of the quadrilateral shape.

2. The system of claim 1, wherein the illumination system is an infrared illumination system that produces light in an infrared spectrum.

3. The system of claim 2, further comprising a filter fitted to the camera designed to block light outside of the infrared spectrum.

4. The system of claim 1, further comprising a payload latch system configured to latch onto the payload when the UAV lands on the payload.

5. The system of claim 1, wherein the camera is a video camera capturing successive frames of video at a fixed framerate, and the targeting system locates the payload target in each video frame in real-time as they are captured.

6. The system of claim 1, wherein the retro-reflective payload target comprises a plurality of concentric squares of retro-reflective material on a substantially non-reflective background.

7. The system of claim 6, wherein the targeting system locates the payload target by locating squares in the image.

8. A method of unmanned aerial vehicle (UAV) navigation, comprising:

illuminating an area under a UAV with infrared light;

acquiring an image of the area under the UAV with an infrared camera;

locating a payload target in the image, wherein the payload target is attached to a payload;

determining a navigation instruction to navigate the UAV to the payload target; and

transmitting the navigation instruction to a navigation system of the UAV, wherein the navigation system receives the navigation instructions and navigates the UAV to the payload target;

wherein the payload target is retroreflective;

wherein the payload target comprises a plurality of concentric squares of retroreflective material;

wherein locating the payload target in the image comprises;

identifying a plurality of edges in the image;

identifying a quadrilateral shape formed by four edges of the plurality of edges;

determining that the vertices of the quadrilateral shape are all substantially right angles;

finding the geometric center of the quadrilateral shape.

9. The method of claim 8, wherein the navigation instruction includes an estimated distance from the UAV to the payload target and a direction to the payload target.

10. The method of claim 9, wherein the navigation system navigates the UAV to the payload target by closing the distance from the UAV to the payload target while decreasing the altitude of the UAV.

11. The method of claim 8, further comprising:

landing the UAV on the payload target; and

loading the payload onto the UAV.

12. A method of autonomous payload handling by an unmanned cargo aircraft, comprising:

receiving a rough coordinate of a payload, the payload having a retroreflective payload target on a top side, the payload target comprising a plurality of concentric squares of retroreflective material;

navigating the aircraft to the rough coordinate;

acquiring, using a camera, an image of an area around the rough coordinate;

locating the retroreflective payload target in the image, including;

identifying a plurality of edges in the image;

identifying a quadrilateral shape formed by four edges of the plurality of edges; and

finding the geometric center of the quadrilateral shape;

navigating the aircraft to the payload based on the location of the retroreflective payload target;

landing the aircraft on the payload; and

loading the payload onto the aircraft.

13. The method of claim 12, wherein the rough coordinate is a global navigation satellite system coordinate.

14. The method of claim 12, wherein the navigating the aircraft to the payload includes:

capturing a plurality of images at a first framerate;

locating the retroreflective payload target in each of the plurality of images; and

generating navigational instructions to move the aircraft to the retroreflective payload target.

15. The method of claim 12, wherein the loading the payload onto the aircraft includes:

engaging a portion of the payload with a payload latch attached to the aircraft.

16. The method of claim 12, wherein the camera is an infrared camera.