UNMANNED AERIAL VEHICLE OBSTACLE DETECTION AND AVOIDANCE

• US 20170076616A1
• Filed: 01/06/2016
• Published: 03/16/2017
• Est. Priority Date: 09/11/2015
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Gehlhaar, Jeffrey Baginsky, Kanade, Parag Mohan, Sweet, Charles Wheeler III
• Granted Patent: US 10,019,907 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 20/17 taken from planes or by drones
• CPC Class Codes: G06V 20/38 Outdoor scenes
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft
• CPC Class Codes: G08G 5/045 Navigation or guidance aids, e.g. determination of anti-collision manoeuvers radar or analogous systems specially adapted for anti-collision between aircraft G01S13/933

Abstract

Apparatuses and methods for detecting an obstacle in a path of an Unmanned Aerial Vehicle (UAV) are described herein, including, but not limited to, receiving data from a single image/video capturing device of the UAV, computing a score based on the received data, and performing at least one obstacle avoidance maneuver based on the score.

Claims

1. A method for detecting an obstacle in a path of an Unmanned Aerial Vehicle (UAV), the method comprising:

receiving data corresponding to an image frame from a single image/video capturing device of the UAV;

computing a score based on the data; and

performing at least one obstacle avoidance maneuver based on the score.

2. The method of claim 1, wherein the at least one obstacle avoidance maneuver comprises one or more of changing a speed of the UAV, changing the direction associated with the path, changing an altitude of the UAV, adjusting pitch of the UAV, adjusting yaw of the UAV, adjusting roll of the UAV, finding an alternative course, notifying the user/operator, landing, returning to base, coming to a complete halt or hovering in place, transmitting the data to the operator, requesting the operator'"'"'s guidance, or switching to manual operation by the operator.

3. The method of claim 1, wherein the image/video capturing device is a camera.

4. The method of claim 1, wherein the data comprises at least one of an image or a sampled video.

5. The method of claim 1, wherein the score corresponds to a confidence level of safe flight as the UAV continues in the path.

6. The method of claim 1, wherein the score is computed based on machine learning.

7. The method of claim 1, wherein performing the at least one obstacle avoidance maneuver based on the score further comprises continuing to fly along the path based on the score.

8. The method of claim 1, wherein computing the score based on the data comprises:

extracting at least one feature from the data; and

computing the score for the data based on the at least one feature.

9. The method of claim 8, wherein the at least one feature is extracted based on clutter on a horizon in the data.

10. The method of claim 8, wherein:

the at least one feature is extracted with a deep convolution network; and

the score is computed by a support vector machine.

11. The method of claim 1, further comprising:

receiving a trigger for computing a score; and

computing the score for a portion of the image frame of the data based on the trigger.

12. The method of claim 11, wherein:

the trigger is in response to detecting the UAV is turning in a first direction or initiating computing to find an alternative course in the first direction; and

the portion of the image frame corresponds to the first direction.

13. The method of claim 1, further comprising:

receiving a trigger for computing a new score;

rotating the image/video capturing device based on the trigger; and

computing the new score based on new data obtained from rotating the image/video capturing device.

14. The method of claim 13, wherein the trigger is in response to at least one of:

detecting the UAV is turning in a first direction;

or

initiating computing to find an alternative course corresponding to turning the UAV in the first direction.

15. The method of claim 1, further comprising:

receiving a trigger for computing a new score;

activating the at least one additional image/video capturing device; and

computing the new score based on new data obtained from at least one additional image/video capturing device.

16. The method of claim 15, wherein the trigger is at least one of:

detecting the UAV is turning in a first direction;

or

initiating computing to find an alternative course corresponding to turning the UAV in a first direction.

17. The method of claim 1, wherein the image/video capturing device captures a field of view in a direction of motion of the UAV.

18. The method of claim 1, further comprising activating at least one of a stereo camera, sonar, radar, computer vision sensor, additional camera, infrared camera, or moisture sensor based on the score.

19. An apparatus for detecting an obstacle in a path of an Unmanned Aerial Vehicle (UAV), the apparatus comprising:

a single image/video capturing device;

a processor coupled to the single image/video capturing device, the processor configured to;

receive data corresponding to an image frame from the single image/video capturing device of the UAV;

compute a score based on the data; and

perform at least one obstacle avoidance maneuver based on the score.

20. An apparatus for detecting an obstacle in a path of an Unmanned Aerial Vehicle (UAV), the apparatus comprising:

means for receiving data from a single image/video capturing device of the UAV;

means for computing a score based on the data; and

means for performing at least one obstacle avoidance maneuver based on the score.

21. A non-transitory computer-readable medium for storing computer-readable code, such that, when executed, causes a processor to perform a method for detecting an obstacle in a path of an Unmanned Aerial Vehicle (UAV), the method comprising:

receiving data corresponding to an image frame from the single image/video capturing device of the UAV;

computing a score based on the data; and

performing at least one obstacle avoidance maneuver based on the score.

22. The non-transitory computer-readable medium of claim 21, wherein the at least one obstacle avoidance maneuver comprises one or more of changing a speed of the UAV, changing the direction associated with the path, changing an altitude of the UAV, adjusting pitch of the UAV, adjusting yaw of the UAV, adjusting roll of the UAV, finding an alternative course, notifying the user/operator, landing, returning to base, coming to a complete halt or hovering in place, transmitting the data to the operator, requesting the operator'"'"'s guidance, or switching to manual operation by the operator.

23. The non-transitory computer-readable medium of claim 21, wherein the image/video capturing device is a camera.

24. The non-transitory computer-readable medium of claim 21, wherein the data comprises at least one of an image or a sampled video.

25. The non-transitory computer-readable medium of claim 21, wherein the score corresponds to a confidence level of safe flight as the UAV continues in the path.