Autonomous aerial navigation in low-light and no-light conditions

Patent metadata

Field	Value
Publication number	US-12266131-B2
Application number	US-202117505257-A
Country	US
Kind code	B2
Filing date	Oct 19, 2021
Priority date	Mar 31, 2021
Publication date	Apr 1, 2025
Grant date	Apr 1, 2025

Abstract

Autonomous aerial navigation in low-light and no-light conditions includes using night mode obstacle avoidance intelligence and mechanisms for vision-based unmanned aerial vehicle (UAV) navigation to enable autonomous flight operations of a UAV in low-light and no-light environments using infrared data.

First claim

What is claimed is:

1. A method, comprising:
causing an onboard light source of an unmanned aerial vehicle to emit infrared light while the unmanned aerial vehicle is in a night mode configuration;
collecting image data using an onboard camera of the unmanned aerial vehicle while the onboard light source emits the infrared light;
filtering the image data to reduce pink tones within the image data;
detecting an object within an environment in which the unmanned aerial vehicle is operating based on the filtered image data;
determining a flight operation for the unmanned aerial vehicle to avoid a collision with the object; and
causing the unmanned aerial vehicle to perform the flight operation.

2. The method of claim 1 , comprising:
measuring an intensity of light within the environment in which the unmanned aerial vehicle is operating; and
automatically configuring the unmanned aerial vehicle in one of a day mode configuration or the night mode configuration based on the intensity of light,
wherein the unmanned aerial vehicle is automatically configured in the day mode configuration based on the intensity of light meeting a threshold, and wherein the unmanned aerial vehicle is automatically configured in the night mode configuration based on the intensity of light not meeting the threshold.

3. The method of claim 2 , wherein the onboard camera includes a first onboard camera used while the unmanned aerial vehicle is in the night mode configuration and a second onboard camera while the unmanned aerial vehicle is in the day mode configuration.

4. The method of claim 2 , wherein the unmanned aerial vehicle is configured to switch between the night mode configuration and the day mode configuration based on a change in an amount of light within the environment in which the unmanned aerial vehicle is operating or based on the unmanned aerial vehicle navigating to a new environment.

5. The method of claim 1 , wherein the filtered image data includes infrared data and detecting the object within the environment in which the unmanned aerial vehicle is operating based on the filtered image data comprises:
performing depth estimation in the infrared domain to determine a relative position of the unmanned aerial vehicle with respect to the object.

6. The method of claim 1 , wherein the unmanned aerial vehicle includes one or more protrusions coupled to one or more arms of the unmanned aerial vehicle, wherein the one or more protrusions are configured to reduce an amount of glare caused by the infrared light emitted by the onboard light source from reaching an image sensor of the onboard camera.

7. The method of claim 2 , wherein the onboard light source is selectively disabled while the unmanned aerial vehicle is in the day mode configuration.

8. An unmanned aerial vehicle, comprising:
an onboard light source configured to emit infrared light while the unmanned aerial vehicle is in a night mode configuration;
an onboard camera configured to collect image data including infrared data while the onboard light source emits the infrared light; and
one or more processors configured to run onboard software for processing the image data to determine a flight operation for the unmanned aerial vehicle to avoid an object collision, wherein processing the image data includes filtering the image data using infrared filtering software to reduce pink tones within the image data.

9. The unmanned aerial vehicle of claim 8 , wherein the onboard software run by the one or more processors determines whether to configure the unmanned aerial vehicle is in a day mode configuration or the night mode configuration based on an amount of light within an environment in which the unmanned aerial vehicle is operating.

10. The unmanned aerial vehicle of claim 9 , wherein the onboard camera includes a first onboard camera used while the unmanned aerial vehicle is in the night mode configuration and a second onboard camera used while the unmanned aerial vehicle is in the day mode configuration.

11. The unmanned aerial vehicle of claim 9 , wherein the onboard light source is disabled while the unmanned aerial vehicle is in the day mode configuration.

12. The unmanned aerial vehicle of claim 8 , comprising:
one or more protrusions coupled to one or more arms of the unmanned aerial vehicle, wherein the one or more protrusions are configured to reduce an amount of glare caused by the infrared light emitted by the onboard light source from reaching an image sensor of the onboard camera.

13. The unmanned aerial vehicle of claim 12 , wherein the one or more protrusions partially surround the onboard camera.

14. An apparatus, comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
determine whether to configure an unmanned aerial vehicle in a day mode configuration or a night mode configuration;
responsive to a determination to configure the unmanned aerial vehicle in the day mode configuration:
capture first image data using infrared filtering software including filtering the first image data to reduce pink tones within the first image data;
determine a first flight operation for the unmanned aerial vehicle to avoid collision with a first object detected within an environment in which the unmanned aerial vehicle is operating based on the filtered first image data; and
cause the unmanned aerial vehicle to perform the first flight operation; and

responsive to a determination to configure the unmanned aerial vehicle in the night mode configuration:
capture second image data including infrared data;
determine a second flight operation for the unmanned aerial vehicle to avoid collision with a second object detected within an environment in which the unmanned aerial vehicle is operating based on the second image data; and
cause the unmanned aerial vehicle to perform the second flight operation.

15. The apparatus of claim 14 , wherein the determination as to whether to configure the unmanned aerial vehicle in the day mode configuration or the night mode configuration is based on an amount of light within the environment in which the unmanned aerial vehicle is operating.

16. The apparatus of claim 15 , wherein, to determine whether to configure the unmanned aerial vehicle in the day mode configuration or the night mode configuration, the instructions, when executed by the one or more processors, cause the one or more processors to:
determine whether the amount of light within the environment in which the unmanned aerial vehicle is operating is sufficient for vision-based navigation based on one or more of a threshold defined for one or more cameras of the unmanned aerial vehicle, an exposure setting of the one or more cameras, or a measurement of light captured using an onboard sensor of the unmanned aerial vehicle.

17. The apparatus of claim 15 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
detect the second object based on the second image data; and
perform depth estimation in the infrared domain to determine a relative position of the unmanned aerial vehicle with respect to the second object.

18. The apparatus of claim 14 , wherein the unmanned aerial vehicle includes one or more protrusions coupled to one or more arms of the unmanned aerial vehicle, wherein the one or more protrusions are configured to reduce an amount of glare caused by an infrared light emitted by an onboard light source of the unmanned aerial veh

Assignees

• Skydio Inc

Inventors

• Bachrach Abraham Galton
• Bry Adam Parker
• Cross Gareth Benoit
• Henry Peter Benjamin
• Holtz Kristen Marie
• Kennedy Ryan David
• Martirosyan Hayk
• Nekrasov Vladimir
• Wang Samuel Shenghung

Classifications

• G05D1/2247

  providing the operator with simple or augmented images from one or more cameras · CPC title

• B64U2101/30

  for imaging, photography or videography · CPC title

• B64U70/90

  Launching from or landing on platforms · CPC title

• B64U70/97

  Means for guiding the UAV to a specific location on the platform, e.g. platform structures preventing landing off-centre · CPC title

• B64U80/25

  for recharging batteries; for refuelling · CPC title