Targeting agricultural objects to apply units of treatment autonomously

Patent metadata

Field	Value
Publication number	US-11526997-B2
Application number	US-201916724263-A
Country	US
Kind code	B2
Filing date	Dec 21, 2019
Priority date	Dec 21, 2019
Publication date	Dec 13, 2022
Grant date	Dec 13, 2022

Abstract

Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include, at least, detecting an optical sight to align with an associated agricultural object, tracking the agricultural objects relative to the optical sight, predicting a parameter to track in association with agricultural object, and activating an emitter to apply an action based on the parameter.

First claim

What is claimed:

1. A method comprising:
receiving sensor data representing presence of agricultural objects disposed in an agricultural environment, comprising:
identifying subsets of pixels associated with a plurality of agricultural objects to track relative to one or more optical sights;

correlating a subset of agricultural objects to one or more actions to be performed in association with one or more emitters;
detecting a subset of optical sights in association with the subset of agricultural objects, each optical sight being predicted to align with an associated agricultural object,
tracking the subset of agricultural objects relative to the subset of optical sights;
predicting an agricultural object aligns with an optical sight to form a predicted emission parameter, the predicted emission parameter being tracked in association with agricultural object; and
activating an emitter to apply an action based on the predicted emission parameter.

2. The method of claim 1 , wherein receiving the sensor data representing presence of the agricultural objects comprises:
receiving reflective light from the agricultural object; and
capturing image data and a representing the agricultural object at an image capture device based on the reflective light.

3. The method of claim 2 , wherein capturing the image data comprises:
receiving the reflective light from the agricultural object during one or more time intervals during which the reflective light is visible.

4. The method of claim 3 , wherein the one or more emitters are disposed in between the image capture device and the agricultural object.

5. The method of claim 1 , wherein tracking the subset of agricultural objects relative to the subset of optical sights comprises:
tracking reflective light from the agricultural object in a field of view of an image.

6. The method of claim 1 , wherein tracking the subset of agricultural objects relative to the subset of optical sights comprises:
tracking reflective light from the agricultural object in association with a visible image portion.

7. The method of claim 1 , wherein tracking the subset of agricultural objects relative to the subset of optical sights comprises:
tracking a value of an elapsed time to alignment of the optical sight to the agricultural object.

8. The method of claim 7 , wherein predicting the agricultural object aligns with the optical sight comprises:
calculating a portion of the value of the elapsed time during which the agricultural object is associated with an occluded image field.

9. The method of claim 1 , wherein the predicted emission parameter is a predicted emission time.

10. The method of claim 9 , wherein activating the emitter to apply the action comprises:
triggering emission of an agricultural projectile at the predicted emission time.

11. The method of claim 1 , wherein tracking the subset of agricultural objects relative to the subset of optical sights comprises:
tracking the optical sight relative to the agricultural object as a function of a rate of displacement of the one or more emitters.

12. The method of claim 1 , further comprising:
determining the agricultural object aligns with tracking the optical sight; and
propelling an agricultural projectile to intercept at least a portion of the agricultural object.

13. The method of claim 1 , wherein predicting the agricultural object aligns with the optical sight comprises:
determining the agricultural object aligns with tracking the optical sight at the predicted emission parameter.

14. The method of claim 1 , wherein the optical sight is associated with one or more pixels of an image capture device.

15. The method of claim 1 , wherein activating the emitter to apply the action comprises:
detecting a pixel associated with the optical sight is aligned with an optical ray that extends from the pixel to at least a portion of the agricultural object.

16. The method of claim 1 , wherein receiving the sensor data representing presence of the agricultural objects comprises:
receiving image data representing a plurality of agricultural objects in an image frame at an image capture device.

17. A system comprising:
a memory including executable instructions; and
a processor, responsive to executing the instructions, is configured to:
receive sensor data representing presence of agricultural objects disposed in an agricultural environment;
correlate a subset of agricultural objects to one or more actions to be performed in association with one or more emitters;
detect a subset of optical sights in association with the subset of agricultural objects, each optical sight being predicted to align with an associated agricultural object, track the subset of agricultural objects relative to the subset of optical sights;
predict an agricultural object aligns with an optical sight to form a predicted emission parameter;
activate an emitter to apply an parameter; and
trigger emission of an agricultural projectile at a predicted emission time.

18. The system of claim 17 , wherein a subset of the instructions to receive the sensor data representing presence of the subset of agricultural objects causes the processor to:
receive reflective light from the agricultural object; and
capture image data representing the agricultural object at an image capture device based on the reflective light.

19. A method comprising:
receiving sensor data representing presence of agricultural objects disposed in an agricultural environment;
correlating a subset of agricultural objects to one or more actions to be performed in association with one or more emitters;
detecting a subset of optical sights in association with the subset of agricultural objects, each optical sight being predicted to align with an associated agricultural object,
tracking the subset of agricultural objects relative to the subset of optical sights comprising:
tracking a value of an elapsed time to alignment of the optical sight to the agricultural object; and
calculating a portion of the value of the elapsed time during which the agricultural object is associated with an occluded image field;

predicting an agricultural object aligns with an optical sight to form a predicted emission parameter, the predicted emission parameter being tracked in association with agricultural object; and
activating an emitter to apply an action based on the predicted emission parameter.

20. The method of claim 19 , wherein the predicted emission parameter is a predicted emission time.

21. The method of claim 19 , wherein tracking the subset of agricultural objects relative to the subset of optical sights comprises:
tracking the optical sight relative to the agricultural object as a function of a rate of displacement of the one or more emitters.

22. The method of claim 19 , wherein receiving the sensor data representing presence of the agricultural objects comprises:
identifying subsets of pixels associated with a plurality of agricultural objects to track relative to one or more optical sights.

23. A method comprising:
receiving sensor data representing presence of agricultural objects disposed in an agricultural environment;
correlating a subset of agricultural objects to one or more actions to be performed in association with one or more emitters;
detecting a subset of optical sights in association with the subset of agricultural objects, each optical sight being predicted to align with an

Assignees

• Verdant Robotics Inc

Inventors

• Sibley Gabriel Thurston
• Garner Curtis Dale
• Michelin Andre Robert Daniel
• Ibarria Lorenzo
• Leger Patrick Christopher
• Rewis Benjamin
• Yan Shi

Classifications

• A01M1/20 Primary

  Poisoning, narcotising, or burning insects {(fumigation apparatus A01M13/00)} · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• G06T2207/30188

  Vegetation; Agriculture · CPC title

• G06T7/246 Primary

  using feature-based methods, e.g. the tracking of corners or segments · CPC title