Targeting objects of interest in an agricultural environment

Patent metadata

Field	Value
Publication number	US-11517008-B1
Application number	US-202217840534-A
Country	US
Kind code	B1
Filing date	Jun 14, 2022
Priority date	Oct 20, 2021
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

A method includes receiving, by the treatment system, during operation in an agricultural environment, one or more images comprising one or more agricultural objects in the agricultural environment, identifying, in real-time, one or more objects of interest from the one or more agricultural objects by analyzing the one or more images, wherein the analyzing results in a first object being identified as belonging to one or more target objects and a second object being identified as not belonging to the one or more target objects, logging one or more results of the identification of each of the one or more objects of interest and a corresponding treatment decision; and activating the treatment mechanism to treat the one or more target objects.

First claim

What is claimed is:

1. A method performed by a treatment system on a moving platform, the treatment system having one or more processors, a storage, and a treatment mechanism, comprising:
receiving, by the treatment system, during operation in an agricultural environment, one or more images comprising one or more agricultural objects in the agricultural environment;
identifying, in real-time, one or more objects of interest from the one or more agricultural objects by analyzing the one or more images, wherein the analyzing results in a first object being identified as belonging to one or more target objects and a second object being identified as not belonging to the one or more target objects;
logging one or more results of the identification of each of the one or more objects of interest and a corresponding treatment decision; and
activating the treatment mechanism to treat the one or more target objects;
wherein the activating the treatment mechanism includes: directing an ejection from the treatment mechanism towards the first object at a predicted position of the first object where the ejection is expected to hit the first object;
wherein the predicted position of the first object is determined using an estimated optical flow of the first object.

2. The method of claim 1 , wherein the analyzing the one or more images comprises analyzing the one or more images using a machine learning (ML) algorithm that uses one or more ML models configured to identify the one or more agricultural objects.

3. The method of claim 1 , wherein the predicted position of the first object is determined by estimating a time difference between when an ejector mechanism of the treatment mechanism is activated and a time when a discharge from the ejector mechanism is expected to hit the first object.

4. The method of claim 1 , wherein the ejection is directed from the treatment mechanism towards the first object based on a pose of the treatment mechanism.

5. The method of claim 4 , wherein the pose is determined by determining a global pose using inputs from sensors rigidly connected to the moving platform configured to receive sensor readings of a world environment causing determination of a location and an orientation of the moving platform and a local pose from sensors configured to sense a local environment of the treatment system and to determine a localization and an orientation of the treatment system.

6. The method of claim 1 , wherein the activating the treatment mechanism includes emitting a laser towards the one or more target objects or emitting a fluid projectile towards the one or more target objects or configuring an end effector to physically interact with the one or more target objects.

7. The method of claim 1 , further comprising generating a treatment history of the one or more target objects treated by the treatment mechanism, including the first object.

8. The method of claim 1 , further comprising generating and mapping a first digital agricultural environment comprising one or more first digital assets representing the one or more agricultural objects in the agricultural environment, the generating and mapping at least partially based on the identified one or more objects of interest including the one or more target objects, the first object, the second object, or a combination thereof, the one or more results of the identification, the corresponding treatment decision of the one or more objects of interest identified, or a combination thereof.

9. The method of claim 8 , further comprising generating and mapping, based on a subsequent pass performed by the treatment system identifying the one or more agricultural objects or newly identified objects of interest in the agricultural environment, a second digital agricultural environment comprising one or more second digital assets representing the one or more agricultural objects, newly identified objects of interest, or a combination thereof.

10. The method of claim 9 , wherein the first digital agricultural environment and the second digital agricultural environment map a same agricultural environment and the second digital agricultural environment is an updated version of the first digital agricultural environment such that a plurality of the one or more second digital assets are mappable onto and digitally linked to the one or more first digital assets, each of the linked first and second digital assets representing a same agricultural object.

11. The method of claim 10 , wherein linking of the one or more second digital assets to the one or more first digital assets represent state changes of the identified one or more agricultural objects from a first pass performed by the treatment system to the subsequent pass performed by the treatment system.

12. The method of claim 9 , wherein the first digital agricultural environment and the second digital environment are accessible on a user interface.

13. The method of claim 12 , further including enabling a viewing of a state change of the one or more agricultural objects by displaying a change between the one or more first digital assets and the one or more second digital assets.

14. The method of claim 12 , further including enabling a viewing of a state change of the agricultural environment by displaying a change between the first digital agricultural environment and the second digital agricultural environment.

15. A treatment system on a moving platform, the treatment system comprising:
one or more processors,
a storage configured to store data or processor-executable code, and
a treatment mechanism under control of the one or more processors,
wherein the one or more processors is configured to:
receive, during operation in an agricultural environment, one or more images comprising one or more agricultural objects in the agricultural environment;
identify, in real-time, one or more objects of interest from the one or more agricultural objects by analyzing the one or more images, wherein the analyzing results in a first object being identified as belonging to one or more target objects and a second object being identified as not belonging to the one or more target objects;
log one or more results of the identification of each of the one or more objects of interest and a corresponding treatment decision; and
activate the treatment mechanism to treat the one or more target objects,
wherein the treatment mechanism is activated by directing an ejection from the treatment mechanism towards the first object at a predicted position of the first object where the ejection is expected to hit the first object;
wherein the predicted position of the first object is determined using an estimated optical flow of the first object.

16. The treatment system of claim 15 , wherein the analyzing the one or more images comprises analyzing the one or more images using a machine learning (ML) algorithm that uses one or more ML models configured to identify the one or more agricultural objects.

17. The treatment system of claim 15 , wherein the ejection is directed from the treatment mechanism towards the first object based on a pose of the treatment mechanism.

18. A treatment system on a moving platform, the treatment system comprising:
one or more processors,
a storage configured to store data or processor-executable code, and
a treatment mechanism under control of the one or more processors,
wherein the one or more processors is configured to:
receive, during operation in an agricultural environment, one or more images comprising one or more agricultural objects i

Assignees

• Verdant Robotics Inc

Inventors

• Sibley Gabriel Thurston
• Ibarria Lorenzo
• Garner Curtis Dale
• Leger Patrick Christopher

Classifications

• A01G7/06

  Treatment of growing trees or plants, e.g. for preventing decay of wood, for tingeing flowers or wood, for prolonging the life of plants · CPC title

• A01D91/00

  Methods for harvesting agricultural products · CPC title

• G05B15/02

  electric · CPC title

• A01M9/0092

  Regulating or controlling systems (the delivery being related to the movement of a vehicle B05B9/06) · CPC title

• A01B79/005

  Precision agriculture · CPC title