Detection and precision application of treatment to target objects

Patent metadata

Field	Value
Publication number	US-12137681-B2
Application number	US-202217809253-A
Country	US
Kind code	B2
Filing date	Jun 27, 2022
Priority date	Oct 20, 2021
Publication date	Nov 12, 2024
Grant date	Nov 12, 2024

Abstract

A method performed by a treatment system disposed on a moving platform, the treatment system having one or more processors, a storage and a treatment mechanism, comprising: receiving one or more images of an environment in which the moving platform is operating; identifying, in real-time, a pose of the moving platform using sensor inputs; identifying one or more target objects by processing the one or more images using a machine learning (ML) algorithm; and controlling the treatment mechanism to treat the one or more target objects by orienting the treatment mechanism towards the one or more target objects at least partially based on the pose.

First claim

What is claimed is:

1. A method performed by a treatment system disposed on a moving platform, the treatment system having one or more processors, a storage and a treatment mechanism, comprising:
receiving images of an environment in which the moving platform is operating;
identifying, in real-time, a pose of the moving platform using sensor inputs, wherein the pose is used to estimate a distance traveled by the moving platform between consecutive images;
identifying one or more target objects by only processing non-overlapping portions of the consecutive images using a machine learning (ML) algorithm; and
controlling the treatment mechanism to treat the one or more target objects by orienting the treatment mechanism towards the one or more target objects at least partially based on the pose.

2. The method of claim 1 , wherein the pose is determined by analyzing 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.

3. The method of claim 2 , wherein the sensors include sensors that detect an (x, y, z) orientation.

4. The method of claim 1 , wherein the pose is determined by analyzing inputs from sensors configured to sense a local environment of the treatment system and to determine a localization and an orientation of the treatment system.

5. The method of claim 1 , wherein the controlling the treatment mechanism includes emitting a laser towards the one or more target objects.

6. The method of claim 1 , wherein the controlling the treatment mechanism includes emitting a fluid projectile towards the one or more target objects.

7. The method of claim 1 , wherein the controlling the treatment mechanism includes configuring an end effector to physically interact with the one or more target objects.

8. The method of claim 1 , wherein the treatment mechanism comprises multiple treatment modules, each treatment modules configured to determine a local pose thereof; and wherein the controlling the treatment mechanism includes:
controlling the treatment mechanism to treat the one or more target objects by orienting each of the multiple treatment modules using the pose and a corresponding local pose.

9. A treatment system disposed on a moving platform, comprising:
one or more processors; and
a treatment mechanism,
wherein the one or more processors are configured to implement a method comprising:
receiving one or more images of an environment in which the moving platform is operating;
identifying, in real-time, a pose of the moving platform using sensor inputs, wherein the pose is used to estimate a distance traveled by the moving platform between consecutive images;
identifying one or more target objects by only processing non-overlapping portions of the consecutive images using a machine learning (ML) algorithm; and
controlling the treatment mechanism to treat the one or more target objects by orienting the treatment mechanism towards the one or more target objects at least partially based on the pose.

10. The treatment system of claim 9 , wherein the pose is determined by analyzing 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.

11. The treatment system of claim 10 , wherein the sensors include sensors that detect an (x, y, z) orientation.

12. The treatment system of claim 9 , wherein the pose is determined by analyzing inputs from sensors configured to sense a local environment of the treatment system and to determine a localization and an orientation of the treatment system.

13. The treatment system of claim 9 , wherein the controlling the treatment mechanism includes emitting a laser towards the one or more target objects.

14. The treatment system of claim 9 , wherein the controlling the treatment mechanism includes emitting a fluid projectile towards the one or more target objects.

15. The treatment system of claim 9 , wherein the controlling the treatment mechanism includes configuring an end effector to physically interact with the one or more target objects.

16. The treatment system of claim 15 , wherein the treatment mechanism comprises multiple treatment modules, each treatment modules configured to determine a local pose thereof; and wherein the controlling the treatment mechanism includes:
controlling the treatment mechanism to treat the one or more target objects by orienting each of the multiple treatment modules using the pose and a corresponding local pose.

17. A computer readable medium having processor-executable code stored thereupon, the code, upon execution by a processor of a treatment system disposed on a moving platform, causing the processor to implement a method, comprising:
receiving one or more images of an environment in which the moving platform is operating;
identifying, in real-time, a pose of the moving platform using sensor inputs, wherein the pose is used to estimate a distance traveled by the moving platform between consecutive images;
identifying one or more target objects by only processing non-overlapping portions of the using a machine learning (ML) algorithm; and
controlling a treatment mechanism to treat the one or more target objects by orienting the treatment mechanism towards the one or more target objects at least partially based on the pose.

18. The computer readable medium of claim 17 , wherein the pose is determined by analyzing 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.

19. The computer readable medium of claim 18 , wherein the sensors include sensors that detect an (x, y, z) orientation.

20. The computer readable medium of claim 17 , wherein the pose is determined by analyzing inputs from sensors configured to sense a local environment of the treatment system and to determine a localization and an orientation of the treatment system.

Assignees

• Verdant Robotics Inc

Inventors

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

Classifications

• G05B15/02

  electric · CPC title

• 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

• A01B79/005

  Precision agriculture · CPC title

• A01C21/007

  Determining fertilization requirements · CPC title