Implement management system for determining implement state

Patent metadata

Field	Value
Publication number	US-12026940-B2
Application number	US-202117349688-A
Country	US
Kind code	B2
Filing date	Jun 16, 2021
Priority date	Jun 16, 2021
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

An implement management system detects implement wear and monitors implement states to modify operating modes of a vehicle. The system can determine implement wear using the pull of the implement on the vehicle, the force and angle of which is represented by an orientation vector. The system may measure a current orientation vector and determine an expected orientation vector using sensors and a model (e.g., a machine learned model). Additionally, the implement management system can determine an implement state based on images of the soil and the implement captured by a camera onboard the vehicle during operation. The system may apply different models to the images to determine a likely state of the implement. The difference between the expected and current orientation vectors or the determined implement state may be used to determine whether and how the vehicle's operating mode should be modified.

First claim

What is claimed is:

1. A method comprising:
accessing information representative of a state of soil obtained via sensors of a vehicle pulling an implement through the soil;
selecting an implement state model indicating a ground engagement state of the implement from among a plurality of implement state models based on the accessed information, the plurality of implement state models respectively corresponding to various states of soil;
accessing a set of images captured by the vehicle, the set of images comprising images of the implement;
applying the selected implement state model to the set of images to determine the state of the implement; and
modifying an operating mode of the vehicle based on the determined state of the implement.

2. The method of claim 1 , wherein the implement comprises one or more of a shank, sweep, disk, blade, wheel, tine, or knife.

3. The method of claim 1 , wherein the state of soil comprises one or more of a soil type, a soil moisture measurement, or a soil compaction measurement.

4. The method of claim 1 , wherein the state of the implement is raised or ground-engaged.

5. The method of claim 1 , further comprising:
accessing implement state information obtained via height sensors of the vehicle;
determining a height of the implement based on the accessed implement state information; and
determining the state of the implement based on the determined height and an output of the selected implement state model.

6. The method of claim 5 , wherein the height sensors include one or more of potentiometers, altimeter, angle sensors, GPS, radar, or sonar.

7. The method of claim 5 , wherein determining the height of the implement comprises:
determining an expected elevation based on GPS and a predefined route of vehicle;
determining an empirical elevation of the implement using an altimeter; and
calculating a difference between the expected elevation and the empirical elevation to determine the height.

8. The method of claim 1 , further comprising determining the state of the implement using a collective decision based on the applied implement state model and one or more of hydraulic information, hitch information, sensor information, or perception information.

9. The method of claim 8 , wherein the collective decision is vote-based, the determined state of the implement receiving most votes.

10. The method of claim 1 , further comprising:
determining a location of the vehicle within a predefined route of the vehicle; and
in response to the determined location matching a predetermined location for checking the implement state, determining the state of the implement.

11. The method of claim 1 , wherein modifying the operating mode of the vehicle comprises, in response to a next vehicle maneuver requiring the state of the implement to be raised and the determined state of the implement is ground-engaged, pausing operation of the vehicle.

12. The method of claim 1 , wherein modifying the operating mode comprises, in response to a next vehicle maneuver requiring the state of the implement to be raised and the determined state of the implement is raised, authorizing the vehicle to perform the next vehicle maneuver.

13. The method of claim 12 , wherein the next vehicle maneuver is a tight turn.

14. The method of claim 1 , wherein modifying the operating mode comprises, in response to the operating mode requiring the state of the implement to be ground-engaged and the determined state of the implement is raised, instructing the vehicle to engage the implement with the soil.

15. The method of claim 1 , wherein the accessed information comprises images of the soil and wherein selecting the implement state model comprises:
applying a machine learning model to the images of the soil to determine a plasticity level of the soil based on images of the soil; and
selecting the implement state model based on the determined plasticity level of the soil.

16. The method of claim 15 , further comprising training the machine learning model on training images of soil, each training image labeled with an empirical plasticity level of the soil.

17. The method of claim 1 , wherein the sensor information comprises a torque measurement of the vehicle, wherein a plurality of torque measurements correspond to various states of soil.

18. A system comprising a hardware processor and a non-transitory computer-readable storage medium storing executable instructions that, when executed by the processor, are configured to cause the system to perform steps comprising:
accessing information representative of a state of soil obtained via sensors of a vehicle pulling an implement through the soil;
selecting an implement state model indicating a ground engagement state of the implement from among a plurality of implement state models based on the accessed information, the plurality of implement state models respectively corresponding to various states of soil;
accessing a set of images captured by the vehicle, the set of images comprising images of the implement;
applying the selected implement state model to the set of images to determine the state of the implement; and
modifying an operating mode of the vehicle based on the determined state of the implement.

19. A non-transitory computer readable storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
accessing information representative of a state of soil obtained via sensors of a vehicle pulling an implement through the soil;
selecting an implement state model indicating a ground engagement state of the implement from among a plurality of implement state models based on the accessed information, the plurality of implement state models respectively corresponding to various states of soil;
accessing a set of images captured by the vehicle, the set of images comprising images of the implement;
applying the selected implement state model to the set of images to determine the state of the implement; and
modifying an operating mode of the vehicle based on the determined state of the implement.

Assignees

• Deere & Co

Inventors

• Schleicher Tyler D
• Maeder Curtis A
• Anderson Noel W
• Runde Jeffrey E

Classifications

• G05D1/689

  Pointing payloads towards fixed or moving targets (positioning towed, pushed or suspended implements G05D1/672) · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• A01B79/005

  Precision agriculture · CPC title

• G06N20/00

  Machine learning · CPC title

• G05D1/0094

  involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target · CPC title