# US 2026/0083055 A1 · Machine control using real-time model

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0083055 A1
- Document ID: US20260083055A1
- Status: Published application
- Kind: A1
- Application number: 19/406,423
- Filed: 2025-12-02
- Published: 2026-03-26
- Earliest claimed: 2019-04-10
- Assignees: Deere & Company
- Applicants: Deere & Company
- Inventors: Noel W. ANDERSON; Nathan R. Vandike; Federico Pardina-Malbran; Bhanu Kiran Reddy Palla
- Web page: https://patentgrep.com/patent/US20260083055A1

## CPC

- A01D 41/127: Control or measuring arrangements specially adapted for combines
- A01B 79/005: {Precision agriculture}
- A01D 43/085: {Control or measuring arrangements specially adapted therefor}
- G05B 13/048: {using a predictor}
- H04W 4/021: Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
- H04W 4/38: for collecting sensor information
- H04W 4/40: for vehicles, e.g. vehicle-to-pedestrians [V2P]
- A01D: HARVESTING; MOWING
- A01B: SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting or manuring A01C5/00; mowers convertible to soil working apparatus or capable of soil working A01D42/04; mowers combined with soil working implements A01D43/12; soil working for engineering purposes E01, E02, E21)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A priori georeferenced vegetative index data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the georeferenced vegetative index data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.

## Claims

### Claim 1

A computer implemented method of controlling a machine during an operation at a worksite, the computer implemented method comprising:
obtaining, from a first source, first data corresponding to the worksite;
obtaining, from a second source, second data corresponding to the worksite;
generating first predictive data corresponding to at least a portion of the worksite that is predictive of a characteristic at the worksite based on the first data, the first predictive data including a first set of predictive values of the characteristic;
generating second predictive data corresponding to at least the portion of the worksite that is predictive of the characteristic at the worksite based on the second data, the second predictive data including a second set of predictive values of the characteristic;
calculating a first quality metric, for the first predictive data, indicative of an accuracy of the first predictive data, wherein calculating the first quality metric comprises calculating a first error value indicative of error of the first predictive data based, at least in part, on a comparison of a predictive value of the first set of predictive values of the characteristic to a value of the characteristic detected during the operation and calculating the first quality metric based, at least in part, on the first error value;
calculating a second quality metric, for the second predictive data, indicative of an accuracy of the second predictive data, wherein calculating the second quality metric comprises calculating a second error value indicative of error of the second predictive data based, at least in part, on a comparison of a predictive value of the second set of predictive values of the characteristic to the value of the characteristic detected during the operation or to an additional value of the characteristic detected during the operation and calculating the second quality metric based, at least in part, on the second error value;
selecting one of the first predictive data and the second predictive data as a selected predictive data based on the first quality metric and the second quality metric; and
controlling the machine during the operation based on the selected predictive data.

### Claim 2 (depends on 1)

The computer implemented method of claim 1, wherein the first predictive data comprises a map of the worksite that maps the first set of predictive values to the worksite.

### Claim 3 (depends on 1)

The computer implemented method of claim 1, wherein the second predictive data comprises a map of the worksite that maps the second set of predictive values to the worksite.

### Claim 4 (depends on 1)

The computer implemented method of claim 1, wherein the first source comprises a sensor on the machine.

### Claim 5 (depends on 1)

The computer implemented method of claim 1, wherein the second source comprises a sensor on the machine.

### Claim 6 (depends on 1)

The computer implemented method of claim 1, wherein first source comprises georeferenced data generated prior to the operation.

### Claim 7 (depends on 1)

The computer implemented method of claim 1, wherein the second source comprises georeferenced data generated prior to the operation.

### Claim 8 (depends on 1)

The computer implemented method of claim 1, wherein selecting one of the first predictive data and the second predictive data as the selected predictive data based on the first quality metric and the second quality metric comprises:
comparing the first quality metric to the second quality metric; and
selecting the one of the first predictive data and the second predictive data as the selected predictive data based on the comparison of the first quality metric to the second quality metric.

### Claim 9 (depends on 1)

The computer implemented method of claim 1, wherein selecting one of the first predictive data and the second predictive data as the selected predictive data based on the first quality metric and the second quality metric comprises:
comparing the first quality metric and the second quality metric to a quality threshold; and
selecting the one of the first predictive data and the second predictive data as the selected predictive data based on the comparison of the first quality metric and the second quality metric to the quality threshold.

### Claim 10

A system for controlling a machine during an operation at a worksite, the system comprising:
one or more processors; and
memory storing instructions executable by the one or more processors that, when executed by the one or more processors, configure the one or more processors to:
obtain, from a first source, first data corresponding to the worksite;
obtain, from a second source, second data corresponding to the worksite;
generate first predictive data corresponding to at least a portion of the worksite that is predictive of a characteristic at the worksite based on the first data, the first predictive data including a first set of predictive values of the characteristic;
generate second predictive data corresponding to at least a portion of the worksite that is predictive of the characteristic at the worksite based on the second data, the second predictive data including a second set of predictive values of the characteristic;
calculate a first quality metric, for the first predictive data, indicative of an accuracy of the first predictive data, wherein calculating the first quality metric comprises calculating a first error value indicative of error of the first predictive data based, at least in part, on a comparison of a predictive value of the first set of predictive values of the characteristic to a value of the characteristic detected during the operation and calculating the first quality metric based, at least in part, on the first error value;
calculate a second quality metric, for the second predictive data, indicative of an accuracy of the second predictive data, wherein calculating the second quality metric comprises calculating a second error value indicative of error of the second predictive data based, at least in part, on a comparison of a predictive value of the second set of predictive values of the characteristic to the value of the characteristic detected during the operation or to an additional value of the characteristic detected during the operation and calculating the second quality metric based, at least in part, on the second error value;
select one of the first predictive data and the second predictive data as a selected predictive data based on the first quality metric and the second quality metric; and
control the machine during the operation based on the selected predictive data.

### Claim 11 (depends on 10)

The system of claim 10, wherein the first predictive data comprises a map of the worksite that maps the first set of predictive values to the worksite.

### Claim 12 (depends on 10)

The system of claim 10, wherein the second predictive data comprises a map of the worksite that maps the second set of predictive values to the worksite.

### Claim 13 (depends on 10)

The system of claim 10, wherein the first source comprises a sensor on the machine.

### Claim 14 (depends on 10)

The system of claim 10, wherein the second source comprises a sensor on the machine.

### Claim 15 (depends on 10)

The system of claim 10, wherein first source comprises georeferenced data generated prior to the operation.

### Claim 16 (depends on 10)

The system of claim 10, wherein the second source comprises georeferenced data generated prior to the operation.

### Claim 17 (depends on 10)

The system of claim 10, wherein the first predictive data comprises a predictive model.

### Claim 18 (depends on 10)

The system of claim 10, wherein the second predictive data comprises a predictive model.

### Claim 19

A computer implemented method of controlling a machine during an operation at a worksite, the computer implemented method comprising:
obtaining, from a first source, first data corresponding to the worksite;
obtaining, from a second source, second data corresponding to the worksite;
generating first predictive data corresponding to at least a portion of the worksite that is predictive of a first characteristic at the worksite based on the first data, the first predictive data including a first set of predictive values of the first characteristic;
generating second predictive data corresponding to at least the portion of the worksite that is predictive of a second characteristic at the worksite based on the second data, the second predictive data including a second set of predictive values of the second characteristic;
calculating a first quality metric, for the first predictive data, indicative of an accuracy of the first predictive data, wherein calculating the first quality metric comprises calculating a first error value indicative of error of the first predictive data based, at least in part, on a comparison of a predictive value of the first set of predictive values of the first characteristic to a value of the first characteristic detected during the operation and calculating the first quality metric based, at least in part, on the first error value;
calculating a second quality metric, for the second predictive data, indicative of an accuracy of the second predictive data, wherein calculating the second quality metric comprises calculating a second error value indicative of error of the second predictive data based, at least in part, on a comparison of a predictive value of the second set of predictive values of the second characteristic to a value of the second characteristic detected during the operation and calculating the second quality metric based, at least in part, on the second error value;
selecting at least one of the first predictive data and the second predictive data based on the first quality metric and the second quality metric; and
controlling the machine during the operation based on the selected at least one of the first predictive data and the second predictive data.

### Claim 20 (depends on 19)

The computer implemented method of claim 19, wherein selecting the at least one of the first predictive data and the second predictive data based on the first quality metric and the second quality metric comprises selecting both the first predictive data and the second predictive data based on the first quality metric and the second quality metric; and
wherein controlling the machine comprises controlling a first component of the machine based on the first predictive data and controlling a second component of the machine based on the second predictive data.
