# US 11,079,725 B2 · 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 11,079,725 B2 - Document ID: US11079725B2 - Status: Granted - Kind: B2 - Application number: 16/380,531 - Filed: 2019-04-10 - Published: 2020-10-15 - Granted: 2021-08-03 - Earliest claimed: 2019-04-10 - Assignees: Deere & Company - Applicants: Deere & Company - Inventors: Bhanu Kiran Reddy Palla; Nathan R. Vandike; Federico Pardina-Malbran; Michael A. Waldo; Noel W. Anderson - Web page: https://patentgrep.com/patent/US11079725B2 ## CPC - G05B 13/048: {using a predictor} - A01D 41/127: Control or measuring arrangements specially adapted for combines - A01D 41/1271: {for measuring crop flow} - A01D 41/141: {Automatic header control} - G05B 13/041: {in which a variable is automatically adjusted to optimise the performance} - 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) - A01D: HARVESTING; MOWING ## Abstract A priori geo-referenced 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 geo-referenced 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 method of controlling a machine on a worksite to perform an operation, comprising: identifying geo-referenced vegetative index data for the worksite that was generated prior to the machine performing the operation at the worksite; collecting field data, with a sensor on the machine, as the machine is performing an operation at the worksite, the field data corresponding to a portion of the worksite; generating a predictive model based on the geo-referenced vegetative index data and the field data; calculating an error value indicative of model error based on a comparison of model values from the generated predictive model to field values in the collected field data; calculating a model quality metric, for the predictive model, indicative of model accuracy, based on the error value; determining, while the machine is performing the operation at the worksite, whether the predictive model is a qualified predictive model based on the calculated model quality metric and if so, controlling a subsystem of the machine, using the qualified predictive model, to perform the operation. ### Claim 2 (depends on 1) The method of claim 1 wherein determining whether the predictive model is a qualified predictive model comprises: determining whether the model quality metric meets a model quality threshold. ### Claim 3 (depends on 1) The method of claim 1 further comprising: if the predictive model is determined not to be a qualified predictive model, then identifying, different geo-referenced vegetative index data for generating a different predictive model; generating the different predictive model; determining, while the machine is performing the operation at the worksite, whether the different predictive model is a qualified model; and if so, controlling a subsystem of the machine, using the different predictive model to perform the operation. ### Claim 4 (depends on 1) The method of claim 1 wherein identifying geo-referenced vegetative index data comprises: obtaining a priori georeferenced vegetative index data, from a remote system, corresponding to the worksite. ### Claim 5 (depends on 1) The method of claim 1 wherein collecting field data comprises: obtaining crop yield data corresponding to a portion of the worksite, with a crop yield sensor on the machine, as the machine is performing a harvesting operation at the worksite. ### Claim 6 (depends on 1) The method of claim 1 wherein the machine has a plurality of different subsystems and wherein controlling a subsystem comprises: controlling the plurality of different subsystems on the machine. ### Claim 7 (depends on 6) The method of claim 6 wherein generating a predictive model comprises: generating a plurality of different predictive models, based on a priori data and the field data, for the different subsystems of the work machine. ### Claim 8 (depends on 7) The method of claim 7 wherein calculating a model quality metric comprises: calculating a plurality of different model quality metrics values for the different predictive models, wherein determining whether the predictive model is a qualified predictive model comprises determining whether each of the plurality of predictive models are qualified predictive models based on the calculated model quality metrics values. ### Claim 9 (depends on 8) The method of claim 8 further comprising: if the plurality of different predictive models are qualified predictive models, then controlling each of the different subsystems of the work machine on the worksite, using a different one of the plurality of different predictive models. ### Claim 10 (depends on 1) The method of claim 1 and further comprising: iteratively repeating steps of collecting field data, updating the predictive model based on the field data, calculating a model quality metric for the updated predictive model and determining whether the predictive model is a qualified predicative model, while the machine is performing the operation. ### Claim 11 A computing system on a work machine, comprising: a communication system configured to identify a priori, geo-referenced vegetative index data for a worksite; an in situ data collection system that collects field data, with a sensor on a machine, as the work machine is performing an operation at the worksite, the field data corresponding to a portion of the worksite; a model generator system configured to receive the a priori, geo-referenced vegetative index data and field data and generate a predictive model based on the a priori gco-referenced vegetative index data and the field data, as the work machine is performing the operation at the worksite, using a model generation mechanism the predictive model including predictive values of a characteristic of the worksite; and a control system that, controls a subsystem of the machine using the, predictive model. ### Claim 12 (depends on 11) The computing system of claim 11, and further comprising: a model evaluation system configured to calculate a model quality metric for the predictive model and determine whether the predictive model is a qualified predictive model; and wherein the control system controls the subsystem using the predictive model if the predictive model is a qualified predictive model. ### Claim 13 (depends on 12) The computing system of claim 12 wherein the model evaluation system comprises: model quality metric generator configured to calculate the:model quality metric for the predictive model. ### Claim 14 (depends on 13) The computing system of claim 13 wherein the model evaluation system coin prises: evaluation trigger logic configured to detect an evaluation trigger and, in response, generate a trigger output for the model evaluation system to evaluate an alternative predictive model. ### Claim 15 (depends on 14) The computer system of claim 14 wherein the model generation system is configured to, in response to the trigger output, generate the alternative predictive model using, alternative a priori vegetative index data for the worksites. ### Claim 16 (depends on 14) The computer system of claim 14 wherein the model generation system is configured to, in response to the trigger output, generate the alternative predictive model using an alternative model generation mechanism. ### Claim 17 (depends on 16) The computing system of claim 16 wherein the model generator system is configured to generate a plurality of predictive models each corresponding to a specific controllable subsystem, and wherein the control system uses each of the predictive models to control the corresponding specific controllable subsystem. ### Claim 18 (depends on 11) The computing system of claim 11 wherein the a priori, geo-referenced vegetative index data is generated prior to the work machine performing the operation at the worksite and during a growing season corresponding to the operation performed by the work machine at the worksite. ### Claim 19 A work machine, comprising: a communication system configured to receive geo-referenced vegetative index data for worksite; an in situ data collection system configured to collect field data, with a sensor on the work machine, as the work machine is performing an operation at the worksite, for a portion of the worksite; a plurality of controllable subsystems; a model generator system configured to generate a plurality of different predictive models, based on the geo-referenced vegetative index data and the field data, each corresponding to a different controllable subsystem of the plurality of controllable subsystems of the work machine, the plurality of different predictive models including predictive values of an at least one characteristic of the worksite to be encountered by the work machine; and a control system that generates control signals to control each of the controllable subsystems using a corresponding predictive model. ### Claim 20 (depends on 19) The work machine of claim 19 wherein die controllable subsystems comprise controllable harvester subsystems, and further comprising: a model evaluation, system configured to calculate a model quality metric for each of the predictive models and determine whether each of the predictive models is a qualified predictive model based on the model quality metrics, wherein the control system generates the control signals to control each of the controllable subsystems using a corresponding qualified predictive model.