Agricultural system control based on progressive time horizon model output
A predictive engine obtains as inputs a set of optimization criteria and a time horizon selection input and applies those inputs to a time horizon model in a variable time horizon prediction engine. A user interface is generated that provides actuatable elements that can be actuated in order to access different time horizon models in the variable time horizon prediction engine. Operational parameters can be adjusted so that the variable time horizon prediction engine provides an output indicative of a control signal that can be used to improve operation of the agricultural system over the selected time horizon.
1 . An agricultural operation control system, comprising:
one or more processors; and
memory storing computer executable instructions which, when executed by the one or more processors, configure the one or more processors to:
obtain an input and model an operation performance of an agricultural system across a plurality of different time horizons;
generate, based on the input, a first predictive output indicative of a first predicted operation performance over a first time horizon of the plurality of different time horizons, wherein the first time horizon corresponds to performance of a first set of one or more operations by a first mobile agricultural machine;
generate, based, at least, on the first predictive output, a second predictive output of a second predicted operation performance over a second time horizon of the plurality of different time horizons, wherein the second time horizon corresponds to performance of a second set of one or more operations by a second mobile agricultural machine that is different than the first mobile agricultural machine, the second set of one or more operations different than the first set of one or more operations and including at least one operation that is performed after the first set of one or more operations are performed, wherein the second predictive output of the second predicted operation performance over the second time horizon represents performance characteristics of the second mobile agricultural machine and is generated based on the model before control of the first mobile agricultural machine based on the first predictive output; and
control, based on the second predictive output, a controllable subsystem of the first mobile agricultural machine to controllably actuate at least one component of the controllable subsystem.
2 . The agricultural operation control system of claim 1 , wherein the input comprises a set of optimization criteria, and wherein the computer executable instructions, when executed by the one or more processors, further configure the one or more processors to:
access a data store and obtain the set of optimization criteria from operator preference data in the data store.
3 . The agricultural operation control system of claim 2 , wherein the optimization criteria is obtained as an operator input through an interface subsystem.
4 . The agricultural operation control system of claim 2 , wherein the computer executable instructions, when executed by the one or more processors, further configure the one or more processors to:
receive indication of a selected time horizon of the plurality of different time horizons, wherein the input comprises a parameter value for a time horizon-specific parameter specific to the selected time horizon; and
generate the first predictive output based on the parameter value for the time horizon-specific parameter.
5 . The agricultural operation control system of claim 4 , wherein the computer executable instructions, when executed by the one or more processors, further configure the one or more processors to:
generate a display, the display showing:
the time horizon-specific parameter specific to the selected time horizon and a parameter value actuator that can be actuated to modify the parameter value for the time horizon-specific parameter; and
the selected time horizon and a time horizon actuator that is actuatable to select a different one of the plurality of different time horizons.
6 . The agricultural operation control system of claim 1 , wherein the controllable subsystem comprises at least one of:
a propulsion subsystem,
a steering subsystem, or
a material handling subsystem.
7 . The agricultural operation control system of claim 1 , and further comprising:
a plurality of different predictive time horizon performance models, each different predictive time horizon performance model, of the plurality of different predictive time horizon performance models, modeling operation performance across a different time horizon of the plurality of different time horizons.
8 . The agricultural operation control system of claim 7 , wherein the plurality of different predictive time horizon performance models comprises at least one of:
a current operation model configured to model operation performance of an agricultural machine across a current operation time horizon of the plurality of different time horizons, or
a current season model configured to model operation performance of the agricultural system across a current season time horizon of the plurality of different time horizons.
9 . The agricultural operation control system of claim 7 , wherein the plurality of different predictive time horizon performance models comprises:
a future season model configured to model operation performance of the agricultural system across a future season time horizon of the plurality of different time horizons.
10 . The agricultural operation control system of claim 1 , wherein the first mobile agricultural machine comprises a first agricultural machine type and the second mobile agricultural machine comprises a second agricultural machine type different than the first agricultural machine type.
11 . The agricultural operation control system of claim 1 , wherein the instructions, when executed by the one or more processors, configure the one or more processors to control the controllable subsystem based on the first predictive output.
12 . A computer implemented method comprising:
obtaining an input and model an operation performance of an agricultural system across a plurality of different time horizons;
generating, based on the input, a first predictive output indicative of a first predicted operation performance over a first time horizon of the plurality of different time horizons, wherein the first time horizon corresponds to performance of a first set of one or more operations by a first mobile agricultural machine;
generating, based, at least, on the first predictive output, a second predictive output of a second predicted operation performance over a second time horizon of the plurality of different time horizons, wherein the second time horizon corresponds to performance of a second set of one or more operations by a second mobile agricultural machine that is different than the first mobile agricultural machine, the second set of one or more operations different than the first set of one or more operations and including at least one operation that is performed after the first set of one or more operations are performed, wherein the second predictive output of the second predicted operation performance over the second time horizon represents performance characteristics of the second mobile agricultural machine and is generated based on the model before control of the first mobile agricultural machine based on the first predictive output; and
controlling, based on the second predictive output, a controllable subsystem of the first mobile agricultural machine to controllably actuate at least one component of the controllable subsystem.
13 . The computer implemented method of claim 12 , and further comprising:
obtaining a time horizon-specific parameter value for a time horizon-specific parameter based on the first time horizon;
identifying a time horizon model corresponding to the first time horizon, the time horizon model being identified from a plurality of different time horizon models each modeling operation performance across a different time horizon;
identifying a plurality of potential adjustments to the time horizon-specific parameter value;
generating a plurality of predictive operation outputs with the time horizon model based on the plurality of potential adjustments, each respective predictive operation output, of the plurality of predictive operation outputs, representing predicted operation performance with a respective potential adjustment of the plurality of potential adjustments;
generating a display that represents the plurality of predicted operation outputs and identifies the plurality of potential adjustments; and
identifying a selected predictive operation output of the plurality of predicted operation outputs.
14 . The computer implemented method of claim 12 , and further comprising:
receiving indication of a selected time horizon of the plurality of different time horizons, wherein the input comprises a parameter value for a time horizon-specific parameter specific to the selected time horizon; and
generating the first predictive output based on the parameter value for the time horizon-specific parameter.
15 . The computer implemented method of claim 14 , and further comprising:
generating a display showing:
the time horizon-specific parameter specific to the selected time horizon and a parameter value actuator that can be actuated to modify the parameter value for the time horizon-specific parameter; and
the selected time horizon and a time horizon actuator that is actuatable to select a different one of the plurality of different time horizons.
16 . The computer implemented method of claim 12 , wherein the controllable subsystem comprises at least one of:
a propulsion subsystem,
a steering subsystem, or
a material handling subsystem.
17 . The computer implemented method of claim 12 , and further comprising accessing a plurality of different predictive time horizon performance models, each different predictive time horizon performance model, of the plurality of different predictive time horizon performance models, modeling operation performance across a different time horizon of the plurality of different time horizons.
18 . The computer implemented method of claim 17 , wherein the plurality of different predictive time horizon performance models comprises at least one of:
a current operation model configured to model operation performance of an agricultural machine across a current operation time horizon of the plurality of different time horizons,
a current season model configured to model operation performance of the agricultural system across a current season time horizon of the plurality of different time horizons, or
a future season model configured to model operation performance of the agricultural system across a future season time horizon of the plurality of different time horizons.