Predictive map generation and control system
One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.
1. An agricultural work machine, comprising:
a controllable subsystem;
an operator input sensor configured to sense an input value of a header control setting corresponding to a first geographic location in a field;
a control system comprising a header controller configured to:
receive, as a control input, the input value of the header control setting; and
control, based on the control input, a header of the agricultural work machine at an area of the field corresponding to the first geographic location;
a communication system configured to receive an agricultural characteristic map that includes values of an agricultural characteristic mapped to different geographic locations in the field;
a predictive model generator configured to:
obtain a first value of the agricultural characteristic mapped to the first geographic location in the agricultural characteristic map; and
generate a predictive agricultural model that models a relationship between the agricultural characteristic and the header control setting based on:
the first value of the agricultural characteristic mapped to the first geographic location, and
the input value of the header control setting corresponding to the first geographic location; and
a predictive map generator configured to generate, using the predictive agricultural model, a functional predictive agricultural map of the field that maps a plurality of predictive values of the header control setting to a plurality of locations in the field, wherein each respective predictive value, of the plurality of predictive values, corresponds to a respective location, of the plurality of locations, and is based on a respective value of the agricultural characteristic in the agricultural characteristic map corresponding to the respective geographic location;
wherein the control system is configured to control the controllable subsystem based on the plurality of predictive values in the functional predictive agricultural map.
2. The agricultural work machine of claim 1 , wherein the predictive map generator configures the functional predictive agricultural map for consumption by the control system, and wherein the control system controls at least one of a position or an orientation of the header based on the control input.
3. The agricultural work machine of claim 1 , wherein the control system is configured to receive an operator input that defines the input value of the header control setting, the header control setting comprising a header height setting for the header on the agricultural work machine corresponding to the first geographic location.
4. The agricultural work machine of claim 3 , wherein the agricultural characteristic map comprises a topographic map that includes, as the values of the agricultural characteristic, values of a topographic characteristic corresponding to the different geographic locations in the field, and wherein the predictive model generator is configured to identify a relationship between the header height setting and the topographic characteristic based on the input value of the header height setting detected by the operator input sensor corresponding to the first geographic location and a value of the topographic characteristic, in the topographic map, corresponding to the first geographic location, the predictive agricultural model being configured to receive a value of a topographic characteristic as a model input and generate a predictive value of the header height setting as a model output based on the identified relationship.
5. The agricultural work machine of claim 1 , wherein the control system is configured to receive an operator input that defines the input value of the header control setting, the header control setting comprising a header tilt setting for the header on the agricultural work machine corresponding to the first geographic location.
6. The agricultural work machine of claim 5 , wherein the agricultural characteristic map comprises a topographic map that includes, as the values of the agricultural characteristic, values of a topographic characteristic corresponding to the different geographic locations in the field, and wherein the predictive model generator is configured to identify a relationship between the header tilt setting and the topographic characteristic based on the input value of the header tilt setting detected by the operator input sensor corresponding to the first geographic location and a value of the topographic characteristic, in the topographic map, corresponding to the first geographic location, the predictive agricultural model being configured to receive a value of a topographic characteristic as a model input and generate a predictive value of the header tilt setting as a model output based on the identified relationship.
7. The agricultural work machine of claim 1 , wherein the control system is configured to receive an operator input that defines the input value of the header control setting, the header control setting comprising a header roll setting for the header on the agricultural work machine corresponding to the first geographic location.
8. The agricultural work machine of claim 7 , wherein the agricultural characteristic map comprises a topographic map that includes, as the values of the agricultural characteristic, values of a topographic characteristic corresponding to the different geographic locations in the field, and wherein the predictive model generator is configured to identify a relationship between the header roll setting and the topographic characteristic based on the input value of the header roll setting detected by the operator input sensor corresponding to the first geographic location and a value of the topographic characteristic, in the topographic map, corresponding to the first geographic location, the predictive agricultural model being configured to receive a value of a topographic characteristic as a model input and generate a predictive value of the header roll setting as a model output based on the identified relationship.
9. The agricultural work machine of claim 1 , wherein the controllable subsystem comprises an actuator controllable to adjust a position of the header of the agricultural work machine, relative to a surface of the field.
10. The agricultural work machine of claim 1 , wherein the control system generates a control signal to control a ground pressure setting based on the functional predictive agricultural map and controls the controllable subsystem based on the ground pressure setting.
11. The agricultural work machine of claim 1 , wherein the control system generates a control signal to control a sensitivity setting of the header on the agricultural work machine based on the functional predictive agricultural map and controls the controllable subsystem based on the sensitivity setting.
12. A computer implemented method comprising:
receiving an agricultural characteristic map, at an agricultural work machine, that includes values of an agricultural characteristic mapped to different geographic locations in a field;
detecting, with an operator input sensor, an input value of a header control setting corresponding to a first geographic location;
controlling a header of the agricultural work machine based on the input value of the header control setting;
obtaining a first value of the agricultural characteristic mapped to the first geographic location in the agricultural characteristic map;
generating a predictive agricultural model that models a relationship between the agricultural characteristic and the header control setting based on:
the first value of the agricultural characteristic mapped to the first geographic location, and
the input value of the header control setting corresponding to the first geographic location;
controlling a predictive map generator to generate, using the predictive agricultural model, a functional predictive agricultural map of the field that maps a plurality of predictive values of the header control setting to a plurality of locations in the field, wherein each respective predictive value, of the plurality of predictive values, corresponds to a respective location, of the plurality of locations, and is based on a respective value of the agricultural characteristic in the agricultural characteristic map corresponding to the respective geographic location; and
controlling a controllable subsystem of the agricultural work machine based on the plurality of predictive values in the functional predictive agricultural map.
13. The computer implemented method of claim 12 , wherein controlling the header of the agricultural work machine based on the input value of the header control setting comprises controlling at least one of a position or an orientation of the header, and further comprising:
configuring the functional predictive agricultural map for a control system that controls the controllable subsystem.
14. The computer implemented method of claim 12 , wherein the input value of the header control setting is received from an operator through the operator input sensor.
15. The computer implemented method of claim 12 , wherein obtaining the agricultural characteristic map comprises:
obtaining a topographic map that includes, as the values of the agricultural characteristic, values of a topographic characteristic corresponding to the different geographic locations in the field.
16. The computer implemented method of claim 15 , wherein generating the predictive agricultural model comprises:
identifying a relationship between the topographic characteristic and the header control setting based on the input value of the header control setting detected by the operator input sensor corresponding to the first geographic location and a value of the topographic characteristic, in the topographic map, corresponding to the first geographic location; and
controlling a predictive model generator to generate the predictive agricultural model that receives a value of the topographic characteristic as a model input and generates a predictive value of the header control setting as a model output based on the identified relationship.
17. The computer implemented method of claim 12 , wherein the header control setting comprises a first header control setting, and further comprising:
generating a control signal to control a second header control setting, different than the first header control setting, of the agricultural work machine based on the functional predictive agricultural map.
18. The computer implemented method of claim 12 , further comprising:
controlling an operator interface mechanism to present the functional predictive agricultural map.
19. An agricultural work system, comprising:
a communication system that receives an agricultural characteristic map that includes values of an agricultural characteristic mapped to different geographic locations in a field;
an operator input sensor that detects an input value of a header control setting corresponding to a first geographic location in the field, the input value of the header control setting defining a control input to a header control configured to control, based on the input value of the header control setting, at least one of a position or an orientation of a header of an agricultural work machine at an area of the field corresponding to the first geographic location;
a predictive model generator that obtains a first value of the agricultural characteristic mapped to the first geographic location in the agricultural characteristic map, and generates a predictive header setting model that models a relationship between the agricultural characteristic and the header control setting based on;
the first value of the agricultural characteristic mapped to the first geographic location, and
the input value of the header control setting detected by the operator input sensor corresponding the first geographic location, and
a predictive map generator that generates, using the predictive header setting model, a functional predictive header setting map of the field that maps a plurality of predictive values of the header control setting to a plurality of locations in the field, wherein each respective predictive value, of the plurality of predictive values, corresponds to a respective location, of the plurality of locations, and is based on a respective value of the agricultural characteristic in the agricultural characteristic map corresponding to the respective geographic location; and
a control system that controls a controllable subsystem of the agricultural work machine based on the plurality of predictive values in the functional predictive header setting map.
20. The agricultural work system of claim 19 , wherein the agricultural characteristic map comprises a topographic map that includes, as the values of the agricultural characteristic, values of a topographic characteristic corresponding to the different geographic locations in the field.