DE102021123055A1 - PREDICTIVE PERFORMANCE MAP GENERATION AND CONTROL SYSTEM - Google Patents

Abstract

One or more information cards are obtained from an agricultural work machine. The one or more information maps depict 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 feature as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural trait at various locations in the field based on a relationship between the values in the one or more information maps and the agricultural trait sensed by the in situ sensor . The predictive map can be output and used in automated machine control.

Description

FIELD OF DESCRIPTION

The present description relates to agricultural machines.

BACKGROUND

There are many different types of agricultural machinery. Some agricultural machines include harvesters such as combine harvesters, sugar cane harvesters, cotton harvesters, forage harvesters, and windrowers. Some harvesters can also be fitted with different types of headers to harvest different types of crops.

Agricultural harvesters typically include an engine or other power source that produces a finite amount of power that is provided to the various subsystems of the agricultural harvester. Maintaining efficient power distribution to the various subsystems from a limited amount of power can be difficult to achieve as field conditions change.

SHORT VERSION

One or more information cards are obtained from an agricultural work machine. The one or more information maps depict 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 feature as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural feature at various locations in the field based on a relationship between the values in the one or more information maps and the agricultural feature sensed by the in situ sensor . The predictive map can be output and used in automated machine control.

character list

• 1 12 is a partially pictorial, partially schematic representation of an example combine harvester.
• 2 12 is a block diagram showing in more detail some portions of an agricultural harvesting machine according to some examples of the present disclosure.
• the 3a-3b (herein together as 3 ) show a flow chart illustrating an example of the operation of an agricultural harvesting machine in generating a map.
• 4 Figure 12 is a block diagram showing an example of a predictive model generator and a predictive metric map generator.
• 5 is a flow chart depicting an example of an operation of an agricultural harvester in receiving a vegetative index, crop moisture, soil properties, topography, yield, weeds, or biomass map, recognizing a performance characteristic, and generating a functional predictive performance map for use in controlling the agricultural harvester during a harvesting process shows.
• 6 Figure 12 is a block diagram showing an example agricultural harvester in communication with a remote server environment.
• the 7-9 show examples of mobile devices that can be used in an agricultural harvesting machine.
• 10 Figure 12 is a block diagram showing an example of a computing environment that may be used in an agricultural harvester and the architectures illustrated in the previous figures.

DETAILED DESCRIPTION

For a better understanding of the principles of the present disclosure, reference will now be made to the examples illustrated in the drawings and specific language will be used to describe them. However, it should be understood that no limitation on the scope of the disclosure is intended. All alterations and further modifications to the described devices, systems, methods, and any further application of the principles of the present disclosure are contemplated fully as would normally occur to those skilled in the art to which the disclosure pertains. In particular, it is fully contemplated that the features, components, and/or steps described with respect to one example may be combined with the features, components, and/or steps described with respect to other examples of the present disclosure .

The present description relates to the use of in situ data collected concurrently with a farming operation in combination with predictive or historical data to generate a predictive map and in particular a predictive performance map. In some examples, the predictive performance map may be used to control an agricultural work machine, such as an agricultural harvester. As discussed above, a harvester's power production has a finite limit and overall performance may be impacted when one or more subsystems have an increased power demand.

Harvester performance can be adversely affected based on a number of different criteria. For example, areas with dense crop plants, weeds, or combinations thereof may adversely affect harvester operation because subsystems require more power to process larger amounts of material, which includes crop plants and weeds. A vegetative index may signal where areas of dense crop plants, weeds, or combinations thereof may be present. Or, for example, crop plants or weeds that have a higher moisture content also take more power to process. Or, for example, soil characteristics such as type or moisture can affect power consumption by the steering and propulsion systems. For example, wet clay soils can cause additional slip compared to dry soils, reducing drive train efficiency. Or, for example, the topography of the field can change the performance characteristics of an agricultural harvester. For example, when the harvester is going up a hill, some power needs to be diverted to the drive system to maintain a constant speed. Or, for example, an area of the field with a higher grain yield may require more power to be diverted to the crop processing subsystems. Or, for example, an area of the field containing a large biomass may require more power to be diverted to the crop processing subsystems.

Some current systems provide vegetative index maps. A vegetative index map illustratively maps vegetative index values (which may be indicative of vegetative growth) across various geographic locations in a field of interest. An example of a vegetative index includes a normalized difference vegetative index (NDVI). There are many other vegetative indices that are within the scope of the present disclosure. In some examples, a vegetative index may be derived from sensor readings of one or more bands of electromagnetic radiation reflected from the plants. Without limitation, these bands can be in the microwave, infrared, visible, or ultraviolet portions of the electromagnetic spectrum.

A vegetative index map can be used to identify the presence and location of vegetation. In some examples, these maps allow weeds to be identified and georeferenced in the presence of bare soil, crop residue, or other vegetation, including crop or other weeds. For example, at the end of a growing season, when a crop is mature, the crop plants may have a relatively low proportion of living, growing vegetation. However, weeds often remain in a state of growth after the crop has matured. Therefore, if a vegetative index map is made relatively late in the growing season, the vegetative index map can indicate the position of weeds in the field.

Some current systems provide crop moisture maps. A crop moisture map illustratively depicts crop moisture across various geographic locations in a field of interest. In one example, crop moisture may be sensed prior to a harvesting operation by an unmanned aerial vehicle (UAV) equipped with a moisture sensor. As the UAV moves across the field, the crop moisture measurements are geolocated to create a crop moisture map. This is just an example and the crop moisture map can be created in other ways, for example crop moisture across a field can be predicted based on precipitation, soil moisture, or combinations thereof.

Some current systems provide topographic maps. A topographical map illustratively maps elevations or other topographical features of the ground across various geographic locations in a field of interest. Since ground slope indicates a change in elevation, providing two or more elevation values allows the slope to be calculated over the areas of known elevation values. Greater granularity of slope can be achieved by providing more regions with known elevation values. As an agricultural harvester travels over the terrain in known directions, the pitch and roll of the agricultural harvester can be determined based on the slope of the ground (ie, areas of varying elevation). topography Physical characteristics referred to below may include, but are not limited to, elevation, grade (e.g., including machine orientation relative to grade), and ground profile (e.g., unevenness).

Some current systems provide soil property maps. A soil property map illustratively maps soil property values (which may be indicative of soil type, soil moisture, soil cover, soil structure, as well as various other soil properties) across various geographic locations in a field of interest. The soil property maps thus provide georeferenced soil properties over a field of interest. Soil type can refer to taxonomic units in soil science, with each soil type having defined sets of common properties. For example, soil types may include sandy soil, clay soil, silt soil, peat soil, chalky soil, clay soil, and various other soil types. Soil moisture can refer to the amount of water held or otherwise contained in the soil. Soil moisture is also known as soil wetness. Land cover may refer to the amount of objects or materials covering the ground, including vegetation material such as crop residues or cover crops, debris, as well as various other objects or materials. In agricultural terms, soil cover often includes a level of residual crop residues, such as a residual mass of plant stems, as well as a level of catch crops. Soil structure can refer to the arrangement of solid parts of the soil and the pore space located between the solid parts of the soil. Soil structure may include the manner in which individual particles, such as B. individual particles of sand, silt and clay are assembled. Soil structure can be described in terms of grade (degree of aggregation), class (average size of aggregates), and shape (types of aggregates), as well as a variety of other descriptions. These are just examples. Various other features and properties of the soil can be mapped as soil property values on a soil property map.

These soil property maps may be generated based on data collected during another operation corresponding to the field of interest, for example previous farming operations in the same season, such as planting operations or spraying operations, as well as previous farming operations performed in previous seasons , such as a previous harvest. The agricultural machines that perform these agricultural operations may have onboard sensors that detect features indicative of soil properties, for example features indicative of soil type, soil moisture, soil cover, soil structure, and various other features indicative of various other soil properties are. In addition, operational characteristics or machine settings of the agricultural machines during previous operations can be used along with other data to generate a soil property map. For example, header elevation data indicating an elevation of an agricultural harvester's header over various geographic locations in the field of interest during a previous harvest operation, along with weather data indicating weather conditions such as precipitation data or wind data during an intermediate period (such as the period since the time of previous harvesting operation and the generation of the soil property map) can be used to generate a soil moisture map. For example, by knowing the height of the header, the amount of remaining crop residue, such as crop stalks, can be known or estimated, and together with precipitation data, the soil moisture level can be predicted. This is only an example.

The present discussion also includes predictive maps that predict a feature based on an information map and a relationship with an in situ sensor. Two of these maps include a predictive yield map and a predictive biomass map. In one example, the predictive yield map is obtained by receiving a previous vegetative index map and detecting a yield during a harvesting operation and determining a relationship between the previous vegetative index map and the yield sensor signal and using the relationship to generate the predictive yield map based on the relationship and the previous vegetative index map generated. In one example, the predictive biomass map is generated by receiving a previous vegetative index map and detecting a biomass and determining a relationship between the previous vegetative index map and the biomass sensor signal and using the relationship to generate the predictive biomass map based on the relationship and the previous vegetative index map. The predictive yield and biomass maps may be based on other information maps or may be generated in other ways. For example, the predictive yield and biomass maps can be generated based on satellite data or a growth model.

The present discussion thus continues with respect to examples in which a system receives one or more of a vegetative index, weeds, crop moisture, soil property, topography, predictive yield, or predictive biomass map and also uses an in situ sensor to measure a variable to recognize, which indicates the crop condition during a harvesting process. The system creates a model that models a relationship between the vegetative index values, crop moisture values, soil property values, predicted yield values, or predicted biomass values from the maps and the in situ data from the in situ sensor. The model is used to generate a functional predictive performance map that predicts an expected performance characteristic of the agricultural harvester in the field. The functional predictive performance map generated during the harvesting process may be presented to an operator or other user, or used to automatically control an agricultural harvesting machine during the harvesting process, or both.

1 12 is a partially pictorial, partially schematic representation of a self-propelled agricultural harvester 100. In the example illustrated, the agricultural harvester 100 is a combine harvester. Further, while combines are provided as examples throughout this disclosure, it should be understood that the present description is applicable to other types of harvesting machines, such as cotton harvesters, sugarcane harvesters, forage harvesters, windrowers, or other agricultural work machines. Accordingly, the present disclosure is intended to encompass the various types of harvesters described and is thus not limited to combines. Additionally, the present disclosure is directed to other types of work machines, such as agricultural seeders and sprayers, construction machines, forest machines, and lawn care machines, where predictive map generation may be applicable. Accordingly, the present disclosure is intended to encompass these various types of harvesters and other work machines and is thus not limited to combines.

As in 1 1, agricultural harvester 100 illustratively includes an operator's cab 101 that may include a variety of different operator interface mechanisms for controlling agricultural harvester 100 . The agricultural harvester 100 includes headers, such as a header 102 and a cutter, generally indicated at 104. The agricultural harvester 100 also includes a feeder housing 106, a feed accelerator 108, and a thresher, generally indicated at 110. The feeder housing 106 and the Feed accelerators 108 form part of a material handling subsystem 125 . The header 102 is pivotally coupled to a frame 103 of the agricultural header 100 along the pivot axis 105 . One or more actuators 107 power movement of header 102 about axis 105 in the direction generally indicated by arrow 109 . Thus, a vertical position of the header 102 (the header height) above the ground 111 over which the header 102 travels can be controlled by actuating the actuator 107 . Although in 1 not shown, agricultural harvesting machine 100 may also include one or more actuators operable to apply a pitch angle, a roll angle, or both to the header 102 or portions of the header 102 . Pitch refers to an angle at which the cutter assembly 104 engages the crop. The angle of inclination is increased, for example, by controlling the header 102 so that a distal edge 113 of the cutter 104 is directed more towards the ground. The angle of inclination is reduced by controlling the header 102 so that the distal edge 113 of the cutter 104 is directed further away from the ground. The roll angle refers to the orientation of the header 102 about the front-to-back longitudinal axis of the agricultural harvesting machine 100.

The thresher 110 illustratively includes a threshing rotor 112 and a set of concaves 114. Further, the agricultural harvester 100 also includes a separator 116. The agricultural harvester 100 also includes a cleaning subsystem or cleaning shoe (collectively referred to as the cleaning subsystem 118) that a cleaning fan 120, a chopper 122 and a screen 124 includes. The material handling subsystem 125 also includes a discharge drum 126, a tailings elevator 128, a clean grain elevator 130, and an unloading auger 134 and chute 136. The clean grain elevator conveys clean grain into the clean grain tank 132. The agricultural harvester 100 also includes a tailings subsystem 138 that a chopper 140 and a spreader 142. Agricultural harvester 100 also includes a propulsion subsystem that includes an engine that drives ground engaging components 144, such as wheels or tracks. In some examples, a combine may have more than one of the above subsystems within the scope of the present disclosure exhibit. In some examples, agricultural harvester 100 may include left and right hand cleaning subsystems, separators, etc., shown in 1 are not shown.

In operation and for overview, agricultural harvester 100 illustratively moves through a field in the direction indicated by arrow 147 . During movement of the agricultural harvesting machine 100, the header 102 (and the associated reel 164) engages the crop to be harvested and collects the crop towards the cutting device 104. An operator of the agricultural harvesting machine 100 can be a local human operator, a remote human operator or be an automated system. The operator of agricultural harvesting machine 100 may specify one or more height settings, pitch angle settings, or roll angle settings for header 102 . For example, the operator enters a setting or settings into a control system, described in more detail below, that controls actuator 107 . The control system may also receive a setting from the operator to set up the pitch and roll angle of the header 102 and implement the settings entered by associated actuators, not shown, that operate to change the pitch and roll angle of the header 102. The actuator 107 maintains the header 102 at a height above the ground 111 based on a height adjustment and at desired pitch and roll angles, if any. Each of the elevation, roll, and pitch settings can be implemented independently of the others. The control system responds to header errors (e.g., the difference between the elevation setting and the measured height of the header 104 above the ground 111 and, in some examples, pitch angle and roll angle errors) with a responsiveness that is determined based on a selected sensitivity level. When the sensitivity level is set to a higher sensitivity level, the control system will respond to smaller header position errors and attempt to reduce the detected errors faster than when the sensitivity is at a lower sensitivity level.

Returning to the description of the operation of agricultural harvesting machine 100, after the crop has been cut by cutter 104, the separated crop is moved by a conveyor in feed housing 106 toward feed accelerator 108, which accelerates the crop into threshing unit 110. The crop is threshed by the rotor 112 which rotates the crop against the concaves 114 . The threshed crop material is moved by a separator rotor in the separator 116 with a portion of the residue being moved towards the residue subsystem 138 by the discharge drum 126 . The portion of the tailings that is transferred to tailings subsystem 138 is shredded by tailings chopper 140 and spread by spreader 142 on the field. In other configurations, the residue is released from the agricultural harvester 100 in a windrow. In other examples, residue subsystem 138 may include weed control devices (not shown), such as seed baggers or other seed collectors or seed crushers or other seed destroyers.

The grain falls onto the cleaning subsystem 118. The chopper 122 separates a portion of coarser pieces of material from the grain and the screen 124 separates a portion of finer pieces of material from the clean grain. The clean grain falls onto an auger that moves the grain to an inlet end of the clean grain elevator 130 and the clean grain elevator 130 moves the clean grain up, thereby separating the clean grain in the clean grain tank 132 . Debris is removed from the cleaning subsystem 118 by the air flow of the cleaning fan 120 . The cleaning fan 120 directs air along an airflow path up through the screens and choppers. The airflow carries residue rearward in agricultural harvesting machine 100 toward residue handling subsystem 138.

The tailings elevator 128 returns the tailings to the thresher 110 where the tailings are re-threshed. Alternatively, the tailings can also be fed to a separate after-threshing mechanism by a tailings elevator or other transport device, where the tailings are also after-threshed.

1 Also shows that in one example, agricultural harvester 100 includes ground speed sensor 146, one or more separator loss sensors 148, a clean grain camera 150, a forward-looking image capture mechanism 151, which may be in the form of a stereo or mono camera, and one or more loss sensors 152 provided in the cleaning subsystem 118 is included.

The ground speed sensor 146 detects the ground speed of the agricultural harvesting machine 100 over the ground. The ground speed sensor 146 can determine the ground speed of the agricultural harvesting machine 100 by detecting the rotational speed of the ground engaging components (such as wheels or tracks) of a drive shaft, an axle or other components. In some cases, vehicle speed may be sensed using a positioning system, such as a global positioning system (GPS), dead reckoning system, remote navigation system (LORAN), or a variety of other systems or sensors that provide an indication of vehicle speed.

The loss sensors 152 illustratively provide an output signal indicative of the amount of grain loss occurring on both the right and left sides of the cleaning subsystem 118 . In some examples, the sensors 152 are impact sensors that count grain impacts per unit time or per unit distance to provide an indication of grain loss occurring at the cleaning subsystem 118 . The impact sensors for the right and left sides of the shoe 118 can provide individual signals or a combined or aggregated signal. In some examples, the sensors 152 can include a single sensor, as opposed to separate sensors provided for each cleaning subsystem 118 .

The separator loss sensor 148 provides a signal indicative of grain loss in the left and right separators indicated in 1 are not shown separately. The separator loss sensors 148 may be associated with the left and right separators and may provide separate grain loss signals or a combined or aggregated signal. In some cases, detecting grain loss in the separators can also be done using a variety of different types of sensors.

Agricultural harvester 100 may also include other sensors and measurement mechanisms. For example, the agricultural harvesting machine 100 may include one or more of the following sensors: a header height sensor that detects a height of the header 102 above the ground 111; stability sensors that detect oscillatory or bouncing motion (and amplitude) of agricultural harvesting machine 100; a residue setting sensor configured to detect whether the agricultural harvesting machine 100 is configured to shred the residue, create a windrow, etc.; a shoe box fan speed sensor to detect the speed of the fan 120; a concave distance sensor that detects the distance between the rotor 112 and the concaves 114; a threshing rotor speed sensor that detects a rotor speed of the rotor 112; a chopper gap sensor that senses the size of the openings in the chopper 122; a wire gap sensor that senses the size of the openings in the wire 124; a non-grain material (MOG) moisture sensor that detects a moisture content of the MOG passing through the agricultural harvesting machine 100; one or more machine setting sensors configured to sense various configurable settings of agricultural harvesting machine 100; a machine orientation sensor that detects the orientation of the agricultural harvesting machine 100; and crop property sensors that sense a variety of different types of crop properties, such as crop type, crop moisture, and other crop properties. The crop characteristic sensors can also be configured to detect the characteristics of the separated crop during processing by the agricultural harvesting machine 100 . For example, in some cases, the crop property sensors may sense grain quality, such as broken grain, MOG values; grain components such as starches and protein; and grain feed rate as the grain moves through the feeder house 106, the clean grain elevator 130, or elsewhere in the agricultural harvester 100. The crop property sensors may also sense the rate of advance of biomass through the feeder house 106 , through the separator 116 , or elsewhere in the agricultural harvester 100 . The crop property sensors may also sense haul rate as a mass flow rate of grain through the elevator 130 or through other portions of the agricultural harvesting machine 100, or provide other output signals indicative of other sensed quantities.

Examples of sensors used to detect or measure the performance characteristics include a tension sensor, a current sensor, a torque sensor, a fluid pressure sensor, a fluid flow sensor, a force sensor, a bearing load sensor, and a rotation sensor. Performance characteristics can be measured at different granularities. For example, the power consumption can be recorded machine-wide, sub-system-wide or by individual components of the sub-systems.

Before describing how the agricultural harvesting machine 100 generates a functional predictive performance map and uses the functional predictive performance map for control, a brief description of some elements of the agricultural harvesting machine 100 and their operation is first provided. The description of 2 and 3 describes receiving a general type of information map and combining information from the information map with a georeferenced sensor signal generated by an in situ sensor, the sen sorsignal indicates a feature in the field, such as performance characteristics of the agricultural harvester. Field characteristics may include, but are not limited to, characteristics of a field such as slope, weed intensity, weed species, soil moisture, surface quality; Characteristics of crop properties, such as crop height, crop moisture, crop density, crop condition; Characteristics of grain properties, such as grain moisture, grain size, grain test weight; and machine performance characteristics such as loss levels, job quality, fuel consumption, and power utilization. A relationship between the feature values derived from in situ sensor signals and the information map values is identified and this relationship is used to generate a new functional predictive map. A functional predictive map predicts values at various geographic locations in a field, and one or more of these values can be used to control a machine, such as one or more subsystems of an agricultural harvester. In some cases, a functional predictive map may be presented to a user, such as an operator of an agricultural work machine, which may be an agricultural harvester. A functional predictive map may be presented to a user visually, such as via a display, haptically, or audibly. The user can interact with the functional predictive map to perform editing operations and other user interface operations. In some cases, a functional predictive map may be used for one or more of controls of an agricultural work machine, such as an agricultural harvester, presentation to an operator or other user, and presentation to an operator or user for interaction by the operator or user.

After the general approach regarding the 2 and 3 , a more specific approach to generating a functional predictive performance map that can be presented to an operator or user or used to control the agricultural harvesting machine 100 or both is described with reference to FIG 4 and 5 described. Although the present discussion continues with respect to the agricultural harvester, and more particularly a combine harvester, other types of agricultural harvesters or other agricultural work machines are within the scope of the present disclosure.

2 FIG. 12 is a block diagram showing some portions of an exemplary agricultural harvesting machine 100. FIG. 2 shows that the agricultural harvester 100 illustratively includes one or more processors or servers 201, a data store 202, a geographic position sensor 204, a communication system 206 and one or more in situ sensors 208 that one or more agricultural features of a field simultaneously with record a harvesting process. An agricultural trait can include any trait that can affect the harvesting process. Some examples of agricultural characteristics include characteristics of the harvester, the field, the crops in the field, and the weather. Other types of agricultural characteristics are also considered. An agricultural trait can include any trait that can affect the harvesting process. Some examples of agricultural characteristics include characteristics of the harvester, the field, the crops in the field, and the weather, among others. The in situ sensors 208 generate values corresponding to the sensed features. Agricultural harvester 100 also includes a predictive model or relationship generator (collectively referred to as "predictive model generator 210"), a predictive map generator 212, a control zone generator 213, a control system 214, one or more controllable subsystems 216, and an operator interface mechanism 218. The Agricultural harvester 100 may also include a variety of other agricultural harvester functions 220 . The in situ sensors 208 include, for example, onboard sensors 222, remote sensors 224, and other sensors 226 that sense characteristics of a field during a farming operation. The predictive model generator 210 illustratively includes an information variable-to-in situ variable model generator 228 , and the predictive model generator 210 may include other elements 230 . The control system 214 includes the communication system control 229, the operator interface control 231, an adjustment control 232, the path planning control 234, the throng speed control 236, the header and reel control 238, the draper belt control 240, the top plate position control 242, the residue system control 244, the machine cleaning control 245, the zone control 247 , and system 214 may include other elements 246 . The controllable subsystems 216 include machine and header actuators 248, the propulsion subsystem 250, the steering subsystem 252, the residue subsystem 138, the machine cleaning subsystem 254, and the subsystems 216 may include a variety of other subsystems 256.

2 also shows that the agricultural harvesting machine 100 can receive the information card 258 . As described below, information card 258 includes, for example a vegetative index map or a pre-plant vegetation map. However, the information map 258 may also include other types of data obtained prior to a harvesting operation or a pre-operational map. 2 also shows that an operator 260 can operate the agricultural harvesting machine 100 . The operator 260 interacts with the operator interface mechanisms 218. In some examples, the operator interface mechanisms 218 may include joysticks, levers, a steering wheel, linkages, pedals, buttons, knobs, keypads, user actuable elements (such as icons, buttons, etc.) on a user interface display device, a microphone and speaker (if speech recognition and speech synthesis are provided), as well as a variety of other types of control devices. When a touch-sensitive display system is provided, operator 260 may interact with operator interface mechanisms 218 using touch gestures. These examples described above are provided as illustrative examples and are not intended to limit the scope of the present disclosure. Accordingly, other types of operator interface mechanisms 218 may be used and are within the scope of the present disclosure.

Information map 258 may be downloaded to agricultural harvester 100 and stored in data storage 202 using communication system 206 or otherwise. In some examples, communication system 206 may be a cellular communication system, a system for communicating over a wide area network or a local area network, a system for communicating over a near field communication network, or a communication system configured to communicate over any of a variety of other networks or combinations to communicate from networks. The communication system 206 may also include a system that facilitates downloading or transferring information to and from a Secure Digital (SD) card or a universal serial bus (USB) card, or both.

The geographic position sensor 204 illustratively senses or detects the geographic position or location of the agricultural harvesting machine 100. The geographic position sensor 204 may include, but is not limited to, a global navigation satellite system (GNSS) receiver that receives signals from a GNSS satellite transmitter. The geographic position sensor 204 may also include a real-time kinematics (RTK) component configured to improve the accuracy of the position data derived from the GNSS signal. The geographic position sensor 204 may include a dead reckoning system, a cellular triangulation system, or a variety of other geographic position sensors.

The in situ sensors 208 can be any of the sensors described above with respect to FIG 1 act. The in situ sensors 208 include onboard sensors 222 mounted onboard the agricultural harvester 100 . Such sensors may include, for example, a perception sensor (e.g., a mono or stereo forward-facing camera system and an image processing system), image sensors that are within the agricultural harvesting machine 100 (such as the clean grain camera, or cameras mounted to identify weed seeds exiting the agricultural harvester 100 through the tailings subsystem or out the cleaning subsystem). The in situ sensors 208 also include remote in situ sensors 224 that collect in situ information. In situ data includes data collected by a sensor onboard the harvester or any sensor where the data is detected during the harvesting process.

The predictive model generator 210 generates a model that indicates a relationship between the values sensed by the in situ sensor 208 and a metric mapped by the information map 258 onto the field. For example, if the information map 258 maps a vegetative index value to various locations in the field and the in situ sensor 208 detects a value indicative of header power consumption, then the prior information variable-to-in situ variable model generator 228 generates a predictive Performance model that models the relationship between the vegetative index value and the header power consumption value. The predictive performance model may also be generated based on vegetative index values from information map 258 and multiple in situ data values generated by in situ sensors 208 . Then, the predictive map generator 212 uses the predictive performance model generated by the predictive model generator 210 to generate a functional predictive performance map that represents the value of a performance characteristic, such as power consumption by a subsystem, measured by the in situ sensors 208 at various locations in is detected in the field based on the information map 258 is predicted.

In some examples, the type of values in functional predictive map 263 may be the same as the in situ sensor type sensed by in situ sensors 208 . In some cases, the type of values in the functional predictive map can be 263 have different units than the data collected by the in situ sensors 208 . In some examples, the type of values in functional predictive map 263 may be the same as the type of in situ data sensed by in situ sensors 208, but have a relationship to the type of data sensed by in situ sensors 208 recorded data type. For example, the type of data collected from in situ sensors 208 may indicate the type of values in functional predictive map 263 in some examples. In some examples, the type of data in functional predictive map 263 may differ from the type of data in information map 258 . In some cases, the type of data in functional predictive map 263 may have different entities than the data in information map 258 . In some examples, the type of data in functional predictive map 263 may be different than the data type in information map 258, but is related to the data type in information map 258. For example, in some examples, the data type in information map 258 may be the type of Indicate data in the functional predictive map 263 . In some examples, the type of data in functional predictive map 263 differs from one or both of the in situ data type detected by in situ sensors 208 and the data type in information map 258. In some examples, the type is the Data in functional predictive map 263 is the same as one or both of the in situ data type detected by in situ sensors 208 and the type of data in information map 258. In some examples, the type of data in functional predictive map 263 is the same as the in situ data type detected by the in situ sensors 208 or the data type in the information card 258 and is different from the other.

Continuing with the previous example in which the information map 258 is a vegetative index map and the in situ sensor 208 senses a value indicative of header power consumption, the predictive map generator 212 can determine the vegetative index values in the information map 258 and through the predictive model generator 210 to generate a functional predictive map 263 that predicts header power consumption at various locations in the field. The predictive map generator 212 thus outputs the predictive map 264 .

As in 2 As shown, predictive map 264 predicts the value of a detected feature (detected by in situ sensors 208) or a feature related to the detected feature at various locations across the field based on an information value in information map 258 these positions and the predictive model. For example, if the predictive model generator 210 has generated a predictive model indicative of a relationship between a vegetative index value and header power consumption, then given the vegetative index value at various positions across the field, the predictive map generator 212 generates a predictive map 264 indicative of the value of the Predicts header power consumption at various locations across the field. The vegetative index value obtained from the vegetative index map at these locations and the relationship between the vegetative index value and the header power consumption obtained from the predictive model are used to generate the predictive map 264 .

Some variations in the types of data depicted in information map 258, the types of data captured by in situ sensors 208, and the types of data predicted on predictive map 264 will now be described.

In some examples, the type of data in information map 258 differs from the type of data captured by in situ sensors 208, yet the type of data in predictive map 264 is the same as the type of data captured by in situ sensors 208 will. For example, information map 258 may be a vegetative index map and the variable sensed by in situ sensors 208 may be yield. The predictive map 264 may then be a predictive yield map that maps predicted yield values to various geographic locations in the field. In another example, information map 258 may be a vegetative index map and the variable sensed by in situ sensors 208 may be crop height. The predictive map 264 may then be a predictive crop height map that maps predicted crop height values to various geographic locations in the field.

Also, in some examples, the type of data in information card 258 differs from the type of data sensed by in situ sensors 208, and the type of data in predictive map 264 differs from both the type of data in information card 258 and the type of data , which is detected by the in situ sensors 208 . For example, information map 258 may be a vegetative index map and the variable sensed by in situ sensors 208 may be crop height. The predictive map 264 can then be a predictive biomass map that maps predicted biomass values to various geographic locations in the field. For example, information map 258 may be a vegetative index map and the variable sensed by in situ sensors 208 may be crop height. The predictive map 264 may then be a predictive speed map that maps predicted harvester speed values to various geographic locations in the field.

In some examples, the information map 258 is from a previous pass through the field during a pre-operation and the type of data is different than the type of data captured by in situ sensors 208, but the type of data in the predictive map 264 is the same as that Type of data collected by the in situ sensors 208. For example, information map 258 may be a seed population map generated during planting and the variable sensed by in situ sensors 208 may be stem size. The predictive map 264 may then be a predictive stalk size map that maps predicted stalk size values to various geographic locations in the field. In another example, information map 258 may be a seeding hybrid map and the variable sensed by in situ sensors 208 may be crop condition, such as stalled crop or crop kinked. The predictive map 264 may then be a predictive crop condition map that maps predicted crop condition values to various geographic locations in the field.

In some examples, information map 258 is from a previous pass through the field during pre-operation and the data type is the same as the data type captured by in situ sensors 208 and the data type in predictive map 264 is also the same such as the type of data captured by the in situ sensors 208 . For example, information map 258 may be a yield map generated during a previous year and the variable sensed by in situ sensors 208 may be yield. The predictive map 264 may then be a predictive yield map that maps predicted yield values to various geographic locations in the field. In such an example, the relative yield differences in the georeferenced information map 258 from the previous year may be used by the predictive model generator 210 to generate a predictive model that models a relationship between the relative yield differences in the information map 258 and the yield values generated by In -situ sensors 208 are detected during the current harvesting process. The predictive model is then used by the predictive map generator 210 to create a predictive yield map.

In another example, information map 258 may be a threshing/separating subsystem power usage map generated during a pre-operation, and the variable sensed by in situ sensors 208 may be threshing/separating subsystem power usage. The predictive map 264 may then be a predictive threshing/separating subsystem power utilization map that maps predictive threshing/separating subsystem power utilization values to various geographic locations in the field.

In some examples, a predictive map 264 may be provided to the control zone generator 213 . The control zone generator 213 groups adjacent sections of an area into one or more control zones based on predictive map 264 data values associated with those adjacent sections. A control zone may include two or more contiguous sections of an area, such as a field, for which a control parameter corresponding to the control zone for controlling a controllable subsystem is constant. For example, a response time for changing a setting of controllable subsystems 216 may be insufficient to respond satisfactorily to changes in values contained in a map, such as predictive map 264. In this case, control zone generator 213 analyzes the map and identifies control zones, which have a defined size in order to take the response time of the controllable subsystems 216 into account. In another example, the control zones may be sized to reduce wear from excessive actuator movement resulting from continuous adjustment. In some examples, there may be a different set of control zones for each controllable subsystem 216 or for groups of controllable subsystems 216. The control zones can be added to the predictive map 264 to obtain a predictive control zone map 265 . Thus, the predictive control zone map 265 may be similar to the predictive map 264, except that the predictive control zone map 265 includes control zone information defining the control zones. Thus, a functional predictive map 263 as described herein may include control zones. Both predictive map 264 and predictive control zone map 265 are functional predictive maps 263. In one example, functional predictive map 263 does not include control zones, such as predictive map 264. In another example, functional predictive map 263 includes control zones, such as the predictive control zone map 265. In some examples, multiple crops may be present in a field at the same time when a mixed crop production system is implemented. In this case, the predictive map generator 212 and the control zone generator 213 are able to determine the position and characteristics of the identify two or more crop types and then generate predictive map 264 and predictive map with control zones 265 accordingly.

It should also be noted that the control zone generator 213 can group values to generate control zones and the control zones can be added to a predictive tax zone map 265 or a separate map showing only the generated control zones. In some examples, the control zones may be used to control or calibrate agricultural harvester 100, or both. In other examples, the control zones may be displayed to operator 260 and used to control or calibrate agricultural harvester 100, and in other examples, the control zones may be displayed to operator 260 or another user, or saved for later use.

The predictive map 264 or the predictive control zone map 265 or both are provided to the control system 214, which generates control signals based on the predictive map 264 or the predictive control zone map 265 or both. In some examples, the communication system controller 229 controls the communication system 206 to communicate the predictive map 264 or the predictive control zone map 265 or control signals based on the predictive map 264 or the predictive control zone map 265 to other agricultural harvesting machines harvesting in the same field. In some examples, communication system controller 229 controls communication system 206 to send predictive map 264, predictive control zone map 265, or both to other remote systems.

Operator interface controller 231 is operable to generate control signals to control operator interface mechanisms 218 . Operator interface control 231 is also operable to present operator 260 with predictive map 264 or predictive control zone map 265 or other information derived from or based on predictive map 264, predictive control zone map 265, or both. The operator 260 can be a local operator or a remote operator. As an example, controller 231 generates control signals to control a display mechanism to display one or both of predictive map 264 and predictive control zone map 265 to operator 260 . Controller 231 may create operator actuable mechanisms that are displayed and operable by the operator to interact with the displayed map. The operator can edit the card by, for example, correcting a feature displayed on the card based on the operator's observation. The adjustment controller 232 may generate control signals to control various adjustments on the agricultural harvesting machine 100 based on the predictive map 264, the predictive control zone map 265, or both. For example, the adjustment controller 232 may generate control signals to control the machine and header actuators 248 . In response to the generated control signals, the machine and header actuators 248 operate to adjust, for example, one or more of the sieve and chopper settings, concave clearance, rotor settings, cleaning fan speed settings, header height, header functionality, reel speed, reel position, to control the draper functionality (where the agricultural harvester 100 is coupled to a draper header), the corn header functionality, the internal distribution control, and other actuators 248 that affect the other functions of the agricultural harvester 100. Path planning controller 234 illustratively generates control signals to control steering subsystem 252 to steer agricultural harvester 100 according to a desired path. Path planning controller 234 may control a path planning system to generate a route for agricultural harvester 100 and may control propulsion subsystem 250 and steering subsystem 252 to steer agricultural harvester 100 along that route. Feedrate controller 236 may control various subsystems, such as propulsion subsystem 250 and machine actuators 248, to control feedrate based on predictive map 264 or predictive control zone map 265, or both. For example, as agricultural harvester 100 approaches an area with a predicted subsystem power usage value above a selected threshold, feed rate controller 236 may reduce the speed of agricultural harvester 100 to maintain power allocation to the predicted power consumption needs of the one or more subsystems. The header and reel controller 238 may generate control signals to control a header or reel or other header functionality. The draper band controller 240 may generate control signals to control a draper band or other draper functionality based on the predictive map 264, the predictive control zone map 265, or both. The top plate position controller 242 may generate control signals to based a position of a top plate included in a header location of a predictive map 264 or a predictive control zone map 265 or both, and the backlog system controller 244 may generate control signals to control a backlog subsystem 138 based on a predictive map 264 or a predictive control zone map 265 or both. The machine cleaning controller 245 may generate control signals to control the machine cleaning subsystem 254 . Other controls included in agricultural harvesting machine 100 may also control other subsystems based on predictive map 264 or predictive control zone map 265 or both.

the 3A and 3B (herein together as 3 ) show a flow chart illustrating an example of the operation of the agricultural harvesting machine 100 in generating a predictive map 264 and a predictive control zone map 265 based on the information map 258 .

At 280, agricultural harvester 100 receives information card 258. Examples of information card 258 or receiving information card 258 are discussed with respect to blocks 281, 282, 284, and 286. As discussed above, as indicated at block 282, information card 258 assigns values of a variable corresponding to a first feature to various locations in the field. As indicated at block 281, receiving the information card 258 may include selecting one or more of a plurality of possible information cards that are available. For example, an information map can be a vegetative index map generated from aerial photographs. Another map of information may be a map generated during a previous pass through the field that may have been performed by another machine that performed a previous operation on the field, such as a sprayer or other machine. The process of selecting one or more information cards can be manual, semi-automated, or automated. Information map 258 is based on data collected prior to a current harvest operation. Block 284 indicates this. For example, the data may be collected based on aerial photographs taken during a previous year or earlier in the current growing season or at other times. As indicated by block 285, the information map may be a predictive map that predicts a feature based on an information map and a relationship with an in situ sensor. A process for generating a predictive map is presented in 5 shown. This process can also be done with other sensors and other previous maps to generate, for example, predictive yield maps or predictive biomass maps. These predictive maps can be used as previous maps in other predictive processes, as indicated by block 285. The data may be based on data detected by means other than aerial photography. For example, the data for information card 258 may be transmitted to agricultural harvester 100 using communication system 206 and stored in data storage 202 . Data for information card 258 may be provided in other ways using communications system 206 of agricultural harvester 100, as indicated by block 286 in the flowchart of FIG 3 is shown. In some examples, information card 258 may be received by communication system 206 .

At the start of a harvesting operation, the in situ sensors 208 generate sensor signals indicative of one or more in situ data values indicative of a characteristic, for example a performance characteristic, such as power consumption by one or more subsystems, as indicated by block 288 . Examples of in situ sensors 288 are discussed with respect to blocks 222, 290 and 226. As discussed above, in situ sensors 208 include onboard sensors 222; remote in situ sensors 224, such as UAV-based sensors flown at a time to collect in situ data, as shown in block 290; or other types of in situ sensors, denoted by in situ sensors 226 . In some examples, data from onboard sensors is georeferenced using position, heading, or speed data from geographic location sensor 204 .

The predictive model generator 210 controls the information variable-to-in situ variable model generator 228 to generate a model representing a relationship between the mapped values contained in the information map 258 and the in situ values that by the in situ sensors 208 are modeled as indicated by block 292 . The features or data types represented by the mapped values in information map 258 and the in situ values sensed by in situ sensors 208 may be the same features or data types or different features or data types.

The relationship or model generated by the predictive model generator 210 is provided to the predictive map generator 212 . The predictive map generator 212 generates a predictive map 264 that represents a value of the marker sensed by the in situ sensors 208 times at different geographic locations in a field to be harvested or another feature related to the feature sensed by the in situ sensors 208 using the predictive model and information map 258 as indicated by block 294 .

Note that in some examples, the information map 258 may include two or more different maps or two or more different map layers of a single map. Each map layer may represent a different type of data than the data type of another map layer, or the map layers may have the same type of data obtained at different points in time. Each map in the two or more different maps, or each layer in the two or more different map layers of a map, maps a different type of variable to the geographic locations in the field. In such an example, the predictive model generator 210 generates a predictive model that models the relationship between the in situ data and each of the various variables depicted by the two or more different maps or the two or more different map layers. Likewise, the in situ sensors 208 may include two or more sensors, each sensing a different type of variable. Thus, the predictive model generator 210 creates a predictive model that models the relationships between each variable type represented by the information map 258 and each variable type sensed by the in situ sensors 208 . The predictive map generator 212 may generate a functional predictive map 263 that includes a value for each sensed feature sensed by the in situ sensors 208 (or a feature related to the sensed feature) at different locations in the Field that will be harvested using the predictive model and each of the maps or map layers in information map 258 predicts.

The predictive map generator 212 configures the predictive map 264 such that the predictive map 264 is actionable (or consumable) by the control system 214 . Predictive map generator 212 may provide predictive map 264 to control system 214 or control zone generator 213, or both. Some examples of different ways in which predictive map 264 may be configured or issued are described with respect to blocks 296, 295, 299, and 297. For example, the predictive map generator 212 configures the predictive map 264 so that the predictive map 264 includes values that can be read by the control system 214 and used as a basis for generating control signals for one or more of the various controllable subsystems of the agricultural harvesting machine 100, such as indicated by block 296.

The control zone generator 213 may divide the predictive map 264 into control zones based on the values on the predictive map 264 . Continuously geolocated values that are within a threshold of each other can be grouped into a tax zone. The threshold may be a default threshold, or the threshold may be set based on operator input, based on input from an automated system, or based on other criteria. A size of the zones may be based on a responsiveness of the control system 214, the controllable subsystems 216 based on wear considerations, or other criteria, as indicated by block 295. The predictive map generator 212 configures the predictive map 264 for presentation to an operator or other user. The control zone generator 213 can configure a predictive control zone map 265 for presentation to an operator or other user. Block 299 indicates this. When presented to an operator or other user, the presentation of predictive map 264 or predictive control zone map 265, or both, may contain one or more of the predictive values on predictive map 264 that are correlated to the geographic location, the control zones on the predictive Control zone map 265 correlated to geographic location and containing adjustment values or control parameters used based on the predicted values on map 264 or the zones on predictive control zone map 265. In another example, the presentation may include more abstracted information or more detailed information. The presentation may also include a confidence level indicating an accuracy with which the predicted values on the predictive map 264 or the zones on the predictive control zone map 265 match measured values that can be measured by sensors on the agricultural harvesting machine 100 when moving the agricultural harvesting machine 100 through the field. Furthermore, an authentication and authorization system can be provided that implements authentication and authorization processes when information is presented at multiple locations. For example, there may be a hierarchy of people who are authorized to view and change maps and other presented information. For example, an onboard display device may display the maps locally on the machine in near real time, or the maps may also be generated at one or more remote locations, or both. In some examples it can each physical display device at each location may be associated with a person or user authorization level. The user privilege level can be used to determine what indicator is visible on the physical display device and what values that person can change. For example, a local operator of agricultural harvesting machine 100 may not be able to view the information corresponding to predictive map 264 or make changes to machine operation. However, a supervisor, such as a supervisor at a remote location, can see the predictive map 264 on the display but be prevented from making changes. A manager, who may be at a separate remote location, may be able to see all of the items on the predictive map 264 and may also be able to change the predictive map 264. In some cases, the predictive map 264, accessible and modifiable by a remote manager, can be used in machine control. This is an example of an authorization hierarchy that can be implemented. The predictive map 264 or the predictive control zone map 265 or both can also be configured in other ways, as indicated by block 297 .

At block 298, inputs from the geographic position sensor 204 and other in situ sensors 208 are received by the control system. In particular, at block 300 the control system 214 detects an input from the geographic position sensor 204 identifying a geographic position of the agricultural harvester 100 . Block 302 represents the receipt by the control system 214 of sensor inputs indicative of the trajectory or heading of the agricultural harvester 100, and Block 304 represents the receipt by the control system 214 of a speed of the agricultural harvester 100. Block 306 represents the receipt of other information from various in situ sensors 208 by the control system 214.

At block 308 the control system 214 generates control signals to control the controllable subsystems 216 based on the predictive map 264 or the predictive control zone map 265 or both and the input from the geographic position sensor 204 and any other in situ sensors 208 . At block 310, the control system 214 applies the control signals to the controllable subsystems. It is understood that the particular control signals that are generated and the particular controllable subsystems 216 that are controlled may vary based on one or more different things. For example, the control signals generated and the controllable subsystems 216 that are controlled may be based on the type of predictive map 264 or predictive control zone map 265 or both used. Likewise, the control signals generated and the controllable subsystems 216 that are controlled and the timing of the control signals may be based on various latencies of crop flow through the agricultural harvesting machine 100 and the responsiveness of the controllable subsystems 216.

For example, a generated predictive map 264 in the form of a predictive performance map may be used to control one or more subsystems 216 . For example, the predictive performance map may include power consumption demand values that are georeferenced to locations within the field to be harvested. The power consumption demand values from the predictive performance map can be extracted and used to control the steering and propulsion subsystems 252 and 250 . By controlling the steering and propulsion subsystems 252 and 250, a rate of travel of material moving through the agricultural harvesting machine 100 can be controlled. Similarly, the height of the header can be controlled to accommodate more or less material, and thus the height of the header can also be controlled to control the rate of advance of material through the agricultural harvester 100 . In other examples, when the predictive map 264 maps the predicted header power consumption to positions in the field, power allocation to the header can be implemented. For example, if the values present in the predictive performance map indicate one or more areas of higher power consumption needs for the header subsystems, then the header and reel controller 238 may allocate more power from the engine to the header subsystems, causing the allocation of requiring less power to other subsystems, such as by reducing speed and reducing power to the propulsion subsystem. The preceding example of header control using a predictive performance map is provided as an example only. Consequently, a variety of other control signals may be generated using values obtained from a predictive performance map or other type of predictive map to control one or more of the controllable subsystems 216 .

At block 312, it is determined whether the harvesting operation has been completed. If harvesting is not complete, processing continues at block 314 where in situ sensor data from the geo graphical position sensor 204 and in situ sensors 208 (and possibly other sensors) continue to be read.

In some examples, at block 316, agricultural harvester 100 may also recognize learning trigger criteria to perform machine learning on one or more of predictive map 264, predictive control zone map 265, the model generated by predictive model generator 210, the zones generated by generated by control zone generator 213, one or more control algorithms implemented by controllers in control system 214, and other triggered learning.

The learning trigger criteria can contain a large number of different criteria. Some examples of detecting trigger criteria are discussed with respect to blocks 318, 320, 321, 322, and 324. For example, in some examples, the triggered learning may include restoring a relationship used to generate a predictive model when a threshold amount of in situ sensor data is obtained from the in situ sensors 208 . In such examples, receipt of an amount of in situ sensor data from in situ sensors 208 that exceeds a threshold triggers or causes predictive model generator 210 to generate a new predictive model used by predictive map generator 212 will. Thus, as agricultural harvester 100 continues a harvesting operation, receipt of the threshold amount of in situ sensor data from in situ sensors 208 triggers the generation of a new relationship represented by a predictive model generated by predictive model generator 210 is produced. Furthermore, the new predictive map 264, the predictive control zone map 265, or both can be regenerated using the new predictive model. Block 318 represents detecting a threshold set of in situ sensor data used to trigger creation of a new predictive model.

In other examples, the learning trigger criteria may be based on how much the in situ sensor data from the in situ sensors 208 is changing, such as over time or compared to previous values. For example, if deviations within the in situ sensor data (or the relationship between the in situ sensor data and the information in information card 258) are within a selected range or are less than a defined amount or below a threshold, then no new predictive model generated by the predictive model generator 210. As a result, the predictive map generator 212 does not generate a new predictive map 264, predictive control zone map 265, or both. However, if deviations within the in situ sensor data are outside the selected range, are greater than the defined amount, or are above the threshold, for example, the predictive model generator 210 generates a new predictive model using all or part of the newly received in situ Sensor data that the predictive map generator 212 uses to generate a new predictive map 264 . At block 320, variations in the in situ sensor data, such as a magnitude of an amount by which the data exceeds the selected range or a magnitude of the variation in the relationship between the in situ sensor data and the information in information map 258, used as a trigger to cause the generation of a new predictive model and map. Keeping the examples described above, the threshold, range and defined amount can be set to default values; set by an operator or user interaction via a user interface; set by an automated system; or adjusted in any other way.

Other learning trigger criteria can also be used. For example, if the predictive model generator 210 switches to a different information card (different from the originally selected information card 258), switching to the different information card may require relearning by the predictive model generator 210, the predictive card generator 212, the control zone generator 213, the Trigger control system 214 or other elements. In a further example, the transition of the agricultural harvesting machine 100 to a different topography or to a different control zone can also be used as learning trigger criteria.

In some cases, operator 260 may also edit predictive map 264 or predictive control zone map 265, or both. The edits may change a value on predictive map 264, a size, shape, location, or presence of a control zone on predictive control zone map 265, or both. Block 321 shows that processed information can be used as learning trigger criteria.

Also, in some cases, the operator 260 may observe that automated control of a controllable subsystem is not what the operator desires. In such cases, the operator 260 may provide the controllable sub-system with a manual adjustment that reflects that the operator 260 desires the controllable sub-system to operate differently than from control system 214 is commanded. Thus, a manual change of a setting by the operator 260 may cause one or more of the predictive model generator 210 to relearn a model, the predictive map generator 212 to regenerate the map 264, the control zone generator 213 to create one or more control zones on the regenerate predictive control zone map 265, and control system 214 to relearn a control algorithm or perform machine learning on one or more of control components 232-246 in control system 214 based on adjustment by operator 260, as shown in block 322. Block 324 represents the use of other triggered learning criteria.

In other examples, relearning may be performed periodically or intermittently, for example based on a selected time interval, such as a discrete time interval or a variable time interval, as indicated by block 326 .

When relearning is triggered, whether based on learning trigger criteria or based on the passage of a time interval, as indicated by block 326, one or more of the predictive model generator 210, the predictive map generator 212, the control zone generator 213 and the control system 214 performs machine learning to generate a new predictive model, map, control zone, or control algorithm based on the learning trigger criteria. The new predictive model, map and control algorithm are generated using additional data collected since the last learning. Performing the relearn is indicated by block 328 .

When the harvesting process has been completed, the process proceeds from block 312 to block 330 where one or more of the predictive map 264, the predictive control zone map 265, and the predictive model generated by the predictive model generator 210 are stored. The predictive map 264, predictive control zone map 265, and predictive model may be stored locally on data storage 202 or sent to a remote system using communication system 206 for later use.

It should be noted that while some examples herein describe the predictive model generator 210 and the predictive map generator 212 showing an information map when generating a predictive model or receiving a functional predictive map, the predictive model generator 210 and the predictive map generator 212 in other examples when generating a predictive model and a functional predictive map, each may receive different types of maps including predictive maps such as a functional predictive map generated during the harvesting process.

4 is a block diagram of a portion of the in 1 shown agricultural harvesting machine 100. In particular 4 among other things, examples of the predictive model generator 210 and the predictive map generator 212 in more detail. 4 also illustrates the flow of information between the various components that are shown. The predictive model generator 210 receives one or more of a vegetative index map 332, a crop moisture map 335, a topographical map 337, a soil property map 339, a predictive yield map 341, or a predictive biomass map 343 as an information map. The vegetative index map 332 contains georeferenced vegetative index values. The crop moisture map 335 includes georeferenced crop moisture values. Topographic map 337 includes georeferenced topographic feature values. The soil property map 339 contains georeferenced soil property values.

The predictive yield map 341 includes georeferenced predictive yield values. The predictive yield map 341 can be made using one of the 2 and 3 described process, wherein the information map includes a vegetative index map or a historical yield map and the in situ sensor includes a yield sensor. The predictive yield map 341 can also be generated in other ways.

The predictive biomass map 343 includes georeferenced predictive biomass values. The predictive biomass map 343 can use one of the in the 2 and 3 described process wherein the information map includes a vegetative index map and the in situ sensor includes a rotor drive pressure or an optical sensor that generate sensor signals indicative of biomass. The predictive biomass map 343 can also be generated in other ways.

The predictive model generator 210 also receives a geographic location 334 or an indication of geographic location from the geographic location sensor 204. The in situ sensors 208 include, by way of example, a performance sensor, such as the performance sensor 336, and a processing system 338. The performance sensor 336 senses performance characteristics one or more components of agricultural crops machine 100. In some cases, the power sensor 336 may be onboard the agricultural harvesting machine 100. FIG. Processing system 338 processes sensor data generated by power sensor 336 to generate processed data, some examples of which are described below. The power sensor 336 may include one or more of a voltage sensor, a current sensor, a torque sensor, a fluid pressure sensor, a fluid flow sensor, a force sensor, a bearing load sensor, and a rotation sensor, among others. The outputs of one or more of these or other sensors can be combined to determine one or more performance characteristics.

The present discussion continues with respect to an example where power sensor 336 is one or more of those listed above. It should be understood that these are only examples and other examples of the power sensor 336 are also contemplated. As in 4 shown, the example predictive model generator 210 includes one or more of a vegetative index performance trait model generator 342, crop moisture performance trait model generator 343, topographic performance trait model generator 344, soil trait performance trait model generator 345, yield performance trait model generator 346, biomass trait model generator 347. In other examples, the predictive model generator 210 include additional, fewer, or different components than those in the example of FIG 4 shown. Accordingly, in some examples, the predictive model generator 210 may also include other elements 348, which may include other types of predictive model generators to generate other types of performance models.

Model generator 342 identifies a relationship between a feature at a geographic location corresponding to where performance sensor 336 detected the feature and vegetative index values from vegetative index map 332 that correspond to the same location on the field where the feature was detected became. Based on this relationship established by the model generator 342, the model generator 342 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to map performance characteristics at various locations based on the georeferenced vegetative index values contained in the vegetative index card 332 are contained at the same positions in the field.

The model generator 343 identifies a relationship between a performance feature at a geographic location that corresponds to the location where the performance sensor 336 sensed the feature, and crop moisture values from the crop moisture map 335 that correspond to the same location in the field where the performance model was sensed . Based on this relationship established by the model generator 343, the model generator 343 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to predict performance characteristics at various locations based on the georeferenced crop draft moisture values contained in the crop draft moisture map 335 contained at the same positions in the array.

The model generator 344 identifies a relationship between a feature at a geographic location corresponding to the location where the power sensor 336 detected the feature and a topographical feature value from the topographical map 337 corresponding to the same location on the field where the feature was recorded. Based on this relationship established by the model generator 344, the model generator 344 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to generate performance features at various locations based on the georeferenced topographic feature values contained in the topographic Map 337 contained in the same positions in the field to predict.

The model generator 345 identifies a relationship between a feature at a geographic location corresponding to the location where the performance sensor 336 detected the feature and a soil property value from the soil property map 339 corresponding to the same location in the field where the feature was detected . Based on this relationship established by the model generator 345, the model generator 345 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to predict performance characteristics at various locations based on the soil property values contained in the soil property map 339 contained in the same positions in the field.

The model generator 346 identifies a relationship between a feature at a geographic location that corresponds to the location where the performance sensor 336 found the feature detected, and a yield value from yield map 341 corresponding to the same location in the field where the performance attribute was detected. Based on this relationship established by the model generator 346, the model generator 346 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to generate performance characteristics based on the yield value stored in the predictive yield map 341 at the same positions contained in the field to predict.

The model generator 347 identifies a relationship between a feature at a geographic location corresponding to the location where the power sensor 336 sensed the feature and a biomass value from the biomass map 343 corresponding to the same location on the field where the feature was sensed became. Based on this relationship established by the model generator 347, the model generator 347 generates a predictive performance model 350. The predictive performance model 350 is used by the predictive map generator 212 to generate performance characteristics at various locations based on the biomass value contained in the predictive biomass map 343 contained at the same positions in the field.

In view of the foregoing, predictive model generator 210 is operable to generate a variety of predictive performance models, such as one or more of the predictive performance models generated by model generators 342, 343, 344, 345, 346, and 347. In another example, two or more of the predictive performance models described above may be combined into a single predictive performance model that predicts two or more performance characteristics based on the different values at different locations in the array. Each of these performance models or combinations thereof are collectively represented by the performance model 350 in 4 shown.

The predictive performance model 350 is provided to the predictive map generator 212 . In the example of 4 the predictive map generator 212 includes a crop intervention component map generator 351, a header performance map generator 352, a feeder housing performance map generator 353, a threshing performance map generator 354, a separator performance map generator 355, a residue handling performance map generator 356, and a drive performance map generator 357. In other examples, the predictive map generator 212 may include additional, fewer, or different map generators. Thus, in some examples, the predictive map generator 212 may include other elements 358, which may include other types of map generators to generate performance maps for other types of features.

The crop intervention component map generator 351 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts the performance characteristics of a crop intervention component at various locations in the field. For example, the crop intervention components could include a cutter and a reel, and the crop intervention component map generator 351 generates a map of the estimated power consumption by the reel and the cutter based on a predictive performance model 350 that defines a relationship between crop moisture and power consumption by the reel and the cutter.

The header performance map generator 352 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographic map 337, the soil feature map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts header performance characteristics at various locations in the field. For example, the crop engagement components could include one or more of the following: a cutter, a reel, draper belts, augers, collection components, stalk processing components, and header positioning actuators, and the header performance map generator 352 generates a map of the estimated power consumption by one or more of the following: the reel, the cutter , draper belts, augers, collection components, stalk processing components, and header positioning actuators based on a predictive performance model 350 that defines a relationship between crop moisture and topography and power consumption by one or more of the reel, cutter, draper belts, auger, and header positioning actuators.

The feeder chassis performance map generator 353 receives the predictive performance model 350, that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that shows the performance characteristics of the feeder housing at various positions in the field.

The threshing performance map generator 354 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts the performance characteristics of the threshing subsystems at various positions in the field. For example, the threshing subsystems could include one or more threshing cylinders, concave adjustment actuators, and drums, and the threshing performance map generator 352 generates a map of the estimated power consumption by the one or more threshing cylinders, concave adjustment actuators, and drums based on a predictive performance model 350 that establishes a relationship between vegetative index and power consumption defined by the one or more threshing drums, concave adjustment actuators and drums. Or, for example, the threshing subsystems could include a threshing cylinder and a set of concaves at a given spacing, and the threshing performance map generator 352 generates a map of the estimated power consumption by the threshing cylinder with the set of concaves at the given spacing based on a predictive performance model 350, which defines a relationship between the predicted biomass and the power consumption by the threshing cylinder with the set of concaves at the given spacing. Or, for example, the threshing subsystems could include one or more drums in a given configuration, and the threshing performance map generator 352 generates a map of the estimated power consumption by the one or more drums in the given configuration based on a predictive performance model 350 that establishes a relationship between the predicted biomass and power consumption by the one or more drums in the given configuration.

The separator performance map generator 355 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts the performance characteristics of the separator subsystems at different locations in the field. For example, the separator subsystems could include one or more fans, screens, choppers, and straw walkers, and the predictive performance map generator 355 generates a map of the estimated power consumption by the one or more fans, screens, choppers, and straw walkers based on a predictive performance model 350 that defines a relationship between the predicted yield value and the power consumed by the one or more blowers, screens, choppers and straw walkers. For example, the separator subsystems could include one or more fans running at a given speed and screens, choppers, and straw walkers in a given configuration, and the separator performance map generator 355 generates a map of the estimated power consumption by the one or more fans running with running at the given speed, and sieves, choppers and straw walkers in the given configuration based on a predictive power model 350 that establishes a relationship between the predicted yield value and the power consumed by the one or more fans running at the given speed and sieves, choppers and straw walkers defined in the given configuration.

The residue handling performance map generator 356 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts the performance characteristics of the residue handling subsystems at various locations in the field. For example, the residue handling performance map generator 356 generates a map of the estimated power consumption by a residue distributor based on a predictive performance model 350 that defines a relationship between the predicted biomass value and the power consumption by the residue distributor. For example, the tailings handling performance map generator 356 generates a map of estimated power consumption by a tailings chopper based on a predictive performance model 350 that defines a relationship between predicted earned value and tailings chopper power consumption.

The drive performance map generator 357 receives the predictive performance model 350 that predicts performance characteristics based on values in one or more of the vegetative index map 332, the crop moisture map 335, the topographical map 337, the soil property map 339, the predictive yield map 341 or the predictive biomass map 343, and generates a predictive map that predicts the performance characteristics of the powertrain subsystems at different locations in the field. For example, the propulsion power map generator 357 generates a map of estimated power consumption by the propulsion subsystem based on a predictive performance model 350 that defines a relationship between topographical map value and power consumption by the propulsion system.

The predictive map generator 212 outputs one or more predictive performance maps 360 that are predictive of one or more performance characteristics. Each of the predictive performance maps 360 predicts the respective performance attribute at different positions in a field. Each of the generated predictive performance maps 360 may be provided to control zone generator 213, control system 214, or both. The control zone generator 213 generates control zones and integrates these control zones into the functional predictive map, i. H. the predictive map 360 to generate the predictive control zone map 265. One or both of predictive map 264 and predictive control zone map 265 may be provided to control system 214, which generates control signals to control one or more of controllable subsystems 216 based on predictive map 264, predictive control zone map 265, or both.

5 Figure 3 is a flowchart of an example of the operation of predictive model generator 210 and predictive map generator 212 in generating predictive performance model 350 and predictive performance map 360. At block 362, predictive model generator 210 and predictive map generator 212 receive one or more from a previous vegetative index map 332, a crop moisture map 335, a topographical map 337, a soil feature map 339, a predictive yield map 341, a predictive biomass map 343, or other map 363. At block 364, the processing system 338 receives one or more sensor signals from the power sensor 336. As discussed above, Power sensor 336 may include one or more of a voltage sensor 371, a current sensor 373, a torque sensor 375, a fluid pressure sensor 377, a fluid flow sensor 379, a force sensor 381, a bearing load sensor 383, a rotational sensor 385 or other type of power sensor 370.

At block 372, the processing system 338 processes the one or more received sensor signals to generate data indicative of a performance. As indicated by block 374, the feature may be identified at a machine-wide level. For example, the total power consumption of the entire agricultural harvesting machine. Power consumption at this level can be used to calculate fuel economy, efficiency, and so on. As indicated in block 376, the feature may be identified at a subsystem level. A feature at this level can be used, for example, to allocate power to subsystems. As indicated by block 378, the feature may be identified at a component level. The sensor data may also include other data at other levels indicated by block 380.

At block 382, the predictive model generator 210 also obtains the geographic position corresponding to the sensor data. For example, the predictive model generator 210 may obtain the geographic position from the geographic position sensor 204 and determine an accurate geographic position based on machine delays, machine speed, etc. where the sensor data 340 was sensed or derived.

At block 384, the predictive model generator 210 generates one or more predictive performance models, such as the performance model 350, that represents a relationship between a vegetative index value, a crop moisture value, a soil property value, a predictive yield value, or a predictive biomass value derived from an information map, such as the information map 258 obtained and a performance characteristic detected by the in situ sensor 208 model. For example, the predictive model generator 210 may generate a predictive performance model that models the relationship between a vegetative index value and a sensed feature including the performance usage indicated by the sensor data obtained from the in situ sensor 208 .

At block 386, the predictive performance model, such as predictive performance model 350, is provided to predictive map generator 212, which generates a predictive performance map 360 that includes a predictive performance trait based on a vegetative index map, a crop moisture map, a soil property map, a predictive yield map, or a predictive biomes se map and the predictive performance model 350 . For example, in some examples, the predictive performance map 360 predicts the power consumption/requirements of various subsystems. Furthermore, the predictive performance map 360 may be generated during the course of a farming operation. Thus, when an agricultural harvester moves through a field in which a farming operation is being performed, the predictive performance map 360 is generated while the farming operation is being performed.

At block 394 , the predictive map generator 212 outputs the predictive performance map 360 . At block 391, the predictive performance map generator 212 outputs the predictive performance map for presentation to and possible interaction by the operator 260. At block 393, the predictive map generator 212 may configure the map for the control system 214 to consume. At block 395, the predictive map generator 212 may also provide the map 360 to the control zone generator 213 for generating control zones. At block 397, predictive map generator 212 configures map 360 in other ways as well. The predictive performance map 360 (with or without the control zones) is provided to the control system 214 . At block 396 , the control system 214 generates control signals to control the controllable subsystems 216 based on the predictive performance map 360 .

Thus, it can be seen that the present system creates an information map that maps a trait, such as a vegetative index value, a crop moisture value, a soil property value, a predicted yield value or a predicted biomass value, or information from a preliminary run to various positions in a field. The present system also uses one or more in situ sensors that collect in situ sensor data indicative of a performance characteristic, such as power consumption, power demand, power efficiency, or power loss, and creates a model that expresses a relationship between the In situ sensor detected feature or a related feature and the feature depicted in the information map. Thus, the present system generates a functional predictive map using a model, in situ data, and an information map, and can configure the generated predictive map for consumption by a control system for presentation to a local or remote operator or other user, or both. For example, the control system can use the map to control one or more systems of a combine.

Processors and servers have been mentioned in this discussion. In one example, the processors and servers include computer processors with associated memory and timing circuitry, not shown separately. The processors and servers are functional parts of the systems or devices that the processors and servers belong to and are activated by, and facilitate the functionality of the other components or elements in those systems.

A number of user interface displays were also discussed. The displays can take a number of different forms and can have a number of different user controlled operator interface mechanisms thereon. For example, the user-actuable operator interface mechanisms may include text boxes, check boxes, icons, links, drop-down menus, search boxes, and so on. The user actuatable operator interface mechanisms can also be actuated in a variety of ways. For example, the user actuable operator interface mechanisms can be operator interface mechanisms such as a point-and-click device, a trackball or mouse, hardware buttons, switches, a joystick or keyboard, thumb switches or thumbpads, etc., a virtual keyboard or other virtual Actuators are actuated. In addition, when the screen on which the user actuable operator interface mechanisms are displayed is a touch-sensitive screen, the user actuable operator interface mechanisms can be actuated with touch gestures. User actuatable operator interface mechanisms can also be actuated using voice commands with speech recognition functionality. Speech recognition can be implemented using a speech recognition device, such as a microphone, and software operable to recognize speech and execute commands based on the received speech.

A number of data stores were also discussed. It is pointed out that the data stores can each be divided into several data stores. In some examples, one or more of the data stores may be local to systems accessing the data stores, one or more of the data stores may be remote from a system using the data store, or one or more data stores may be local while others are remote. All of these configurations are contemplated by the present disclosure.

In addition, the figures show a series of blocks with functions associated with each block. It is noted that fewer blocks may be used to illustrate that functionality assigned to multiple different blocks is performed by fewer components. More blocks can also be used, illustrating that functionality can be distributed across multiple components. In different examples, some functionality may be added and some may be removed.

It should be noted that the discussion above has described a variety of different systems, components, logic and interactions. It is understood that any or all such systems, components, logic, and interactions are powered by hardware elements, such as processors, memory, or other processing components, including but not limited to artificial intelligence components, such as neural networks, some of which are detailed below described can be implemented that perform the functions associated with these systems, components, logics or interactions. In addition, any or all of the systems, components, logic, and interactions may be implemented by software loaded into memory and then executed by a processor or server or other computing component, as described below. Any or all of the systems, components, logic, and interactions may also be implemented through various combinations of hardware, software, firmware, etc., some examples of which are described below. These are some examples of different structures that can be used to implement any or all of the systems, components, logic, and interactions described above. Other structures can also be used.

6 12 is a block diagram of agricultural harvester 600 used in FIG 2 shown agricultural harvesting machine 100 may be similar. Agricultural harvester 600 communicates with elements in a remote server architecture 500. In some examples, remote server architecture 500 provides computing, software, data access, and storage services that do not require end-user knowledge of the physical location or configuration of the system that provides the Services. In various examples, remote servers may provide the services over a wide area network, such as the Internet, using appropriate protocols. For example, remote server applications can be deployed over a wide area network and accessed through a web browser or other computer component. Software or components included in 2 shown and related data may be stored on servers at a remote location. The computing resources in a remote server environment can be consolidated at a remote data center site or distributed to a variety of remote data centers. Remote server infrastructures can provide services across shared data centers, although the services appear to the user as a single point of entry. Thus, the components and functions described herein can be provided from a remote server at a remote site via a remote server architecture. Alternatively, the components and functions may be provided by a server, or the components and functions may be installed directly or otherwise on end devices.

in the in 6 example shown are some elements of some of the in 2 items shown are similar and those items are numbered similarly. 6 FIG. 12 specifically shows that the predictive model generator 210 or the predictive map generator 212 or both may be located at a server location 502 that is remote from the agricultural harvester 600. FIG. Therefore engages in the in 6 For example, as shown, agricultural harvester 600 approaches systems via remote server location 502 .

6 also shows another example of a remote server architecture. 6 shows that some elements of 2 may be located at a remote server location 502 while others may be located elsewhere. For example, data store 202 may be located at a separate site from site 502 and accessed through the remote server at site 502 . Regardless of where the elements are located, the elements can be accessed directly by the agricultural harvester 600 over a network, such as a wide area network or a local area network; the items may be hosted at a remote location by a service; or the items may be provided as a service or accessed via a connection service located at a remote location. In addition, data can be stored at any location and the stored data can be retrieved or forwarded to operators, users or systems. For example, physical carriers can be used instead of or in addition to electromagnetic radiation carriers. In some examples where network coverage is poor or is not available, another machine, e.g. a tank truck or other mobile machine or vehicle, have an automatic, semi-automatic or manual information collection system. When the combine harvester apparatus 600 gets close to the machine containing the information gathering system, such as a tanker truck, prior to refueling, the information gathering system collects the information from the combine harvester 600 via any ad hoc wireless link. The information collected may then be relayed to another network when the machine containing the received information reaches a location where wireless telecommunications service coverage or other wireless coverage is available. For example, a fuel truck may enter an area that has wireless communications coverage when it is traveling to a location to fuel other machines, or when it is at a main fuel depot. All of these architectures are considered herein. Furthermore, the information may be stored in the agricultural harvester 600 until the agricultural harvester 600 reaches an area of wireless communication coverage. The agricultural harvester 600 itself can send the information to another network.

It is also noted that the elements of 2 or portions thereof may be located on a variety of different devices. One or more of these devices may include an on-board computer, electronic control unit, display unit, server, desktop computer, laptop computer, tablet computer, or other mobile device, such as a palmtop computer, a mobile phone, a smartphone , a multimedia player, a personal digital assistant, etc.

In some examples, the remote server architecture 500 may include cyber security measures. Without limitation, these measures may include encryption of data on storage devices, encryption of data sent between network nodes, authentication of individuals or processes accessing data, and use of ledgers to record metadata, data, data transfers, data access and involve data transformations. In some examples, the ledgers may be distributed and immutable (eg, implemented as a blockchain).

7 16 is a simplified block diagram of an illustrative example of a portable or mobile computing device that may be used as a user's or customer's portable terminal 16 in which the present system (or portions thereof) may be deployed. For example, a mobile device may be deployed in the cab of agricultural harvester 100 to generate, process, or display the maps discussed above. the 8-9 are examples of portable or mobile devices.

7 provides a general block diagram of the components of a terminal device 16, including some of the 2 components shown that interact with them, or both. A communications link 13 is provided in device 16, enabling the portable device to communicate with other computing devices and, in some examples, providing a channel for automatically receiving information, such as by scanning. Examples of communication links 13 include allowing communication over one or more communication protocols, such as wireless services used to provide cellular access to a network, and protocols that provide local wireless connections to networks.

In other examples, applications may be received on a removable Secure Digital (SD) card connected to an interface 15 . Interface 15 and communications links 13 communicate with a processor 17 (which may also embody the processors or servers of the other FIGS.) via a bus 19 which is also connected to memory 21 and input/output (I/O) components 23 and the clock 25 and the locating system 27 is connected.

I/O components 23 are provided in one example to facilitate input and output operations. I/O components 23 for various examples of terminal device 16 may include input components such as buttons, tactile sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometer sensors, orientation sensors, and output components such as a display, speaker, and/or printer port . Other I/O components 23 can also be used.

Clock 25 illustratively includes a real-time clock component that outputs a time and date. This may also provide timing functions for processor 17, illustratively.

The location system 27 illustratively includes a component that outputs a current geographic position of the device 16 . This may include, for example, a global positioning system (GPS) receiver, a LORAN system, a dead reckoning system, a cellular triangulation system, or other positioning system. For example, location system 27 may also include mapping or navigation software that generates desired maps, navigation routes, and other geographic features.

Memory 21 stores operating system 29, network settings 31, applications 33, application configuration settings 35, data storage 37, communication drivers 39, and communication configuration settings 41. Memory 21 may include all types of tangible volatile and non-volatile computer-readable storage devices. Memory 21 may also include computer storage media (see below). Memory 21 stores computer-readable instructions that, when executed by processor 17, cause the processor to perform computer-implemented steps or functions in accordance with the instructions. The processor 17 can be activated by other components to enhance their functionality as well.

8th FIG. 12 shows an example in which the terminal 16 is a tablet computer 600. FIG. In 8th the computer 600 is shown with the user interface screen 602 . The screen 602 can be a touch screen or a pen-enabled interface that receives input from a pen or stylus. The tablet computer 600 can also use a virtual on-screen keyboard. Of course, the computer 600 can also be connected to a keyboard or other user input device via any suitable attachment mechanism, such as a wireless connection or a USB port. Computer 600 may also illustratively receive voice input.

9 is similar to that 8th except that the device is a smartphone 71 . The smartphone 71 has a touch-sensitive display 73 that displays icons or graphics or other user input mechanisms 75 . The mechanisms 75 can be used by a user to run applications, make calls, perform data transfer operations, etc. In general, the smartphone 71 is built on top of a mobile operating system and offers more advanced computing power and connectivity than a feature phone.

It should be noted that other shapes of devices 16 are possible.

10 is an example of a computing environment in which elements of 2 can be used. With reference to 10 An exemplary system for implementing some embodiments includes a computing device in the form of a computer 810 programmed to operate as discussed above. The components of the computer 810 may include, but are not limited to, a processing unit 820 (which may include processors or servers from the preceding FIGURES), a system memory 830, and a system bus 821 that connects various system components including the system memory to the processing unit 820 couple. The system bus 821 can be any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, and a local bus with a variety of bus architectures. Memory and programs related to 2 may be described in appropriate parts of 10 be used.

Computer 810 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by the computer 810 and includes both volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, computer-readable media can include computer storage media and communications media. Computer storage media is distinct from and does not include a modulated data signal or carrier wave. Computer-readable media includes hardware storage media, having volatile and non-volatile, removable and non-removable media, implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computational storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other storage technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridge, tape, disk storage or other magnetic storage device, or any other medium that can be used to store the desired information accessible via computer 810. Communication media may contain computer-readable instructions, data structures, program modules, or other data in a transport mechanism and includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its Features are set or changed so that information is encoded in the signal.

System memory 830 includes computer storage media in the form of volatile and/or non-volatile memory, or both, such as read-only memory (ROM) 831 and random access memory (RAM) 832. A basic input/output system 833 (BIOS) that contains the basic programs that help To transfer information between elements within the computer 810, such as at startup, is typically stored in ROM 831. RAM 832 typically contains data or program modules, or both, that are immediately accessible to processing unit 820 and/or are currently operating. By way of example and not by way of limitation 10 the operating system 834, the application programs 835, further program modules 836 and the program data 837.

Computer 810 may also include other removable/non-removable volatile/non-volatile computer storage media. For example, in 10 illustrates a hard disk drive 841, by way of example only, reading from or writing to non-removable, non-volatile magnetic media, an optical disk drive 855, and a non-volatile optical disk 856. Hard disk drive 841 is typically connected to system bus 821 via a non-removable storage interface, such as interface 840, and optical disk drive 855 is typically connected to system bus 821 via a removable storage interface, such as interface 850.

Alternatively or additionally, the functionality described herein may be performed at least in part by one or more hardware logic components. Illustrative types of hardware logic components that may be used include, for example, field-programmable gate arrays (FPGAs), application-specific integrated circuits (e.g., ASICs), off-the-shelf application-specific products (e.g., ASSPs), system -on-a-chip systems (SOCs), "Complex Programmable Logic Devices" (CPLDs), etc.

The drives and associated computer storage media discussed above and in 10 , provide storage for computer 810 of computer-readable instructions, data structures, program modules, and other data. In 10 For example, the hard disk 841 is shown as the storing operating system 844, application programs 845, other program modules 846 and program data 847. It should be noted that these components may be either the same as or different from the operating system 834, application programs 835, other program modules 836, and program data 837.

A user may enter commands and information into the computer 810 through input devices such as a keyboard 862, a microphone 863, and a pointing device 861 such as a mouse, trackball, or touchpad. Other input devices (not shown) may include a joystick, gamepad, satellite dish, scanner, or the like. These and other input devices are often connected to the processing unit 820 via a user input interface 860, which is coupled to the system bus, but may also be connected via other interface and bus structures. A visual display 891 or other type of display device is also connected to the system bus 821 via an interface such as a video interface 890 . In addition to the monitor, computers may also include other peripheral output devices, such as speakers 897 and printer 896, which may be connected via an output peripheral interface 895.

Computer 810 operates in a network environment via logical connections (such as CAN, LAN, or WAN) to one or more remote computers, such as remote computer 880.

When used in a LAN network environment, the computer 810 is connected to the LAN 871 via a network interface or adapter 870 . When used in a WAN network environment, the computer 810 typically includes a modem 872 or other means for establishing communication over the WAN 873, such as the Internet. In a networked environment, program modules may be stored on an external storage device. 10 FIG. 12 shows, for example, that remote application programs 885 can reside on remote computer 880. FIG.

It should also be noted that the various examples described herein can be combined in different ways. That is, portions of one or more examples may be combined with portions of one or more other examples. All of these are considered here.

• [0139] ein Kommunikationssystem, das eine Informationskarte empfängt, die Werte eines ersten landwirtschaftlichen Merkmals beinhaltet, die verschiedenen geografischen Positionen in einem Feld entsprechen;
• [0140] einen geografischen Positionssensor, der eine geografische Position der landwirtschaftlichen Arbeitsmaschine erfasst;
• [0141] einen In-situ-Sensor, der einen Wert eines Leistungsmerkmals der landwirtschaftlichen Arbeitsmaschine als ein zweites landwirtschaftliches Merkmal erkennt, das der geografischen Position entspricht;
• [0142] einen prädiktiven Modellgenerator, der ein prädiktives landwirtschaftliches Modell erzeugt, das eine Beziehung zwischen dem ersten landwirtschaftlichen Merkmal und dem zweiten landwirtschaftlichen Merkmal auf Grundlage eines Werts des ersten landwirtschaftlichen Merkmals in der Informationskarte an der geografischen Position und des Werts des zweiten landwirtschaftlichen Merkmals modelliert, das durch den In-situ-Sensor an der geografischen Position erfasst wird; und
• [0143] einen prädiktiven Kartengenerator, der eine funktionelle prädiktive landwirtschaftliche Karte des Feldes erzeugt, die prädiktive Werte des zweiten landwirtschaftlichen Merkmals auf Grundlage der Werte des ersten landwirtschaftlichen Merkmals in der Informationskarte und auf Grundlage des prädiktiven landwirtschaftlichen Modells auf die verschiedenen geografischen Positionen in dem Feld abbildet.

Example 1 is an agricultural working machine comprising:

• [0139] a communication system that receives an information map that includes values of a first agricultural characteristic that correspond to different geographic positions in a field;
• [0140] a geographical position sensor that detects a geographical position of the agricultural working machine;
• [0141] an in situ sensor that detects a value of a performance attribute of the agricultural work machine as a second agricultural attribute that corresponds to the geographic location;
• [0142] a predictive model generator that generates a predictive agricultural model that models a relationship between the first agricultural feature and the second agricultural feature based on a value of the first agricultural feature in the information map at the geographical position and the value of the second agricultural feature , which is detected by the in situ sensor at the geographic position; and
• a predictive map generator that generates a functional predictive agricultural map of the field that applies predictive values of the second agricultural feature based on the values of the first agricultural feature in the information map and based on the predictive agricultural model to the different geographical positions in the field depicts.

Example 2 is the agricultural work machine of any or all of the preceding examples, wherein the predictive map generator configures the functional predictive agricultural map for consumption by a control system that generates control signals to control a controllable subsystem on the agricultural work machine based on the functional predictive agricultural map .

Example 3 is the agricultural work machine of any or all of the preceding examples, wherein the in situ sensor on the agricultural work machine is configured to detect power consumption of one or more subsystems corresponding to the geographic location as the value of the second agricultural characteristic.

Example 4 is the agricultural work machine of any or all of the preceding examples, wherein the in situ sensor includes one or more of a voltage sensor, a current sensor, a torque sensor, a fluid pressure sensor, a fluid flow sensor, a force sensor, a bearing load sensor, and a rotation sensor.

Example 5 is the agricultural work machine of any or all of the preceding examples, wherein the information map comprises a vegetative index map that maps vegetative index values to the various geographic locations in the field as the first agricultural feature.

Example 6 is the agricultural work machine of any or all of the preceding examples, wherein the predictive model generator is configured to generate a relationship between the performance attribute and the vegetative index based on the performance attribute value recognized at the geographic location and the vegetative index value in the vegetative index map at the geographic location, wherein the predictive agricultural model is configured to receive an input vegetative index value as a model input and to generate a predicted performance attribute value as a model output based on the identified relationship.

Example 7 is the agricultural work machine of any or all of the preceding examples, wherein the information map comprises a crop moisture map that maps crop moisture values to the various geographic locations in the field as the first agricultural characteristic.

Example 8 is the agricultural work machine of any or all of the preceding examples, wherein the predictive model generator is configured to generate a relationship between the performance attribute and crop moisture based on the performance attribute value recognized at the geographic location and the crop moisture value in the crop moisture map at the geographic location identify position, wherein the predictive model is configured to receive an input crop moisture value as a model input and to generate a predicted performance attribute value as a model output based on the identified relationship.

Example 9 is the agricultural work machine of any or all of the preceding examples, wherein the information map includes a predictive yield map that maps predictive yield values to the various geographic locations in the field as the first agricultural feature, and wherein the predictive model generator is configured to establish a relationship between the identify predictive yield and the performance attribute based on the performance attribute value detected at the geographic location and the yield value in the predictive yield map at the geographic location, the predictive agricultural model being configured to: receive an input predicted earned value as a model input; and generate a predicted performance attribute value as a model output based on the identified relationship.

Example 10 is the agricultural work machine of any or all of the preceding examples, wherein the information map includes a predictive biomass map that maps predictive biomass values to the various geographic locations in the field as the first agricultural feature, and wherein the predictive model generator is configured to establish a relationship between the identify predictive biomass and the performance attribute based on the performance attribute value detected at the geographic location and the biomass value in the predictive biomass map at the geographic location, wherein the predictive agricultural model is configured to receive an input predictive biomass value as model input and a predicted performance attribute value as generate model output based on the identified relationship.

Example 11 is the agricultural work machine of any or all of the preceding examples, wherein the informational map comprises a topographic map having as a first agricultural feature topographical feature values mapped to the various geographic locations in the field, and wherein the predictive model generator is configured to establish a relationship between the identify the topographical feature and the feature based on the feature value detected at the geographic location and the topographical value in the topographic map at the geographic location, wherein the predictive agricultural model is configured to receive an input topographical feature value as a model input and a predicted one generate feature value as a model output based on the identified relationship.

• Empfangen einer Informationskarte in einer landwirtschaftlichen Arbeitsmaschine, die Werte eines ersten landwirtschaftlichen Merkmals angibt, die verschiedenen geografischen Positionen in einem Feld entsprechen;
• Erfassen einer geografischen Position der landwirtschaftlichen Arbeitsmaschine;
• Erkennen eines Leistungsmerkmalwerts mit einem In-situ-Sensor als ein zweites landwirtschaftliches Merkmal, das der geografischen Position entspricht;
• Erzeugen eines prädiktiven landwirtschaftlichen Modells, das eine Beziehung zwischen dem ersten landwirtschaftlichen Merkmal und dem zweiten landwirtschaftlichen Merkmal modelliert; und
• Steuern eines prädiktiven Kartengenerators, um die funktionelle prädiktive landwirtschaftliche Karte des Feldes zu erzeugen, die prädiktive Werte des zweiten landwirtschaftlichen Merkmals auf Grundlage der Werte des ersten landwirtschaftlichen Merkmals in der Informationskarte und des prädiktiven landwirtschaftlichen Modells zuordnet.

Example 12 is a computer-implemented method for generating a functional predictive agricultural map, comprising:

• receiving, at an agricultural work machine, an information map indicating values of a first agricultural characteristic corresponding to different geographic locations in a field;
• detecting a geographical position of the agricultural working machine;
• detecting a performance attribute value with an in situ sensor as a second agricultural attribute corresponding to the geographic location;
• creating a predictive agricultural model that models a relationship between the first agricultural trait and the second agricultural trait; and
• controlling a predictive map generator to generate the functional predictive agricultural map of the field assigning predictive values of the second agricultural feature based on the values of the first agricultural feature in the information map and the predictive agricultural model.

• Konfigurieren der funktionellen prädiktiven landwirtschaftlichen Karte für ein Steuersystem, das Steuersignale erzeugt, um ein steuerbares Teilsystem auf der landwirtschaftlichen Arbeitsmaschine auf Grundlage der funktionellen prädiktiven landwirtschaftlichen Karte zu steuern.

Example 13 is the computer-implemented method of any or all of the preceding examples, further comprising:

• configuring the functional predictive agricultural map for a control system that generates control signals to control a controllable subsystem on the agricultural work machine based on the functional predictive agricultural map.

Example 14 is the computer-implemented method of any or all of the preceding examples, wherein detecting a performance attribute value as a second agricultural attribute with an in situ sensor includes detecting a power consumption demand of a subsystem of the agricultural work machine that corresponds to the geographic location.

Example 15 is the computer-implemented method of any or all of the preceding examples, wherein detecting a performance attribute value with an in situ sensor as a second agricultural attribute includes detecting a power consumption demand of a component of the subsystem that corresponds to the geographic location.

• Empfangen einer Informationskarte, die von einem vorherigen Vorgang erzeugt wurde, der im Feld durchgeführt wurde.

Example 16 is the computer-implemented method of any or all of the preceding examples, wherein receiving an information card comprises:

• Receiving an information map generated from a previous operation performed in the field.

Example 17 is the computer-implemented method of any or all of the preceding examples, wherein the first agricultural trait comprises one of: a vegetative index, a crop moisture, a topographi cal trait, a soil property, a predictive yield and a predictive biomass.

• Steuern eines Bedienerschnittstellenmechanismus, um die prädiktive landwirtschaftliche Karte zu präsentieren.

Example 18 is the computer-implemented method of any or all of the preceding examples, further comprising:

• Controlling an operator interface mechanism to present the predictive agricultural map.

• ein Kommunikationssystem, das eine Informationskarte empfängt, die landwirtschaftliche Merkmalswerte angibt, die verschiedenen geografischen Positionen in einem Feld entsprechen;
• einen geografischen Positionssensor, der eine geografische Position der landwirtschaftlichen Arbeitsmaschine erfasst;
• einen In-situ-Sensor, der einen Leistungsmerkmalswert eines Leistungsmerkmals erkennt, der der geografischen Position entspricht;
• einen prädiktiven Modellgenerator, der ein prädiktives Leistungsmodell erzeugt, das eine Beziehung zwischen den landwirtschaftlichen Merkmalswerten und dem Leistungsmerkmal auf Grundlage eines landwirtschaftlichen Merkmalswerts in der Informationskarte an der geografischen Position und des Leistungsmerkmalwerts des Leistungsmerkmals modelliert, das durch den In-situ-Sensor an der geografischen Position erfasst wird; und
• einen prädiktiven Kartengenerator, der eine funktionelle prädiktive Leistungskarte des Feldes erzeugt, die prädiktive Leistungskennwerte auf Grundlage der landwirtschaftlichen Kennwerte in der Informationskarte und auf Grundlage des prädiktiven Leistungsmodells auf die verschiedenen Positionen in dem Feld abbildet.

Example 19 is an agricultural work machine comprising:

• a communication system that receives an information map indicative of agricultural feature values corresponding to various geographic locations in a field;
• a geographic position sensor that detects a geographic position of the agricultural working machine;
• an in situ sensor that detects a feature value of a feature that corresponds to the geographic location;
• a predictive model generator that generates a predictive performance model that models a relationship between the agricultural feature values and the performance attribute based on an agricultural feature value in the information map at the geographical location and the performance attribute value of the feature detected by the in situ sensor at the geographical location position is detected; and
• a predictive map generator that generates a functional predictive performance map of the field that maps predictive performance characteristics to the various locations in the field based on the agricultural characteristics in the information map and based on the predictive performance model.

Example 20 is the agricultural work machine of any or all of the preceding examples, the information map indicating agricultural traits indicating one or more of the following: a vegetative index, crop moisture, a topographical trait, a soil property, a predictive yield, and a predictive biomass.

Although the subject matter has been described in language specific to structural features or methodical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the features and acts described above are disclosed as example forms of the claims.

Claims (15)

Agricultural working machine (100), comprising: a communication system (206) receiving an information map (258) including values of a first agricultural characteristic corresponding to different geographic locations in a field; a geographic position sensor (204) that detects a geographic position of the agricultural work machine; an in situ sensor (208) that detects a value of a performance characteristic of the agricultural work machine (100) as a second agricultural characteristic that corresponds to the geographic location; a predictive model generator (210) that generates a predictive agricultural model that establishes a relationship between the first agricultural feature and the second agricultural feature based on a value of the first agricultural feature in the information map (258) at the geographic location and the value of the second modeling an agricultural feature sensed by the in situ sensor (208) at the geographic location; and a predictive map generator (212) that generates a functional predictive agricultural map of the field that applies predictive values of the second agricultural feature to the different geographic locations based on the values of the first agricultural feature in the information map (258) and based on the predictive agricultural model depicted in the field. Agricultural working machine after claim 1 , wherein the predictive map generator configures the functional predictive agricultural map for consumption by a control system that generates control signals to control a controllable subsystem on the agricultural work machine based on the functional predictive agricultural map. Agricultural working machine after claim 1 , wherein the in situ sensor on the agricultural work machine is configured to detect a power consumption of one or more subsystems corresponding to the geographic location as the value of the second agricultural characteristic. Agricultural working machine after claim 3 wherein the in situ sensor comprises one or more of a strain sensor, a current sensor, a torque sensor, a fluid pressure sensor, a fluid flow sensor, a force sensor, a bearing load sensor, and a rotation sensor. Agricultural working machine after claim 1 wherein the information map comprises a vegetative index map mapping vegetative index values to the various geographic locations in the field as the first agricultural trait. Agricultural working machine after claim 5 , wherein the predictive model generator is configured to identify a relationship between the feature and the vegetative index based on the feature value recognized at the geographic location and the vegetative index value in the vegetative index map at the geographic location, the predictive agricultural Model is configured to receive an input vegetative index value as a model input and generate a predicted performance characteristic value as a model output based on the identified relationship. Agricultural working machine after claim 1 wherein the map of information comprises a crop moisture map mapping crop moisture values to the various geographic locations in the field as the first agricultural characteristic. Agricultural working machine after claim 7 , wherein the predictive model generator is configured to identify a relationship between the performance characteristic and the crop moisture based on the performance characteristic value detected at the geographic location and the crop moisture value in the crop moisture map at the geographic location, the predictive model being configured, to receive an inputted crop moisture value as a model input and to generate a predicted performance attribute value as a model output based on the identified relationship. Agricultural working machine after claim 1 , wherein the information map comprises a predictive yield map, the first agricultural trait mapping predictive yield values to the various geographic locations in the field, and wherein the predictive model generator is configured to establish a relationship between the predictive yield and the performance trait based on the at the geographic Identify position of recognized performance attribute value and yield value in the predictive yield map at the geographic position, wherein the predictive agricultural model is configured to receive an input predictive yield value as model input and to generate a predicted performance attribute value as model output based on the identified relationship. Agricultural working machine after claim 1 , wherein the information map comprises a predictive biomass map, which as a first agricultural characteristic maps predictive biomass values to the different geographic positions in the field, and wherein the predictive model generator is configured to generate a relationship between the predictive biomass and the performance characteristic based on the an identifying the geographical position recognized performance characteristic value and the biomass value in the predictive biomass map at the geographical position, wherein the predictive agricultural model is configured to receive an input predictive biomass value as a model input and to generate a predicted performance characteristic value as a model output based on the identified relationship . Agricultural working machine after claim 1 , wherein the information map comprises a topographic map having as a first agricultural feature topographic feature values mapped to the various geographic locations in the field, and wherein the predictive model generator is configured to generate a relationship between the topographic feature and the performance property based on the at the geographic Position detected feature value and identify the topographical value in the topographical map at the geographic location, wherein the predictive agricultural model is configured to receive an inputted topographical feature value as model input and to generate a predicted feature value as model output based on the identified relationship. A computer-implemented method for generating a functional predictive agricultural map, comprising: receiving at an agricultural work machine (100) an information map (258) indicating values of a first agricultural characteristic corresponding to various geographic locations in a field; detecting a geographic position of the agricultural work machine (100); Capturing a performance metric with an In-si tu sensor (258) as a second agricultural feature corresponding to geographic location; creating a predictive agricultural model that models a relationship between the first agricultural trait and the second agricultural trait; and controlling a predictive map generator (212) to generate the functional predictive agricultural map of the field that includes predictive values of the second agricultural feature based on the values of the first agricultural feature in the information map (258) and the predictive agricultural model at the various positions in depicts the field. Computer-implemented method claim 12 , further comprising: configuring the functional predictive agricultural map for a control system that generates control signals to control a controllable subsystem on the agricultural work machine based on the functional predictive agricultural map. Computer-implemented method claim 12 , wherein detecting a performance attribute value as a second agricultural attribute with an in situ sensor comprises detecting a power consumption demand of a subsystem of the agricultural work machine that corresponds to the geographic location. Agricultural working machine (100), comprising: a communications system (206) receiving an information map (258) indicative of agricultural feature values corresponding to various geographic locations in a field; a geographic position sensor (204) that detects a geographic position of the agricultural work machine; an in situ sensor (208) that detects a feature value of a feature that corresponds to the geographic location; a predictive model generator (210) that generates a predictive performance model that models a relationship between the agricultural attribute values and the attribute based on an agricultural attribute value in the information map (258) at the geographical position and the attribute value of the attribute generated by the in- situ sensor (208) is detected at the geographical position; and a predictive map generator that generates a functional predictive performance map of the field that maps predictive performance characteristic values to the various locations in the field based on the values of the agricultural characteristic in the information map (258) and based on the predictive performance model.

Images