Machine control using prediction maps

Abstract

One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural property values at different geographic locations of a field. An on-board sensor on the agricultural work machine senses the agricultural property as the agricultural work machine moves through the field. A prediction map generator generates a prediction map that predicts the agricultural property at different locations in the field based on a relationship between values in the one or more information maps and the agricultural property sensed by the on-board sensor. The prediction map can be output and used for automated machine control.

Description

TECHNICAL FIELD

[0001] This description relates to agricultural machines, forestry machines, construction machines, and turf management machines. BACKGROUND

[0002] There are various different types of agricultural machines. Some agricultural machines include harvesters, such as combine harvesters, sugar cane harvesters, cotton harvesters, self-propelled forage harvesters, and swathers. Some harvesters can be equipped with different types of headers to harvest different types of crops.

[0003] Pests present in a field have many detrimental effects on harvesting operations. For example, when a harvester encounters an area of a field affected by pests, the machine performance of the harvester can deteriorate. As a result, during a harvesting operation, an operator can attempt to modify the controls of the harvester when encountering areas affected by pests.

[0004] The above discussion is merely provided as general background information and is not intended to aid in the determination of the scope of the claimed subject matter. SUMMARY

[0005] One or more information maps are obtained by the agricultural work machine. The one or more information maps map one or more agricultural property values at different geographic locations of a field. Onboard sensors sense the agricultural property as the agricultural work machine moves through the field. A prediction map generator generates a prediction map that predicts the agricultural property at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural property sensed by the onboard sensors. The prediction map can be output and used for automatic machine control.

[0006] This Summary is provided to introduce some concepts in a simplified form that are further described below in the DETAILED DESCRIPTION. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used in determining the scope of the claimed subject matter. The claimed subject matter is not limited to implementations that solve any or all disadvantages noted in the background. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is a partial schematic view of an example of a combine harvester.

[0008] Figure 2 is a block diagram showing some parts of an agricultural harvester in more detail according to some examples of the present disclosure.

[0009] Figures 3A-3B (Hereinafter referred to collectively as FIG. 3) shows a flowchart illustrating an example of the operation of an agricultural harvester in generating a map.

[0010] Figure 4is a block diagram illustrating one example of a prediction model generator and a prediction map generator.

[0011] Figure 5 is a flowchart illustrating one example of operations of an agricultural harvester in receiving an information map, detecting pest properties, and generating a functional prediction pest map for controlling the agricultural harvester during a harvesting operation.

[0012] Figure 6A is a block diagram illustrating one example of a prediction model generator and a prediction map generator.

[0013] Figure 6B is a block diagram illustrating one example of a field sensor.

[0014] Figure 7 is a flowchart illustrating one example of operations of an agricultural harvester including generating a functional prediction map using a prior information map and field sensor inputs.

[0015] Figure 8 is a block diagram illustrating one example of a control zone generator.

[0016] Figure 9 is a flowchart illustrating one example of operations of the control zone generator illustrated in Figure 8

[0017] Figure 10 is a flowchart illustrating one example of operations of a control system in selecting a target setpoint value to control an agricultural harvester.

[0018] Figure 11 is a block diagram illustrating one example of an operator interface controller.

[0019] Figure 12 is a flowchart illustrating one example of an operator interface controller.

[0020] Figure 13 is a schematic diagram illustrating one example of an operator interface display.

[0021] Figure 14 is a block diagram illustrating one example of an agricultural harvester in communication with a remote server environment.

[0022] Figures 15-17 is shown an example of a mobile device that can be used with an agricultural harvester.

[0023] Figure 18 is a block diagram illustrating one example of a computing environment that can be used with an agricultural harvester. DETAILED DESCRIPTION

[0024] ​To facilitate an 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 the same. It will, nevertheless, be understood that no limitation of the scope of the disclosure is intended. Any alterations and further modifications in the described devices, systems, methods, and any further applications of the principles of the present disclosure are fully contemplated as would normally occur to one skilled in the art to which the disclosure relates. In particular, it is fully contemplated that the features, components, and / or steps described with respect to one example can be combined with the features, components, and / or steps described with respect to other examples of the present disclosure.

[0025] This specification relates to using in-field data acquired contemporaneously with an agricultural operation in conjunction with prior data (previous data) to generate a prediction map, such as a prediction pest map. In some examples, the prediction map can be used to control an agricultural harvesting machine, such as an agricultural harvester. In some examples, the prediction pest map can be used to generate additional prediction maps. As discussed above, when an agricultural harvester engages a pest patch, the performance of the agricultural harvester can be degraded.

[0026] The performance of an agricultural harvester can be adversely affected based on many different criteria. For example, the intensity of pests in a pest patch can have a deleterious effect on the operation of an agricultural harvester.

[0027] Pests can include pathogens, such as bacterial and viral diseases, fungi, protozoan worms; vertebrates, such as birds, deer, elk, wild boar, other mammals, etc.; invertebrates, such as nematodes, worms, insects, etc. Some common pests include corn earworms in corn, seed corn maggot in winter wheat, European corn borer in corn, fusarium wilt in legumes, aflatoxins in peanuts. Note that these are examples only, and these pests can also be relevant to other crops.

[0028] A measure of pest intensity can be a binary value (such as pest present or pest absent), or a continuous value (such as a percentage of pests in a defined area or volume), or a set of discrete values (such as a low, medium, or high pest intensity value). Similarly, different types of pests encountered by an agricultural harvester can affect the agricultural harvester differently. For example, different pest types can affect the physical structure of nearby plants (e.g., thinner stems, narrower leaves, etc.). These changes in plant structure can also cause changes in the performance of the agricultural harvester when the agricultural harvester engages such plants adjacent to such pests.

[0029] The vegetation index map illustratively maps values of a vegetation index (which can be indicative of vegetation growth) at different geographic locations in the field of interest. One example of a vegetation index includes the normalized difference vegetation index (NDVI). There are many other vegetation indices as well, and all are within the scope of the present disclosure. In some examples, the vegetation index can be derived from sensor readings of one or more bands of electromagnetic radiation reflected by the plant. Without limitation, these bands can be in the microwave, infrared, visible, or ultraviolet portions of the electromagnetic spectrum.

[0030] Accordingly, the vegetation index map can be used to identify the presence and location of vegetation. In some examples, the vegetation index map enables identification and georeferencing of crops in the presence of bare soil, crop residue, or other plant matter, including crops or weeds. For example, at the beginning of the growing season, when the crops are in a vegetative state, the vegetation index can show the progress of crop development. Accordingly, if the vegetation index map is generated early in the growing season or mid-way through the growing season, the vegetation index map can indicate the progress of development of the crop plants. For example, the vegetation index map can indicate whether the plants are underdeveloped, whether sufficient canopy has been established, or other plant attributes of plant development.

[0031] The reconnaissance map can be automatically generated by an agricultural reconnaissance robot or manually generated by one or more humans. For example, the reconnaissance robot can navigate over the field along the crop rows during the growing season without significant impact on the growing plants. The robot can perceive the number of damaged crop plants, diseased plants, animal markings, presence of animals, eaten crop material, uprooted plants, pods, ears, heads, and so forth.

[0032] Animal activity maps can be generated automatically or manually by one or more people. For example, an animal activity map can be generated by a camera monitoring a field that is capable of detecting animal movement across the field. Or, for example, a person can manually identify locations where they have found animal activity. Some example animals of interest include wild boar, birds, raccoons, deer, elk, etc. Locations where animals are detected can be plotted on a map. These locations can also serve as a temporal reference of when the animal was found. This can be useful, for example, because in early stages of growth, animals can pull crop plants up entirely by the roots, while the impact of certain animals on crop plants is less in later stages of growth. While in some cases, animals can cause minimal damage to later stage crops, they can completely reduce grain yield of a given plant (e.g., a deer eating the ear of a corn plant). Temporal references can also be aggregated to identify hotspots of animal activity in a field over time. This can be useful, for example, because the longer an animal spends in a given location in a field, the greater the likelihood of crop damage due to that animal.

[0033] Historical pest maps schematically plot past locations of pests from past years or the current growing season. Historical pest maps can be generated manually based on reports by operators in past years. For example, when an operator observes a pest or an area affected by a pest in a field, an interface can be provided that allows the operator to mark these geographic locations as containing a pest or being affected by a pest. In other examples, historical pest maps can be generated from data collected earlier in the current growing season by scouting, modeling, or other means.

[0034] Optical property maps schematically map electromagnetic radiation values for different geographic locations in a field of interest. The electromagnetic radiation values can be from the entire electromagnetic spectrum. The present disclosure uses electromagnetic radiation values from the infrared, visible, and ultraviolet portions of the electromagnetic spectrum as examples only, and other portions of the spectrum are also contemplated. Optical property maps can map data points by wavelength (e.g., the vegetation indices described above). In other examples, optical property maps identify textures, patterns, colors, shapes, or other relationships of data points. Textures, patterns, or other relationships of data points can be indicative of the presence or identity of objects in the field, such as crop status (e.g., fallen / laying or standing crops), plant presence, plant type, animal presence, insect presence, insect type, mammal type, bird type, etc. For example, plant type can be identified by a given leaf pattern that can be used to identify a plant. Or, for example, insects can be identified using insect silhouettes or bite patterns in leaves. Or, for example, diseases can be found on plants.

[0035] Accordingly, the present discussion is directed to systems that receive a prior information map of a field or a map generated during a prior operation and also use in-field sensors to detect variables indicative of one or more of the agricultural properties. The system generates a model that models the relationship between the values on the prior information map and the output values from the in-field sensors. The model is used to generate a functional prediction map that predicts the agricultural properties at different locations in the field. The functional prediction map generated during a harvesting operation can be presented to an operator or other user, or used to automatically control an agricultural harvester during the harvesting operation, or both. The functional prediction map can be used to control the agricultural harvester.

[0036] Figure 1 is a partial schematic view of a self-propelled agricultural harvester 100. In the example shown, the agricultural harvester 100 is a combine harvester. In addition, although a combine harvester is provided as an example throughout this disclosure, it should be understood that the present description also applies to other types of harvesters, such as cotton harvesters, sugar cane harvesters, self-propelled forage harvesters, swathers, or other agricultural work machines. Accordingly, the present disclosure is intended to encompass the various types of harvesters described, and is therefore not limited to combine harvesters. Moreover, the present disclosure is directed to other types of work machines, such as agricultural planters and sprayers, construction equipment, forestry equipment, and lawn care equipment, in which the generation of a prediction map can be applied. Accordingly, the present disclosure is intended to encompass these various types of harvesters and other work machines, and is therefore not limited to combine harvesters.

[0037] As Figure 1 shown, the agricultural harvester 100 schematically includes an operator compartment 101 that can have various different operator interface mechanisms for controlling the agricultural harvester 100. The agricultural harvester 100 includes front end equipment, such as a header 102 and a cutter 104 generally indicated at 104. In the illustrated example, the cutter 104 is included on the header 102. The agricultural harvester 100 also includes a feedhouse 106, a feed accelerator 108, and a threshing machine generally indicated at 110. The feedhouse 106 and the feed accelerator 108 form part of a material handling subsystem 125. The header 102 is pivotally coupled to a frame 103 of the agricultural harvester 100 along a pivot axis 105. One or more actuators 107 drive the header 102 to move about the axis 105 in a direction generally indicated by arrow 109. Accordingly, a vertical position (header height) of the header 102 above a ground surface 111 on which the header 102 travels is controllable by actuating the actuators 107. Although in the illustrated example the header 102 is pivotally coupled to the frame 103, it should be understood that the header 102 can be coupled to the frame 103 in other ways, such as by a telescoping mechanism, or by a mechanism that does not pivot about an axis. Figure 1As shown in FIG. 1, agricultural harvester 100 includes header 102, which is coupled to a frame 101 of agricultural harvester 100. Header 102 includes a cutterbar 104, which includes a plurality of cutters 106. Cutters 106 are coupled to a frame 108 of header 102. In some examples, agricultural harvester 100 can include one or more actuators that operate to apply a tilt angle, roll angle, or both, to header 102 or a portion of header 102. Tilt refers to the angle at which cutters 106 engage the crop. For example, tilt angle is increased by controlling header 102 to point distal edges 113 of cutters 106 more toward the ground. Tilt angle is decreased by controlling header 102 to point distal edges 113 of cutters 106 more away from the ground. Roll angle refers to the orientation of header 102 about a fore-aft longitudinal axis of agricultural harvester 100.

[0038] Threshing machine 110 illustratively includes a threshing rotor 112 and a set of concaves 114. Additionally, agricultural harvester 100 includes a separator 116. Agricultural harvester 100 also includes a grain cleaning subsystem or grain cleaning house (collectively referred to as grain cleaning subsystem 118), which includes a grain cleaning fan 120, a chaffer 122, and a sieve 124. Material handling subsystem 125 also includes an unloading threshing cylinder 126, a tailings elevator 128, a clean grain elevator 130, and an unloading auger 134 and spout 136. Clean grain elevator moves clean grain into a clean grain tank 132. Agricultural harvester 100 also includes a residue subsystem 138, which can include a chopper 140 and a spreader 142. Agricultural harvester 100 also includes a propulsion subsystem, which includes an engine that drives ground engaging components 144 (e.g., wheels or tracks). In some examples, a combine within the scope of the present disclosure can have more than one of any of the above-mentioned subsystems. In some examples, agricultural harvester 100 can have a left and right grain cleaning subsystem, a separator, etc., which are not shown in Figure 1

[0039] ​In operation, and as outlined, the agricultural harvester 100 illustratively moves through a field in a direction indicated by arrow 147. As the agricultural harvester 100 moves, the header 102 (and associated reel 164) engages the crop to be harvested and gathers the crop toward the cutter 104. The operator of the agricultural harvester 100 can be a local human operator, a remote human operator, or an automated system. Operator commands are commands issued by the operator. The operator of the agricultural harvester 100 can determine one or more of a height setting, a tilt angle setting, or a roll angle setting of the header 102. For example, the operator inputs one or more settings to a control system that controls the actuator 107 (described in more detail below). The control system can also receive settings from the operator to establish the tilt angle and roll angle of the header 102 and implement the input settings by controlling associated actuators (not shown) that operate to change the tilt angle and roll angle of the header 102. The actuator 107 maintains the header 102 at a height above the ground 111 based on the height setting, and, where applicable, at a desired tilt and roll angle. Each of the height, roll, and tilt settings can be implemented independently of the other settings. The control system responds to header errors (e.g., a difference between the height setting and a measured height of the header 104 above the ground 111, and in some examples, tilt angle and roll angle errors) with a responsiveness determined based on a selected level of sensitivity. If the level of sensitivity is set at a higher level of sensitivity, the control system responds to smaller header position errors and attempts to reduce detected errors more quickly than if the level of sensitivity is at a lower level of sensitivity.

[0040] Returning to the description of the operation of the agricultural harvester 100, after the crop is cut by the cutter 104, the cut crop material moves through the feeder house 106 toward the feed accelerator 108, which accelerates the crop material into the threshing machine 110. The crop material 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, where a portion of the straw is moved by the unloading threshing cylinder 126 toward the straw sub-system 138. The portion of the straw that is conveyed to the straw sub-system 138 is chopped by the straw chopper 140 and spread on the field by the spreader 142. In other configurations, the straw is released from the agricultural harvester 100 into a pile. In other examples, the straw sub-system 138 can include a weed seed rejector (not shown), such as a seed bagger or other seed collector, or a seed crusher or other seed destroyer.

[0041] The grain falls to the clean grain subsystem 118. The chaffer 122 separates some of the larger pieces of material from the grain, and the sieve 124 separates some of the finer pieces of material from the clean grain. The clean grain falls onto an auger that moves the grain to the inlet end of the clean grain elevator 130, and the clean grain elevator 130 moves the clean grain upward, storing the clean grain in the clean grain bin 132. The chaff is removed from the clean grain subsystem 118 by the airflow generated by the clean grain fan 120. The clean grain fan 120 directs air up the airflow path through the sieve and the chaffer. The airflow carries the chaff in the agricultural harvester 100 rearward toward the chaff handling subsystem 138.

[0042] The tailings elevator 128 returns the tailings to the threshing machine 110, where the tailings are re-threshed. Alternatively, the tailings can also be passed to a separate re-threshing mechanism by the tailings elevator or another transport device, where the tailings are also re-threshed.

[0043] Figure 1 It is also shown in one example that the agricultural harvester 100 includes a machine speed sensor 146, one or more separator loss sensors 148, a clean grain camera 150, a forward view image capture mechanism 151 that can be in the form of a stereo camera or a monocular camera, and one or more loss sensors 152 disposed in the clean grain subsystem 118.

[0044] The machine speed sensor 146 senses the speed of travel of the agricultural harvester 100 over the ground. The machine speed sensor 146 can sense the speed of travel of the agricultural harvester 100 by sensing the rotational speed of ground-engaging components such as wheels or tracks, drive shafts, axles, or other components. In some cases, a positioning system can be used to sense the speed of travel, such as a global positioning system (GPS), a dead reckoning system, a LORAN system, or various other systems or sensors that provide an indication of the speed of travel.

[0045] The loss sensors 152 schematically provide output signals indicative of the amount of grain loss occurring in the right and left sides of the clean grain subsystem 118. In some examples, the sensors 152 are impact sensors that count the grain impacts per unit of time or per unit of travel distance to provide an indication of the grain loss occurring at the clean grain subsystem 118. The impact sensors for the right and left sides of the clean grain subsystem 118 can provide separate signals or combined or aggregated signals. In some examples, the sensors 152 can include a single sensor rather than providing separate sensors for each clean grain subsystem 118.

[0046] The separator loss sensors 148 provide signals indicative of grain loss in the left and right separators (not shown separately in FIG. 1). The separator loss sensors 148 can be associated with the left and right separators and can provide separate grain loss signals or a combined or aggregated signal. In some cases, sensing grain loss in the separators can also be performed using various different types of sensors. Figure 1

[0047] The agricultural harvester 100 can also include other sensors and measurement mechanisms. For example, the agricultural harvester 100 can include one or more of the following sensors: a header height sensor that senses the height of the header 102 above the ground 111; a stability sensor that senses the vibration or bounce (and amplitude) of the agricultural harvester 100; a residue setting sensor configured to sense whether the agricultural harvester 100 is configured to chop residue, produce a windrow, etc.; a clean grain bin fan speed sensor to sense the fan 120 speed; a concave gap sensor that senses the gap between the rotor 112 and the concave 114; a threshing rotor speed sensor that senses the rotor speed of the rotor 112; a chaffer gap sensor that senses the size of the openings in the chaffer 122; a screen gap sensor that senses the size of the openings in the screen 124; a material other than grain (MOG) moisture sensor that senses the moisture level of the MOG passing through the agricultural harvester 100; one or more machine setting sensors configured to sense various configurable settings of the agricultural harvester 100; a machine orientation sensor that senses the orientation of the agricultural harvester 100; and a crop property sensor that senses various different types of crop properties such as crop type, crop moisture, and other crop properties. The crop property sensor can also be configured to sense the properties of cut crop material as it is processed by the agricultural harvester 100. For example, in some cases, the crop property sensor can sense: grain quality such as broken grain, MOG levels; grain constituents such as starch and protein; and grain feed rate as the grain travels through the feedhouse 106, the clean grain elevator 130, or other places in the agricultural harvester 100. The crop property sensor can also sense the feed rate of biomass through the feedhouse 106, the separator 116, or other places in the agricultural harvester 100. The crop property sensor can also sense the feed rate through the elevator 130 or through other portions of the agricultural harvester 100 as a grain mass flow rate, or provide other output signals indicative of other sensed variables. The crop property sensor can include one or more yield sensors that sense the yield of the crop being harvested by the agricultural harvester.

[0048] ​The yield sensor(s) can include a grain flow sensor that detects the flow of crop, e.g., grain, in the material handling subsystem 125 or other portion of the agricultural harvester 100. For example, the yield sensor can include a gamma ray attenuation sensor that measures the flow of harvested grain or other type of radiation sensor that utilizes radiation properties to determine yield. In another example, the yield sensor includes an impact plate sensor that detects impacts of grain on a sensing plate or surface to measure the mass flow of harvested grain. In another example, the yield sensor includes one or more load cells that measure or detect the load or mass of harvested grain. For example, the one or more load cells can be located at the bottom of the grain tank 132, where changes in the weight or mass of grain within the grain tank 132 during a measurement interval are indicative of the total yield during the measurement interval. Measurement intervals can be increased for averaging or decreased for more instantaneous measurements. In another example, the yield sensor includes a camera or optical sensing device that detects the size or shape of accumulated masses of harvested grain, e.g., the shape of a grain pile or the height of a grain pile in the grain tank 132. Changes in the shape or height of the grain pile during a measurement interval are indicative of the total yield during the measurement interval. In other examples, other yield sensing techniques are employed. For example, in one example, the yield sensor includes two or more of the above-described sensors, and the yield for a measurement interval is determined from signals output by each of the multiple different types of sensors. For example, the yield is determined based on signals from a gamma ray attenuation sensor, an impact plate sensor, a load cell within the grain tank 132, and an optical sensor along the grain tank 132.

[0049] Before describing how the agricultural harvester 100 generates a functional prediction pest map and uses the functional prediction pest map for control or for further processing, a brief description of some items on the agricultural harvester 100 and their operation will first be described. Figure 2and the description of FIG. 3 describes receiving a general type of prior information map and combining information from the prior information map with georeferenced sensor signals generated by on-site sensors, where the sensor signals are indicative of characteristics in the field, such as characteristics of a pest present in the field. The characteristics of the field can include, but are not limited to, characteristics of the field (such as slope, pest intensity, pest type, soil moisture, surface quality); characteristics of crop properties (such as crop height, crop moisture, crop density, crop status); characteristics of grain properties (such as grain moisture, grain size, grain test weight); and characteristics of machine performance (such as loss level, job quality, fuel consumption, and power utilization). Relationships between characteristic values obtained from the on-site sensor signals and prior information map values are identified, and the relationships are used to generate a new functional prediction map. The functional prediction map predicts values at different geographic locations in the field, and one or more of the values can be used to control a machine, such as one or more subsystems of an agricultural harvester. In some cases, the functional prediction map can be presented to a user, such as an operator of an agricultural work machine, which can be an agricultural harvester. The functional prediction map can be presented to the user in a visual manner (such as through a display), in a tactile manner, or in an audible manner. The user can interact with the functional prediction map to perform editing operations and other user interface operations. In some cases, the functional prediction map can be used to control an agricultural work machine (such as an agricultural harvester), presented to an operator or other user, and presented to an operator or user for one or more of operator or user interaction.

[0050] In reference to Figure 2 and FIG. 3 describes a general method, reference is made to Figure 4 and Figure 5 a more specific method for generating a functional prediction pest map is described, which can be presented to an operator or user, or used to control the agricultural harvester 100, or both. Again, although this discussion is directed to an agricultural harvester, and in particular a combine harvester, the scope of the present disclosure encompasses other types of agricultural harvesters or other agricultural work machines.

[0051] Figure 2 is a block diagram showing some portions of an example agricultural harvester 100. Figure 2An agricultural harvester 100 is schematically shown, including one or more processors or servers 201, a data storage device 202, a geolocation sensor 204, a communication system 206, and one or more field sensors 208 that sense one or more agricultural characteristics of the field during harvesting operations. Agricultural characteristics can include any characteristic that can have an impact on the harvesting operation. Some examples of agricultural characteristics include characteristics of the harvester, the field, the plants on the field, and the weather. Other types of agricultural characteristics are also included. The field sensors 208 generate values ​​corresponding to the sensed characteristics. The agricultural harvester 100 also includes a prediction model or relation generator (hereinafter collectively referred to as "prediction model generator 210"), a prediction map generator 212, a control area 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. Field sensors 208 include, for example, onboard sensors 222, remote sensors 224, and other sensors 226 that sense field characteristics during agricultural operations. Predictive model generator 210 schematically includes a priori information variable-to-field variable model generator 228, and may include other items 230. Control system 214 includes a communication system controller 229, an operator interface controller 231, a settings controller 232, a path planning controller 234, a feed rate controller 236, a header and reel controller 238, a belt conveyor controller 240, a platform position controller 242, a stubble system controller 244, a machine clearing controller 245, a zone controller 247, and may include other items 246. The controllable subsystem 216 includes a machine and header actuator 248, a propulsion subsystem 250, a steering subsystem 252, a stubble subsystem 138, a machine grain cleaning subsystem 254, and the subsystem 216 may include a variety of other subsystems 256.

[0052] Figure 2 The agricultural harvester 100 is also shown to receive a priori information map 258. As described below, the priori information map 258 includes, for example, a vegetation index map or a vegetation map or a map predicting pests from a priori operations. However, the priori information map 258 may also encompass other types of data obtained prior to the harvesting operation or maps from a priori operations. Figure 2The diagram also illustrates that operator 260 can operate agricultural harvester 100. Operator 260 interacts with operator interface mechanism 218. In some examples, operator interface mechanism 218 may include joysticks, joysticks, steering wheels, linkages, pedals, buttons, dials, keypads, user-actuable elements (such as icons, buttons, etc.) on a user interface display device, microphones and speakers (where speech recognition and speech synthesis are provided), and various other types of control devices. Where a touch-sensitive display system is provided, operator 260 may interact with operator interface mechanism 218 using touch gestures. The examples described above are provided as illustrative examples and are not intended to limit the scope of this disclosure. Therefore, other types of operator interface mechanisms 218 may be used, and other types of operator interface mechanisms are within the scope of this disclosure.

[0053] The prior information map 258 can be downloaded to the agricultural harvester 100 and stored in the data storage device 202 using the communication system 206 or other means. In some examples, the communication system 206 may be a cellular communication system, a system for communication over a wide area network or a local area network, a system for communication over a near-field communication network, or a communication system configured to communicate over any one or a combination of various other networks. The communication system 206 may also include systems that facilitate the downloading or transfer of information to or from a secure digital (SD) card or a universal serial bus (USB) card, or both.

[0054] The geolocation sensor 204 schematically senses or detects the geolocation or orientation of the agricultural harvester 100. The geolocation sensor 204 may include, but is not limited to, a GNSS receiver that receives signals from a Global Navigation Satellite System (GNSS) satellite transmitter. The geolocation sensor 204 may also include a real-time kinematic (RTK) component configured to improve the accuracy of the position data derived from the GNSS signals. The geolocation sensor 204 may include any of a dead reckoning system, a cellular triangulation system, or a variety of other geolocation sensors.

[0055] The field sensor 208 can be referenced above. Figure 1Any of the sensors described. Field sensor 208 includes onboard sensor 222 mounted on the agricultural harvester 100. Such sensors may include, for example, sensing sensors (e.g., forward-looking monocular or stereo camera systems and image processing systems), and image sensors inside the agricultural harvester 100. Field sensor 208 also includes remote field sensor 224 that captures field information. Field data includes data acquired from sensors mounted on the harvester, or data acquired by any sensor that detects data during harvesting operations.

[0056] Predictive model generator 210 generates a model indicating the relationship between values ​​sensed by field sensors 208 and measures mapped to the field by prior information map 258. For example, if prior information map 258 maps vegetation index values ​​to different locations in the field, and field sensors 208 sense values ​​indicating pest intensity, then prior information variable to field variable model generator 228 generates a predictive pest model that models the relationship between vegetation index values ​​and pest intensity values. The predictive pest model can also be generated based on vegetation index values ​​from prior information map 258 and multiple field data values ​​generated by field sensors 208. Then, predictive map generator 212 uses the predictive pest model generated by predictive model generator 210 to generate a functional predictive pest map that predicts the values ​​of pest properties (such as intensity) sensed by field sensors 208 at different locations in the field based on prior information map 258.

[0057] In some examples, the type of values ​​in functional prediction graph 263 may be the same as the field data type sensed by field sensor 208. In some cases, the type of values ​​in functional prediction graph 263 may have a different unit than the data sensed by field sensor 208. In some examples, the type of values ​​in functional prediction graph 263 may be different from the data type sensed by field sensor 208, but related to the data type sensed by field sensor 208. For example, in some examples, the data type sensed by field sensor 208 may indicate the type of values ​​in functional prediction graph 263. In some examples, the type of data in functional prediction graph 263 may be different from the data type in prior information graph 258. In some cases, the type of data in functional prediction graph 263 may have a different unit than the data in prior information graph 258. In some examples, the type of data in functional prediction graph 263 may be different from the data type in prior information graph 258, but related to the data type in prior information graph 258. For example, in some examples, the data type in prior information graph 258 may represent the type of data in functional prediction graph 263. In some examples, the type of data in the functional prediction graph 263 is different from one or both of the field data type sensed by the field sensor 208 and the data type in the prior information graph 258. In some examples, the type of data in the functional prediction graph 263 is the same as one or both of the field data type sensed by the field sensor 208 and the data type in the prior information graph 258. In some examples, the type of data in the functional prediction graph 263 is the same as one of the field data type sensed by the field sensor 208 or the data type in the prior information graph 258, but different from the other.

[0058] Continuing with the previous example, where prior infographic 258 is a vegetation index map and field sensor 208 senses values ​​indicating pest intensity, prediction map generator 212 can use the vegetation index values ​​from prior infographic 258 and the model generated by prediction model generator 210 to generate a functional prediction map 263 predicting pest intensity at different locations in the field. Prediction map generator 212 then outputs prediction map 264.

[0059] like Figure 2As shown, prediction map 264 uses prior information values ​​from prior information map 258 at various locations on the field and a prediction model to predict the values ​​of sensed characteristics (sensed by field sensors 208) or characteristics related to sensed characteristics at these locations. For example, if prediction model generator 210 has generated a prediction model indicating the relationship between vegetation index values ​​and pest intensity, then, given vegetation index values ​​at different locations on the field, prediction map generator 212 generates prediction map 264 predicting pest intensity values ​​at different locations on the field. The vegetation index values ​​at these locations obtained from the vegetation index map and the relationship between vegetation index values ​​and pest intensity obtained from the prediction model are used to generate prediction map 264.

[0060] The following will describe some changes in the data types mapped in prior information graph 258, the data types sensed by field sensor 208, and the data types predicted in prediction graph 264.

[0061] In some examples, the data type in the prior infographic 258 differs from the data type sensed by the field sensor 208, but the data type in the prediction infographic 264 is the same as the data type sensed by the field sensor 208. For example, the prior infographic 258 could be a vegetation index map, and the variable sensed by the field sensor 208 could be yield. The prediction infographic 264 could then be a predicted yield map that maps predicted yield values ​​to different geographic locations in the field. In another example, the prior infographic 258 could be a vegetation index map, and the variable sensed by the field sensor 208 could be crop height. The prediction infographic 264 could then be a predicted crop height map that maps predicted crop height values ​​to different geographic locations in the field.

[0062] Furthermore, in some examples, the data type in the prior information map 258 differs from the data type sensed by the field sensor 208, and the data type in the prediction map 264 differs from both the data type in the prior information map 258 and the data type sensed by the field sensor 208. For example, the prior information map 258 could be a vegetation index map, and the variable sensed by the field sensor 208 could be crop height. The prediction map 264 could then be a predicted biomass map that maps predicted biomass values ​​to different geographic locations in the field. In another example, the prior information map 258 could be a vegetation index map, and the variable sensed by the field sensor 208 could be yield. The prediction map 264 could then be a predicted velocity map that maps predicted harvester velocity values ​​to different geographic locations in the field.

[0063] In some examples, the prior information map 258 is derived from previous passage through the field during a priori operations, and its data type differs from the data type sensed by the field sensor 208, but the data type in the prediction map 264 is the same as that sensed by the field sensor 208. For example, the prior information map 258 could be a seed population map generated during planting, and the variable sensed by the field sensor 208 could be stem size. The prediction map 264 could then be a predicted stem size map that maps predicted stem size values ​​to different geographic locations in the field. In another example, the prior information map 258 could be a seed mix map, and the variable sensed by the field sensor 208 could be crop state, such as upright or lodged crop. The prediction map 264 could then be a predicted crop state map that maps predicted crop state values ​​to different geographic locations in the field.

[0064] In some examples, the prior information map 258 is derived from a field previously traversed during a prior operation, and the data type is the same as that sensed by the field sensor 208, and the data type in the prediction map 264 is also the same as that sensed by the field sensor 208. For example, the prior information map 258 could be a yield map generated during the previous year, and the variable sensed by the field sensor 208 could be yield. The prediction map 264 could then be a predicted yield map that maps predicted yield values ​​to different geographic locations within the field. In such an example, the prediction model generator 210 could use the relative yield differences from the geographic reference prior information map 258 from the previous year to generate a prediction model that models the relationship between the relative yield differences on the prior information map 258 and the yield values ​​sensed by the field sensor 208 during the current harvest operation. The prediction model is then used by the prediction map generator 210 to generate the predicted yield map.

[0065] In another example, the prior information map 258 could be a pest intensity map generated during a prior operation (such as from a sprayer), and the variable sensed by the field sensor 208 could be pest intensity. The prediction map 264 could then be a predicted pest intensity map that maps the predicted pest intensity values ​​to different geographic locations in the field. In such an example, a map of pest intensity at spraying time is georeferenced and provided to the agricultural harvester 100 as the prior information map 258 of pest intensity. The field sensor 208 can detect pest intensity at geographic locations in the field, and the prediction model generator 210 can then build a predictive model that models the relationship between pest intensity at harvest and pest intensity at spraying time. This is because a sprayer affects pest intensity at spraying time, but pests may reappear in similar areas at harvest time. However, based on harvest time, weather, pest type, etc., the pest area at harvest time may have different intensities.

[0066] In some examples, prediction map 264 may be provided to control zone generator 213. Control zone generator 213 groups adjacent portions of a region into one or more control zones based on data values ​​in prediction map 264 associated with those adjacent portions. A control zone may include two or more consecutive portions of a region (such as a field) for which control parameters corresponding to the control zones used to control the controllable subsystem are constant. For example, the response time to changing the settings of controllable subsystem 216 may not be satisfactory in responding to changes in values ​​contained in a map such as prediction map 264. In this case, control zone generator 213 analyzes the map and identifies control zones with defined dimensions to accommodate the response time of controllable subsystem 216. In another example, the size of the control zone may be determined to reduce wear caused by excessive actuator movement due to continuous adjustment. In some examples, there may be different groups of control zones for each controllable subsystem 216 or group of controllable subsystems 216. Control zones may be added to prediction map 264 to obtain prediction control zone map 265. The predicted control area map 265 can therefore be similar to the predicted map 264, except that the predicted control area map 265 includes control area information that defines the control area. Therefore, as described herein, the functional predicted map 263 may or may not include a control area. Both the predicted map 264 and the predicted control area map 265 are functional predicted maps 263. In one example, the functional predicted map 263 does not include a control area, as in the predicted map 264. In another example, the functional predicted map 263 does include a control area, as in the predicted control area map 265. In some examples, if an intercropping production system is implemented, multiple crops may coexist in the field. In this case, the predicted map generator 212 and the control area generator 213 are able to identify the location and characteristics of two or more crops and then generate the predicted map 264 and the predicted control area map 265 accordingly.

[0067] It should also be understood that the control region generator 213 can cluster values ​​to generate control regions, and these control regions can be added to the predicted control region map 265 or a separate map, thus showing only the generated control regions. In some examples, the control regions can be used to control or calibrate the agricultural harvester 100 or both. In other examples, the control regions can be presented to the operator 260 for controlling or calibrating the agricultural harvester 100, and in still other examples, the control regions can be presented to the operator 260 or another user or stored for later use.

[0068] Predictive map 264 or predictive control area map 265, or both, is provided to control system 214, which generates control signals based on predictive map 264 or predictive control area map 265, or both. In some examples, communication system controller 229 controls communication system 206 to communicate predictive map 264 or predictive control area map 265, or control signals based on predictive map 264 or predictive control area map 265, to other agricultural harvesters harvesting in the same field. In some examples, communication system controller 229 controls communication system 206 to send predictive map 264, predictive control area map 265, or both, to other remote systems.

[0069] Operator interface controller 231 is operable to generate control signals to control operator interface mechanism 218. Operator interface controller 231 is also operable to present operator 260 with prediction map 264 or prediction control area map 265, or other information derived from or based on prediction map 264, prediction control area map 265, or both. Operator 260 can be a local operator or a remote operator. As an example, controller 231 generates control signals to control the display mechanism to display one or both of prediction map 264 and prediction control area map 265 to operator 260. Controller 231 can generate operator-actuable mechanisms that are shown and can be actuated by the operator to interact with the displayed maps. The operator can edit the maps by, for example, correcting the types of pests displayed on the maps based on the operator's observation. Setting controller 232 can generate control signals based on prediction map 264, prediction control area map 265, or both to control various settings on agricultural harvester 100. For example, controller 232 can generate control signals to control the machine and header actuator 248. In response to the generated control signals, the machine and header actuator 248 operate to control, for example, screen and chaff screen settings, recess clearance, rotor settings, grain clearing fan speed settings, header height, header functions, reel speed, reel position, belt conveyor functions (where the harvester 100 is coupled to the belt conveyor header), corn header functions, internal distribution controls, and other actuators 248 that affect other functions of the harvester 100. Path planning controller 234 schematically generates control signals to control steering subsystem 252 to turn the harvester 100 according to a desired path. Path planning controller 234 can control the path planning system to generate a route for the harvester 100 and can control propulsion subsystem 250 and steering subsystem 252 to turn the harvester 100 along that route. The feed rate controller 236 can control various subsystems (such as the propulsion subsystem 250 and the machine actuator 248) to control the feed rate based on prediction diagram 264 or prediction control area diagram 265, or both. The header and reel controller 238 can generate control signals to control the header or reel or other header functions. The belt conveyor controller 240 can generate control signals based on prediction diagram 264, prediction control area diagram 265, or both to control the belt conveyor belt or other belt conveyor functions. The tabletop position controller 242 can generate control signals based on prediction diagram 264, prediction control area diagram 265, or both to control the position of the tabletop included on the header, and the stubble system controller 244 can generate control signals based on prediction diagram 264, prediction control area diagram 265, or both to control the stubble subsystem 138. The machine cleaning controller 245 can generate control signals to control the machine cleaning subsystem 254.For example, based on the different types of pests passing through machine 100, specific types of machine clearing operations or the frequency of performing clearing operations can be controlled. Other controllers included on the agricultural harvester 100 can also control other subsystems based on prediction diagram 264 or prediction control area diagram 265 or both.

[0070] Figure 3A and Figure 3B (Hereinafter referred to as Figure 3) shows a flowchart illustrating an example of the operation of an agricultural harvester 100 in generating a prediction map 264 and a prediction control area map 265 based on prior information map 258.

[0071] At 280, the agricultural harvester 100 receives a priori information map 258. Examples of priori information map 258 or receiving priori information map 258 are discussed with respect to boxes 281, 282, 284, and 286. As discussed above, as shown in box 282, priori information map 258 maps the values ​​of variables corresponding to a first characteristic to different locations in the field. As shown in box 281, receiving priori information map 258 may include selecting one or more of a plurality of possible priori information maps available. For example, one priori information map may be a vegetation index map generated from aerial imagery. Another priori information map may be a map generated during a previous pass through the field, which may be performed by a different machine (such as a sprayer or other machine) performing the previous operation in the field. The process of selecting one or more priori information maps may be manual, semi-automatic, or automatic. Priori information map 258 is based on data collected prior to the current harvesting operation. This is indicated by box 284. For example, the data may be collected based on aerial imagery taken during the previous year, early in the current growing season, or at other times. The data can be based on data detected in a manner different from that using aerial imagery. The data from the prior information map 258 can be transmitted to the agricultural harvester 100 using the communication system 206 and stored in the data storage device 202. The data from the prior information map 258 can also be provided to the agricultural harvester 100 in other ways using the communication system 206, as indicated by box 286 in the flowchart of Figure 3. In some examples, the prior information map 258 can be received by the communication system 206.

[0072] At the start of the harvesting operation, field sensor 208 generates sensor signals indicating one or more field data values ​​that indicate characteristics, such as plant characteristics or pest characteristics, as shown in box 288. Examples of field sensor 288 are discussed with respect to boxes 222, 290, and 226. As explained above, field sensor 208 includes airborne sensor 222, remote field sensor 224 (such as a UAV-based sensor that collects field data on each flight (as shown in box 290)), or other types of field sensors specified by field sensor 226. In some examples, position, heading, or speed data from geolocation sensor 204 is georeferenced against data from airborne sensors.

[0073] The predictive model generator 210 controls the prior information variable to field variable model generator 228 to generate a model that models the relationship between the mapped values ​​contained in the prior information graph 258 and the field values ​​sensed by the field sensor 208, as shown in box 292. The characteristics or data types represented by the mapped values ​​in the prior information graph 258 and the field values ​​sensed by the field sensor 208 can be the same or different characteristics or data types.

[0074] The relation or model generated by the prediction model generator 210 is provided to the prediction map generator 212. The prediction map generator 212 uses the prediction model and the prior information map 258 to generate a prediction map 264, which predicts the values ​​of different characteristics sensed by the field sensor 208 at different geographical locations in the field being harvested, or the values ​​of different characteristics related to the characteristics sensed by the field sensor 208, as shown in box 294.

[0075] It should be noted that in some examples, the prior information map 258 may include two or more different maps or two or more different layers of a single map. Each layer may represent a data type different from that of another layer, or the layers may have the same data type acquired at different times. Each map in the two or more different maps or each layer in the two or more different layers of a map maps different types of variables to geographic locations in the field. In such an example, the predictive model generator 210 generates a predictive model that models the relationship between the field data and each of the different variables mapped by the two or more different maps or two or more different layers. Similarly, the field sensor 208 may include two or more sensors, each sensing a different type of variable. Therefore, the predictive model generator 210 generates a predictive model that models the relationship between each type of variable mapped by the prior information map 258 and each type of variable sensed by the field sensor 208. The prediction map generator 212 can use each of the plots or layers in the prediction model and prior information map 258 to generate a functional prediction map 263 that predicts the value of each sensed property (or property associated with the sensed property) at different locations in the field being harvested, as sensed by the field sensor 208.

[0076] Prediction map generator 212 configures prediction map 264 such that prediction map 264 can be operated (or consumed) by control system 214. Prediction map generator 212 can provide prediction map 264 to control system 214 or to control area generator 213 or both. Some examples of different ways in which prediction map 264 can be configured or output are described with respect to boxes 296, 295, 299 and 297. For example, prediction map generator 212 configures prediction map 264 such that prediction map 264 includes values ​​that can be read by control system 214 and used as the basis for generating one or more control signals in different controllable subsystems of agricultural harvester 100, as shown in box 296.

[0077] Control zone generator 213 can divide prediction map 264 into control zones based on values ​​on prediction map 264. Values ​​of consecutive geographic locations within each other's thresholds can be grouped into control zones. Thresholds can be default thresholds, or thresholds can be set based on operator input, input from the automation system, or other criteria. Zone sizes can be based on the responsiveness of control system 214, controllable subsystem 216, wear considerations, or other criteria, as shown in box 295. Prediction map generator 212 configures prediction map 264 for presentation to operators or other users. Control zone generator 213 can configure prediction control zone map 265 for presentation to operators or other users. This is indicated by box 299. When presented to operators or other users, the presentation of prediction map 264 or prediction control zone map 265, or both, can include geographic location-related predicted values ​​on prediction map 264, geographic location-related control zones on prediction control zone map 265, and one or more of the setting values ​​or control parameters used based on the predicted values ​​on map 264 or the zones on prediction control zone map 265. In another example, the presentation may include more abstract or more detailed information. The presentation may also include a confidence level indicating the accuracy of the predicted values ​​on prediction map 264 or the area on prediction control map 265 as measured by sensors on harvester 100 moving through the field. Additionally, where information is presented to more than one location, an authentication and authorization system may be provided to implement the authentication and authorization process. For example, there may be a hierarchy of individuals authorized to view and modify the map and other presented information. As an example, the onboard display device may display the map locally on the machine in near real-time, or the map may be generated at one or more remote locations, or both. In some examples, each physical display device at each location may be associated with a person or user permission level. The user permission level may be used to determine which display markers are visible on the physical display device and which values ​​the corresponding person can change. For example, the local operator of machine 100 may not be able to see the information corresponding to prediction map 264 or make any changes to the operation of the machine. However, a supervisor, such as one at a remote location, might be able to see Predictive Map 264 on a monitor but be prevented from making any changes. A manager at a separate, remote location might be able to see all elements on Predictive Map 264 and also be able to modify it. In some cases, Predictive Map 264 can be accessed and modified by a remote administrator and can be used for machine control. This is an example of an authorization hierarchy that can be implemented. Predictive Map 264 or Predictive Control Area Map 265, or both, can also be configured in other ways, as shown in box 297.

[0078] In box 298, the control system receives input from the geolocation sensor 204 and other field sensors 208. Specifically, in box 300, the control system 214 detects input from the geolocation sensor 204 indicating the geolocation of the harvester 100. Box 302 represents sensor input received by the control system 214 indicating the trajectory or heading of the harvester 100, and box 304 represents the speed of the harvester 100 received by the control system 214. Box 306 represents other information received by the control system 214 from various field sensors 208.

[0079] In block 308, control system 214 generates control signals to control controllable subsystem 216 based on prediction map 264 or prediction control area map 265 or both, and inputs from geographic location sensor 204 and any other field sensors 208. In block 310, control system 214 applies the control signals to the controllable subsystem. It should be understood that the specific control signals generated and the specific controllable subsystem 216 controlled can vary based on one or more different factors. For example, the generated control signals and the controlled subsystem 216 can be based on the type of prediction map 264 or prediction control area map 265 or both being used. Similarly, the timing of the generated control signals, the controlled subsystem 216, and the control signals can be based on various delays in the crop flow through agricultural harvester 100 and the responsiveness of controllable subsystem 216.

[0080] As an example, the generated prediction map 264, in the form of a predicted pest map, can be used to control one or more subsystems 216. Values ​​obtained from the predicted pest map or other types of prediction maps can be used to generate various control signals to control one or more of the controllable subsystems 216.

[0081] In box 312, it is determined whether the harvesting operation has been completed. If the harvesting is not completed, the process proceeds to box 314, where field sensor data from geolocation sensor 204 and field sensor 208 (and possibly other sensors) are read.

[0082] In some examples, at box 316, the agricultural harvester 100 may also detect learning trigger criteria to perform machine learning on one or more of the following: the prediction map 264, the prediction control region map 265, the model generated by the prediction model generator 210, the region generated by the control region generator 213, one or more control algorithms implemented by the controller in the control system 214, and other trigger learning.

[0083] The learning trigger criterion can include any of a variety of different criteria. Some examples of detecting trigger criters are discussed with respect to boxes 318, 320, 321, 322, and 324. For example, in some examples, triggering learning may include recreating the relationships used to generate the predictive model when a threshold amount of field sensor data is received from field sensor 208. In such examples, an amount of field sensor data received from field sensor 208 exceeding a threshold triggers or causes predictive model generator 210 to generate a new predictive model used by predictive map generator 212. Thus, as the agricultural harvester 100 continues its harvesting operation, receiving a threshold amount of field sensor data from field sensor 208 triggers the creation of a new relationship represented by the predictive model generated by predictive model generator 210. Furthermore, the new predictive model can be used to regenerate a new predictive map 264, a predictive control area map 265, or both. Box 318 represents detecting a threshold amount of field sensor data used to trigger the creation of a new predictive model.

[0084] In other examples, the learning trigger criterion can be based on the degree of change in field sensor data from field sensor 208, such as the degree of change over time or compared to previous values. For example, if the change within the field sensor data (or the relationship between the field sensor data and the information in the prior information map 258) is within a selected range, less than a defined amount, or below a threshold, a new predictive model is not generated by predictive model generator 210. As a result, predictive map generator 212 does not generate a new predictive map 264, predictive control area map 265, or both. However, for example, if the change within the field sensor data is outside the selected range, greater than a defined amount, or above a threshold, predictive model generator 210 uses all or part of the newly received field sensor data used by predictive map generator 212 to generate a new predictive map 264 to generate a new predictive model. In box 320, changes in the field sensor data (such as the magnitude of the amount by which the data exceeds a selected range or the magnitude of the change in the relationship between the field sensor data and the information in the prior information map 258) can be used as triggers to cause the generation of new predictive models and predictive maps. Continuing with the example described above, thresholds, ranges, and defined quantities can be set to default values, set by operators or users through user interface interaction, set by the automation system, or otherwise.

[0085] Other learning trigger criteria can also be used. For example, if the predictive model generator 210 switches to a different prior infographic (different from the initially selected prior infographic 258), the switch to a different prior infographic can trigger relearning by the predictive model generator 210, the predictive map generator 212, the control area generator 213, the control system 214, or others. In another example, the transition of the agricultural harvester 100 to different terrain or to a different control area can also be used as a learning trigger criterion.

[0086] In some cases, operator 260 can also edit prediction graph 264 or prediction control area graph 265, or both. Editing can change the values ​​on prediction graph 264, change the size, shape, position, or presence of control areas on prediction control area graph 265, or both. Box 321 shows that the edited information can be used as a learning trigger criterion.

[0087] In some cases, operator 260 may also observe that the automatic control of the controllable subsystem is not as the operator expects. In this case, operator 260 may provide manual adjustments to the controllable subsystem, reflecting operator 260's expectation that the controllable subsystem will operate in a manner different from that commanded by control system 214. Therefore, manual changes to the settings by operator 260 may result in one or more of the following: based on operator 260's adjustments (as shown in box 322), predictive model generator 210 relearns the model, predictive graph generator 212 regenerates graph 264, control area generator 213 regenerates one or more control areas on predictive control area graph 265, and control system 214 relearns the control algorithm or performs machine learning on one or more of the controller components 232 to 246 in control system 214. Box 324 indicates the use of other triggering learning criteria.

[0088] In other examples, relearning can be performed periodically or intermittently, for example based on a chosen time interval, such as a discrete time interval or a variable time interval, as shown in box 326.

[0089] If relearning is triggered (whether based on a learning trigger criterion or on the elapsed time interval, as shown in box 326), one or more of the predictive model generator 210, predictive graph generator 212, control region generator 213, and control system 214 perform machine learning to generate a new predictive model, a new predictive graph, a new control region, and a new control algorithm, respectively, based on the learning trigger criterion. The new predictive model, new predictive graph, and new control algorithm are generated using any additional data collected since the last learning operation. The execution of relearning is indicated by box 328.

[0090] If the harvesting operation is complete, the operation moves from box 312 to box 330, where one or more of the prediction map 264, prediction control area map 265, and prediction model generated by prediction model generator 210 are stored. Prediction map 264, prediction control area map 265, and prediction model can be stored locally on data storage device 202 or sent to a remote system for later use using communication system 206.

[0091] It will be noted that while some examples in this paper describe the predictive model generator 210 and the predictive graph generator 212 receiving prior information graphs when generating the predictive model and the functional prediction graph, respectively, in other examples, the predictive model generator 210 and the predictive graph generator 212 may receive other types of graphs, including prediction graphs, such as the functional prediction graph generated during the harvesting operation, when generating the predictive model and the functional prediction graph, respectively.

[0092] Figure 4 yes Figure 1 A block diagram of a portion of an agricultural harvester 100 is shown. Specifically, Figure 4 Examples of the prediction model generator 210 and the prediction graph generator 212 are shown in more detail. Figure 4 The information flow between the different components is also illustrated. The predictive model generator 210 receives one or more of the following as information maps: historical pest map 329, optical map 331, vegetation index map 332, reconnaissance map 333, and animal activity map 335. As shown, in some examples, the reconnaissance map 333 and animal activity map 335 can represent pest maps without analysis by the generator 210. The predictive model generator 210 receives the vegetation index map 332 as a prior information map. The predictive model generator 210 also receives a geographic location 334 or a geographic location indication from the geographic location sensor 204. The field sensor 208 schematically includes pest sensors (such as pest sensor 336) and a processing system 338. In some cases, the pest sensor 336 may be located on the agricultural harvester 100. In some cases, the pest sensor 336 may include an operator input sensor that allows the user to manually identify pests. The processing system 338 processes the sensor data generated from the pest sensor 336 to generate processed data, some examples of which are described below.

[0093] In some examples, the pest sensor 336 may be an optical sensor (such as a camera) that generates images of an area of ​​the field to be harvested. In some cases, the optical sensor may be arranged on the harvester 100 to collect images of areas adjacent to the harvester 100, such as areas in front of, to the side of, behind, or in another direction relative to the harvester 100 as the harvester 100 moves through the field during harvesting operations.

[0094] The processing system 338 processes one or more images obtained by the pest sensor 336 to generate processed image data identifying one or more characteristics of pests in the images. The pest characteristics detected by the processing system 338 may include the location of the pest present in the image, the intensity of the pest in the image, or the type of pest in the image.

[0095] The field sensor 208 may be or include other types of sensors, such as a camera positioned along the path of the cut material traveling in the harvester 100 (hereinafter referred to as a "process camera"). The process camera can at least partially observe the interior of the harvester 100 and can capture images of the material (including signs of pests, such as damaged grain or plant material) as the material moves through or exits the harvester 100. In some examples, pests or portions of pests can be detected. In other examples, toxins, excrement, or byproducts of pests can be detected.

[0096] In some examples, raw or processed data from the pest sensor 336 can be presented to the operator 260 via the operator interface mechanism 218. The operator 260 can be on the agricultural harvester 100 or at a remote location.

[0097] This discussion focuses on the example of a biohazard sensor 336 being an image sensor (such as a camera). It should be understood that this is merely one example, and other sensors mentioned above are also considered herein as examples of biohazard sensors 336. Figure 4 As shown, the example prediction model generator 210 includes one or more of the following: a historical pest characteristic to pest characteristic generator 339, an optical characteristic to pest characteristic model generator 341, a vegetation index to pest characteristic model generator 342, an animal activity to pest characteristic model generator 344, and a reconnaissance characteristic to pest characteristic model generator 346. In other examples, compared to Figure 4The components shown in the examples may be additional, fewer, or different components in the prediction model generator 210. Therefore, in some examples, the prediction model generator 210 may also include other items 348, which may include other types of prediction model generators to generate other types of harmful biological characteristic models.

[0098] Model generator 339 identifies the relationship between pest characteristics detected in image data 340 at geographic locations corresponding to the obtained image data 340 and historical pest characteristics at the same locations in the field corresponding to the detected pest characteristics from historical pest map 329. Based on this relationship established by model generator 339, model generator 339 generates a predictive pest model. The predictive pest model is used by pest location map generator 356 to predict pest characteristics at different locations in the field based on geographic reference historical pest characteristics included in historical pest map 329 at the same locations in the field.

[0099] Model generator 341 identifies the relationship between pest characteristics detected in image data 340 at a geographic location corresponding to the obtained image data 340 and optical characteristic values ​​from optical map 331 corresponding to the same location in the field where the pest characteristics were detected. Based on this relationship established by model generator 341, model generator 341 generates a predictive pest model. The predictive pest model is used by pest location map generator 356 to predict pest characteristics at different locations in the field based on georeferenced optical characteristic values ​​in optical characteristic map 331 containing the same locations in the field.

[0100] Model generator 342 identifies the relationship between pest characteristics detected in image data 340 at geographic locations corresponding to the obtained image data 340 and vegetation index values ​​from vegetation index map 332 corresponding to the detected pest characteristics in the same location in the field. Based on this relationship established by model generator 342, model generator 342 generates a pest prediction model. The pest location map generator 356 uses the predicted pest model to predict pest characteristics at different locations in the field based on georeferenced vegetation index values ​​in vegetation index map 332 containing the same locations in the field.

[0101] Model generator 344 identifies the relationship between pest types at a specific location in the field, identified by processed image data 340, and animal activity values ​​from animal activity map 335 at the same location. Model generator 344 generates a predictive pest model, which pest type map generator 356 uses to predict pest characteristics at that specific location in the field based on animal activity values.

[0102] Model generator 346 identifies the relationship between pest characteristics represented in processed data 340 at a geographic location corresponding to data 340 and reconnaissance values ​​at the same geographic location. Reconnaissance values ​​are geographic reference values ​​included in reconnaissance map 333. Model generator 346 then generates a predictive pest model, which pest map generator 356 uses to predict pest characteristics at a specific location in the field based on the reconnaissance values ​​at that location.

[0103] In light of the above, the prediction model generator 210 is operable to generate multiple pest prediction models, such as one or more of the pest prediction models generated by model generators 339, 341, 342, 344, 346, and 348. In another example, two or more of the pest prediction models described above can be combined into a single pest prediction model, which predicts two or more of pest location, pest intensity, and pest type based on historical pest values, optical values, vegetation index values, scouting values, or animal activity values ​​at different locations in the field. Any one of these pest models or combinations thereof in Figure 4 The model is represented by the 350 pest model.

[0104] The pest prediction model 350 is provided to the prediction map generator 212. Figure 4 In one example, the prediction map generator 212 includes a pest map generator 356. In other examples, the prediction map generator 212 may include additional, fewer, or different map generators. Therefore, in some examples, the prediction map generator 212 may include additional items 358, which may include other types of map generators for generating pest maps for other pest characteristics. The pest map generator 356 receives the predicted pest model 350 and generates a prediction map that maps (draws) predictions of the presence, intensity, type, or other characteristics of pests at different locations in the field.

[0105] The prediction map generator 212 outputs one or more prediction pest maps 360, predicting one or more of the following: pest location, pest intensity, pest type, or another pest characteristic. Each prediction pest map 360 predicts the corresponding pest characteristic at a different location in the field. Each of the generated prediction pest maps 360 can be provided to a control zone generator 213, a control system 214, or both. The control zone generator 213 generates control zones and incorporates these control zones into the functional prediction map 360. One or more functional prediction maps can be provided to the control system 214, which generates control signals based on the one or more functional prediction maps to control one or more controllable subsystems 216.

[0106] Figure 5 This is a flowchart illustrating an example of the operation of the prediction model generator 210 and the prediction map generator 212 in generating a prediction pest model 350 and a prediction pest map 360. In box 362, the prediction model generator 210 and the prediction map generator 212 receive historical pest maps, optical property maps, vegetation index maps, reconnaissance maps, animal activity maps, or combinations thereof. In box 364, the processing system 338 receives one or more images from a pest sensor 336. As discussed above, the pest sensor 336 can be a camera, such as a forward-looking camera 366; an optical sensor 368 observing the interior of a combine harvester, such as a camera; or another type of pest sensor 370. In some examples, pest-related toxins or other chemicals may fluoresce upon exposure to ultraviolet light. In some examples, pest-related chemicals may be airborne and then detected by a gas sensor or electronic nose.

[0107] In box 372, processing system 338 processes one or more received images to generate image data indicating the characteristics of pests present in the one or more images. In box 374, the image data may indicate the location of pests, pest intensity, or both, that may be present at a location (such as in front of a combine harvester). In some cases, as shown in box 376, the image data may indicate pests located inside or discharged from the combine harvester. In some cases, as shown in box 380, the image data may indicate the type of pest. Therefore, the image data includes a pest type indicator 378 that identifies the type of one or more pests encountered by the combine harvester. The type of pest may be determined based on one or more images of the pest, one or more images of the crop or weeds affected by the pest, or one or more images containing a subject indicating the type of pest. The image data may also include other data.

[0108] In box 382, ​​the predictive model generator 210 also obtains the geographic location corresponding to the image data. For example, the predictive model generator 210 can obtain the geographic location from the geographic location sensor 204 and determine the precise geographic location of the captured image or the image data 340 derived from it based on machine latency, machine speed, etc.

[0109] In box 384, the prediction model generator 210 generates one or more predictive pest models, such as pest type 350, that model the relationship between vegetation index values ​​obtained from a priori infographic (such as priori infographic 258) and pest characteristics or related characteristics sensed by field sensors 208. For example, the prediction model generator 210 may generate a predictive pest model that models the relationship between vegetation index values ​​and sensed characteristics, including pest location, pest intensity, or pest type indicated by image data obtained from field sensors 208. Alternatively, the prediction model generator 210 may generate a predictive pest model that models the relationship between reconnaissance values ​​and sensed characteristics, including pest location, pest intensity, or pest type indicated by image data obtained from field sensors 208. Alternatively, the prediction model generator 210 may generate a predictive pest model that models the relationship between animal activity values ​​and sensed characteristics, including pest location, pest intensity, or pest type indicated by image data obtained from field sensors 208.

[0110] In box 386, a pest prediction model (such as pest prediction model 350) is provided to a prediction map generator 212, which generates a prediction pest map 360 based on values ​​from one or more of historical pest maps, optical property maps, vegetation index maps, reconnaissance maps, animal activity maps, or certain other maps, and the prediction pest model 350. This prediction pest map maps the predicted pest characteristics. For example, in some examples, the prediction pest map 360 predicts the location of pests. In some examples, the prediction pest map 360 predicts both the location of pests and pest intensity values ​​(as shown in box 388). In some examples, the prediction pest map 360 predicts both the location of pests and the type of pest (as shown in box 390), and in other examples, the prediction map 360 predicts other items (as shown in box 392). For example, the degree or impact of the pest on the crop. Furthermore, the prediction pest map 360 can be generated during agricultural operations. Therefore, as agricultural harvesters move through fields to perform agricultural operations, a predicted pest map 360 is generated while agricultural operations are being performed.

[0111] In block 394, the prediction map generator 212 outputs a predicted pest map 360. In block 391, the predicted pest map generator 212 outputs a predicted pest map for presentation to operator 260 and possible interaction by operator 260. In block 393, the prediction map generator 212 can configure the map for use by control system 214. In block 395, the prediction map generator 212 can also provide map 360 to control area generator 213 to generate control areas. In block 397, the prediction map generator 212 also configures map 360 in other ways. The predicted pest map 360 (with or without control areas) is provided to control system 214. In block 396, control system 214 generates control signals based on the predicted pest map 360 to control controllable subsystem 216.

[0112] Figure 6A yes Figure 1 A block diagram of an example portion of an agricultural harvester 100 is shown. Specifically, Figure 6A Examples of the prediction model generator 210 and the prediction map generator 212 are shown in particular. In the illustrated example, the prior information map 258 is one or more of the sensed pest map 337, the predicted pest map 360, or the prior operation map 400. The prior operation map 400 may include the value of another agricultural characteristic at different locations in the field. The agricultural characteristic value may be a value collected during a prior operation (e.g., a prior operation performed by a sprayer). For example, the sprayer may be equipped with a camera to detect the presence of pests or other characteristics.

[0113] Moreover, in Figure 6A In the example shown, the field sensor 208 may include one or more of the following: yield sensor 402, grain quality sensor 403, operator input sensor 404, and processing system 406. The field sensor 208 may also include other sensors 408.

[0114] The yield sensor 402 senses variables indicating the yield being harvested by the agricultural harvester 100. The grain quality sensor 403 senses the quality of the grain being processed, such as whether the grain is broken, diseased, rotten, spoiled, toxic, or contaminated.

[0115] Operator input sensor 404 schematically senses various operator inputs. Inputs may be setting inputs or other control inputs used to control settings on the agricultural harvester 100, such as steering inputs and other inputs. Therefore, when operator 260 changes settings or provides command inputs through operator interface mechanism 218, such inputs are detected by operator input sensor 404, which provides a sensor signal indicating the sensed operator input. Crop status sensor 405 detects the crop status of crops near the agricultural harvester 100. Crop status may include upright crops, lodged crops, partially lodged crops, and the orientation of lodged or partially lodged crops, etc.

[0116] Processing system 406 may receive sensor signals from biomass sensor 402 or operator input sensor 404, or both, and generate an output indicating the sensed variable. For example, processing system 406 may receive sensor input from optical sensor 410 or rotor pressure sensor 412 and generate an output indicating biomass. Processing system 406 may also receive input from operator input sensor 404 and generate an output indicating the sensed operator input.

[0117] Predictive model generator 210 may include a pest trait-to-yield model generator 416, a pest trait-to-grain quality model generator 417, a pest trait-to-crop status model generator 420, and a pest trait-to-operator command model generator 422. In other examples, predictive model generator 210 may include additional, fewer, or other model generators 424. Predictive model generator 210 may receive a geographic location indicator 334 from geographic location sensor 204 and generate a predictive model 426 that models the relationship between information in one or more of the prior information graph 258 and one or more of the following items: yield sensed by yield sensor 402, grain quality sensed by grain quality sensor 403, crop status sensed by crop status sensor 405, and operator input commands sensed by operator input sensor 404.

[0118] For example, the pest trait-to-yield model generator 416 generates a relationship between pest trait values ​​and yield values ​​sensed by yield sensor 402. The pest trait-to-grain quality model generator 418 schematically generates a model representing the relationship between pest trait and variables indicating grain quality sensed by grain quality sensor 403. The pest trait-to-crop state model generator 420 schematically generates a model representing the relationship between pest trait and variables indicating crop state sensed by crop state sensor 405. The pest trait-to-operator command model generator 422 generates a model that models the relationship between pest trait and operator input commands sensed by operator input sensor 404. The prediction model 426 generated by prediction model generator 210 may include one or more of the prediction models generated by pest trait-to-yield model generator 416, pest trait-to-grain quality model generator 417, pest trait-to-crop state model generator 420, pest trait-to-operator command model generator 422, and other model generators that may be included as part of other items 424.

[0119] exist Figure 6A In one example, the prediction graph generator 212 includes a prediction yield graph generator 429, a prediction grain quality graph generator 430, a prediction crop status graph generator 431, and a prediction operator command graph generator 432. In other examples, the prediction graph generator 212 may include additional, fewer, or other graph generators 434.

[0120] The predicted yield map generator 429 receives one or more of the prediction model 426 and the information map 258. The predicted yield map generator 429 generates a functional predicted yield map 436 based on one or more of the pest characteristics in the prior information map 258 at different locations in the field and based on the prediction model 426, predicting the yield at those locations in the field.

[0121] The grain quality prediction map generator 430 receives one or more of the prediction model 426 and the information map 258. Based on the pest characteristics in one or more of the prior information maps 258 at different locations in the field and based on the prediction model 426, the grain quality prediction map generator 430 generates a functional grain quality prediction map 437 that predicts the grain quality at those locations in the field.

[0122] The crop state prediction map generator 431 receives one or more of the prediction model 426 and the information map 258. Based on the pest characteristics in one or more of the prior information maps 258 at different locations in the field and based on the prediction model 426, the crop state prediction map generator 431 generates a functional crop state prediction map 438 that predicts the crop state at those locations in the field.

[0123] The predictive operator command graph generator 432 receives a predictive model 426 (such as a predictive model generated by the pest characteristic to command model generator 422) that models the relationship between pest characteristics and operator command inputs detected by the operator input sensor 404, and generates a functional predictive operator command graph 439 of the predictive operator command inputs at different locations in the field based on pest characteristic values ​​from one or more information graphs 258 and the predictive model 426.

[0124] Other graph generator 434 may receive a prediction model 426 from another model generator 424, which models the relationship between pest characteristics and agricultural characteristics sensed by another sensor 408. Other graph generator 434 generates a functional predictive agricultural characteristic graph 440 based on pest characteristic values ​​from one or more information graphs 258 and the prediction model 426, predicting agricultural characteristics at different locations in the field.

[0125] Prediction graph generator 212 outputs one or more of functional prediction graphs 436, 437, 438, 439, and 440. Each of the functional prediction graphs 436, 437, 438, 439, and 440 can be provided to control area generator 213, control system 214, or both. Control area generator 213 generates control areas to provide a predicted control area graph 265 corresponding to each of the graphs 436, 437, 438, 439, and 440 received by control area generator 213. Any or all of the functional prediction graphs 436, 437, 438, or 440 and the corresponding graph 265 can be provided to control system 214, which generates control signals based on one or all of the functional prediction graphs 436, 437, 438, 439, and 430, or including the corresponding graph 265 of the control area, to control one or more of the controllable subsystems 216. Any or all of Figures 436, 437, 438, 439, or 440, or the corresponding Figure 265, may be presented to operator 260 or another user.

[0126] Figure 6B This is a block diagram showing some examples of the real-time (field) sensor 208. Figure 6B Some of the sensors shown, or different combinations thereof, may simultaneously have sensor 336 and processing system 338. Figure 6BSome of the possible field sensors 208 shown are illustrated and described relative to the previous figures and are similarly numbered. Figure 6B The field sensors 208 shown may include operator input sensors 980, machine sensors 982, harvested material property sensors 984, field and soil property sensors 985, and environmental property sensors 987, and may include a variety of other sensors 226. Non-machine sensors 983 include one or more operator input sensors 980, one or more harvested material property sensors 984, one or more field and soil property sensors 985, one or more environmental property sensors 987, and may also include other sensors 226. The operator input sensor 980 may be a sensor that senses operator input via operator interface mechanism 218. Therefore, the operator input sensor 980 may sense user movement via linkages, joysticks, steering wheels, buttons, dials, or pedals. The operator input sensor 980 may also sense user interaction with other operator input structures, such as interaction with a touchscreen, a microphone utilizing voice recognition, or any of various other operator input mechanisms.

[0127] Machine sensor 982 can sense various characteristics of the agricultural harvester 100. For example, as discussed above, machine sensor 982 may include machine speed sensor 146, separator loss sensor 148, clean grain camera 150, forward-view image capture mechanism 151, loss sensor 152, or geolocation sensor 204, examples of which are described above. Machine sensor 982 may also include machine setting sensor 991 that senses machine settings. (See above references) Figure 1Examples of machine setups are described. A front-end equipment (e.g., header) position sensor 993 can sense the position of the header 102, reel 164, cutter 104, or other front-end equipment relative to the frame of the harvester 100. For example, sensor 993 can sense the height of the header 102 above the ground. Machine sensor 982 may also include a front-end equipment (e.g., header) orientation sensor 995. Sensor 995 can sense the orientation of the header 102 relative to the harvester 100 or relative to the ground. Machine sensor 982 may include a stability sensor 997. Stability sensor 997 senses vibrational or bouncing motions (and amplitude) of the harvester 100. Machine sensor 982 may also include a stubble setup sensor 999 configured to sense whether the harvester 100 is configured to chop stubble, produce a stockpile, or otherwise process stubble. Machine sensor 982 may include a cleaning chamber fan speed sensor 951 that senses the speed of the cleaning fan 120. Machine sensor 982 may include a recess gap sensor 953 for sensing the gap between the rotor 112 and the recess 114 on the harvester 100. Machine sensor 982 may include a husk sieve gap sensor 955 for sensing the size of the openings in the husk sieve 122. Machine sensor 982 may include a threshing rotor speed sensor 957 for sensing the rotor speed of the rotor 112. Machine sensor 982 may include a rotor pressure sensor 959 for sensing the pressure used to drive the rotor 112. Machine sensor 982 may include a sieve gap sensor 961 for sensing the size of the openings in the sieve 124. Machine sensor 982 may include a MOG humidity sensor 963 for sensing the humidity level of the MOG passing through the harvester 100. Machine sensor 982 may include a machine orientation sensor 965 for sensing the orientation of the harvester 100. Machine sensor 982 may include a material feed rate sensor 967 for sensing the feed rate of material as it travels through the feed chamber 106, the clean grain elevator 130, or other locations within the harvester 100. Machine sensor 982 may include a biomass sensor 969 that senses biomass traveling through feed chamber 106, separator 116, or other locations within the harvester 100. Machine sensor 982 may include a fuel consumption sensor 971 that senses the rate of fuel consumption of the harvester 100 over time. Machine sensor 982 may include a power utilization sensor 973 that senses power utilization in the harvester 100 (such as which subsystems are using power), or the rate at which subsystems are using power, or the distribution of power among subsystems in the harvester 100. Machine sensor 982 may include a tire pressure sensor 977 that senses the inflation pressure in the tires 144 of the harvester 100. Machine sensor 982 may include a variety of other machine performance sensors or machine characteristic sensors (as shown in box 975).The machine performance sensor and machine characteristic sensor 975 can sense the machine performance or characteristics of the agricultural harvester 100.

[0128] While crop material is being processed by the agricultural harvester 100, the harvest material property sensor 984 can sense the characteristics of the cut crop material. Crop properties may include things such as crop type, crop moisture content, grain quality (e.g., broken grain), MOG level, grain composition (e.g., starch and protein), MOG moisture content, and other crop material properties. Other sensors can sense straw “toughness,” corn and ear adhesion, and other characteristics that can be beneficially used to control processing to achieve better grain capture, reduced grain damage, lower power consumption, reduced grain loss, etc.

[0129] The 985 field and soil property sensor can sense the characteristics of fields and soils. Field and soil properties may include soil moisture, soil density, presence and location of waterlogging, soil type, and other soil and field characteristics.

[0130] The environmental characteristic sensor 987 can sense one or more environmental characteristics. Environmental characteristics may include things such as wind direction and speed, precipitation, fog, dust level or other obfuscation or other environmental features.

[0131] In some examples, Figure 6B One or more of the sensors shown are processed to receive processed data 309, which is used as input to model generator 210. Model generator 210 generates a model indicating the relationship between the sensor data and one or more of the prior information graphs or prediction information graphs. This model is provided to graph generator 212, which generates mappings corresponding to the data from the prior information graphs or prediction information graphs. Figure 6B A graph showing the predicted sensor data values ​​or related characteristics of the sensor.

[0132] Figure 7 A flowchart illustrating an example of the operation of the predictive model generator 210 and the predictive graph generator 212 in generating one or more predictive models 426 and one or more functional predictive graphs 436, 437, 438, 439 and 440 is shown.

[0133] In box 442, the prediction model generator 210 and the prediction map generator 212 receive a prior information map 258. The prior information map 258 may be a sensed pest map 337, a predicted pest map 360, or a prior operation map 400 created using data obtained during prior operations in the field.

[0134] In box 444, the prediction model generator 210 receives sensor signals containing sensor data from field sensor 208. Box 446 indicates that the sensor signals received by the prediction model generator 210 include data indicating the type of yield. Box 448 indicates that the sensor signal data can indicate grain quality. Box 449 indicates that the sensor signal data can indicate crop status. Box 450 indicates that the sensor signals received by the prediction model generator 210 can be sensor signals sensed by operator input sensor 404, containing data of the type indicating operator command input. The prediction model generator 210 can also receive other field sensor inputs (as shown in box 452).

[0135] In block 454, processing system 406 processes data contained in one or more sensor signals received from one or more field sensors 208 to obtain processed data 409, such as... Figure 6A As shown. Data contained in one or more sensor signals may be in its raw format, which is processed to receive processed data 409. For example, a temperature sensor signal includes resistance data, which can be processed into temperature data. In other examples, processing may include digitizing, encoding, formatting, scaling, filtering, or classifying the data. The processed data 409 may indicate one or more of yield, grain quality, crop status, operator input commands, or other agricultural characteristics. The processed data 409 is provided to the predictive model generator 210.

[0136] Back Figure 7 In box 456, the prediction model generator 210 also receives geographic location 334 from the geographic location sensor 204, such as Figure 6A As shown. Geographic location 334 can be associated with or corresponding to the geographic location obtained from or associated with the sensed variable(s) sensed by the field sensor 208. For example, the predictive model generator 210 can obtain geographic location 334 from geographic location sensor 204 and determine the precise geographic location corresponding to the processed data 409 based on machine latency, machine speed, etc.

[0137] In box 458, the prediction model generator 210 generates one or more prediction models 426 that model the relationship between the mapped values ​​in the prior infographic and the characteristics represented in the processed data 409. For example, in some cases, the mapped values ​​in the prior infographic may be pest characteristics, and the prediction model generator 210 uses the mapped values ​​of the prior infographic and characteristics sensed by the field sensor 208 (as represented in the processed data 490) or related characteristics (such as characteristics related to the characteristics sensed by the field sensor 208) to generate the prediction model.

[0138] For example, in box 460, prediction model generator 210 can generate a prediction model 426 that models the relationship between one or more pest traits obtained from one or more prior infographics and yield. In another example, prediction model generator 210 can generate a prediction model 426 that models the relationship between pest traits obtained from one or more prior infographics and grain quality obtained from field sensors. In yet another example, prediction model generator 210 can generate a prediction model 426 that models the relationship between pest traits and crop status. In yet another example, prediction model generator 210 can generate a prediction model 426 that models the relationship between pest traits and operator command input.

[0139] One or more prediction models 426 are provided to the prediction map generator 212. In box 466, the prediction map generator 212 generates one or more functional prediction maps. The functional prediction maps can be a functional yield prediction map 437, a functional grain quality prediction map 436, a functional crop status prediction map 438, a functional operator command prediction map 439, a functional agricultural characteristic prediction map 440, or any combination of these maps. The functional grain quality prediction map 436 predicts the grain quality that the harvester 100 will encounter at different locations in the field. The functional yield prediction map 437 predicts the expected yield that the harvester 100 will encounter at different locations in the field. The functional crop status prediction map 438 predicts the crop status that the harvester 100 will encounter at different locations in the field. The functional operator command prediction map 439 may predict operator command inputs at different locations in the field. The functional agricultural characteristic prediction map 440 predicts one or more agricultural characteristics at different locations in the field. One or more of the functional prediction graphs 436, 437, 438, 439, and 440 can be generated during the agricultural operation process. Therefore, as the agricultural harvester 100 moves through the field to perform agricultural operations, one or more prediction graphs 436, 437, 438, 439, and 440 are generated along with the performance of the agricultural operations.

[0140] In box 468, the prediction graph generator 212 outputs one or more functional prediction graphs 436, 437, 438, 439, and 440. In box 470, the prediction graph generator 212 can configure the graphs to be presented to operator 260 or another user, and to be interacted with by operator 260 or another user. In box 472, the prediction graph generator 212 can configure the graphs for use by the control system 214. In box 474, the prediction graph generator 212 can provide one or more prediction graphs 436, 437, 438, 439, and 440 to the control area generator 213 to generate a control area. In box 476, the prediction graph generator 212 can otherwise configure one or more prediction graphs 436, 437, 438, 439, and 440. In the example (where one or more functional prediction graphs 436, 437, 438, 439 and 440 are provided to the control area generator 213), one or more functional prediction graphs 436, 437, 438, 439 and 440 and the control areas they include (represented by the corresponding graph 265, as described above) can be presented to the operator 260 or another user, or can also be provided to the control system 214.

[0141] In block 478, control system 214 then generates control signals to control the controllable subsystem based on one or more functional prediction maps 436, 437, 438, 439 and 440 (or functional prediction maps 436, 437, 438, 439 and 440 with control areas) and inputs from geolocation sensor 204.

[0142] In other examples, the agricultural harvester 100 can also be controlled in other ways. For example, the header actuator 248 can be controlled based on predicted crop conditions. Or, for example, the propulsion subsystem 250 can be controlled to avoid areas predicted to have pests. Or, for example, the grain cleaning subsystem can be controlled to close the chaff screen and increase the fan speed to keep pests outside the clean grain bin. Or, for example, the grain cleaning subsystem can be controlled to open the chaff screen and decrease the fan speed to prevent pests from being deposited on the field. Or, for example, the stubble subsystem 253 can be controlled to allow material to be separated.

[0143] In one example of the receive function prediction diagram of control system 214, path planning controller 234 controls steering subsystem 252 to turn harvester 100. In another example of the receive function prediction diagram of control system 214, stubble system controller 244 controls stubble subsystem 138. In another example of the receive function prediction diagram of control system 214, setting controller 232 controls threshing settings of threshing machine 110. In another example of the receive function prediction diagram of control system 214, setting controller 232 or another controller 246 controls material handling subsystem 125. In another example of the receive function prediction diagram of control system 214, setting controller 232 controls crop cleaning subsystem. In another example of the receive function prediction diagram of control system 214, machine cleaning controller 245 controls machine cleaning subsystem 254 on harvester 100. In another example of the receive function prediction diagram of control system 214, communication system controller 229 controls communication system 206. In another example of the receive function prediction diagram of control system 214, operator interface controller 231 controls operator interface mechanism 218 on harvester 100. In another example of the function prediction diagram received by control system 214, platform position controller 242 controls machine / header actuators to control the platform on the agricultural harvester 100. In another example of the function prediction diagram received by control system 214, belt conveyor controller 240 controls machine / header actuators to control the belt conveyor belt on the agricultural harvester 100. In another example of the function prediction diagram received by control system 214, other controllers 246 control other controllable subsystems 256 on the agricultural harvester 100.

[0144] Figure 8 A block diagram illustrating an example of a control area generator 213 is shown. The control area generator 213 includes a work machine actuator (WMA) selector 486, a control area generation system 488, and a regime area generation system 490. The control area generator 213 may also include other items 492. The control area generation system 488 includes a control area standard identifier component 494, a control area boundary definition component 496, a target setting identifier component 498, and other items 520. The regime area generation system 490 includes a regime area standard identifier component 522, a regime area boundary definition component 524, a set resolver identifier component 526, and other items 528. Before describing the overall operation of the control area generator 213 in more detail, a brief description of some of the items in the control area generator 213 and their corresponding operations will be provided first.

[0145] The agricultural harvester 100 or other operating machine may have various types of controllable actuators that perform different functions. The controllable actuators on the agricultural harvester 100 or other operating machine are collectively referred to as operating machine actuators (WMAs). Each WMA can be controlled independently based on values ​​on a function prediction map, or WMAs can be controlled in groups based on one or more values ​​on the function prediction map. Therefore, the control area generator 213 can generate control areas corresponding to each individual controllable WMA, or corresponding to groups of WMAs with coordinated control.

[0146] WMA selector 486 selects the WMA or WMA group for which a corresponding control region is to be generated. Control region generation system 488 then generates a control region for the selected WMA or WMA group. For each WMA or WMA group, different criteria can be used to identify the control region. For example, for a WMA, the WMA response time can be used as a criterion for defining the boundary of the control region. In another example, wear characteristics (e.g., the degree of wear of a particular actuator or mechanism due to its movement) can be used as a criterion for identifying the boundary of the control region. Control region criterion identifier component 494 identifies the specific criterion that will be used to define the control region for the selected WMA or WMA group. Control region boundary definition component 496 processes the values ​​on the function prediction map in the analysis to define the boundary of the control region on the function prediction map based on the values ​​on the function prediction map in the analysis and based on the control region criteria of the selected WMA or WMA group.

[0147] The target setting identifier component 498 sets the value of the target setting, which will be used to control the WMA or WMA group in different control areas. For example, if the selected WMA is the propulsion system 250 and the function prediction map in the analysis is the function prediction speed map 438, then the target setting in each control area can be a target speed setting based on the speed values ​​contained in the function prediction speed map 238 within the identified control area.

[0148] In some examples, when controlling the harvester 100 based on its current or future position, multiple target settings are possible for the WMA at a given position. In this case, the target settings may have different values ​​and may compete with each other. Therefore, it is necessary to resolve the target settings so that only a single target setting is used to control the WMA. For example, in the case where the WMA is an actuator controlled in the propulsion system 250 to control the speed of the harvester 100, there may be multiple different competing sets of criteria, which are considered by the control zone generation system 488 when identifying the control zone and the target settings of the WMA selected in the control zone. For example, different target settings for controlling machine speed may be generated based on, for example, detected or predicted feed rate values, detected or predicted fuel efficiency values, detected or predicted grain loss values, or combinations of these values. However, at any given time, the harvester 100 cannot travel on the ground at multiple speeds simultaneously. Instead, at any given time, the harvester 100 travels at a single speed. Therefore, one of the competing target settings is selected to control the speed of the agricultural harvester 100.

[0149] Therefore, in some examples, the dynamic zone generation system 490 generates dynamic zones to resolve multiple different competing target settings. The dynamic zone criterion identification component 522 identifies the criteria used to establish dynamic zones on the selected WMA or WMA group on the functional prediction map in the analysis. Some criteria that can be used to identify or define dynamic zones include, for example, crop type or crop species based on the planting map, or another source of crop type or crop species, pest type, pest intensity, or crop state (such as whether the crop is lodged, partially lodged, or upright). Just as each WMA or WMA group may have a corresponding control zone, different WMAs or WMA groups may have corresponding dynamic zones. The dynamic zone boundary definition component 524 identifies the boundaries of the dynamic zones on the functional prediction map in the analysis based on the dynamic zone criteria identified by the dynamic zone criterion identification component 522.

[0150] In some examples, dynamic zones may overlap. For instance, a crop type dynamic zone may partially or completely overlap with a crop state dynamic zone. In such examples, different dynamic zones can be assigned priority levels such that, in the case of two or more overlapping dynamic zones, the dynamic zone assigned a higher priority level or importance takes precedence over the dynamic zone with a lower priority level or importance. The priority levels of dynamic zones can be set manually or automatically using rule-based systems, model-based systems, or other systems. As an example, in the case of an overlap between a lodged crop dynamic zone and a crop type dynamic zone, the lodged crop dynamic zone can be assigned greater importance in the priority level than the crop type dynamic zone, thus giving priority to the lodged crop dynamic zone.

[0151] Furthermore, for a given WMA or WMA group, each dynamic region may have a unique setting resolver. The setting resolver identifier component 526 identifies a specific setting resolver for each dynamic region identified on the function prediction graph in the analysis, and for a specific setting resolver for the selected WMA or WMA group.

[0152] Once a setting resolver is identified for a specific dynamic zone, it can be used to resolve competing target settings, in which more than one target setting is identified based on the control zone. Different types of setting resolvers can take different forms. For example, a setting resolver identified for each dynamic zone could include a human-selected resolver, in which the competing target setting is presented to an operator or other user for resolution. In another example, the setting resolver could include a neural network or other artificial intelligence or machine learning system. In this case, the setting resolver can resolve competing target settings based on a predicted or historical quality metric corresponding to each of the different target settings. As an example, an increased vehicle speed setting might reduce harvesting time and corresponding time-based labor and equipment costs, but could increase grain loss. A decreased vehicle speed setting might increase harvesting time and corresponding time-based labor and equipment costs, but could reduce grain loss. When grain loss or harvesting time is selected as a quality metric, given two competing vehicle speed setting values, the predicted or historical value of the selected quality metric can be used to resolve the speed setting. In some cases, setting the parser can be a set of threshold rules, which can be used to replace or supplement the dynamic region. Examples of threshold rules can be expressed as follows:

[0153] If the predicted biomass value within 20 feet of the header of the agricultural harvester 100 is greater than x kg (where x is the selected or predetermined value), the target setting value selected based on the feed rate rather than other competing target settings is used; otherwise, the target setting value based on grain loss rather than other competing target settings is used.

[0154] A setting parser can be a logical component that executes logical rules when identifying a target setting. For example, a setting parser can parse a target setting while attempting to minimize harvest time, minimize total harvest cost, or maximize harvested grain, or other variables calculated as a function of different candidate target settings. Harvesting time can be minimized when the amount harvested is reduced to or below a selected threshold. Total harvest cost can be minimized when it is reduced to or below a selected threshold. Harvested grain can be maximized when the amount harvested is increased to or above a selected threshold.

[0155] Figure 9 This is a flowchart illustrating an example of the operation of the control region generator 213 when it receives a graph for region processing (e.g., a graph in analysis) and generates control regions and dynamic regions.

[0156] In box 530, the control region generator 213 receives the graph in the analysis for processing. In one example, as shown in box 532, the graph in the analysis is a function prediction graph. For example, the graph in the analysis could be one of function prediction graphs 436, 437, 438, or 440. Box 534 indicates that the graph in the analysis could also be other graphs.

[0157] In box 536, WMA selector 486 selects the WMA or WMA group for which a control zone is to be generated on the graph in the analysis. In box 538, control zone criterion identification component 494 obtains the control zone definition criteria for the selected WMA or WMA group. Box 540 indicates an example where the control zone criteria are or include the wear characteristics of the selected WMA or WMA group. Box 542 indicates an example where the control zone definition criteria are or include the amplitude and variation of input source data, such as the amplitude and variation of values ​​on the graph in the analysis or the amplitude and variation of inputs from various field sensors 208. Box 544 indicates an example where the control zone definition criteria are or include physical machine characteristics, such as the physical dimensions of the machine, the speed of operation of different subsystems, or other physical machine characteristics. Box 546 indicates an example where the control zone definition criteria are or include the responsiveness of the selected WMA or WMA group when a setpoint for a new command is reached. Box 548 indicates an example where the control zone definition criteria are or include machine performance metrics. Box 550 indicates an example where the control zone definition criterion is or includes operator preferences. Box 552 indicates an example where the control zone definition criterion is or includes other items. Box 549 indicates an example where the control zone definition criterion is time-based, meaning that the harvester 100 will not cross the boundary of the control zone until a selected amount of time has elapsed since the harvester 100 entered the specific control zone. In some cases, the selected amount of time may be a minimum amount of time. Therefore, in some cases, the control zone definition criterion can prevent the harvester 100 from crossing the boundary of the control zone until at least the selected amount of time has elapsed. Box 551 indicates an example where the control zone definition criterion is based on a selected size value. For example, a control zone definition criterion based on a selected size value can exclude the definition of control zones smaller than the selected size. In some cases, the selected size may be a minimum size.

[0158] In box 554, the dynamic zone standard identification component 522 obtains the dynamic zone definition standard of the selected WMA or WMA group. Box 556 indicates an example where the dynamic zone definition standard is based on manual input from operator 260 or another user. Box 558 shows an example where the dynamic zone definition standard is based on crop type or crop variety. Box 560 shows an example where the dynamic zone definition standard is based on pest type or pest intensity or both. Box 562 shows an example where the dynamic zone definition standard is based on or includes crop status. Box 564 indicates an example where the dynamic zone definition standard is also or includes other standards.

[0159] In box 566, the control zone boundary definition component 496 generates the boundary of the control zone on the graph in the analysis based on the control zone criteria. The dynamic zone boundary definition component 524 generates the boundary of the dynamic zone on the graph in the analysis based on the dynamic zone criteria. Box 568 indicates an example in which the boundary of the control zone and the dynamic zone is identified. Box 570 shows that the target setting identifier component 498 identifies the target settings for each in the control zone. The control zone and the dynamic zone can also be generated in other ways, and this is indicated by box 572.

[0160] In box 574, the set parser identifier component 526 identifies the set parser for the selected WMA in each dynamic region defined by the dynamic region boundary definition component 524. As discussed above, the dynamic region parser can be a human parser 576, an artificial intelligence or machine learning system parser 578, a parser 580 based on predicted quality or historical quality set for each competing objective, a rule-based parser 582, a performance criterion-based parser 584, or another parser 586.

[0161] In box 588, WMA selector 486 determines if there are more WMAs or WMA groups to process. If there are additional WMAs or WMA groups to process, processing returns to box 436, where the next WMA or WMA group for which a control area and dynamic area are defined is selected. When no additional WMAs or WMA groups remain for which a control area or dynamic area is to be generated, processing moves to box 590, where control area generator 213 generates a graph for each output in each WMA or WMA group, with a control area, target settings, dynamic area, and settings resolver. As discussed above, the output graph can be presented to operator 260 or another user; the output graph can be provided to control system 214; or the output graph can be output in other ways.

[0162] Figure 10 An example is shown of a control system 214 controlling the operation of an agricultural harvester 100 based on a map output by a control zone generator 213. Thus, in box 592, the control system 214 receives a map of the work site. In some cases, this map may be a functional prediction map that includes control zones and dynamic zones (as shown in box 594). In some cases, the received map may be a functional prediction map that excludes control zones and dynamic zones. Box 596 indicates an example where the received work site map may be a priori information map with control zones and dynamic zones identified thereon. Box 598 indicates an example where the received map may include multiple different maps or multiple different layers. Box 610 indicates an example where the received map may also take other forms.

[0163] In block 612, control system 214 receives sensor signals from geolocation sensor 204. Sensor signals from geolocation sensor 204 may include data indicating the geolocation 614 of harvester 100, the speed 616 of harvester 100, the heading 618 of harvester 100, or other information 620. In block 622, area controller 247 selects a dynamic area, and in block 624, area controller 247 selects a control area on a map based on the geolocation sensor signals. In block 626, area controller 247 selects a WMA or WMA group to be controlled. In block 628, area controller 247 obtains one or more target settings for the selected WMA or WMA group. The target settings obtained for the selected WMA or WMA group can come from a variety of different sources. For example, block 630 shows an example where one or more of the target settings for the selected WMA or WMA group are based on input from a control area on a map from the work site. Block 632 shows an example where one or more of the target settings are obtained from manual input from operator 260 or another user. Box 634 illustrates an example where the target settings are obtained from field sensor 208. Box 636 illustrates an example where one or more target settings are obtained from one or more sensors on other machines operating simultaneously with the agricultural harvester 100 in the same field, or from one or more sensors on machines that have previously operated in the same field. Box 638 illustrates an example where the target settings are also obtained from other sources.

[0164] In box 640, the zone controller 247 accesses the settings resolver of the selected dynamic zone and controls the settings resolver to parse the competing target settings into a resolved target setting. As discussed above, in some cases, the settings resolver may be a human resolver, in which case the zone controller 247 controls the operator interface mechanism 218 to present the competing target settings to the operator 260 or another user for resolution. In some cases, the settings resolver may be a neural network or other artificial intelligence or machine learning system, and the zone controller 247 submits the competing target settings to the neural network, artificial intelligence, or machine learning system for selection. In some cases, the settings resolver may be based on predicted or historical quality metrics, based on threshold rules, or based on logic components. In any of these later examples, the zone controller 247 executes the settings resolver to obtain the resolved target setting based on predicted or historical quality metrics, based on threshold rules, or when using logic components.

[0165] At block 642, if the zone controller 247 has identified the resolved target setting, it provides the resolved target setting to other controllers in the control system 214. These controllers generate control signals based on the resolved target setting and apply the control signals to the selected WMA or WMA group. For example, if the selected WMA is a machine or header actuator 248, the zone controller 247 provides the resolved target setting to the setting controller 232 or the header / actual controller 238, or both, to generate control signals based on the resolved target setting, and those generated control signals are applied to the machine or header actuator 248. At block 644, if an additional WMA or additional WMA group is to be controlled at the current geographic location of the harvester 100 (as detected in block 612), the process returns to block 626, where the next WMA or WMA group is selected. The process represented by blocks 626 through 644 continues until all WMAs or WMA groups to be controlled at the current geographic location of the harvester 100 have been resolved. If no additional WMA or WMA group remains to be controlled at the current geographic location of the harvester 100, the process proceeds to box 646, where the area controller 247 determines whether an additional control area to be considered exists in the selected dynamic area. If an additional control area to be considered exists, the process returns to box 624, where the next control area is selected. If no additional control area needs to be considered, the process proceeds to box 648, where it is determined whether there is an additional dynamic area to be considered. The area controller 247 determines whether there is an additional dynamic area to be considered. If there is an additional dynamic area to be considered, the process returns to box 622, where the next dynamic area is selected.

[0166] In box 650, the zone controller 247 determines whether the operation being performed by the harvester 100 has been completed. If not, the zone controller 247 determines whether control zone criteria have been met to continue processing, as shown in box 652. For example, as mentioned above, control zone definition criteria may include criteria defining when the harvester 100 can cross the control zone boundary. For example, whether the harvester 100 can cross the control zone boundary may be defined by a selected time period, meaning that the harvester 100 is prevented from crossing the zone boundary until the selected amount of time has elapsed. In this case, in box 652, the zone controller 247 determines whether the selected time period has elapsed. Additionally, the zone controller 247 can perform processing continuously. Therefore, the zone controller 247 does not wait for any specific time period before continuing to determine whether the operation of the harvester 100 has been completed. In box 652, the zone controller 247 determines that it is time to continue processing, and then processing continues in box 612, where the zone controller 247 again receives input from the geolocation sensor 204. It should also be understood that the zone controller 247 can use a multiple-input multiple-output controller to control the WMA and WMA group simultaneously, rather than controlling the WMA and WMA group sequentially.

[0167] Figure 11 This is a block diagram illustrating an example of an operator interface controller 231. In the illustrated example, the operator interface controller 231 includes an operator input command processing system 654, other controller interaction systems 656, a voice processing system 658, and a motion signal generator 660. The operator input command processing system 654 includes a voice processing system 662, a touch gesture processing system 664, and other items 666. The other controller interaction system 656 includes a controller input processing system 668 and a controller output generator 670. The voice processing system 658 includes a trigger detector 672, a recognition unit 674, a synthesis unit 676, a natural language understanding system 678, a dialogue management system 680, and other items 682. The motion signal generator 660 includes a visual control signal generator 684, an audio control signal generator 686, a tactile control signal generator 688, and other items 690. Figure 11 Before processing various operator interface actions, the example operator interface controller 231 shown in the figure first provides a brief description of some of the items in the operator interface controller 231 and their associated operations.

[0168] The operator input command processing system 654 detects operator input on the operator interface mechanism 218 and processes these command inputs. The voice processing system 662 detects voice input and processes interaction with the voice processing system 658 to process voice command inputs. The touch gesture processing system 664 detects touch gestures on touch-sensitive elements in the operator interface mechanism 218 and processes these command inputs.

[0169] Other controller interaction system 656 handles interactions with other controllers in control system 214. Controller input processing system 668 detects and processes inputs from other controllers in control system 214, and controller output generator 670 generates outputs and provides these outputs to other controllers in control system 214. Voice processing system 658 recognizes voice input, determines the meaning of these inputs, and provides outputs indicating the meaning of the spoken input. For example, voice processing system 658 can recognize voice input from operator 260 as a setting change command, where operator 260 is instructing control system 214 to change the settings of controllable subsystem 216. In such an example, voice processing system 658 recognizes the content of the spoken command, identifies the meaning of the command as a setting change command, and provides the meaning of the input back to voice processing system 662. Voice processing system 662 then interacts with controller output generator 670 to provide command outputs to the appropriate controllers in control system 214 to complete the spoken setting change command.

[0170] The voice processing system 658 can be invoked in various ways. For example, in one example, the voice processing system 662 continuously provides input from a microphone (as part of the operator interface mechanism 218) to the voice processing system 658. The microphone detects speech from the operator 260, and the voice processing system 662 provides the detected speech to the voice processing system 658. A trigger detector 672 detects a trigger indicating that the voice processing system 658 has been invoked. In some cases, when the voice processing system 658 receives continuous voice input from the voice processing system 662, the voice recognition unit 674 performs continuous speech recognition on all speech uttered by the operator 260. In some cases, the voice processing system 658 is configured to be invoked using a wake-up word. That is, in some cases, the operation of the voice processing system 658 can be initiated based on the recognition of a selected spoken word (referred to as a wake-up word). In such an example, when the recognition unit 674 recognizes the wake-up word, the recognition unit 674 provides an indication to the trigger detector 672 that the wake-up word has been recognized. Trigger detector 672 detects that voice processing system 658 has been invoked or triggered by a wake word. In another example, voice processing system 658 may be invoked by operator 260 actuating an actuator on the user interface mechanism, such as by touching an actuator on a touch-sensitive display, by pressing a button, or by providing another trigger input. In such an example, trigger detector 672 can detect that voice processing system 658 has been invoked when a trigger input is detected via the user interface mechanism. Trigger detector 672 may also detect that voice processing system 658 has been invoked in other ways.

[0171] Once the speech processing system 658 is invoked, speech input from operator 260 is provided to the speech recognition unit 674. The speech recognition unit 674 recognizes linguistic elements in the speech input, such as words, phrases, or other linguistic units. The natural language understanding system 678 identifies the meaning of the recognized speech. This meaning can be any of the following: natural language output, command output identifying a command reflected in the recognized speech, value output identifying a value in the recognized speech, or a variety of other outputs reflecting an understanding of the recognized speech. For example, more generally, the natural language understanding system 678 and the speech processing system 568 can understand the meaning of speech recognized in the environment of the agricultural harvester 100.

[0172] In some examples, the voice processing system 658 can also generate output for user-guided navigation of the operator 260 based on voice input. For instance, the dialogue management system 680 can generate and manage dialogues with the user to identify what the user wants to do. This dialog box can disambiguate user commands, identify one or more specific values ​​required to execute the user command, or obtain other information from or provide other information to the user, or both. The synthesis component 676 can generate speech synthesis, which can be presented to the user through an audio operator interface mechanism such as a speaker. Therefore, dialogues managed by the dialogue management system 680 can be exclusively verbal dialogues or a combination of visual and verbal dialogues.

[0173] Motion signal generator 660 generates motion signals to control operator interface mechanism 218 based on outputs from one or more of operator input command processing system 654, other controller interaction system 656, and voice processing system 658. Visual control signal generator 684 generates control signals to control visual items in operator interface mechanism 218. Visual items may be lights, displays, warning indicators, or other visual items. Audio control signal generator 686 generates outputs to control audio elements of operator interface mechanism 218. Audio elements include speakers, audible alarm mechanisms, horns, or other audible elements. Tactile control signal generator 688 generates control signals that are output to control tactile elements of operator interface mechanism 218. Tactile elements include vibratory elements that can be used to make vibrations, such as an operator's seat, steering wheel, pedals, or joystick used by the operator. Tactile elements may include tactile feedback or force feedback elements that provide tactile or force feedback to the operator through the operator interface mechanism. Tactile elements may also include a variety of other tactile elements.

[0174] Figure 12 This is a flowchart illustrating an example of the operation of the operator interface controller 231 when generating an operator interface display on an operator interface mechanism 218 that may include a touch-sensitive display screen. Figure 12 An example of how the operator interface controller 231 can detect and process operator interactions with the touch-sensitive display is also shown.

[0175] In box 692, the operator interface controller 231 receives a graph. Box 694 indicates that the graph is an example of a functional prediction graph, while box 696 indicates that the graph is an example of another type of graph. In box 698, the operator interface controller 231 receives input from the geolocation sensor 204 identifying the geolocation of the harvester 100. As shown in box 700, the input from the geolocation sensor 204 may include the heading and position of the harvester 100. Box 702 indicates an example where the input from the geolocation sensor 204 includes the speed of the harvester 100, and box 704 indicates an example where the input from the geolocation sensor 204 includes other items.

[0176] In box 706, the vision control signal generator 684 in the operator interface controller 231 controls the touch-sensitive display in the operator interface mechanism 218 to generate a display showing all or part of the field represented by the received map. Box 708 indicates that the displayed field may include a current position marker indicating the current position of the harvester 100 relative to the field. Box 710 indicates an example where the displayed field includes a next work unit marker identifying the next work unit (or area on the field) in which the harvester 100 will operate. Box 712 indicates an example where the displayed field includes an upcoming area display showing areas not yet processed by the harvester 100, while box 714 indicates an example where the displayed field includes a previously visited display showing areas of the field already processed by the harvester 100. Box 716 indicates an example where the displayed field shows various characteristics of the field having a geographic reference location on the map. For example, if the received map is a pest map, the displayed fields can show the different pest types present in the georeferenced fields within the displayed fields. Mapping characteristics can be shown in previously visited areas (as shown in box 714), upcoming areas (as shown in box 712), and the next work unit (as shown in box 710). Box 718 indicates that the fields displayed therein also include examples of other items.

[0177] Figure 13 This illustration shows an example of a user interface display 720 that can be generated on a touch-sensitive display screen. In other embodiments, the user interface display 720 can be generated on other types of displays. The touch-sensitive display screen can be installed in the operator's cab of an agricultural harvester 100, on a mobile device, or elsewhere. (Continuing the description...) Figure 12 Before the flowchart shown, the user interface display 720 will be described.

[0178] exist Figure 13In the example shown, the user interface display 720 illustrates a touch-sensitive display including display features for operating a microphone 722 and a speaker 724. Therefore, the touch-sensitive display can be communicatively coupled to the microphone 722 and the speaker 724. Box 726 indicates that the touch-sensitive display may include various user interface control actuators, such as buttons, keypads, soft keypads, links, icons, switches, etc. Operator 260 can actuate the user interface control actuators to perform various functions.

[0179] exist Figure 13 In the example shown, the user interface display 720 includes a field display portion 728 that displays at least a portion of the field in which the harvester 100 is operating. The field display portion 728 is shown as having a current position marker 708 corresponding to the current position of the harvester 100 within the portion of the field shown in the field display portion 728. In one example, the operator can control the touch-sensitive display to zoom in on a portion of the field display portion 728, or pan or scroll the field display portion 728 to display different portions of the field. The next work unit 730 is shown as the field area directly in front of the current position marker 708 of the harvester 100. The current position marker 708 can also be configured to identify the direction of travel of the harvester 100, the speed of travel of the harvester 100, or both. Figure 13 In the image, the shape of the current position marker 708 provides an indication of the orientation of the agricultural harvester 100 in the field, which can be used as an indication of the direction of travel of the agricultural harvester 100.

[0180] The size of the next work unit 730 marked on the field display section 728 can vary based on various criteria. For example, the size of the next work unit 730 can vary based on the travel speed of the harvester 100. Therefore, the area of ​​the next work unit 730 may be larger when the harvester 100 travels faster compared to when the harvester 100 travels slower. The field display section 728 is also shown displaying previously visited areas 714 and upcoming areas 712. The previously visited area 714 represents areas that have already been harvested, while the upcoming area 712 represents areas that still need to be harvested. The field display section 728 is also shown displaying different characteristics of the field. Figure 13 In the example shown, the map being displayed is a pest map. Therefore, multiple different pest markers are displayed on the field display section 728. A set of pest characteristic display markers 732 is shown in the already visited area 714. A set of pest characteristic display markers 734 is also shown in the upcoming area 712, and a set of pest characteristic display markers 736 is shown in the next work unit 730. Figure 13The pest characteristic display marks 732, 734, and 736 are shown to consist of different symbols. Each of the symbols represents a pest type. In the example shown in Figure 3, the @ symbol indicates animal activity in the field; the * symbol indicates diseased plants; and the # symbol indicates fungi. Thus, the field display section 728 shows different types of pests located in different areas of the field. These are merely examples, and other pests may also be displayed on the user interface display 720. As previously stated, the display mark 732 may consist of different symbols, and as described below, the symbols may be any display feature, such as different colors, shapes, patterns, intensities, text, icons, or other display features. In some cases, each location in the field may have a display mark associated with it. Thus, in some cases, display marks may be provided at each location of the field display section 728 to identify the nature of the characteristic mapped to each particular location of the field. Therefore, this disclosure includes providing display marks at one or more locations on the field display section 728, for example (as in...). Figure 11 In the context of this example, loss level display marker 732 is used to identify the nature, degree, etc. of the characteristic being displayed, thereby identifying the characteristic at the corresponding location in the field being displayed.

[0181] exist Figure 13 In the example, the user interface display 720 also has a control display section 738. The control display section 738 allows the operator to view information and interact with the user interface display 720 in various ways.

[0182] The actuators and display markers in part 738 can be displayed as, for example, individual items, fixed lists, scrollable lists, drop-down menus, or drop-down lists. Figure 13 In the example shown, display portion 738 displays information about three different types of pests corresponding to the three symbols mentioned above. Display portion 738 also includes a set of touch-sensitive actuators that operator 260 can interact with by touch. For example, operator 260 can touch a touch-sensitive actuator with a finger to activate the corresponding actuator.

[0183] The marker column 739 displays markers that have been set automatically or manually. The marker actuator 740 allows operator 260 to mark locations and then add information indicating the type of pest found at that location. For example, when operator 260 actuates marker actuator 740 by touching it, the touch gesture processing system 664 in the operator interface controller 231 identifies the location as a location where deer are present or where deer were previously present. When operator 260 touches button 742, the touch gesture processing system 664 identifies the location as a location where one or more diseased plants are present. When operator 260 touches button 744, the touch gesture processing system 664 identifies the location as a location where fungi are present or where one or more plants affected by fungi are present. The touch gesture processing system 664 also controls the visual control signal generator 684 to add symbols corresponding to the identified pest type on the field display section 728 at locations marked by the user before, after, or during the actuation of buttons 740, 742, or 744.

[0184] Column 746 displays symbols corresponding to each pest type tracked on field display section 728. Column 748 shows designators (which can be text designators or other designators) that identify the pest type. Without limitation, the pest symbols in column 746 and the designators in column 748 can include any display markings, such as different colors, shapes, patterns, intensities, text, icons, or other display markings. Column 750 displays pest characteristic values. Figure 13 In the example shown, the pest characteristic value is a value representing the pest density. The value displayed in column 750 can be a predicted value or a value measured by field sensor 208. The value in column 750 can include any of the pest properties included in the pest intensity range, as well as values ​​for pest types and other values. In one example, operator 260 can select a specific portion of field display section 728 for which the values ​​in column 750 will be displayed. Thus, the values ​​in column 750 can correspond to the values ​​in display sections 712, 714, or 730. Column 752 displays an action threshold. The action threshold in column 752 can be a threshold corresponding to the measured value in column 750. If the measured value in column 750 meets the corresponding action threshold in column 752, the control system 214 takes the action identified in column 754. In some cases, the measured value can satisfy the corresponding action threshold by meeting or exceeding it. In one example, operator 260 can select a threshold, for example, to change the threshold by touching the threshold in column 752. Once selected, operator 260 can change the threshold. The threshold in column 752 can be configured to perform a specified action when the measured value 750 exceeds, is equal to, or is less than the threshold.

[0185] Similarly, operator 260 can touch the action identifier in column 754 to change the action to be taken. Multiple actions can be taken when a threshold is met. For example, at the bottom of column 754, deceleration and fan increase actions are identified as actions to be taken if the measured value in column 750 meets the threshold in column 752.

[0186] The actions that can be set in column 754 can be any of a variety of different types of actions. For example, these actions can include a prohibition action that, when executed, prevents the harvester 100 from harvesting further in the area. These actions can include a mitigation activation that, when executed, performs a mitigation action, such as a bad grain collector, blowing away the grain. These actions can include a speed-changing action that, when executed, changes the speed at which the harvester 100 travels through the field. These actions can include setting-changing actions for changing the settings of internal actuators or another WMA or WMA group, or setting-changing actions for implementing changes to the header settings. These are merely examples, and a wide variety of other actions are considered herein.

[0187] The display markers shown on the user interface display 720 can be visually controlled. Visually controlling the interface display 720 can be performed to capture the attention of the operator 260. For example, the display markers can be controlled to modify the intensity, color, or pattern of the displayed markers. Additionally, the flashing of the display markers can be controlled. As an example, a description of changes to the visual appearance of the display markers is provided. Therefore, other aspects of the visual appearance of the display markers can be changed. Thus, the display markers can be modified in a desired manner in various situations to, for example, capture the attention of the operator 260.

[0188] Various functions that can be performed by operator 260 using user interface display 720 can also be performed automatically, such as through other controllers in control system 214. For example, when different types of pests are identified by field sensor 208, operator interface controller 231 can automatically add a flag at the current position of agricultural harvester 100 (which corresponds to the position of the encountered pest type) and generate a display in the flag column, a corresponding symbol in the symbol column, and a specifier in specifier column 748. When identifying different pest types, operator interface controller 231 can also generate measured values ​​in column 750 and thresholds in column 752. Operator interface controller 231 or another controller can also automatically identify actions added to column 754.

[0189] Now back Figure 12The flowchart continues to describe the operation of the operator interface controller 231. In block 760, the operator interface controller 231 detects input for setting a flag and controls the touch-sensitive user interface display 720 to display the flag on the field display section 728. The detected input can be operator input (as shown in 762) or input from another controller (as shown in 764). In block 766, the operator interface controller 231 detects field sensor input indicating a measured characteristic of the field from one of the field sensors 208. In block 768, the vision control signal generator 684 generates control signals to control the user interface display 720 to display actuators for modifying the user interface display 720 and for modifying machine control. For example, block 770 indicates that one or more actuators for setting or modifying values ​​in columns 739, 746, and 748 can be displayed. Therefore, the user can set flags and modify the characteristics of these flags. For example, the user can modify the pest type and pest designator corresponding to the flag. Block 772 indicates that the action thresholds in column 752 are displayed. Box 776 indicates that the action in column 754 is displayed, and box 778 indicates that the field data of the measurement in column 750 is displayed. Box 780 indicates that various other information and actuators can also be displayed on the user interface display 720.

[0190] In box 782, the operator input command processing system 654 detects and processes operator input corresponding to the interaction performed by operator 260 with the user interface display 720. If the user interface mechanism displayed on the user interface display 720 is a touch-sensitive display, the interaction input performed by operator 260 with the touch-sensitive display can be a touch gesture 784. In some cases, the operator interaction input can be input using a clicking device 786 or other operator interaction inputs 788.

[0191] In box 790, operator interface controller 231 receives a signal indicating an alarm condition. For example, box 792 indicates a signal that can be received by controller input processing system 668, indicating that the detected value in column 750 satisfies a threshold condition present in column 752. As previously explained, threshold conditions can include values ​​below, above, or below a threshold. Box 794 shows that action signal generator 660 can, in response to receiving an alarm condition, generate a visual alarm using visual control signal generator 684, an audio alarm using audio control signal generator 686, a tactile alarm using tactile control signal generator 688, or any combination thereof to alert operator 260. Similarly, as shown in box 796, controller output generator 670 can generate outputs to other controllers in control system 214, causing these controllers to perform the corresponding actions identified in column 754. Box 798 shows that operator interface controller 231 can also detect and process alarm conditions in other ways.

[0192] Box 900 illustrates that the voice processing system 662 can detect and process input that invokes the voice processing system 658. Box 902 illustrates that performing voice processing may include using the dialogue management system 680 to converse with the operator 260. Box 904 illustrates that voice processing may include providing a signal to the controller output generator 670 to automatically perform control operations based on the voice input.

[0193] Table 1 below shows an example of a dialogue between the operator interface controller 231 and the operator 260. In Table 1, the operator 260 invokes the voice processing system 658 using a trigger word or wake-up word detected by the trigger detector 672. In the example shown in Table 1, the wake-up word is "Johnny".

[0194] Table 1

[0195] Operator: "Johnny, tell me about the current situation with the pests."

[0196] Operator interface controller: "65% of crops are infected with fungi, threshold is 10%".

[0197] Operator: "Johnny, what should I do because of the pests?"

[0198] Operator interface controller: "The fungal-infected crop is too tall. Stop harvesting in this area and reduce the bad grain later."

[0199] Table 2 illustrates an example in which the speech synthesis unit 676 provides output to the audio control signal generator 686 to provide auditory updates intermittently or periodically. The interval between updates can be based on time (such as every five minutes), or on coverage or distance (such as every five acres), or on anomalies (such as when a measured value is greater than a threshold).

[0200] Table 2

[0201] Operator interface controller: "In the past 10 minutes, the harvest consisted of 90% normal crop and 10% diseased crop."

[0202] Operator interface controller: "The next 1 acre of land is estimated to include 95% normal crop and 5% diseased crop."

[0203] The examples shown in Table 3 illustrate some actuators or user input mechanisms on the touch-sensitive display 720 that can be supplemented by voice dialogue. The examples in Table 3 also show that the motion signal generator 660 can generate motion signals to automatically mark crop blocks affected by pests in a field being harvested.

[0204] Table 3

[0205] Human: "Johnny, mark the pest block."

[0206] Operator interface controller: "Crop areas infected by pests have been marked."

[0207] The example shown in Table 4 illustrates that the action signal generator 660 can communicate with the operator 260 to start and stop marking of pest areas.

[0208] Table 4

[0209] Human: "Johnny, start marking crops infected with pests."

[0210] Operator interface controller: "Mark areas infected by harmful organisms".

[0211] Human: "Johnny, stop marking harmful biomes."

[0212] Operator interface controller: "Stop marking areas infected by harmful organisms".

[0213] The examples shown in Table 5 illustrate that the motion signal generator 160 can generate signals for marking harmful organism blocks in a manner different from that shown in Tables 3 and 4.

[0214] Table 5

[0215] Human: "Johnny, mark the next 100 feet as a pest block."

[0216] Operator interface controller: "The next 100 feet are marked as an area infected by harmful organisms."

[0217] Return again Figure 12 Box 906 illustrates that the operator interface controller 231 can also detect and process situations for outputting messages or other information in other ways. For example, the other controller interaction system 656 can detect input from other controllers indicating alarms or output messages that should be presented to the operator 260. Box 908 illustrates that the output can be an audio message. Box 910 illustrates that the output can be a visual message, and Box 912 illustrates that the output can be a tactile message. Until the operator interface controller 231 determines that the current harvesting operation is complete (as shown in Box 914), processing returns to Box 698, where the geographical location of the harvester 100 is updated, and processing continues as described above to update the user interface display 720.

[0218] Once the operation is complete, any desired values ​​displayed or already displayed on the user interface display 720 can be saved. These values ​​can also be used in machine learning to improve different parts of the predictive model generator 210, predictive map generator 212, control area generator 213, control algorithm, or other components. The saved desired values ​​are indicated by box 916. These values ​​can be saved locally on the agricultural harvester 100, or they can be saved at a remote server location or sent to another remote system.

[0219] Therefore, the prior information map is obtained by the agricultural harvester and shows the pest characteristic values ​​at different geographical locations in the field being harvested. Field sensors on the harvester sense characteristics with values ​​indicating agricultural properties as the harvester moves through the field. A prediction map generator produces a prediction map that predicts control values ​​at different locations in the field based on the pest characteristic values ​​in the prior information map and the agricultural properties sensed by the field sensors. The control system controls the controllable subsystems based on the control values ​​in the prediction map.

[0220] A control value is a value upon which an action can be based. As described herein, a control value can include any value (or a characteristic indicated by or derived from that value) that can be used to control the agricultural harvester 100. A control value can be any value indicating an agricultural characteristic. A control value can be a predicted value, a measured value, or a detected value. A control value can include any value provided by a graph (such as any of the graphs described herein), for example, a control value can be a value provided by an infographic, a value provided by a priori infographic, or a value provided by a predictive graph, such as a functional predictive graph. A control value can also include any characteristic indicated by or derived from a value detected by any of the sensors described herein. In other examples, control values ​​can be provided by the operator of the agricultural machine, such as commands entered by the operator of the agricultural machine.

[0221] The current discussion has already mentioned processors and servers. In some examples, processors and servers include computer processors with associated memory and timing circuitry (not shown separately). Processors and servers are functional parts of the system or device to which they belong, and are activated and facilitated by other components or items in these systems.

[0222] Furthermore, numerous user interface displays have been discussed. Displays can take various forms and can have various user-actuable operator interface structures set on them. For example, user-actuable operator interface mechanisms can be text boxes, checkboxes, icons, links, drop-down menus, search boxes, etc. User-actuable operator interface mechanisms can also be actuated in various ways. For example, user-actuable operator interface mechanisms can be actuated using operator interface mechanisms such as click devices (e.g., trackballs or mice, hardware buttons, switches, joysticks or keyboards, thumb switches or thumb pads, etc.), virtual keyboards, or other virtual actuators). Furthermore, if the screen displaying the user-actuable operator interface mechanisms is a touch-sensitive screen, touch gestures can be used to actuate the user-actuable operator interface mechanisms. Moreover, voice recognition functionality can be used to actuate user-actuable operator interface mechanisms using voice commands. Voice recognition can be implemented using voice detection devices (such as microphones) and software for recognizing the detected voice and executing commands based on the received voice.

[0223] Many data storage devices are also discussed. It should be noted that data storage can be divided into multiple data storage devices. In some examples, one or more of the data storage devices may be local to the system accessing the data storage devices; one or more of the data storage devices may all be located remotely from the system utilizing the data storage devices; or one or more data storage devices may be local while others are remote. This disclosure considers all of these configurations.

[0224] Furthermore, the accompanying diagram shows multiple boxes, with each function belonging to a specific box. It should be noted that fewer boxes can be used to illustrate that functions attributed to multiple different boxes are performed by fewer components. Moreover, more boxes can be used to show that the function can be distributed across more components. In different examples, some functions can be added, and some functions can be removed.

[0225] It should be noted that the foregoing discussion has described various different systems, components, logic, and interactions. It should be understood that any or all of such systems, components, logic, and interactions can be implemented by hardware items such as processors, memory, or other processing units, including but not limited to artificial intelligence units (such as neural networks, some of which are described below) that perform functions associated with those systems, components, logic, or interactions. Furthermore, any or all of the systems, components, logic, and interactions can be implemented by software loaded into memory and subsequently executed by a processor, server, or other computing unit, as described below. Any or all of the systems, components, logic, and interactions can also be implemented by different 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 may also be used.

[0226] Figure 14 This is a block diagram of the agricultural harvester 600, which can be similar to... Figure 2 The agricultural harvester 100 is shown in the diagram. The agricultural harvester 600 communicates with components in a remote server architecture 500. In some examples, the remote server architecture 500 can provide computing, software, data access, and storage services without requiring end users to know the physical location or configuration of the system delivering the services. In various examples, the remote server can deliver services over a wide area network (such as the Internet) using appropriate protocols. For example, the remote server can deliver applications over a wide area network and can be accessed via a web browser or any other computing component. Figure 2 The software or components shown herein, along with their associated data, can be stored on servers at remote locations. Computing resources in a remote server environment can be consolidated at a remote data center location, or they can be distributed across multiple remote data centers. Remote server infrastructure can deliver services through shared data centers, even if it appears as a single access point for a user. Therefore, the components and functions described herein can be provided from remote servers at remote locations using a remote server architecture. Alternatively, components and functions can be provided from servers, or they can be installed directly or otherwise on client devices.

[0227] exist Figure 14In the examples shown, some items are similar to Figure 2 The items shown are numbered similarly. Figure 14 Specifically, it is shown that the prediction model generator 210 or the prediction graph generator 212, or both, can be located at a server location 502, away from the agricultural harvester 600. Therefore, in Figure 14 In the example shown, the agricultural harvester 600 accesses the system via a remote server location 502.

[0228] Figure 14 Another example of a remote server architecture is also described. Figure 14 It shows Figure 2 Some components can be located at a remote server location 502, while others can be located elsewhere. As an example, data storage device 202 can be placed at a location separate from location 502 and accessed via a remote server at location 502. Regardless of their location, these components can be directly accessed by the combine harvester 600 via a network (such as a wide area network or local area network), hosted by a service at a remote site, provided as a service, or accessed by a connection service residing at a remote location. Furthermore, data can be stored anywhere, and the stored data can be accessed or forwarded to an operator, user, or system. For example, a physical carrier wave can be used instead of an electromagnetic carrier wave, or a physical carrier wave can be used in addition to an electromagnetic carrier wave. In some examples, where wireless telecommunications service coverage is poor or absent, another machine (such as a fuel truck or other mobile machine or vehicle) can have an automatic, semi-automatic, or manual information collection system. When the combine harvester 600 approaches the machine (such as a fuel truck) containing the information collection system before refueling, the information collection system collects information from the combine harvester 600 using any type of temporary dedicated wireless connection. Then, when the machine containing the received information reaches a location with wireless telecommunications service coverage or other available wireless coverage, the collected information can be forwarded to another network. For example, when a fuel truck travels to a location to refuel other machines or to a main fuel storage location, the fuel truck can enter an area with wireless communication coverage. All these architectures are considered in this paper. Furthermore, information can be stored on the agricultural harvester 600 until the agricultural harvester 600 enters an area with wireless communication coverage. The agricultural harvester 600 itself can transmit the information to another network.

[0229] It will also be noted that Figure 2The components or parts thereof can be mounted on a variety of different devices. One or more of these devices may include airborne computers, electronic control units, display units, servers, desktop computers, laptop computers, tablet computers, or other mobile devices such as PDAs, cellular phones, smartphones, multimedia players, personal digital assistants, etc.

[0230] In some examples, the remote server architecture 500 may include network security measures. These measures, without limitation, include encryption of data on storage devices, encryption of data sent between network nodes, authentication of personnel or processes accessing data, and the use of a ledger to record metadata, data, data transfer, data access, and data transformation. In some examples, the ledger may be distributed and immutable (e.g., implemented as a blockchain).

[0231] Figure 15 This is a simplified block diagram illustrating a schematic example of a handheld or mobile computing device 16 that can be used as a user's or customer's handheld device 16, which may be deployed in this system (or as part thereof). For example, a mobile device may be deployed in the operator's cab of an agricultural harvester 100 for use in generating, processing, or displaying the diagrams discussed above. Figures 16-17 Examples are handheld or mobile devices.

[0232] Figure 15 A general block diagram of the components of client device 16, which can operate... Figure 2 The device 16 includes some of the components shown, interacts with them, or both. In device 16, a communication link 13 is provided that allows the handheld device to communicate with other computing devices, and in some examples, a channel is provided for automatically receiving information (e.g., by scanning). Examples of communication link 13 include those that allow communication via one or more communication protocols, such as wireless services for providing cellular access to a network, and protocols for providing local wireless connectivity to a network.

[0233] In other examples, the application can receive data on a removable Secure Digital (SD) card connected to interface 15. Interface 15 and communication link 13 communicate along bus 19 with processor 17 (which may also be a processor or server from another diagram), which is also connected to memory 21 and input / output (I / O) components 23, as well as clock 25 and position system 27.

[0234] In one example, I / O components 23 are provided to facilitate input and output operations. Various examples of I / O components 23 in device 16 may include input components (such as buttons, touch sensors, optical sensors, microphones, touchscreens, proximity sensors, accelerometers, orientation sensors) and output components (such as display devices, speaker and / or printer ports). Other I / O components 23 may also be used.

[0235] Clock 25 schematically includes a real-time clock component that outputs the time and date. Schematically, it may also provide timing functions for processor 17.

[0236] Location system 27 schematically includes components that output the current geographic location of 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 systems. Location system 27 may also include, for example, mapping or navigation software that generates desired maps, navigation routes, and other geographic functions.

[0237] Memory 21 stores operating system 29, network settings 31, applications 33, application configuration settings 35, data storage device 37, communication driver 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 (described below). Memory 21 stores computer-readable instructions that, when executed by processor 17, cause the processor to perform computer-implemented steps or functions. Processor 17 may also be activated by other components to facilitate their functions.

[0238] Figure 16 The illustration shows an example where device 16 is a tablet computer 600. Figure 16 In the diagram, computer 601 is shown as having a user interface display screen 602. Screen 602 can be a touchscreen or a pen-enabled interface that receives input from a pen or stylus. Tablet 600 can also utilize an on-screen virtual keyboard. Of course, computer 601 can also be attached to a keyboard or other user input device, for example, via a suitable attachment structure (such as a wireless link or USB port). Computer 601 can also schematically receive voice input.

[0239] Figure 17 Similar to Figure 16The device is a smartphone 71. The smartphone 71 has a touch-sensitive display 73 that shows icons, blocks, or other user input mechanisms 75. Users can use the mechanisms 75 to run applications, make calls, perform data transfer operations, etc. Generally, smartphones 71 are built on a mobile operating system and offer more advanced computing power and connectivity than feature phones.

[0240] Note that other forms of device 16 are possible.

[0241] Figure 18 It is one of the deployable ones Figure 2 An example of a computing environment for the components. Reference Figure 18 An example system for implementing some embodiments includes a computing device in the form of a computer 810 programmed to operate as discussed above. Components of the computer 810 may include, but are not limited to, a processing unit 820 (which may include a processor or server from the previous figures), system memory 830, and a system bus 821 that couples various system components, including the system memory, to the processing unit 820. The system bus 821 may be any of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, and a local bus using any of various bus architectures. Regarding... Figure 2 The described memory and program can be deployed in Figure 18 In the corresponding part.

[0242] Computer 810 typically includes a variety of computer-readable media. Computer-readable media can be any available medium accessible to computer 810, and includes 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 communication media. Computer storage media are distinct from and do not include modulated data signals or carriers. Computer-readable media include hardware storage media, including volatile and non-volatile, removable and non-removable media implemented in any way or by any technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disc storage devices, magnetic tape, magnetic tape, disk storage devices or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to computer 810. Communication media can implement computer-readable instructions, data structures, program modules, or other data in a transmission mechanism, and includes any information delivery medium. The term "modulated data signal" refers to a signal that has one or more of its characteristics set or changed in a manner that encodes information in the signal.

[0243] 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. The basic input / output system 833 (BIOS) (which contains basic routines such as those that help transfer information between components within computer 810 during startup) is typically stored in ROM 831. RAM 832 typically contains data and / or program modules, or both, that are readily accessible to and / or currently being operated by processing unit 820. This is by way of example and not limitation. Figure 18 The operating system 834, application program 835, other program modules 836, and program data 837 are shown.

[0244] Computer 810 may also include other removable / non-removable volatile / non-volatile computer storage media. This is just one example. Figure 18 A hard disk drive 841 is shown that reads from or writes to a non-removable, non-volatile magnetic medium, an optical disk drive 855, and a non-volatile optical disk 856. The hard disk drive 841 is typically connected to the system bus 821 via a non-removable memory interface (such as interface 840), and the optical disk drive 855 is typically connected to the system bus 821 via a removable memory interface (such as interface 850).

[0245] Alternatively or additionally, the functions described herein may be performed at least in part by one or more hardware logic components. For example, but not limited to, illustrative types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (e.g., ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), and the like.

[0246] The above discussion and Figure 18 The driver and its associated computer storage media shown provide storage for computer-readable instructions, data structures, program modules, and other data for computer 810. For example, in Figure 18In this diagram, hard disk drive 841 is shown storing operating system 844, application programs 845, other program modules 846, and program data 847. Note that these components may be the same as or different from operating system 834, application programs 835, other program modules 836, and program data 837.

[0247] Users can input commands and information to computer 810 through input devices such as keyboard 862, microphone 863, and pointing devices 861 (such as mouse, trackball, or touchpad). Other input devices (not shown) may include joysticks, game controllers, satellite dishes, scanners, etc. These and other input devices are typically connected to processing unit 820 via user input interface 860 coupled to the system bus, but may also be connected via other interfaces and bus structures. Visual display 891 or other types of display devices are also connected to system bus 821 via an interface such as video interface 890. In addition to the monitor, the computer may also include other peripheral output devices, such as speakers 897 and printers 896, which can be connected via peripheral output interface 895.

[0248] Computer 810 operates in a networked environment using logical connections (such as Controller Area Network (CAN), Local Area Network (LAN), or Wide Area Network (WAN)) to one or more remote computers (such as remote computer 880).

[0249] When used in a LAN networking environment, computer 810 connects to LAN 871 via a network interface or adapter 870. When used in a WAN networking environment, computer 810 typically includes a modem 872 or other devices for establishing communication over a WAN 873 (such as the Internet). In a networking environment, program modules can be stored in remote memory storage devices. For example, Figure 18 This demonstrates that remote application 885 can reside on remote computer 880.

[0250] It should also be noted that the different examples described in this article can be combined in different ways. That is, parts of one or more examples can be combined with parts of one or more other examples. All of this is considered in this article.

[0251] Example 1 is an agricultural operating machine, comprising:

[0252] A communication system that receives an information map including values ​​of pest characteristics corresponding to different geographical locations in a field;

[0253] A geolocation sensor that detects the geographical location of agricultural machinery;

[0254] A field sensor that detects values ​​of agricultural characteristics corresponding to a geographical location;

[0255] A prediction map generator that generates a functional predictive agriculture map of fields that maps predictive control values ​​to different geographic locations in the field, based on the values ​​of pest characteristics in the infographic and the values ​​of agricultural characteristics.

[0256] Controllable subsystem; and

[0257] A control system that generates control signals to control controllable subsystems based on the geographical location of agricultural machinery and control values ​​in a functional predictive agricultural map.

[0258] Example 2 is any or all of the agricultural operating machines of the foregoing examples, wherein the prediction map generator includes:

[0259] A predictive yield map generator that generates a predictive agricultural map that maps predicted yield values, which serve as control values, to different geographic locations within the field.

[0260] Example 3 is any or all of the agricultural operating machines of the foregoing examples, wherein the control system includes:

[0261] A feed rate controller generates a feed rate control signal based on the detected geographic location and functional predictive agricultural map, and controls a controllable subsystem based on the feed rate control signal to control the feed rate of material through the agricultural machinery.

[0262] Example 4 is the agricultural operating machine of claim 1, wherein the prediction map generator comprises:

[0263] A grain quality prediction map generator that generates a predictive agricultural map that maps predicted grain quality values, which serve as control values, to different geographical locations in the field.

[0264] Example 5 is any or all of the agricultural operating machines of the foregoing examples, wherein the control system includes:

[0265] The stubble controller generates stubble control signals based on the detected geographic location and functional predictive agricultural map, and controls the stubble subsystem based on the stubble control signals to control the stubble handling operations of agricultural machinery.

[0266] Example 6 is any or all of the agricultural operating machines of the foregoing examples, wherein the control system controls the grain collector to retain low-quality, pest-infected grain.

[0267] Example 7 is any or all of the agricultural operating machines of the foregoing examples, wherein the control system includes:

[0268] A setting controller is configured to generate operator command control signals that indicate operator commands based on the detected geographic location and function prediction operator command map, and to control the controllable subsystem to execute operator commands based on the operator command control signals.

[0269] Example 8 is any or all of the agricultural operating machines of the foregoing examples, and also includes:

[0270] A predictive model generator generates a predictive agriculture model that models the relationship between pest characteristics and agricultural characteristics based on the values ​​of pest characteristics in a prior information map of a geographic location and the values ​​of agricultural characteristics detected by field sensors at that geographic location. The predictive map generator generates a functional predictive agriculture map based on the values ​​of pest characteristics in the prior information map and the predictive agriculture model.

[0271] Example 9 is any or all of the agricultural operating machines of the foregoing examples, wherein the control system further includes:

[0272] An operator interface controller generates a user interface diagram representation of a predictive agricultural map, the user interface diagram representation including a field portion having a current location indicator indicating the geographic location of agricultural machinery on the field portion and a pest characteristic symbol indicating the value of pest characteristics at one or more geographic locations on the field portion.

[0273] Example 10 is any or all of the agricultural operating machines of the foregoing examples, wherein the operator interface controller generates a user interface diagram representation to include an interactive display portion that displays a sensed characteristic indicating a detected agricultural characteristic, an interactive threshold display portion that indicates an action threshold, and an interactive action indicator that indicates a control action to be taken when the detected agricultural characteristic meets the action threshold, and the control system generates control signals based on the control actions to control a controllable subsystem.

[0274] Example 11 is a computer-implemented method for controlling agricultural machinery, including...

[0275] Obtain an infographic that includes values ​​for pest characteristics corresponding to different geographical locations in the field;

[0276] Detecting the geographical location of agricultural machinery;

[0277] Utilize on-site sensors to detect agricultural characteristics corresponding to that geographical location;

[0278] Based on pest characteristic values ​​in the infographic and agricultural characteristic values, a functional predictive agriculture map of the field is generated, mapping predictive control values ​​to different geographical locations within the field; and

[0279] The controllable subsystem is controlled based on the geographical location of agricultural machinery and the control values ​​in the functional predictive agricultural map.

[0280] Example 12 is a computer-implemented method of any or all of the foregoing examples, wherein generating a functional prediction graph includes:

[0281] Generate a functional forecast production map that maps the forecast production values ​​as control values.

[0282] Example 13 is a computer-implemented method of any or all of the foregoing examples, wherein controlling the controllable subsystem includes:

[0283] Based on the detected geographical location and functional prediction output map, a feed rate control signal is generated; and

[0284] The controllable subsystem is controlled based on the feed rate control signal to control the feed rate of materials through agricultural machinery.

[0285] Example 14 is a computer-implemented method of any or all of the foregoing examples, wherein generating a functional prediction graph includes:

[0286] Generate a functional grain quality prediction map that maps the predicted grain quality values ​​as control values.

[0287] Example 15 is a computer-implemented method of any or all of the foregoing examples, wherein controlling the controllable subsystem includes:

[0288] Based on the detected geographical location and functional prediction of grain quality maps, stubble control signals are generated; and

[0289] The controllable subsystem is based on the stubble control signal to control the stubble treatment subsystem of agricultural machinery.

[0290] Example 16 is a computer-implemented method of any or all of the foregoing examples, wherein generating a functional prediction graph includes:

[0291] Generate a function prediction operator command map that maps prediction operator commands to different geographic locations in the field.

[0292] Example 17 is a computer-implemented method of any or all of the foregoing examples, wherein controlling the controllable subsystem includes:

[0293] Based on the detected geographic location and function prediction operator command map, operator command control signals that indicate operator commands are generated; and

[0294] The controllable subsystem is controlled based on operator command control signals to execute operator commands.

[0295] Example 18 is a computer-implemented method of any or all of the foregoing examples, and also includes:

[0296] A predictive agriculture model is generated based on the values ​​of pest characteristics in an information map at a geographic location and the values ​​of agricultural characteristics detected by field sensors at that geographic location. This model models the relationship between pest characteristics and agricultural characteristics. The generation of the functional predictive agriculture map includes generating the functional predictive agriculture map based on the values ​​of pest characteristics in the information map and the predictive agriculture model.

[0297] Example 19 is an agricultural operating machine, comprising:

[0298] A communication system that receives a priori information map including values ​​of agricultural characteristics corresponding to different geographical locations in a field;

[0299] A geolocation sensor that detects the geographical location of agricultural machinery;

[0300] A field sensor that detects values ​​corresponding to the characteristics of harmful organisms at that geographical location;

[0301] A predictive model generator generates a predictive agricultural model that models the relationship between pest characteristics and agricultural characteristics based on the values ​​of agricultural characteristics in a prior information map of a geographic location and the values ​​of pest characteristics detected by field sensors at that geographic location.

[0302] A predictive map generator that generates functional predictive agricultural maps of fields that map predictive control values ​​to different geographic locations in the fields, based on the values ​​of agricultural characteristics in a priori information map and a predictive agriculture model.

[0303] Controllable subsystem; and

[0304] A control system that generates control signals to control controllable subsystems based on the geographical location of agricultural machinery and control values ​​in a functional predictive agricultural map.

[0305] Example 20 is any or all of the agricultural operating machines of the foregoing examples, wherein the prior information map includes values ​​for historical pest characteristics, optical characteristics, vegetation indices, scouting characteristics, and animal activity.

[0306] Although the subject matter has been described in language specific to structural features or methodological actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as examples of the claims.

Claims

1. An agricultural operating machine (100), comprising: A geolocation sensor (204) detects the geolocation of the agricultural machinery while it is currently operating in the field; Field sensor (208) detects the value of a first agricultural characteristic when the agricultural machinery is currently operating in the field; A pest sensor that detects values ​​of pest characteristics corresponding to the geographical location while agricultural machinery is currently operating in a field; A communication system (206) receives an information map, the information map including values ​​of a second agricultural characteristic corresponding to different geographical locations in the field, wherein the second agricultural characteristic is different from the first agricultural characteristic; A prediction map generator (212) generates a functional prediction pest characteristic map of the field that maps the predicted values ​​of the pest characteristics to different geographical locations in the field, based on the values ​​of the second agricultural characteristics in the information map and the values ​​of the pest characteristics detected by the pest sensor. It also generates a functional prediction agricultural map of the field that maps the predicted values ​​of the first agricultural characteristics to different geographical locations in the field, based on the values ​​of the pest characteristics in the functional prediction pest characteristic map and the values ​​of the first agricultural characteristics detected by the field sensor. Controllable subsystem (216); as well as The control system (214) generates control signals to control the controllable subsystem (216) based on the geographical location of the agricultural machine and based on the predicted value of a first agricultural characteristic in the functional predictive agricultural map. Memory; as well as One or more processors configured to perform the operation of the prediction graph generator (212).

2. The agricultural machinery according to claim 1, wherein, The prediction map generator includes: A predicted yield map generator generates a functional predicted agricultural map that maps predicted yield values, which are the predicted values ​​of a first agricultural characteristic, to different geographical locations in the field.

3. The agricultural machinery according to claim 2, wherein, The control system includes: A feed rate controller generates a feed rate control signal based on the detected geographical location and the functional predictive agricultural map, and controls the controllable subsystem based on the feed rate control signal to control the feed rate of material through the agricultural operation machine.

4. The agricultural machinery according to claim 1, wherein, The prediction map generator includes: A grain quality prediction map generator generates a functional predictive agriculture map that maps predicted grain quality values, which are the predicted values ​​of the first agricultural characteristic, to different geographical locations in the field.

5. The agricultural machinery according to claim 4, wherein, The control system includes: A stubble controller generates a stubble control signal based on the detected geographical location and the functional predictive agriculture map, and controls the stubble subsystem based on the stubble control signal to control the stubble handling operation of the agricultural machinery.

6. The agricultural machinery according to claim 1, wherein, The control system controls the grain collector to retain low-quality grain that is infected with harmful organisms.

7. The agricultural machinery according to claim 1, further comprising: A predictive model generator generates a predictive agricultural model that models the relationship between the pest characteristics and the first agricultural characteristic based on the values ​​of pest characteristics in the functional predictive pest characteristic map and the values ​​of the first agricultural characteristic detected by the field sensor. The predictive map generator generates the functional predictive agricultural map based on the values ​​of pest characteristics in the functional predictive pest characteristic map and the predictive agricultural model.

8. A computer-implemented method for controlling agricultural machinery (100), comprising: Detect the geographical location of the agricultural machinery (100); The value of the first agricultural characteristic is detected using a field sensor (208); Using pest sensors to detect values ​​of pest characteristics; Obtain an information map, the information map including values ​​of a second agricultural characteristic corresponding to different geographical locations in the field, wherein the second agricultural characteristic is different from the first agricultural characteristic; Based on the values ​​of the second agricultural characteristic in the information map and the values ​​of the pest characteristic detected by the pest sensor, a functional predicted pest characteristic map of the field is generated, which maps the predicted values ​​of the pest characteristic to different geographical locations in the field. Based on the values ​​of pest characteristics in the functional predicted pest characteristic map and based on the values ​​of the first agricultural characteristic detected by field sensors, a functional predicted agricultural map of the field is generated, which maps the predicted values ​​of the first agricultural characteristic to different geographical locations in the field. as well as The controllable subsystem (216) is controlled based on the geographical location of the agricultural machine (100) and the predicted value of the first agricultural characteristic in the functional prediction agricultural map.

Images