BR102022019938A2 - AGRICULTURAL WORKING MACHINE, AND, METHOD FOR OPERATING AN AGRICULTURAL WORKING MACHINE - Google Patents

Abstract

An agricultural work machine includes a geographic position sensor that detects a geographic location of the agricultural work machine. An in situ sensor detects a value of a dynamic response characteristic of the agricultural work machine corresponding to the geographic location. A predictive model generator generates a predictive model that models a relationship between the terrain aspect characteristic and the dynamic response characteristic based on a value of the terrain aspect characteristic on a map of prior information at the geographic location and a value of the dynamic response characteristic sensed by the sensor in situ at the geographic location. A predictive map generator generates a functional predictive dynamic response map of the field, which maps predictive values of the dynamic response characteristic to the different geographic locations in the field, based on the terrain aspect characteristic values in the prior information map and with based on the predictive model.

Description

AGRICULTURAL WORKING MACHINE, AND, METHOD FOR OPERATING AN AGRICULTURAL WORKING MACHINE DESCRIPTION FIELD

[001] The present description refers to agricultural machinery, forestry machinery, construction machinery and lawn cultivation machinery.

FUNDAMENTALS

[002] There is a wide variety of different types of agricultural machinery. Some agricultural machines include harvesters, such as combination harvesters, sugar cane harvesters, cotton harvesters, self-propelled forage harvesters, and reapers. Some harvesters can also be equipped with different types of cutting decks to harvest different types of crops.

[003] The speed of an agricultural machine on the ground is often tied directly to the rate at which the agricultural machine performs its operation. Thus, in order to perform an operation quickly, it may be desirable to make an agricultural machine move relatively quickly. However, as agricultural machine speed increases, wear and tear on various machine parts increases and the potential for vehicle dynamics to impact operating efficiency increases. Additionally, on agricultural machinery that requires an operator to drive the machine, operator comfort may be affected if the machine moves too quickly over a rough surface. In the past, the balance between machine speed and machine wear/operator comfort was set manually by an operator in the cab. However, as agricultural machinery has become more complex, various vehicle dynamics and terrain conditions can quickly change in ways that are not noticeable or able to be handled manually, which can lead to undesirable wear and/or operator discomfort. .

[004] The above discussion is provided merely for general background information and is not intended to be used as an aid in determining the scope of the claimed subject matter.

SUMMARY

[005] An agricultural work machine includes a communication system that receives a map of prior information that includes values of a terrain aspect characteristic corresponding to different geographic locations in a field. The agricultural work machine also includes a geographic position sensor that detects a geographic location of the agricultural work machine. An in situ sensor detects a value of a dynamic response characteristic of the agricultural work machine corresponding to the geographic location. A predictive model generator generates a predictive model that models a relationship between the terrain aspect characteristic and the dynamic response characteristic based on the value of the first terrain aspect characteristic on the prior information map at the geographic location and a value of the characteristic dynamic response sensed by the in situ sensor at the geographic location. A predictive map generator generates a functional predictive dynamic response map of the field, which maps predictive values of the dynamic response characteristic to the different geographic locations in the field, based on the terrain aspect characteristic values in the prior information map and with based on the predictive model.

[006] This summary is provided to present a selection of concepts in a simplified form, which are further described below in the detailed description. This summary is not intended to identify the important aspects or essential aspects of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. The claimed matter is not limited to examples resolving any or all of the disadvantages noted in the grounds.

BRIEF DESCRIPTION OF THE DRAWINGS

[007] Figure 1 is a partially pictorial, partially schematic illustration of an example of a combined harvester.

[008] Figure 2 is a block diagram showing some portions of an agricultural harvester in greater detail, according to some examples of the present description.

[009] Figures 3A-3B (collectively referred to here as figure 3) show a flowchart illustrating an example of operation of an agricultural harvester in generating a map.

[0010] Figure 4 is a block diagram showing an example of a predictive model generator and a predictive metric map generator.

[0011] Figure 5 is a flowchart of a method for generating and using a confidence metric with respect to a predictive dynamic response model for an agricultural machine.

[0012] Figure 6 is a block diagram showing an example of an agricultural harvester communicating with a remote server environment.

[0013] Figures 7 to 9 show examples of mobile devices that can be used in an agricultural harvester.

[0014] Figure 10 is a block diagram showing an example of a computing environment that can be used in an agricultural harvester and the architectures illustrated in the previous figures.

DETAILED DESCRIPTION

[0015] For the purposes of promoting an understanding of the principles of the present description, reference will now be made to the examples illustrated in the drawings, and specific language will be used to describe the same. However, it will be understood that no limitation of the scope of the invention is intended. Any additional changes and modifications to the described devices, systems, methods, and any further application of the principles of the present description are fully contemplated as would normally occur to one skilled in the art to which the invention relates. In particular, it is fully contemplated that the aspects, components and/or steps described in relation to one example may be combined with the aspects, components and/or steps described in relation to other examples of the present description.

[0016] The present description refers to the use of in situ data taken simultaneously with an agricultural operation, in combination with previous data, to generate a predictive map and, more particularly, a predictive response map. In some examples, the predictive response map can be used to control an agricultural work machine, such as an agricultural harvester. Although embodiments will be described with respect to a particular agricultural combine, embodiments are applicable to a wide variety of agricultural machines.

[0017] Terrain variability and the response to a vehicle moving on variable terrain are complex interactions. Terrain roughness can be affected by temperature, weather conditions, previous passes by other vehicles, and ground profile roughness. Furthermore, the dynamics of a vehicle traveling over terrain can also be affected by a number of different variables including, without limitation, machine mass, mass distribution, travel speed, damping factor of any suspension, and the direction of travel. displacement. When used here, terrain is intended to encompass fields, highways, or any other ground surface over which agricultural machinery may be driven or transported.

[0018] Transportation of agricultural equipment is often done on highways that include less than desirable response to operator driving comfort and vehicle/implement interactions such as persistent bouncing and towing spikes. The road characteristic includes the type of road surface (i.e., asphalt, cement, gravel, dirt), surface roughness, wear rate, climate, etc. The road characteristic may also be variable by years, and the response of the vehicle/implement to these may be dependent on the direction of travel, the speed of travel, and the mass or mass distribution of the implement/towed machine. In some cases, vehicle/implement response to such aspects may require the vehicle to be slowed, or perhaps even stopped, to eliminate unwanted dynamics. Additionally, the variability of terrain, travel speed, mass and mass distribution of the machine, roughness of the soil profile and/or path can influence not only the dynamic response of the machine, but also the response of the operator's seat.

[0019] Figure 1 is a partly pictorial, partly schematic illustration of a self-propelled agricultural harvester 100. In the illustrated example, the agricultural harvester 100 is a combined harvester. Furthermore, although combination harvesters are provided as examples throughout this description, it will be recognized that the present description is also applicable to other types of agricultural machinery, such as cotton harvesters, sugar cane harvesters, self-propelled forage harvesters. , reapers. Consequently, the present invention is intended to encompass the various types of agricultural machinery described and is thus not limited to combined harvesters. Furthermore, the present invention is directed to other types of work machines, such as agricultural seeders and sprayers, construction equipment, forestry equipment, and lawn cultivation equipment, in which the generation of a predictive map may be applicable. . Accordingly, the present invention is intended to encompass these various types of harvesters and other work machines and is thus not limited to combination harvesters.

[0020] As shown in Figure 1, the agricultural combine 100 illustratively includes an operator compartment with an operator seat 101 therein and a variety of different operator interface mechanisms, for controlling the agricultural combine 100. The agricultural combine 100 includes front end equipment, such as a cutting deck 102, and a mower generally indicated at 104. The agricultural combine 100 also includes a feeder 106, a feed accelerator 108, and a thresher generally indicated at 110. The feeder 106 and feed accelerator 108 are part of a material handling subsystem 125. The cutting deck 102 is pivotably coupled to a frame 103 of the agricultural harvester 100 along the pivot axis 105. One or more actuators 107 actuate the movement of the cutting deck 102 around the geometric axis 105 in the direction generally indicated by the arrow 109. Thus, a vertical position of the cutting deck 102 (the height of the cutting deck) above the ground 111 on which the cutting deck 102 moves is controllable by actuation of actuator 107. Although not shown in Figure 1, agricultural combine 100 may also include one or more actuators that operate to apply a tilt angle, a roll angle, or both, to the cutting deck. 102 or portions of the cutting deck 102. Slope refers to an angle at which the mower 104 engages the crop. The tilt angle is increased, for example, by controlling the cutting deck 102 to point the distal edge 113 of the cutter 104 more toward the ground. The tilt angle is decreased by controlling the cutting deck 102 to point the distal edge 113 of cutter 104 further away from the ground. The roll angle refers to the orientation of the cutting deck 102 around the front-to-back longitudinal axis of the agricultural combine 100.

[0021] The thresher 110 illustratively includes a threshing rotor 112 and a concave assembly 114. Additionally, the agricultural combine 100 also includes a separator 116. The agricultural combine 100 also includes a cleaning subsystem or cleaning shoe (collectively referred to as as cleaning subsystem 118) which includes a cleaning fan 120, upper screen 122, and screen 124. The material handling subsystem 125 also includes the discharge beater 126, the threshing residue elevator 128, the clean grain elevator 130, as well as discharge worm screw 134 and discharge mouth 136. The clean grain elevator moves clean grain into the clean grain tank 132. The agricultural harvester 100 also includes a residue subsystem 138 that may include the chopper 140 and the spreader 142. The agricultural harvester 100 also includes a propulsion subsystem that includes a motor that drives ground-engaging components 144, such as wheels or tracks. In some examples, a combine harvester within the scope of the present invention may have more than one of any of the subsystems mentioned above. In some examples, the agricultural combine 100 may have left and right cleaning subsystems, separators, etc., which are not shown in Figure 1.

[0022] In operation, and by way of overview, the agricultural combine 100 illustratively moves through a field in the direction indicated by arrow 147. As the agricultural combine 100 moves, the cutting deck 102 (and associated spool 164) engages the crop to be harvested and gathers the crop toward the mower 104. An agricultural harvester operator 100 may be a local human operator, a remote human operator, or an automatic system. An operator command is a command by an operator. The operator of agricultural combine 100 may determine one or more of a height setting, a tilt angle setting, or a roll angle setting for the cutting deck 102. For example, the operator feeds a setting or settings to a control system, described in more detail below, that controls the actuator 107. The control system may also receive adjustment from the operator to establish the tilt angle and roll angle of the cutting deck 102 and implement the adjustments fed through the control of associated actuators, not shown, which operate to change the tilt angle and roll angle of the cutting deck 102. The actuator 107 maintains the cutting deck 102 at a height above the ground 111 based on a height adjustment and, where applicable, at the desired pitch and roll angles. Each of the height, roll, and tilt adjustments can be implemented independently of the others. The control system responds to a cutting deck error (e.g., the difference between the height setting and the measured height of the cutting deck 104 above the ground 111 and, in some examples, tilt angle and tilt angle errors). scrolling) with a responsiveness that is determined based on a selected sensitivity level. If the sensitivity level is set at a higher sensitivity level, the control system responds to smaller cutting deck position errors, and attempts to reduce detected errors more quickly than when the sensitivity is at a lower sensitivity level.

[0023] Returning to the description of the operation of agricultural harvester 100, after crops are cut by the cutter 104, the separated crop material is moved through a conveyor in the feeder 106 in the direction of the feed accelerator 108, which accelerates the harvesting material. crop material into the thresher 110. The crop material is threshed by the rotor 112 rotating 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 residue is moved by the threshing beater. discharge 126 toward the residue subsystem 138. The portion of residue transferred to the residue subsystem 138 is chopped by the residue chopper 140 and spread in the field by the spreader 142. In other configurations, the residue is released from the agricultural combine 100 in a deposit in cash.

[0024] Grain falls into the cleaning subsystem 118. The upper sieve 122 separates some larger pieces of material from the grain, and the sieve 124 separates some of the finer pieces of material from the cleaned grain. Clean grain falls into a screw that moves the grain to an inlet end of the clean grain elevator 130, and the clean grain elevator 130 moves the clean grain upward, depositing the clean grain in the clean grain tank 132. Residue is removed from the cleaning subsystem 118 by airflow generated by the cleaning fan 120. The cleaning fan 120 directs air along an upward airflow path through the upper sieves and screens. The airflow transports the residue backwards in the agricultural combine 100 toward the residue handling subsystem 138.

[0025] The threshing waste elevator 128 returns the threshing waste to the threshing machine 110 where the threshing waste is rethreshed. Alternatively, the threshing residue may also be passed to a separate rethreshing mechanism by a threshing residue elevator or other transport device in which the threshing residue is also rethreshed.

[0026] Figure 1 also shows that, in one example, the agricultural combine 100 includes the ground speed sensor 146, one or more separator loss sensors 148, a clean grain camera 150, an image capture mechanism forward oriented 151, which may be in the form of a stereo or mono camera, and one or more loss sensors 152 provided in the cleaning subsystem 118.

[0027] The ground speed sensor 146 senses the travel speed of the agricultural harvester 100 on the ground. The ground speed sensor 146 can sense the travel speed of the agricultural harvester 100 by sensing the rotational speed of components engaging the ground (such as wheels or tracks), a drive shaft, an axle, or other components. In some cases, speed of travel may be sensed using a positioning system, such as a global positioning system (GPS), a passive reconnaissance system, a long-range navigation system (LORAN), or a wide variety of other systems or sensors that provide an indication of travel speed.

[0028] The loss sensors 152 illustratively provide an output signal indicative of the amount of grain loss occurring on both the right and left sides of the cleaning subsystem 118. In some examples, the sensors 152 are shock sensors that count shocks of grain per unit time or per unit distance traveled to provide an indication of grain loss occurring in the cleaning subsystem 118. The shock sensors for the right and left sides of the cleaning subsystem 118 may provide individual signals or a combined signal or aggregate. In some examples, the sensors 152 may include a single sensor, as opposed to separate sensors provided for each cleaning subsystem 118.

[0029] The separator loss sensor 148 provides a signal indicating grain loss in the left and right separators, not separately shown in figure 1. The separator loss sensors 148 can be associated with the left and right separators and can provide signals of separate grain loss or a combined or aggregated signal. In some cases, grain loss sensing in separators can also be carried out using an extensive variety of different types of sensors.

[0030] The agricultural harvester 100 may also include other sensors and measuring mechanisms. For example, the agricultural harvester 100 may include one or more of the following sensors: a cutting deck height sensor that senses a height of the cutting deck 102 above the ground 111; a residue regulation sensor, which is configured to sense whether the agricultural combine 100 is configured to chop the residue, produce a row deposit, etc.; a cleaning shoe fan speed sensor for sensing the speed of the fan 120; a concave clearance sensor that senses the clearance between the rotor 112 and the concaves 114; a threshing rotor speed sensor, which senses a rotor speed of the rotor 112; an upper screen gap sensor, which senses the size of openings in the upper screen 122; a sieve gap sensor that senses the size of openings in the sieve 124; a non-grain (MOG) moisture sensor, which senses a moisture level of the MOG passing through the agricultural combine 100; one or more machine setting sensors configured to sense various configurable settings of the agricultural harvester 100; a machine orientation sensor, which senses the orientation of the agricultural combine 100; and crop property sensors, which sense a variety of different types of crop properties, such as crop type, crop moisture, and other crop properties. The crop property sensors may also be configured to sense characteristics of cut crop material when the crop material is being processed by the agricultural combine 100. For example, in some cases, the crop property sensors may sense grain quality. , such as broken grain, MOG levels; grain constituents such as starches and protein; and grain feed rate as grain moves through feeder 106, clean grain elevator 130, or other locations on agricultural combine 100. Crop property sensors can also sense the biomass feed rate through feeder 106 , through separator 116 or elsewhere on the agricultural combine 100. The crop property sensors may also sense the feed rate as a mass flow rate of grain through the elevator 130 or through other portions of the agricultural combine 100 or other output signals indicative of other sensed variables are provided.

[0031] Before describing how the agricultural combine 100 generates a functional predictive dynamic response map, and uses the functional predictive dynamic response map for control, a brief description of some of the items in the agricultural combine 100, and their operation, will be first done. The description of Figures 2 and 3 describe the reception of a generic type of preview map and the combination of information from the preview map with a georeferenced sensor signal generated by an in situ sensor, where the sensor signal is indicative of a characteristic in, or of, the field, such as a surface roughness characteristic present in the field. Field characteristics may include, but are not limited to, characteristics of a field, such as slope, soil profile roughness, moisture, surface quality; characteristics of cultivation properties, such as cultivation height, cultivation humidity, cultivation density, cultivation state; grain property characteristics such as grain moisture, grain size, grain test weight; and machine performance characteristics such as loss levels, work quality, fuel consumption, and energy utilization. A relationship between characteristic values obtained from in situ sensor signals and values from the prior information map is identified, and this relationship is used to generate a new functional predictive map. A functional predictive map predicts values at different geographic locations in a field, and one or more of those values can be used for machine control, such as one or more subsystems of an agricultural combine. In some cases, a functional predictive map may be presented to a user, such as an operator of an agricultural work machine, which may be an agricultural harvester. A functional predictive map may be presented to a user visually, such as through a display, haptically, or audibly. The user can interact with the functional predictive map to perform editing operations and other user interface operations. In some cases, a functional predictive map may be used for one or more of the control of an agricultural work machine, such as an agricultural combine, presentation to an operator or other user, and presentation to an operator or user for interaction by an operator. or user.

[0032] After the generic approach is described with respect to Figures 2 and 3, a more specific approach for generating a functional predictive dynamic response map, which can be presented to an operator or user, or used to control the agricultural harvester 100, or both, is described with respect to Figures 4 and 5. Again, although the present discussion continues with respect to the agricultural harvester and, particularly, a combination harvester, the scope of the present invention encompasses other types of agricultural combines or other agricultural work machines . As defined here, an agricultural work machine is a machine used for agricultural purposes to perform work. The agricultural work machine can be a tractor, a harvester, a sprayer, etc. Furthermore, the agricultural work machine can tow an agricultural implement such as a planter or sprayer.

[0033] Figure 2 is a block diagram showing some portions of an example agricultural harvester 100. Figure 2 shows that the agricultural harvester 100 illustratively includes one or more processors or servers 201, database 202, the position sensor geographic location 204, the communication system 206, and one or more in situ sensors 208, which sense one or more agricultural characteristics of a field simultaneously with a harvesting operation. An agricultural characteristic can include any characteristic, which can have an effect on the harvesting operation. Some examples of agricultural characteristics include characteristics of the harvesting machine, the field, the plants in the field, and the climate. Other types of agricultural traits are also included. The in situ sensors 208 generate values corresponding to the sensed characteristics. The agricultural combine 100 also includes a predictive model or relationship generator (collectively referred to hereinafter as “predictive model generator 210”), the predictive map generator 212, the control zone generator 213, the control system 214, one or more controllable subsystems 216, and an operator interface mechanism 218. The agricultural combine 100 may also include an extensive variety of other functionalities of agricultural combines 220. In situ sensors 208 include, for example, on-board sensors 222, sensors remotes 224, and other sensors 226 that sense characteristics of a field or machine operation during the course of an agricultural operation. The predictive model generator 210 illustratively includes an in situ variable-to-variable model generator of prior information 228, and the predictive model generator 210 may include other items 230. The control system 214 includes the communication system controller 229, the operator interface controller 231, a tuning controller 232, the path planning controller 234, the feed rate controller 236, the cutting deck and reel controller 238, the draper belt controller 240, the cover plate position controller 242, the waste system controller 244, the machine cleaning controller 245, the zone controller 247, and the system 214 may include other items 246. The controllable subsystems 216 include the machine actuators and cutting deck 248, the propulsion subsystem 250, the steering subsystem 252, the active suspension subsystem 253, the active seating subsystem 254, and the subsystems 216 may include an extensive variety of other subsystems 256.

[0034] Figure 2 also shows that the agricultural harvester 100 can receive the preview map 258. As described below, the preview map 258 includes, for example, a topographic map or other appropriate terrain map, which refers the geographical position with the terrain conditions of a previous operation. However, the prior information map 258 may also encompass other types of data that were obtained prior to a harvesting operation or a map from a previous operation. 2 also shows that an operator 260 can operate the agricultural harvester 100. An operator 260 interacts with the operator interface mechanisms 218. In some examples, the operator interface mechanisms 218 may include control levers, levers, a steering wheel , connection systems, pedals, keys, dials, keyboards, user-actuable elements (such as icons, keys, etc.) on a user interface display device, a microphone and speaker (where speech recognition and synthesis are provided), among a wide variety of other types of control devices. When a touch-sensitive display system is provided, the operator 260 can interact with operator interface mechanisms 218 using touch gestures. These examples described above are provided as illustrative examples and are not intended to limit the scope of the present invention. Accordingly, other types of operator interface mechanisms 218 may be used and are within the scope of the present invention.

[0035] The preview information map 258 can be downloaded to the agricultural harvester 100 and stored in the database 202, using the communication system 206 or in other ways. In some examples, the communication system 206 may be a cellular communication system, a system for communicating over a wide area network or a local area network, a system for communicating over a near field communication network, or a communication system configured to communicate over any of a variety of other networks or combinations of networks. The communication system 206 may also include a system that downloads or transfers information to and from a Secure Digital (SD) card or a universal serial bus (USB) card, or both.

[0036] The geographic position sensor 204 illustratively senses or detects the geographic position or location of the agricultural harvester 100. The geographic position sensor 204 may include, but is not limited to, a global navigation satellite system (GNSS) receiver. , which receives signals from a GNSS satellite transmitter. The geographic position sensor 204 may also include a real-time kinematic (RTK) component that is configured to improve the position accuracy of data derived from the GNSS signal. The geographic position sensor 204 may include a passive recognition system, a cellular triangulation system, or any of a variety of other geographic position sensors.

[0037] The in situ sensors 208 may be any of the sensors described above with respect to figure 1. The in situ sensors 208 include onboard sensors 222, which are mounted on board the agricultural harvester 100. Such sensors may include, for example, an inertial measurement unit (IMU), a vertical displacement sensor, and/or a perception sensor (e.g., a forward-facing stereo or mono camera system). The in situ sensors 208 also include remote in situ sensors 224, which capture in situ information. In situ data includes data taken from a sensor on board the combine or taken by any sensor on which data is detected during the harvesting operation.

[0038] The predictive model generator 210 generates a model that is indicative of a relationship between values sensed by the in situ sensor 208 and a metric mapped to the field by the prior information map 258. For example, if the prior information map 258 represent the terrain, and the in situ sensor 208 is sensing a value indicative of vertical displacement, then the prior information in situ variable-to-variable model generator 228 generates a predictive response model that models the relationship between the conditions terrain and the vertical displacement value. The predictive response model may also be generated based on terrain data from the preview map 258 and multiple values of in situ data generated by the in situ sensors 208. Then, the predictive map generator 212 uses the generated predictive response model by the predictive model generator 210 to generate a functional predictive dynamic response map, which predicts the response of the agricultural machine to terrain properties, such as soil roughness, sensed by the in situ sensors 208 at different locations in the field based on the map of prior information 258.

[0039] The examples here describe the generation of a predictive model and, in some examples, the generation of a functional predictive map based on the predictive model. The examples described here are distinguished from other approaches by the use of a model that is at least one multivariate, nonlinear, or location-specific (i.e., georeferenced, such as map-based). Additionally, the model is reviewed when the work machine is performing an operation and while additional in situ sensor data is collected. The model can also be applied in the future beyond the current workplace. For example, the model may form a baseline (e.g., starting point) for a subsequent operation at a different workplace or at the same workplace at a future time.

[0040] Revision of the model in response to new data may employ machine learning methods. Without limitation, machine learning methods may include memory networks, Bayes systems, decision trees, Eigenvectors, Eigenvalues and Machine Learning, Evolutionary and Genetic Algorithms, Expert Systems/Rules, Support Vector Machines, Engines/ Symbolic Reasoning, Generative Adversarial Networks (GANs), Graph Analytics and ML, Linear Regression, Logistic Regression, LSTMs and Recurrent Neural Networks (RNNSs), Convolutional Neural Networks (CNNs), MCMC, Cluster Analysis, Random Forests, Reinforcement Learning or Rewards-Based Machine Learning. Learning can be supervised or unsupervised

[0041] Model implementations can be mathematical, making use of mathematical equations, empirical correlations, statistics, tables, matrices, and the like. Other model implementations may rely more on symbols, knowledge bases, and logic, such as rule-based systems. Some implementations are hybrid, using both mathematics and logic. Some models may incorporate random, non-deterministic, or unpredictable elements. Some model implementations may make use of values from data networks, such as neural networks. These are just a few examples of models.

[0042] The predictive paradigm examples described here differ from non-predictive approaches, in which an actuator or other machine parameter is fixed in machine time, the system or component is coupled, established once before the machine enters the work site , is reactively adjusted manually based on operator perception, or is reactively adjusted based on a sensor value.

[0043] The functional predictive map examples described here also differ from other map-based approaches. In some examples of these other map-based approaches, an a priori control map is used without any modification based on in situ sensor data or otherwise a determined difference between in situ sensor data and a predictive map is used to calibrate the in situ sensor. In some examples of the other approaches, sensor data can be mathematically combined with a priori data to generate control signals, but in a location agnostic manner, that is, an adjustment to an a priori, georeferenced predictive setting, is applied. regardless of the location of the working machine in the workplace. The continued use or end of use of the setting is not dependent on the work machine being in a particular defined location or region within the work site.

[0044] In the examples described here, the functional predictive maps and predictive actuator control can employ the obtained maps and in situ data, which are used to generate predictive models. The predictive models are then reviewed during operation to generate revised functional predictive maps and revised actuator control. In some examples, actuator control is provided based on functional predictive control zone maps, which are reviewed during operation on the job site. In some examples, revisions (e.g., adjustments, calibrations, etc.) are associated with regions or zones of the workplace, rather than the entire workplace or some non-georeferenced condition. For example, adjustments are applied to one or more areas of a workplace to which an adjustment is determined to be relevant (e.g., such as satisfying one or more conditions, which may result in application of a change to one or more more locations, while not applying the change to one or more other locations), as opposed to applying a change in a blanket manner to each location in a non-selective manner.

[0045] In some examples described here, the models determine and apply those adjustments to selective portions or zones of the workplace based on an a priori data set, which, in some cases, is multivariate in nature. For example, adjustments may, without limitation, be tied to defined portions of the job site based on site-specific factors such as topography, soil type, crop variety, soil moisture, as well as various other factors alone. or in combination. Consequently, adjustments are applied to portions of the field in which site-specific factors satisfy one or more criteria, and not to other portions of the field in which those site-specific factors do not satisfy one or more criteria. Thus, in some examples described here, the model generates a revised functional predictive map for at least the current location or zone, the unworked portion of the workplace, or the entire workplace.

[0046] As an example, in which the adjustment is applied only to particular areas of the field, consider the following. The system may determine that a detected in situ characteristic value (e.g., detected vertical displacement value) varies from a predictive value of the characteristic (e.g., predictive vertical displacement value), such as by a threshold amount. This deviation can only be detected in areas of the field where the work site elevation is above a defined level. Therefore, the review to predictive value is only applied to other areas of the workplace having elevation above the defined level. In this simplest example, the predictive feature value and elevation occurred at the point of the offset and the detected feature value and elevation at the point of the offset that crosses the threshold are used to generate a linear equation. The linear equation is used to adjust the predictive feature value in unharvested areas of the job site on the functional predictive map as a function of elevation and the predicted feature value. This results in a revised functional predictive map, in which some values are adjusted, while others remain unchanged, based on the selected criteria, for example, elevation as well as threshold deviation. The revised functional map is then used to generate a revised functional control zone map for machine control.

[0047] As an example, without limitation, consider a case of the paradigm described here, which is parameterized as follows.

[0048] One or more maps of the field, workplace, or stay are obtained;
In situ sensors generate sensor data indicative of in situ characteristic values, such as vertical height displacement.

[0049] A predictive model generator generates one or more predictive models based on the one or more obtained maps and in situ sensor data, such as a predictive vertical height offset.

[0050] A predictive map generator generates one or more functional predictive maps based on a model generated by the predictive model generator and the one or more maps obtained. For example, the predictive map generator may generate a functional predictive dynamic response map, which maps dynamic response values to one or more locations in the workplace based on a predictive dynamic response model and the one or more maps obtained.

[0051] Control zones, which include machine setting values, can be incorporated into the functional predictive dynamic response map to generate a functional predictive dynamic response map with control zones.

[0052] As the mobile machine continues to operate at the job site, additional in situ sensor data is collected. A learning trigger criterion may be detected, such as a threshold amount of additional in situ sensor data being collected, a magnitude of change in a relationship (e.g., the in situ feature values vary by a selected threshold degree, from a predictive value of the feature), and the operator or user makes edits to the predictive map(s) or a control algorithm, or both, a selected amount of time (e.g., threshold) elapses, as well as well as several other learning trigger criteria. The predictive model(s) are then revised based on additional in situ sensor data and obtained map values. The functional predictive maps or the functional predictive control zone maps, or both, are then revised based on the revised model(s) and the values in the maps obtained.

[0053] In some examples, the type of values in the functional predictive map 263 may be the same as the type of in situ data sensed by the in situ sensors 208. In some cases, the type of values in the functional predictive map 263 may have different units of data sensed by in situ sensors 208. In some examples, the type of values in the functional predictive map 263 may be different from the type of data sensed by in situ sensors 208, but has a relationship to the type of data sensed by in situ sensors 208. For example, in some examples, the type of data sensed by in situ sensors 208 may be indicative of the type of values in the functional predictive map 263. In some examples, the type of data in the functional predictive map 263 may be different from the type of data in the prior information map 258. In some cases, the data type in the functional predictive map 263 may have different units from the data in the prior information map 258. In some examples, the data type in the functional predictive map 263 may be different from the data type in the prior information map 258, but has a relationship to the data type in the prior information map 258. For example, in some examples, the data type in the prior information map 258 may be indicative of the type data type in the functional predictive map 263. In some examples, the data type in the functional predictive map 263 is different from one of, or both, the in situ data type sensed by the in situ sensors 208 and the data type in the functional predictive map 263. prior information 258. In some examples, the data type in the functional predictive map 263 is the same as one of, or both of, the in situ data type sensed by the in situ sensors 208 and the data type in the prior information map 258. In some examples, the data type in the functional predictive map 263 is the same as one of the in situ data type sensed by the in situ sensors 208 or the data type in the prior information map 258, and different from each other.

[0054] Continuing with the preceding example, in which the prior information map 258 is a terrain or soil profile roughness map and the in situ sensor 208 senses a value indicative of vertical displacements, the predictive map generator 212 can use values in the prior information map 258, and the model generated by the predictive model generator 210, to generate a functional predictive map 263, which predicts vertical displacement at different locations in the field. The predictive map generator 212 Thus provides predictive map 264.

[0055] As shown in Figure 2, the predictive map 264 predicts the value of a sensed feature (sensed by in situ sensor(s) 208), or a feature related to the sensed feature, at various locations across the field based on a prior information value in the prior information map 258 at those locations and using the predictive model. For example, if the predictive model generator 210 has generated a predictive model indicative of a relationship between dynamic machine responses and a vertical displacement, then, given the vertical displacement at different locations across the field, the predictive map generator 212 generates a predictive map 264, which predicts the dynamic machine response to a vertical displacement at different locations across the field.

[0056] Some variations in the types of data, which are mapped in the prior information map 258, the types of data sensed by in situ sensors 208, and the types of data predicted in the predictive map 264 will now be described.

[0057] In some examples, the type of data in the preview map 258 is different from the type of data sensed by the in situ sensors 208, yet the type of data in the predictive map 264 is the same as the type of data sensed by the sensors in situ 208.

[0058] Also, in some examples, the type of data in the preview map 258 is different from the type of data sensed by the in situ sensors 208, and the type of data in the predictive map 264 is different from both the type of data in the map of prior information 258 and the type of data sensed by the in situ sensors 208.

[0059] In some examples, the prior information map 258 is from a previous pass through the field during a previous operation and the data type is different from the data type sensed by the in situ sensors 208, yet the data type in the map predictive data 264 is the same as the type of data sensed by in situ sensors 208.

[0060] In some examples, the prior information map 258 is from a previous pass through the field during a previous operation and the data type is the same as the data type sensed by the in situ sensors 208, and the data type in the predictive map 264 is also the same as the type of data sensed by the in situ sensors 208.

[0061] In some examples, the predictive map 264 may be provided to the control zone generator 213. The control zone generator 213 groups adjacent portions of an area into one or more control zones based on data values from the predictive map 264, which are associated with those adjacent portions. A control zone may include two or more contiguous portions of an area, such as a field, for which a control parameter corresponding to the control zone for control of a controllable subsystem is constant. For example, a response time to change a setting of the controllable subsystems 216 may be inadequate to satisfactorily respond to changes in values contained in a map, such as the predictive map 264. In which case, the control zone generator 213 analyzes the maps and identifies control zones, which are of a defined size to accommodate the response time of the controllable subsystems 216. In another example, the control zones can be sized to reduce wear from excessive actuator movement that results from continuous adjustment. In some examples, a different set of control zones may exist for each controllable subsystem 216 or for groups of controllable subsystems 216. The control zones may be added to the predictive map 264 to obtain predictive control zone map 265. predictive control zone 265 may thus be similar to predictive control zone map 264, except that predictive control zone map 265 includes control zone information defining the control zones. Thus, a functional predictive map 263 as described herein may or may not include control zones. Both the predictive map 264 and the predictive control zone map 265 are functional predictive maps 263. In one example, a functional predictive map 263 does not include control zones, as does the predictive map 264. In another example, a functional predictive map 263 includes control zones, such as predictive control zone map 265. In some examples, multiple crops may be simultaneously present in a field if intercrop production is implemented. In this case, the predictive map generator 212 and the control zone generator 213 are able to identify the location and characteristics of the two or more crops and then generate the predictive map 264 and predictive map with control zones 265 accordingly.

[0062] It will also be recognized that the control zone generator 213 can group values to generate control zones and the control zones can be added to the predictive control zone map 265, or a separate map showing only the control zones that are generated. In some examples, control zones may be used for control or calibration of the agricultural combine 100, or both. In other examples, control zones may be presented to an operator 260 and used for control or calibration of the agricultural combine 100, and in other examples, control zones may be presented to an operator 260 or other user or stored for subsequent use.

[0063] The predictive map 264 or the predictive control zone map 265, or both, are provided to the control system 214, which generates control signals based on the predictive map 264 or the predictive control zone map 265, or both. In some examples, the communication system controller 229 controls the communication system 206 to communicate the predictive map 264 or the predictive control zone map 265 or control signals based on the predictive map 264 or the predictive control zone map. 265 to other agricultural harvesters, which are harvesting in the same field. In some examples, the communication system controller 229 controls the communication system 206 to send the predictive map 264, predictive control zone map 265, or both, to other remote systems.

[0064] The operator interface controller 231 is operable to generate control signals for controlling the operator interface mechanisms 218. The operator interface controller 231 is also operable to present the predictive map 264 or the zone map of predictive control 265 or other information derived from, or based on, the predictive map 264, predictive control zone map 265, or both, for the operator 260. The operator 260 may be a local operator or a remote operator. As an example, controller 231 generates control signals for controlling a display mechanism to display one or both of the predictive map 264 and the predictive control zone map 265 to an operator 260. The controller 231 may generate mechanisms actuable by the operator, which are displayed and can be actuated by an operator to interact with the displayed map. An operator can edit the map based on the operator's observation. The timing controller 232 may generate control signals for controlling various settings on the agricultural combine 100 based on the predictive map 264, the predictive control zone map 265, or both. For example, the tuning controller 232 may generate control signals for controlling the machine and cutting deck actuators 248. In response to the generated control signals, the machine and cutting deck actuators 248 operate to control, e.g. example, one or more of the sieve and upper sieve settings, thresher clearance, rotor settings, cleaning fan speed settings, cutting deck height, cutting deck functionality, spool speed, spool, draper functionality (where the agricultural combine 100 is coupled to a front draper frame), corn cutting deck functionality, internal distribution control, and other actuators 248, which affect the other functions of the agricultural combine 100. The planning controller path 234 illustratively generates control signals for controlling the steering subsystem 252 to orient the agricultural harvester 100 according to a desired path. The path planning controller 234 may control a path planning system to generate a route for the agricultural combine 100 and may control the propulsion subsystem 250 and the steering subsystem 252 to guide the agricultural combine 100 along that route. The feed rate controller 236 can control various subsystems, such as the propulsion subsystem 250 and the machine actuators 248, for controlling a feed rate based on the predictive map 264 or the predictive control zone map 265. or both. The cutting deck and reel controller 238 may generate control signals for controlling a cutting deck or a reel or other cutting deck functionality. The draper belt controller 240 may generate control signals for controlling a draper belt or other draper functionality based on the predictive map 264, predictive control zone map 265, or both. The cover plate position controller 242 may generate control signals for controlling a position of a cover plate included in a cutting deck based on the predictive map 264 or the predictive control zone map 265, or both. and the waste system controller 244 may generate control signals for controlling a waste subsystem 138 based on the predictive map 264 or the predictive control zone map 265, or both. The machine cleaning controller 245 may generate control signals for controlling the machine cleaning subsystem 254. Other controllers included in the agricultural combine 100 may control other subsystems based on the predictive map 264 or the predictive control zone map 265, or also both.

[0065] Figures 3A and 3B (collectively referred to herein as Figure 3) show a flowchart illustrating an example of the operation of the agricultural harvester 100 in generating a predictive map 264 and a predictive control zone map 265 based on the prior information 258.

[0066] At 280, the agricultural harvester 100 receives the preview map 258. Examples of the preview map 258 or receiving the preview map 258 are discussed with respect to blocks 281, 282, 284 and 286. As discussed above, the prior information map 258 maps values of a variable, corresponding to a first characteristic, to different locations in the field, as indicated in block 282. As indicated in block 281, reception of the prior information map 258 may involve selecting a or more than a plurality of possible prior information maps that are available. For example, a prior information map may be a topographic map generated from aerial imaging or a prior field operation. Another prior information map may be a map generated during a previous pass through the field, which may have been performed by a different machine performing a prior or previous operation in the field, such as a sprayer or other machine. The process by which one or more prior information maps are selected may be manual, semi-automatic, or automatic. The prior information map 258 is based on data collected prior to a current harvesting operation. This is indicated by block 284. For example, data may be collected based on aerial images taken during a previous year, or earlier in the current growing season, or at other times. The data can be based on data detected in other ways than using aerial imagery. The data for the preview map 258 can be transmitted to the agricultural combine 100 using the communication system 206 and stored in the database 202. The data for the preview map 258 can be provided to the agricultural combine 100 using the communication system 206 also in other ways, and this is indicated by block 286 in the flowchart of Figure 3. In some examples, the prior information map 258 may be received by the communication system 206.

[0067] At the beginning of a harvesting operation, the in situ sensors 208 generate sensor signals indicative of one or more in situ data values indicative of a characteristic, e.g., a vertical displacement or acceleration characteristic, as indicated by the block 288. Examples of in situ sensors 222 include, without limitation: current position sensor 300, vertical displacement sensor 301, heading sensor 302, mass sensor 303, speed sensor 304, mass 305, and/or motion sensor 306.

[0068] The current position sensor 300 can be a GPS sensor or any other appropriate sensor, which is capable of providing a signal indicative of the geographic location.

[0069] Vertical displacement sensor 301 includes any sensor that employs technology capable of sensing changes in the vertical displacement of the agricultural machine, or a portion thereof, from the ground. Examples include, without limitation, an ultrasonic sensor directed toward the ground to provide an indication of distance to the ground, an inertial measurement unit configured to generate a signal indicative of acceleration in a vertical direction, and a laser displacement sensor. Another example of a vertical height sensor is a physical body, such as a cutting deck height rod operatively coupled to a potentiometer.

[0070] Heading sensor 302 may be any suitable device that provides an electronic compass heading indication. In one example, the heading sensor 302 is simply an electronic compass module.

[0071] The mass sensor 303 can be a load cell positioned inside the agricultural machine, which is capable of sensing the load (for example, the mass of the harvested material) and providing a signal indicative of the load. Additionally, the mass sensor 303 may include software or logic that calculates a quantity of harvested material as a function of the operating time of the combine. In another example, the mass sensor 303 may include one or more cameras within the combine, which obtain one or more images of the harvested material within the combine.

[0072] The speed sensor 304 may be a known speed sensor, operatively coupled to a mechanical element of the agricultural machine in order to provide a speed indicative signal. Additionally, or alternatively, the speed sensor 304 could be a logic module or code, which processes repeated indications of the current position, from the current position sensor 300 to determine the speed. Another example of a speed sensor includes a ground radar system.

[0073] The mass distribution sensor 305 may be a plurality of load cells, such that differences in signals between the plurality of load cells may indicate the distribution of the load within the agricultural machine. Similarly, one or more cameras may also display the harvested material inside the combine, where the image provides an indication of distribution. In embodiments in which multiple cameras are employed, stereovision processing techniques may be employed to detect a three-dimensional representation of harvested material within the combine, which three-dimensional representation may show areas of more or less material within the combine and thus indicate the mass distribution.

[0074] The motion sensor 306 may include any appropriate sensor that provides information related to the movement of the agricultural machine or portions thereof. For example, motion sensor 306 could include one or more inertial measurement units.

[0075] As explained above, in situ sensors 222 include other types of in situ sensors, referred to as in situ sensors 226. In some examples, onboard sensor data is georeferenced using position, heading, or position sensor data. speed from the geographic position sensor 204.

[0076] The predictive model generator 210 controls the prior information in situ variable-to-variable model generator 228 to generate a model that models a relationship between the mapped values contained in the prior information map 258 and the in situ values sensed by the in situ sensors 208, as indicated by block 292. The features or data types represented by the values mapped in the prior information map 258 and the in situ values sensed by the in situ sensors 208 may be the same features or data types or different characteristics or types of data.

[0077] The relationship or model generated by the predictive model generator 210 is provided to the predictive map generator 212. The predictive map generator 212 generates a predictive map 264, which predicts a value of the characteristic sensed by the in situ sensors 208 at different locations geographic features in a field being harvested, or a different feature that is related to the feature sensed by the in situ sensors 208, using the predictive model and the prior information map 258, as indicated by block 294.

[0078] 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 map layers of a single map. Each map layer can represent a different data type than the data type of another map layer, or the map layers can have the same data types, which were obtained at different times. For example, a first map may provide georeferenced soil profile roughness with respect to a first direction, and a second map may provide georeferenced soil profile roughness with respect to the second direction, which may be perpendicular to the first direction. Furthermore, each map in the two or more different maps or each layer in the two or more different map layers of a map maps a different type of variable to geographic locations in the field. In one such example, the predictive model generator 210 generates a predictive model that models the relationship between the in situ data and each of the different variables mapped by the two or more different maps or the two or more different map layers. Similarly, in situ sensors 208 may include two or more sensors, each sensing a different type of variable. Thus, the predictive model generator 210 generates a predictive model that models the relationships between each type of variable mapped by the prior information map 258 and each type of variable sensed by the in situ sensors 208. In one example, the predictive model generator may modeling machine dynamic responses based on input variable including, without limitation, terrain variability; machine speed; machine mass; machine mass distribution; soil profile roughness; and direction of travel. The predictive map generator 212 may generate a functional predictive map 263, which predicts a value for each sensed feature, sensed by the in situ sensors 208 (or a feature related to the sensed feature) at different locations in the field being harvested, using the predictive model. and each of the maps or map layers in the prior information map 258.

[0079] The predictive map generator 212 configures the predictive map 264 in such a way that the predictive map 264 is actionable (or consumable) by the control system 214. The predictive map generator 212 can provide the predictive map 264 to the system control zone 214 or to the control zone generator 213, or both. Some examples of different ways in which the predictive map 264 can be configured or provided are described with respect to blocks 296, 295, 299 and 297. For example, the predictive map generator 212 configures the predictive map 264 so that predictive map 264 include values, which can be read by the control system 214 and used as the basis for generating control signals for one or more of the different controllable subsystems of the agricultural combine 100, as indicated by block 296.

[0080] The control zone generator 213 can divide the predictive map 264 into control zones based on the values in the predictive map 264. Contiguously geolocated values, which are within a threshold value of one another, can be grouped into a control zone. The threshold value can be a standard threshold value, or the threshold value can be adjusted based on operator input, based on input from an automatic system, or based on other criteria. A size of the zones may be based on the responsiveness of the control system 214, the controllable subsystems 216, based on wear considerations, or other criteria, as indicated by block 295. The predictive map generator 212 configures the predictive map 264 to presentation to an operator or other user. The control zone generator 213 may configure the predictive control zone map 265 for presentation to an operator or other user. This is indicated by block 299. When presented to an operator or other user, the presentation of the predictive map 264 or the predictive control zone map 265, or both, may contain one or more of the predictive values in the predictive map 264, correlated to the geographic location, the control zones on the predictive control zone map 265, correlated to the geographic location, and values of settings or control parameters, which are used based on the predicted values on the map 264 or zones on the predictive control zone map 265. The presentation may, in another example, include more abstract information or more detailed information. The presentation may also include a confidence level, which indicates an accuracy with which the predictive values in the predictive map 264 or the zones in the predictive control zone map 265 conform to the measured values, which can be measured by sensors on the agricultural combine. 100, when the agricultural harvester 100 moves through the field. Furthermore, where information is presented at more than one location, an authentication and authorization system can be provided to implement authentication and authorization processes. For example, there may be a hierarchy of individuals who are authorized to view and change the maps and other information presented. By way of example, an onboard display device may display maps in near real time locally on the machine, or maps may also 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 can be used to determine which display elements are visible on the physical display device and which values the corresponding person can change. As an example, a local operator of machine 100 may be unable to view information corresponding to predictive map 264 or make any changes to the operation of the machine. A supervisor, such as a supervisor at a remote location, however, may be able to view the predictive map 264 on the display but be prevented from making any changes. A manager, which may be at a separate remote location, may be able to view all of the elements in the predictive map 264 and also be able to change the predictive map 264. In some cases, the predictive map 264 is accessible and changeable by a manager. Remotely positioned can be used to control the machine. This is an example of an authorization hierarchy, which can be implemented. The predictive map 264 or the predictive control zone map 265, or both, may also be configured in other ways, as indicated by block 297.

[0081] In block 298, inputs from geographic position sensor 204 and other in situ sensors 208 are received by the control system. Particularly, in block 300, control system 214 detects an input from geographic position sensor 204 identifying a geographic location of agricultural harvester 100. Block 302 represents reception by control system 214 of sensor inputs indicative of the trajectory or heading of the agricultural combine 100, and block 304 represents the reception by the control system 214 of the speed of the agricultural combine 100. Block 307 represents the reception by the control system 214 of other information from the various in situ sensors 208.

[0082] In block 308, the control system 214 generates control signals for controlling the controllable subsystems 216 based on the predictive map 264 or the predictive control zone map 265, or both, and the input from the geographic position sensor 204 and any other in situ sensors 208. In block 310, control system 214 applies control signals to controllable subsystems. It will be recognized that the particular control signals, which are generated, and the particular controllable subsystems 216, which are controlled, may vary based on one or more different factors. For example, the control signals that are generated and the controllable subsystems 216 that are controlled may be based on the type of predictive map 264 or the predictive control zone map 265, or both, that are being used. Similarly, the control signals, which are generated, and the controllable subsystems 216, which are controlled, and the timing of the control signals, may be based on various crop flow latencies through the agricultural combine 100 and the responsiveness of the controllable subsystems. 216.

[0083] By way of example, a generated predictive map 264 in the form of a predictive terrain aspect map may be used for controlling one or more subsystems 216. For example, the predictive terrain aspect map may include values of soil profile roughness, georeferenced to locations within the field being harvested. Ground profile roughness values from the predictive terrain aspect map can be extracted and used for control of the propulsion, active suspension subsystem, and active seat suspension subsystems 250, 253, and 254, respectively. By controlling subsystems 250, 253, and 254, the speed of the agricultural harvester 100 on the ground as well as the dynamic response of the suspension and/or seat can be controlled. Consequently, a wide variety of other control signals can be generated using values obtained from a predictive dynamic response map or other type of predictive map for controlling one or more of the controllable subsystems 216. The control signals can be provided for a vehicle active suspension system 253 (shown in figure 2), provided for an agricultural machine propulsion system 250 (e.g., for deceleration), and/or for an active seat suspension system 254.

[0084] In block 312, a determination is made as to whether the harvest operation has been completed. If harvesting has not been completed, processing advances to block 314, in which in situ sensor data from geographic position sensor 204 and in situ sensors 208 (and perhaps other sensors) continue to be read.

[0085] In some examples, in block 316, the agricultural harvester 100 may also detect the learning trigger criterion to perform machine learning on one or more of the predictive map 264, predictive control zone map 265, of the model generated by the predictive model generator 210, of the zones generated by the control zone generator 213, one or more control algorithms implemented by the controllers in the control system 214, and other triggered learning.

[0086] The learning trigger criteria can include any of a wide variety of different criteria. Some examples of trigger criteria detection are discussed with respect to blocks 318, 320, 321, 322 and 324. For example, in some examples, triggered learning may involve recreation of a relationship used to generate a predictive model, when a quantity threshold of in-situ sensor data is obtained from in-situ sensors 208. In such examples, receipt of an amount of in-situ sensor data from in-situ sensors 208 that exceeds a threshold triggers or causes the predictive model generator to 210 generates a new predictive model that is used by the predictive map generator 212. Thus, as the agricultural combine 100 continues the harvesting operation, reception of the threshold amount of in situ sensor data from the in situ sensors 208 triggers the creation of a new relationship represented by a predictive model generated by the predictive model generator 210. Additionally, the new predictive map 264, predictive control zone map 265, or both, may be regenerated using the new predictive model. Block 318 represents the detection of a threshold amount of in situ sensor data, used to trigger the creation of a new predictive model.

[0087] In other examples, the learning trigger criterion may be based on how much the in situ sensor data from the in situ sensors 208 is changing, such as over time or in comparison to previous values. For example, if variations within the in situ sensor data (or the relationship between the in situ sensor data and the information in the prior information map 258) are within a selected range or are less than a defined amount, or below a threshold value, then a new predictive model is not generated by the predictive model generator 210. As a result, the predictive map generator 212 does not generate a new predictive map 264, predictive control zone map 265, or both. However, if variations within the in situ sensor data are outside the selected range, are greater than the defined amount, or are above the threshold value, for example, then the predictive model generator 210 generates a new predictive model using all or a portion of the new in situ sensor data received, which the predictive map generator 212 uses to generate a new predictive map 264. In block 320, variations in the in situ sensor data, such as a magnitude of a quantity, by which the data exceed the selected range, or a magnitude of variation of the relationship between the in situ sensor data and the information in the prior information map 258, can be used as a trigger, to cause the generation of a new predictive model and predictive map. Keeping with the examples described above, the limit, range, and set quantity can be set to default values; adjusted by an operator or user interaction through a user interface; adjusted by an automatic system; or adjusted in other ways.

[0088] Other learning trigger criteria can also be used. For example, if the predictive model generator 210 switches to a different prior information map (different from the originally selected prior information map 258), then switching to the different prior information map may trigger relearning by the predictive model generator 210 , the predictive map generator 212 , the control zone generator 213 , the control system 214 , or other items. In another example, the transition of the agricultural harvester 100 to a different topography or to a different control zone can also be used as a learning trigger criterion.

[0089] In some cases, the operator 260 may also edit the predictive map 264 or the predictive control zone map 265, or both. Edits may change a value in the predictive map 264, change a size, shape, position, or existence of a control zone in the predictive control zone map 265, or both. Block 321 shows that edited information can be used as a learning trigger criterion.

[0090] In some cases, the operator 260 may also observe that automatic control of a controllable subsystem is not what the operator desires. In such cases, the operator 260 may provide a manual adjustment to the controllable subsystem, reflecting that the operator 260 desires the controllable subsystem to operate in a manner other than that being commanded by the control system 214. Thus, manually changing a regulation by operator 260 may cause one or more of the predictive model generators 210 to relearn a model, the predictive map generator 212 generates the map 264, the control zone generator 213 generates one or more control zones on the zone map of predictive control 265, and the control system 214 relearns a control algorithm or performs machine learning on one or more of the controller components 232 to 246 in the control system 214 based on tuning by the operator 260, as shown in block 322. Block 324 represents the use of other triggered learning criteria.

[0091] In other examples, relearning may be performed periodically or intermittently based on, for example, a selected time interval, such as a discrete time interval or a variable time interval, as indicated by block 326.

[0092] If relearning is triggered, whether based on learning trigger criteria or based on the passage of a time interval, as indicated by block 326, then one or more of the predictive model generator 210, the map generator Predictive system 212, control zone generator 213, and control system 214 perform machine learning to generate a new predictive model, a new predictive map, a new control zone, and a new control algorithm, respectively, with based on the learning trigger criterion. The new predictive model, the new predictive map, and the new control algorithm are generated using any additional data that has been collected since the last learning operation was performed. Relearning is indicated by block 328.

[0093] If the harvest operation has been completed, the operation moves from block 312 to block 330, where one or more of the predictive map 264, predictive control zone map 265, and predictive model generated by the predictive model generator 210 are stored. The predictive map 264, predictive control zone map 265, and predictive model may be stored locally in database 202 or sent to a remote system using communication system 206 for later use.

[0094] It will be noted that, some examples given here describe the predictive model generator 210 and the predictive map generator 212 receiving a map of prior information in generating a predictive model and a functional predictive map, respectively. In other examples, the predictive model generator 210 and the predictive map generator 212 may receive other types of maps, including predictive maps, such as a functional predictive map generated during the harvesting operation.

[0095] Figure 4 is a block diagram of a portion of the agricultural harvester 100 shown in Figure 1. In particular, Figure 4 shows, among other components, examples of the predictive model generator 210 and the predictive map generator 212 in more detail. Figure 4 also illustrates the flow of information between the various components shown. The predictive model generator 210 receives a terrain aspect map 332 as a preview map. The terrain aspect map may include any appropriate terrain information, such as soil profile roughness, soil type (e.g., pavement, gravel, black soil, clay, sand, tillage, waterway, etc.), height of the soil, which is referred to the geographic location. The predictive model generator 210 also receives a geographic location 334, or an indication of a geographic location, from the geographic position sensor 204. In situ sensors 208 illustratively include the vehicle speed sensor, a vehicle direction sensor , a vehicle motion sensor 336, such as a vertical displacement sensor and/or IMU, a mass sensor, and/or a mass distribution sensor, as well as a processing system 338. When used here, a sensor in situ is any sensor positioned on the agricultural machine, on an implement towed by it, or on a seat on the agricultural machine. Processing system 338 processes sensor data 340 generated from in situ sensors 208, such as on-board vehicle motion sensor 336, to generate processed data, some examples of which are described below. These in situ sensors 208, or combinations thereof, provide sensor data 340 that are indicative of a dynamic response of the agricultural machine to the surface over which they travel. For example, if the agricultural machine encounters uneven ground and undergoes a vertical movement, such as a jump, the vertical displacement is sensed by a vertical displacement sensor. Similarly, if the terrain causes the towed implement to generate thrust or drag, an IMU on the implement or towing machine will provide a signal indicative of the thrust/drag.

[0096] In some examples, the vehicle motion sensor 336 may be a multi-axis inertial measurement unit (IMU), which provides an indication of acceleration and/or displacement in at least two orthogonal axes. However, vehicle motion sensor 336 may also include a vertical displacement sensor.

[0097] The present discussion continues with respect to an example in which the onboard sensor 336 is a multi-axis IMU. It will be recognized that this is only an example, and the sensors mentioned above are also contemplated here. As shown in Figure 4, the example predictive model generator 210 includes one or more of a vehicle terrain aspect-response model generator 342, seat terrain aspect-response model generator 344, and a response-to-terrain aspect model generator 346. In other examples, the predictive model generator 210 may include additional, fewer, or different components than those shown in the example of FIG. 4. Accordingly, in some examples , the predictive model generator 210 may also include other items 348, which may include other types of predictive model generators to generate other types of models.

[0098] The model generator 342 identifies a relationship between the measured vehicle dynamic response (e.g., the vehicle's vertical displacement or acceleration, pitch and/or roll, etc.) to the terrain at a geographic location of the feature map 332 At the same location in the field where the vehicle dynamic response was detected. Based on this relationship established by the model generator 342, the model generator 342 generates a predictive response model. The predictive response model is used by the vehicle response map generator 352 to predict the vehicle dynamic response at different locations in the field based on the georeferenced terrain aspect value(s), contained (s) on terrain aspect map 332 at the same locations in the field.

[0099] The model generator 344 identifies a relationship between operator seat response at a geographic location corresponding to the terrain aspects of the terrain aspect map 332 at the same geographic location where the dynamic seat response was detected. Again, the terrain aspect value is the georeferenced value contained in the terrain aspect map 332. The model generator 344 then generates a predictive seat response model that is used by the seat response map generator 354 to predict the seating response at a field location based on the terrain aspect value for that field location.

[00100] The model generator 346 identifies a relationship between the implement dynamic response at a particular location in the field and the terrain aspect map 332 at that same location. The model generator 346 generates a predictive implement response model, which is used by the implement response map generator 356 to predict the implement response at a particular location in the field based on the value(s) of appearance of land at that location in the field.

[00101] In light of the above, the predictive model generator 210 is operable to produce a plurality of predictive dynamic response models, such as one or more of the predictive dynamic response models, generated by the model generators 342, 344 and 346. In another example, two or more of the predictive response models described above can be combined into a single predictive response model, which predicts two or more of the vehicle dynamic response, seat response, and implement dynamic response based on the values of terrain appearance at different locations in the field. Any such models, or combinations thereof, are collectively represented by response model 350 in Figure 4.

[00102] The predictive response model 350 is provided for the predictive map generator 212. In the example of Figure 4, the predictive map generator 212 includes a vehicle response map generator 352, a seat response map generator 354, and an implement response map generator 356. In other examples, the predictive map generator 212 may include additional, fewer, or different map generators. Thus, in some examples, the predictive map generator 212 may include other items 358, which may include other types of the map generator to generate response maps for other types of features. The vehicle response map generator 352 receives the predictive response model 350, which predicts the vehicle dynamic response based on a terrain aspect value together with the terrain aspect map 332, and generates a predictive map, which predicts vehicle dynamic response at different locations in the field.

[00103] The seat response map generator 354 generates a predictive seat response map, which predicts seat response at different locations in the field based on terrain aspect values at those locations in the field, and the predictive response model 350 The implement response map generator 356 illustratively generates a predictive implement response map, which predicts implement responses at different locations in the field based on terrain aspect values at those locations in the field and the predictive response model 350.

[00104] The predictive map generator 212 provides one or more 360 predictive maps, which are predictive of one or more of the vehicle dynamic response, seat response, and implement response. Each of the 360 predictive maps predicts the respective response characteristic at different locations in a field. Each of the generated 360 predictive maps may be provided to the control zone generator 213, the control system 214, or both. The control zone generator 213 generates control zones and incorporates those control zones into the functional predictive map, i.e., the predictive map 360, to produce the predictive control zone map 265. One, or both, of the predictive map 264 and the predictive control zone map 265 may be provided to the control system 214, which generates control signals for controlling one or more of the controllable subsystems 216 based on the predictive map 264, predictive control zone map 265, or both.

[00105] One of the main components of the response of a mechanical system, such as an agricultural combine, to a mechanical input, such as driving over a speed bump, is the mass of the mechanical system. In many agricultural operations, mass and/or mass distribution can change significantly over the course of the agricultural operation. For example, as the combine harvests a crop, the mass of the harvested crop inside the combine increases the total mass of the combine and affects the dynamic response of the combine. Furthermore, if the harvester is full and unloads its material, the changed mass will generate a significant difference in the machine's dynamics. For example, a final turn performed before the combine discharges its material (i.e., full) will have a different dynamic response after the combine discharges its material (i.e., empty). Conversely, as a sprayer sprays its liquid over a field, the mass of the sprayer will decrease, which also affects the dynamic response of the system. At least some embodiments described here take into account this change in mass and/or mass distribution with respect to the agricultural machine and/or implement when the agricultural machine performs its function. Mass change and/or mass distribution of agricultural machinery can be approached in several ways. In one way, if the mass of the machine deviates from an initial mass of the machine by a set limit, a criterion shot such as that described in Figure 3B can be generated. In another example, the model itself may receive mass and/or mass distribution information, such that the mass and/or mass distribution is provided as an input, among several other inputs, to the generator(s). ) model.

[00106] Terrain aspects may change depending on the type of terrain and the event or condition affecting the terrain. For example, a gravel road will be more affected by heavy rain than a paved road. Additionally, asphalt can be affected by freeze/thaw cycles or can show ripples under high temperatures. Over the course of a winter, rougher areas of a stay or surface can become worse due to the effects of snow clearing. Additionally, in a field at harvest time, a number of trucks or machines passing over the surface can affect the surface.

[00107] Figure 5 is a flowchart of a method for generating and using a confidence metric with respect to a predictive dynamic response model for an agricultural machine. Method 400 begins at block 402, where an initial terrain aspect map is generated. This can be done in any appropriate way. In one example, the map may simply be a terrain map or topographic map of the area. In another example, the prior information map may be generated from a collection of in situ information from sensors or from a historical response from several displacements over the area. Once the map is generated, control passes to block 404 where an initial confidence value is set. This can be a confidence value for the entire map, it can be a confidence value for positions within the map, or a combination thereof. In one example, the confidence metric is simply a value ranging between 0 and 1.0, which is initially set to 1. However, any appropriate initial confidence metric can be adjusted. The important feature is that when creating the map, confidence in the newly created map is very high.

[00108] In block 406, it is determined whether any events that may reduce trust have occurred since the last time the trust level was used. Such events include, without limitation, the passage of time 408. For example, for a surface such as a gravel road, the passage of time, such as a year, can have a significant impact on the quality of the surface. Another event that can affect confidence is the number of times the surface has been covered. This is illustrated in Figure 5 as passes 410. These passes can be counted by the agricultural machine itself and reported to a centralized tracking facility or simply stored in the memory of the agricultural machine. Additionally, passes from other machines, such as agricultural machines, or road transport machines, such as semi-tractor trailers can be counted and reported to the centralized installation. In this way, surface usage (e.g., field, drag, or highway) can be weighted against surface type to determine confidence metric degradation. Another event that can affect the confidence metric is weather 412. For example, periods of rain can significantly affect a field. Thus, in block 406, method 400 identifies weather events that have occurred since the last use of the confidence metric in the geographic location of the agricultural machine. If significant weather events occurred, the confidence metric will be reduced. Next, in block 414, method 400 determines the degree of degradation of the trust metric based on one or more of the events listed above. This computation can be performed by a controller or processor of the agricultural device. Additionally, or alternatively, this computation could be performed by a remote device and communicated to the agricultural machine. At the completion of block 414, the trust degrades metric is generated or otherwise obtained.

[00109] In block 416, the trust metric degrades is compared to a threshold to determine whether the trust metric degrades is below a threshold. This limit may be a pre-defined limit set by the agricultural machine manufacturer, a user-selectable limit, or any other appropriate limit. If the metric is below the threshold, then control passes to block 418, where the predictive map can be re-generated or the model relearned. Additionally, or alternatively, the confidence degrade metric can be used with an appropriate setting for one or more control outputs. For example, the adjusted control output may slow down the agricultural machine when the confidence metric is below the threshold. Additionally, a second lower limit could be used, in which method 400 would simply stop the agricultural machine. Returning to block 416, if the confidence metric degrades is not below the threshold, control passes to block 422, where the predictive dynamic response map is used normally, without any confidence-based adjustments to the control(s). output(s).

[00110] It can thus be seen that the present system takes a map of prior information, which maps a feature, such as a terrain aspect value or information from a previous operation pass to different locations. The present system also uses one or more in situ sensors that sense in situ sensor data that is indicative of a characteristic, such as a vehicle dynamic response, and generates a model that models a relationship between the sensored characteristic using the in situ sensor, or a related feature, and the feature mapped in the prior information map. Thus, the present system generates a functional predictive map using a model, in situ data, and a prior information map and can configure the generated functional predictive map for consumption by a control system, for presentation to a local or remote operator. or another user, or both. For example, the control system may use the map to control one or more systems of a combine harvester.

[00111] The present discussion mentioned processors and servers. In some examples, the processors and servers include computer processors with associated memory and timing circuits, not separately shown. Processors and servers are functional parts of the systems or devices to which the processors and servers belong and by which they are activated and facilitate the functionality of other components or items in those systems.

[00112] Also, a number of user interface views have been discussed. Displays can take a wide variety of different forms and can have a wide variety of different user-actuable operator interface mechanisms arranged within them. For example, user-actuable operator interface mechanisms may include text boxes, check boxes, icons, connections, drop-down menus, search boxes, etc. User-actuable operator interface mechanisms can also be actuated in a wide variety of different ways. For example, user-actuable operator interface mechanisms may be actuated using operator interface mechanisms, such as a point-and-click device such as a rolling ball or mouse, hardware keys, switches, a control lever, control or keyboard, thumb switches or thumb pad, etc., a virtual keyboard or other virtual actuators. In addition, when the screens on which the user-actuable operator interface mechanisms are displayed is a touch screen, the user-actuable operator interface mechanisms may be actuated using touch gestures. Also, user-actuable operator interface mechanisms can be actuated using voice commands using speech recognition functionality. Speech recognition can be implemented using a voice detection device, such as a microphone, and software, which functions to recognize the detected voice and execute commands based on the received voice.

[00113] A number of databases were also discussed. It will also be noted that they can each be broken down into multiple databases. In some examples, all may be local to the systems that access them, all may be remote from a system that uses the databases, or one or more databases may be local while others are remote. All of these configurations are covered here.

[00114] Also, the figures show a number of blocks with functionality assigned to each block. It will be noted that fewer blocks can be used to illustrate that the functionality assigned to multiple different blocks is performed by fewer components. Also, more blocks can be used, illustrating that functionality can be distributed among more components. In different examples, some functionality may be added, and some may be removed.

[00115] It will be noted that the above discussion described a variety of different systems, components, logic, and interactions. It will be recognized that any or all of such systems, components, logic, and interactions may be implemented by hardware items, such as processors, memory, or other processing components, some of which are described below, that perform the functions associated with those systems, components, logic, or interactions. Furthermore, any or all of the systems, components, logic and interactions may be implemented by software that is loaded into memory and is subsequently executed by a processor or server or other computing component, 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 frameworks, which can be used to implement any or all of the systems, components, logic and interactions described above. Other structures can also be used.

[00116] Figure 6 is a block diagram of agricultural combine 600, which may be similar to the agricultural combine 100 shown in Figure 2. Agricultural combine 600 communicates with elements in a remote server architecture 500. In some examples, the remote server architecture 500 provides computing, software, data access, and storage services, which do not require the end user's knowledge of the physical location or configuration of the system providing the services. In various examples, remote servers may provide services over a wide area network, such as the Internet, using appropriate protocols. For example, remote servers can deliver applications over a wide area network and can be accessible through a Web browser or any other computing component. Software or components shown in figure 2 as well as data associated with them can be stored on servers in a remote location. The computing resources in a remote server environment may be consolidated into a local remote data center, or the computing resources may be dispersed to a plurality of remote data centers. Remote server infrastructures can provide services across shared data centers, even if the services appear as a single access point to the user. Thus, the components and functions described here can be provided from a remote server at a remote location using a remote server architecture. Alternatively, the components and functions may be provided from a server, or the components and functions may be installed on client devices directly, or in other ways.

[00117] In the example shown in figure 6, some items are similar to those shown in figure 2 and those items are similarly enumerated. 6 specifically shows that the predictive model generator 210 or predictive map generator 212, or both, may be positioned on a local server 502 that is remote to the agricultural combine 600. Therefore, in the example shown in Figure 6, the combine agricultural 600 accesses the systems through the remote server location 502.

[00118] Figure 6 also represents another example of a remote server architecture. Figure 6 shows that some elements of Figure 2 can be arranged at a remote server location 502, while others can be positioned anywhere. By way of example, database 202 may be arranged in a location separate from site 502 and accessed via the remote server at site 502. Regardless of where the elements are positioned, the elements may be accessed directly by the agricultural combine 600 through of a network, such as a wide area network or a local area network; elements can be hosted on a remote site by a service; or the elements may be provided as a service or accessed by a connection service, which resides in a remote location. Also, data can be stored in any location, and the stored data can be accessed by, or transmitted to, operators, users, or systems. For example, physical carriers can be used instead of, or in addition to, electromagnetic wave carriers. In some examples, where wireless telecommunications service coverage is poor or non-existent, another machine, such as a fuel truck or other mobile machine or vehicle, may have an automatic, semi-automatic, or manual information collection system. As the combine harvester 600 approaches the machine containing the information collection system, such as a fuel truck before fueling, the information collection system collects information from the combine harvester 600 using any type of wireless connection for that purpose. . The collected information may then be transmitted to another network when the machine containing the received information arrives at a location in which wireless telecommunications service coverage or other wireless coverage is available. For example, a fuel truck may enter an area having wireless communications coverage when moving to a location to fuel other machines or when at a primary fuel storage location. All of these architectures are covered here. Furthermore, information may be stored in the agricultural combine 600 until the agricultural combine 600 enters an area having wireless communication coverage. The agricultural harvester 600 itself can send information to another network.

[00119] It will also be noted that the elements of figure 2, or portions thereof, can be arranged in a wide variety of different devices. One or more of those devices may include an on-board computer, an electronic control unit, a display unit, a server, a desktop computer, a portable computer, a tablet computer, or other mobile device, such as a pocket computer, a cell phone, a smart phone, a multimedia player, a personal digital assistant, etc.

[00120] In some examples, the remote server architecture 500 may include cybersecurity measures. Without limitation, these measures may include encrypting data on storage devices, encrypting data sent between network nodes, authenticating people or processes accessing data, as well as using hardeners for recording metadata, data, data transfers. data, data accesses, and data transformations. In some examples, reinforcements may be distributed and immutable (e.g., implemented as blockchains).

[00121] Figure 7 is a simplified block diagram of an illustrative example of a portable or mobile computing device, which can be used as a user or client portable device 16, wherein the present system (or parts thereof ) can be implemented. For example, a mobile device may be implemented in the operator compartment of the agricultural combine 100 for use in generating, processing, or displaying the maps discussed above. Figures 8 and 9 are examples of portable or mobile devices.

[00122] Figure 7 provides a general block diagram of the components of the client device 16 that can run some components shown in Figure 2, which interact with them, or both. In device 16, a communication connection 13 is provided, which allows the portable device to communicate with other computing devices and, in some examples, provides a channel for receiving information automatically, such as by scanning. Examples of communications connection 13 include enabling communication through one or more communication protocols, such as wireless services used to provide cellular access to a network, as well as protocols that provide local wireless connections to networks.

[00123] In other examples, applications may be received on a removable Secure Digital (SD) card, which is connected to an interface 15. The interface 15 and communication connections 13 communicate with a processor 17 (which may also incorporate the processors or servers of the other figures) along a bus 19, which is also connected to memory 21 and input/output (I/O) components 23, as well as clock 25 and location system 27.

[00124] I/O components 23, in one example, are provided to facilitate input and output operations. I/O components 23 for various examples of device 16 may include input components such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation, and output components, such as a display device, a speaker, and/or a printer port. Other I/O components 23 may also be used.

[00125] Clock 25 illustratively comprises a real-time clock component, which provides the time and date. Illustratively, it may also provide timing functions for processor 17.

[00126] Location system 27 illustratively includes a component that provides a current geographic location of device 16. This may include, for example, a global positioning system (GPS) receiver, a LORAN system, a passive recognition system, a cellular triangulation system, or other positioning system. The location system 27 may also include, for example, mapping software or navigation software that generates desired maps, desired navigation routes, and other geographic functions.

[00127] Memory 21 stores the operating system 29, network settings 31, applications 33, application configuration settings 35, database 37, communication controllers 39, and communication configuration settings 41. Memory 21 may include all types of tangible, volatile and non-volatile, computer-readable memory 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 in accordance with the instructions. The processor 17 can be activated by other components to also facilitate its functionality.

[00128] Figure 8 shows an example, in which the device 16 is a tablet computer 600. In Figure 8, the computer 600 is shown with the user interface display screen 602. The screen 602 may be a touch screen touch or a pen-enabled interface, which receives input from a pen or needle. The tablet computer 600 can also use a virtual on-screen keyboard. Of course, computer 601 could also be affixed to a keyboard or other user input device via an appropriate affixing mechanism, such as a wireless connection or USB port, for example. Computer 601 illustratively may also receive voice input.

[00129] Figure 9 is similar to Figure 8, except that the device is a smart phone 71. The smart phone 71 has a touch-sensitive display 73 that displays icons or tiles or other user input mechanisms 75. The mechanisms 75 can be used by a user to run applications, make calls, perform data transfer operations, etc. In general, the smart phone 71 is built on a mobile operating system and offers more advanced computing power and connectivity than a regular phone.

[00130] Note that other shapes of the devices are possible.

[00131] Figure 10 is an example of a computing environment, in which the elements of Figure 2 can be implemented. Referring to Figure 10, an exemplary system for implementing some embodiments includes a computing device in the form of a computer 810 programmed to operate as discussed above. Computer components 810 may include, but are not limited to, a processing unit 820 (which may comprise the processors or servers of the preceding figures), a system memory 830, and a system bus 821 that couples various system components. including system memory to processing unit 820. System bus 821 can be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The memory and programs described with respect to Figure 2 can be implemented in corresponding portions of Figure 10.

[00132] Computer 810 typically includes a variety of computer-readable media. The computer-readable media may be any available media that can be accessed by the computer 810 and includes both volatile and non-volatile media, removable media and non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media is different from, and does not include, a modulated data signal or carrier wave. Computer-readable media includes hardware storage media including removable and non-removable media, both volatile and non-volatile, implemented in any method or technology for storing information, such as computer-readable instructions, data structures, modules of program or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile discs (DVD) or other optical disc storage, magnetic cassettes, magnetic tape , storage on magnetic disk or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer810. The media may incorporate computer-readable instructions, data structures, program modules or other data in a transport mechanism and include any means of providing information. The term “modulated data signal” means a signal that has one or more of its characteristics adjusted or altered in such a way as to encode information in the signal.

[00133] System memory 830 includes computer storage media in the form of volatile and/or non-volatile memory, or both, such as read-only memory (ROM) 831 and random access memory (RAM) 832. A system Basic input/output module 833 (BIOS), containing the basic routines that help transfer information between elements within computer 810, such as during startup, is typically stored in ROM 831. RAM 832 typically contains data or memory modules. program or both, which are immediately accessible to, and/or currently being operated by, processing unit 820. By way of example, and not limitation, Figure 18 illustrates operating system 834, application programs 835, other modules program data 836, and program data 837.

[00134] Computer 810 may also include other removable/non-removable, volatile/non-volatile computer storage media. By way of example only, Figure 18 illustrates a hard disk drive 841 that reads or writes to non-volatile, non-removable magnetic media, an optical disk drive 855, and the non-volatile optical disk 856. The hard disk drive 841 is typically connected to the system bus 821 through a non-removable memory interface, such as interface 840, and the optical disk drive 855 is typically connected to the system bus 821 through a removable memory interface, such as interface 850 .

[00135] Alternatively or in addition, the functionality described here may be performed, at least in part, by one or more logical hardware components. For example, and without limitation, illustrative types of hardware logic components that may be used include programmable logic gate networks (FPGAs), application-specific integrated circuits (e.g., ASICs), application-specific integrated circuits (e.g., ASSPs ), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[00136] The controllers and their associated computer storage means discussed above and illustrated in Figure 18, provide storage of computer readable instructions, data structures, program modules and other data for the computer 810. In Figure 18, for For example, hard disk drive 841 is illustrated as storing operating system 844, application programs 845, other program modules 846, and program data 847. Note that these components may be either the same as, or different from, operating system 834, application programs 835, other program modules 836, and program data 837.

[00137] A user can feed commands and information to computer 810 through input devices, such as a keyboard 862, a microphone 863, and a pointing device 861, such as a mouse, rolling ball or touch panel. Other input devices (not shown) may include a control stick, game panels, satellite dish, scanner, or the like. These and other input devices are often connected to the processing unit 820 through a user input interface 860 that is coupled to the system bus, but may be connected through other interface and bus structures. A visual display 891 or other type of display device is also connected to system bus 821 through an interface, such as a video interface 890. In addition to the monitor, computers may also include other peripheral output devices, such as such as speakers 897 and printer 896, which can be connected via a peripheral output interface 895.

[00138] Computer 810 is operated in a networked environment using logical connections (such as a controller area network, – CAN, local area network, – LAN, or WAN wide area network) to one or more computers remote computers, such as a remote computer 880.

[00139] When used in a LAN-connected environment, the computer 810 is connected to the LAN 871 through a network, interface, or adapter 870. When used in a WAN-networked environment, the computer 810 typically includes a Modem 872 or other means of establishing communications over the WAN 873, such as the Internet. In a networked environment, program modules can be stored on a remote memory storage device. 18 illustrates, for example, that remote application programs 885 may reside on remote computer 880.

[00140] It should also be noted that the different examples described here 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 covered here.

[00141] Example 1 is an agricultural work machine, comprising: a communication system that receives a map of prior information that includes values of a terrain aspect characteristic corresponding to different geographic locations; a geographic position sensor that detects a geographic location of the agricultural work machine; an in situ sensor that detects a value of a dynamic response characteristic of the agricultural work machine corresponding to the geographic location; a predictive model generator that generates a predictive model that models a relationship between the terrain aspect feature and the dynamic response feature based on the value of the terrain aspect feature on the prior information map at the geographic location and a value of the feature dynamic response sensed by the sensor in situ at the geographic location; and a predictive map generator that generates a functional predictive dynamic response map, which maps predictive values of the dynamic response characteristic to the different geographic locations, based on the terrain aspect characteristic values in the prior information map and based on the predictive model.

[00142] Example 2 is the agricultural work machine according to any or all of the previous examples, wherein the predictive map generator configures the functional predictive dynamic response map for consumption by a control system that generates control signals for controlling a controllable subsystem in agricultural working machine based on functional predictive dynamic response map.

[00143] Example 3 is the agricultural work machine according to any or all of the preceding examples, wherein the controllable subsystem is selected from the group consisting of: a vehicle propulsion subsystem, an active suspension system, and an active seating subsystem.

[00144] Example 4 is the agricultural work machine according to any or all of the preceding examples, wherein the agricultural work machine has a mass characteristic that changes as the agricultural work machine operates, and the agricultural work machine The agricultural machine further comprises a mass-related sensor that detects a mass-related value related to at least one of a mass of the agricultural work machine and a mass of an implement towed by the agricultural work machine, and wherein the predictive map generator is further configured to generate the functional predictive map based, in part, on the mass-related value.

[00145] Example 5 is the agricultural work machine according to any or all of the previous examples, wherein the mass-related sensor is a sensor selected from the group consisting of: a load cell; and a camera arranged to provide an image of a quantity of material housed within at least one of the agricultural work machine and an implement towed by the agricultural work machine to provide an indication of the mass of the at least one agricultural work machine and implement that changes during the operation of the agricultural work machine.

[00146] Example 6 is the agricultural work machine according to any or all of the previous examples, wherein the mass sensor comprises logic configured to compute mass based on operation of the agricultural work machine.

[00147] Example 7 is the agricultural work machine according to any or all of the previous examples, in which the logic computes mass based on operating time.

[00148] Example 8 is the agricultural work machine according to any or all of the previous examples, in which the logic computes mass based on distance traveled.

[00149] Example 9 is the agricultural work machine according to any or all of the preceding examples, wherein the mass-related sensor is selected from the group consisting of: a plurality of load cells arranged to provide a mass-related indication to mass distribution, and a plurality of cameras arranged to provide images of a quantity of material housed within at least one of the agricultural work machine and an implement towed by the agricultural work machine that changes during operation of the agricultural work machine , the images being indicative of the mass distribution of the material.

[00150] Example 10 is the agricultural work machine according to any or all of the previous examples, wherein the prior information map comprises a terrain map that maps terrain at different geographic locations, and wherein the model generator predictive model is configured to identify a relationship between the terrain and the dynamic response characteristic sensed at the geographic location and the terrain aspect value, on the terrain aspect map, at the geographic location, the predictive model being configured to receive a geographic location as a model input and generate the dynamic response characteristic as an output of the predictive model generator based on the identified relationship.

[00151] Example 11 is the agricultural work machine according to any or all of the preceding examples, wherein the predictive dynamic response characteristic is selected from the group consisting of: a predictive vehicle dynamic response characteristic, a implement dynamic response feature, and a seat dynamic response feature.

[00152] Example 12 is the agricultural work machine according to any or all of the previous examples, wherein the in situ sensor is selected from the group consisting of: a motion sensor, a vertical displacement sensor, and a inertial measurement unit (IMU).

[00153] Example 13 is a method for generating a computer-implemented functional predictive dynamic response map, comprising receiving a map of prior information, on an agricultural work machine, which indicates values of a terrain aspect characteristic corresponding to different geographic locations; detect a geographical location of the agricultural work machine; detect, with an in situ sensor, a value of a dynamic response of the agricultural machine corresponding to the geographic location; generate a predictive model that models a relationship between the terrain aspect characteristic and the dynamic response; and controlling a predictive map generator to generate the functional predictive dynamic response map, which maps dynamic response predictive values to the different locations based on the terrain aspect values in the prior information map and the predictive model.

[00154] Example 14 is the computer-implemented method in accordance with any or all of the preceding examples, and further comprising configuring the functional predictive dynamic response map for a control system that generates control signals for controlling a controllable subsystem in agricultural working machine based on functional predictive dynamic response map.

[00155] Example 15 is the computer-implemented method in accordance with any or all of the preceding examples, wherein the controllable subsystem is selected from the group consisting of: a vehicle propulsion subsystem of an active suspension system, and an active seating subsystem.

[00156] Example 16 is the computer-implemented method according to any or all of the previous examples, wherein the prior information map includes ground surface roughness.

[00157] Example 17 is the computer-implemented method in accordance with any or all of the previous examples, wherein the prior information map includes The road feature.

[00158] Example 18 is a method for operating an agricultural work machine. The method includes obtaining a terrain aspect map having a confidence level, determining whether one or more events have occurred that degrade the confidence level, calculating a degraded confidence level based on the one or more events, comparing the confidence level trust level degraded to a threshold, and selectively perform an action based on comparing the trust level degraded to the threshold.

[00159] Example 19 is the method according to any or all of the previous examples, wherein selectively performing an action includes an action selected from the group consisting of: triggering model relearning if the confidence level is below the threshold , adjust a control output for a controllable subsystem of the agricultural machine, and proceed with an unadjusted control output for a controllable subsystem.

[00160] Example 20 is the method according to any or all of the previous examples, wherein the one or more events include an event selected from the group consisting of: passage of time, a number of passes of the agricultural machine over a given geographic location, and a climatic event.

[00161] Although the subject matter has been described in language specific to structural aspects or methodological acts, it should be understood that the subject matter defined in the attached claims is not necessarily limited to the specific aspects or acts above. Rather, the specific aspects and acts described above are set out as exemplary forms of the claims.

Claims (15)

Agricultural work machine (100), characterized by the fact that it comprises:
a communication system (206) that receives a prior information map (258) that includes values of a terrain aspect characteristic corresponding to different geographic locations;
a geographic position sensor (204) that detects a geographic location of the agricultural work machine (100);
an in situ sensor (208) that detects a value of a dynamic response characteristic of the agricultural work machine (101) corresponding to the geographic location;
a predictive model generator (210) that generates a predictive model (350) that models a relationship between the terrain aspect characteristic and the dynamic response characteristic based on a value of the terrain aspect characteristic in the prior information map ( 258) at the geographic location and the value of the dynamic response characteristic sensed by the in situ sensor (208) at the geographic location; It is
a predictive map generator (212) that generates a functional predictive dynamic response map (264), which maps dynamic response characteristic predictive values to the different geographic locations, based on the terrain aspect characteristic values in the information map preview (258) and based on the predictive model (350). Agricultural work machine (100) according to claim 1, characterized by the fact that the predictive map generator (212) configures the functional predictive dynamic response map (264) for consumption by a control system that generates control signals. control for controlling a controllable subsystem (216) in the agricultural work machine (100) based on the functional predictive dynamic response map (264). Agricultural work machine (100) according to claim 2, characterized in that the controllable subsystem (216) is selected from the group consisting of: a vehicle propulsion subsystem (250), an active suspension system ( 253), and an active seat subsystem (254). Agricultural work machine (100) according to claim 1, characterized by the fact that the agricultural work machine (100) has a mass characteristic that changes as the agricultural work machine (100) operates, and the agricultural work machine (100) agricultural work (100) further comprises a mass-related sensor (303, 305) that detects a mass-related value related to at least one of a mass of the agricultural work machine (100) and a mass of an implement towed by the machine of agricultural work (100), and wherein the predictive map generator (212) is further configured to generate the functional predictive response map (264) based, in part, on the mass-related value. Agricultural work machine (100) according to claim 4, characterized by the fact that the mass-related sensor (303, 305) is a sensor selected from the group consisting of:
a load cell; It is
a camera arranged to provide an image of a quantity of material housed within at least one of the agricultural work machine (100) and an implement towed by the agricultural work machine (100) to provide an indication of the mass of the at least one agricultural work machine (100) agricultural work (100) and implement that changes during the operation of the agricultural work machine (100). Agricultural work machine (100) according to claim 4, characterized by the fact that the mass sensor comprises logic configured to compute mass based on operation of the agricultural work machine (100). Agricultural work machine according to claim 6, characterized by the fact that the logic computes mass based on operating time. Agricultural work machine according to claim 6, characterized by the fact that the logic computes mass based on the distance traveled. Agricultural work machine (100) according to claim 4, characterized in that the mass-related sensor (303, 305) is selected from the group consisting of: a plurality of load cells arranged to provide a related indication to mass distribution, and a plurality of cameras arranged to provide images of a quantity of material housed within at least one of the agricultural work machine (100) and an implement towed by the agricultural work machine (100) that changes during operation of the agricultural work machine (100), the images being indicative of the mass distribution of the material. Agricultural work machine (100) according to claim 1, characterized by the fact that the advance information map (258) comprises a terrain map that maps the terrain in different geographic locations, and wherein the predictive model generator ( 210) is configured to identify a relationship between terrain and the dynamic response characteristic based on the dynamic response characteristic sensed at the geographic location, the predictive model being configured to receive a geographic location as a model input and generate the response characteristic dynamics as an output of the predictive model generator (350) based on the identified relationship. Agricultural work machine (100) according to claim 10, characterized by the fact that the predictive dynamic response characteristic is selected from the group consisting of: a predictive vehicle dynamic response characteristic (352), a response characteristic implement dynamics (356), and a seat dynamic response characteristic (354). Agricultural work machine according to claim 1, characterized by the fact that the in situ sensor (222) is selected from the group consisting of a motion sensor (306), a vertical displacement sensor (301), and a inertial measurement unit (IMU). Method (400) for operating an agricultural work machine (100), characterized by the fact that the method comprises:
obtaining (402) a terrain aspect map having a confidence level (404);
determining (406) whether one or more events have occurred that degrade the confidence of the confidence level;
calculating (414) a degraded confidence level based on the one or more events;
compare (416) the degraded confidence level to a threshold; It is
selectively perform (420, 422) an action based on comparing the degraded confidence level to the threshold. Method according to claim 13, characterized by the fact that selectively performing (420, 422) an action includes an action selected from the group consisting of: triggering model relearning (418) if the confidence level is below the threshold , adjust a control output (420) for a controllable subsystem (216) of the agricultural machine (100) and proceed with an unadjusted control output (422) for a controllable subsystem (216). Method according to claim 13, characterized in that the one or more events include an event selected from the group consisting of: passage of time (408), a number of passes (410) of the agricultural machine (100) over a given geographic location, and a climatic event (412).

Images