Vehicle automation systems using reusable mission elements

Abstract

An automated machine management and motion control system is provided. The system utilizes reusable digital assets to efficiently create mission plans with predictable commands. The reusable digital assets are generated so that they can be applied to multiple machines, locations, implements, and operations. Machine, implement, or location-specific configurations can be utilized in conjunction with the reusable digital assets to generate mission planning commands.

Description

[Technical Field]

[0001] The present invention generally relates to the activity of automated vehicles and machines. [Background technology]

[0002] Autonomous machines exist in off-highway and other off-road vehicle sectors (such as agriculture, turf, construction, and mining) where a single machine performs a task autonomously or semi-autonomously with human supervision. In some cases, multiple autonomous machines work on a single mission, but are constrained to work within a designated area to prevent direct interaction (interference) with other machines in the mission.

[0003] Machine automation systems (e.g., vehicle automation systems) use on-board operating systems to operate and control machines (e.g., vehicles). The systems may also include on-board sensors to identify potential obstacles and provide feedback for the operation and operation of the machine.

[0004] Machine automation has been adapted to work on a field or specific work site. The field or work site includes pre-planned lines for traversing the field, including waypoints (reference points) and boundary markers. In some embodiments, the system has helped identify turning and headland movements to manage movement between work paths, such as parallel mowing lines. Machine automation is designed for a given project operation on a specified field. This project can be saved for future repetition of the same project operation on a specific field by the machine. Summary of the Invention [Problem to be solved by the invention]

[0005] Automation planning and operation does not cover off-site setup and transition requirements. For example, a human operator or transporter must transport the machine to the start of the field and then to another field. This limits the potential scope and benefits of automation for individual field operations.

[0006] In addition to the range limitations for individual fields, the repeatability of operations is limited when performing operations with the same machine in the same field again, for example, a program stored for a machine to mow a field may be executed each time the machine needs to mow the field. [Means for solving the problem]

[0007] The present disclosure provides an automated system for assigning and managing machine (e.g., vehicle) tasks (operations) through the generation of mission plans designed to improve efficiency and planning flexibility. The present disclosure provides a system for generating reusable digital assets that constitute subsections of an overall project that can be applied to other tasks (operations), fields, machines, and projects. Additionally, the present disclosure supports pre-task and post-task operations as well as transition operations that include a more robust range of automation elements and allow a project to expand to multiple independent fields. These additional non-task operations may be reusable digital assets that can be applied to multiple machines.

[0008] The present disclosure further provides a system for generating a mission plan for an extended, stable project from start to finish. The mission plan can be constructed using reusable digital assets. In some embodiments, the mission plan can integrate reusable digital assets that can cover unknown or flexible operations with additional tailored operational actions to create a mission plan tailored to the requirements of a specific machine, location, or operation.

[0009] The present disclosure provides the ability to increase the efficiency of creating mission plans that have the flexibility to perform modified operations. Mission plans become safer over time because integrated reusable digital assets have been performed in the past and are predictably applied to associated machines and projects. Machine profiles containing detailed machine information can increase predictability by supporting direct characteristic comparisons between machines that have worked with reusable digital assets in the past and machines that may utilize reusable digital assets in future projects.

[0010] Embodiments may provide a communication and control system for multiple work machines, including machines designed for agriculture, mining, construction, turf, logistics projects, etc. The machines may be mobile machines (e.g., off-highway or other off-road mobile machines) that may perform automated cooperative operations. The work machines are often vehicle-type machines that are capable of moving from one location to another in addition to performing work operations.

[0011] An embodiment may include a plurality of work machines, each of which may include a communication device configured to transmit work machine status information and receive a set of machine commands, and these updates and commands may be transmitted via available communications corresponding to available communication modules provided on the work machine.

[0012] The work machine may include a controller that controls the operation of the work machine. The controller may be a computerized system for directing and driving control actuators throughout the work machine. Additionally, the controller may collect real-time operational information by receiving feedback regarding operation via various operational sensors, such as on-board sensor systems, proximity sensors, positioning systems, workload sensors, and other sensor systems.

[0013] In some embodiments, the work machine may send status updates to and receive machine-specific commands from the remote system, which may process and send a mission plan, including the machine-specific commands, to the work machine.

[0014] In some embodiments, if the work machine is operated in a manner different from that programmed by the machine instruction set, the work machine's communication device may be configured to transmit an updated machine instruction set to the remote system over the cellular communication network. In some embodiments, if the work machine is operating in a manner different from that dictated by the mission plan, the remote system may monitor such changes in machine status information received over the cellular communication network. The remote system may modify the mission plan to recognize the operational changes.

[0015] In some embodiments, the updates may include reasons or instructions for modifications based on monitoring by sensors on the work machine. The remote system may evaluate the modifications to determine whether the changes are permanent or semi-permanent. In such embodiments, the remote system may incorporate the modifications into a reusable instruction set.

[0016] Some embodiments include a networked ecosystem including multiple implements with automation systems, such as machines designed for agricultural, construction, turf, and logistics projects. Embodiments of the networked ecosystem may also include a remote cloud management system and control system. The remote cloud management system may receive communications from the multiple implements and control systems. In some embodiments, the remote cloud management system may receive communications from other sources, such as a machine deployment system.

[0017] In some embodiments, the remote cloud management system includes storage for holding and managing activity directives, machine profile information, and mission planning rules and constraints. In some embodiments, the cloud management system includes collected data of selectable mission activities and interactions (actions) that may be applied as part of the mission planning directives when there is a work machine that needs to perform the activity. In some embodiments, the collected data may be stored in a database format.

[0018] In some embodiments, the storage may store reusable digital assets related to locations, movement options, field layouts, project constraints, and / or other information. The reusable digital assets may be compiled together or with other activity directives to create activity directives and mission plans.

[0019] In some embodiments, the cloud management system assists in the creation of a mission plan. The cloud management system may receive a mission plan request from the control system that configures a project for the mission plan to be accomplished. The control system may have a dedicated user interface. In some embodiments, a remote user interface accesses the control system via a wireless network connection, such as for cellular phone applications.

[0020] In some embodiments, configuring a project for mission planning may include identifying account information, project location or boundaries, available materials and machines, project goals, project constraints, and other information. In some embodiments, a control system may be utilized to define a mission plan using information from a cloud management system.

[0021] In some embodiments, the remote cloud management system may include an automated system that creates a mission plan based on machine profiles and mission activities, and the automated system may identify applicable reusable digital assets as a starting point for creating the mission plan.

[0022] Embodiments may include a learning system that uses the sensor system and defined operational protocols to determine applicable machine characteristics. The learning system may be used to generate reusable digital assets for machine learning. The system may further identify similar applicable characteristics for other machines by inferring the characteristics of the learning machine to identify additional applications of the reusable digital assets.

[0023] In some embodiments, the reusable digital asset may be a machine learning model. The machine learning model may be tailored to the specific conditions, implementation, or characteristics of a project, machine, or field. In some embodiments, the machine learning model may be used to manage a sensor system, including sensor settings, sensor data analysis, and other contextual information. [Brief explanation of the drawings]

[0024] Embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which: [Figure 1] FIG. 1 is a block diagram of a system according to one embodiment. [Figure 2] FIG. 1 illustrates a dynamic project map according to one embodiment. [Figure 3] 1 is a flowchart illustrating system operation for mission planning according to one embodiment. [Figure 4] 1 is a flowchart illustrating system operations for asset generation according to an embodiment of the system. DETAILED DESCRIPTION OF THE INVENTION

[0025] While the present invention can be embodied in many different embodiments, preferred embodiments of the present invention will be described in detail, with the understanding that the present disclosure should be considered as an exemplification of the principles of the invention and is not intended to limit the broad aspects of the invention to the illustrated embodiments. It will be understood that the present invention can be embodied in other specific embodiments without departing from its spirit or central characteristics. The present embodiments, therefore, are to be considered in all respects as illustrative and not restrictive, and the invention is not to be limited to the details set forth herein.

[0026] FIG. 1 illustrates an embodiment of a system that utilizes a cloud system 102 to manage work vehicles 126, 128. In this embodiment, the cloud system 102 includes a cloud management system 104, a mission planning system 106, machine information storage 108, and activity program storage 110. This embodiment illustrates activity program storage 110 including reusable asset storage 112 and operational asset storage 114. In some embodiments, the mission planning system 106 may include subsystems that manage the development of one or more components of a mission plan. For example, some embodiments may include a machine information analysis system, an activity program analysis system, a path planning system, or other system components.

[0027] In some embodiments, these system components may be separate components within cloud system 102 or may be one or more dedicated servers. In other embodiments, multiple system components may be integrated. In some embodiments, certain system components are maintained within mission planning system 106, while other system components are operatively connected to mission planning system 106 to provide services via wireless connections, wired network connections, or direct wired connections such as bus interfaces.

[0028] Machine information storage 108 and activity program storage 110 may be any type of electronic storage structure or memory device. Additionally, the machine profiles, data, reusable digital assets, available assets, and other information stored in machine information storage 108 and activity program storage 110 may be stored in the memory structures in various forms, such as databases, indexed file systems, or other formats. In some embodiments, the reusable digital assets and available assets may include specific scripts for integrating into a mission plan and instructing the machine control system on how to operate. In some embodiments, the reusable digital assets and / or available assets may include models generated by machine learning systems. Machine learning models may be configured for perception sensors, operational sensors, or maintenance system sensors to improve sensor functionality.

[0029] The mission planning system 106 can access or receive information from the machine information storage 108 and the activity program storage 110. In some embodiments, the mission planning system 106 can also send information to the machine information storage 108 or the activity program storage 110. For example, a finalized mission plan, or portions thereof, may be sent to the activity program storage for later evaluation or use.

[0030] In some embodiments, machine information storage 108 maintains machine profiles for multiple work machines. Each machine's machine profile may contain detailed identification information, operational information, and other machine-specific characteristics, acting as a configuration or information file. Identification information may include machine make and model data, serial number, owner or user information, and / or other identification information.

[0031] The operational information may include various machine operational information and capabilities, such as speed, torque, turning radius, dimensions, PTO drive speed, sensor array, automation kit, and control information. Additional information may include machine-specific tool operational information, such as tool load type, range of motion, lift load, reach, operating speed range, interaction limits, and other information. For machines that may use a variety of optional accessories, associated information corresponding to each optional accessory may also be stored. In some embodiments, the basic information for the machine may be stored along with information from each optional accessory to account for any changes in machine operational information resulting from connecting one accessory or another. In some embodiments, the optional accessories include adjustment information that may be used during analysis to update the machine's operational information based on the connected accessories.

[0032] Machine information storage 108 may also include information about the machine's operating history, information about known wear and tear on the machine or specific components, schedule information, or other information about the use and maintenance needs of a particular machine. Machine information may include additional information about the machine's current state, such as location, battery or fuel levels, currently installed accessories, and other status information. In some embodiments, types of information may be stored as separate records for independent access and analysis. Machine information may store telematic records and usage records that indicate past operation, usage data and history, and current status information.

[0033] Activity program storage 110 may contain a selection of activity scripts for various work machine operations in reusable asset storage 112 and operational asset storage 114. An activity script may contain program code for performing a specific activity by a machine. For example, an activity script may direct the initiation process for starting a certain class of machine using a particular automation kit or electronic control unit. Some activity scripts can run on multiple machines, while others are more specific. Some activity scripts are machine-specific.

[0034] As described further herein, the reusable asset storage 112 can store reusable digital assets, including scripts, available maps or routes, machine operation adjustments, implement control information, or other data or code that can be applied to the original machine or other machines. The reusable asset storage 112 can include additional definitions, parameters, and compliance information associated with each reusable digital asset to identify the asset and its applicability to future projects. For example, a reusable digital asset for a transition between two work areas can include an identifying title, such as "Transition from Field A to Field B," and associated data, such as the locations of Field A and Field B, route constraints (such as maximum route width, weight limits, speed limits, angle of travel, obstacles, etc.), and other features to ensure compatibility with the program.

[0035] In some embodiments, reusable digital assets may provide specific paths and behaviors that can only be changed by triggering rules, such as detecting obstacles or safety sensors. These reusable digital assets may be considered tangible assets. Tangible assets are configured features, such as boundaries, lines, curves, waypoints, prescription maps, tramways, and controlled traffic routes, that are included in the reusable digital asset. Other reusable digital assets may include soft assets that allow flexibility and adaptive behavior so that machines can adapt to their environment and tasks.

[0036] In some embodiments, a reusable digital asset may include machine learning models configured for one or more sensor systems for a machine. The system may include machine learning models for distinct location conditions and characteristics to tailor sensor operation for specific applications. For example, a machine learning system may develop perceptual sensor models trained for specific field conditions, such as a dry field with limited color, a warm field with abundant color, or a field with abundant color and a risk of mud. Each model may be designed to configure perceptual sensors and / or perceptual sensor analytics to more clearly identify obstacles, risks, boundaries, vegetation conditions, and other information from field conditions. As another example, a system may have a set of machine learning models for machine vibration sensors or sensor arrays tailored to specific work options and / or implements. In some embodiments, the machine learning models may be integrated with specific machine operating instructions to tailor responses to sensor information to specific conditions.

[0037] In most embodiments, a reusable digital asset integrates a combination of hard and soft asset features. For example, a reusable digital asset for a transition between two fields might provide start and end waypoints as hard assets and known path indicators as soft assets, allowing the machine to determine a path based on a combination of detected surroundings, surveyed boundaries, zones, lines, and points, combined with customized rules to fit a given operation. In such embodiments, the machine can monitor obstacles, other machines, and other information to manage movement and collision avoidance on the fly.

[0038] In some embodiments, reusable digital assets can be configured for machines and separate accessory implements. Each machine and implement reusable digital asset can include detailed configuration information for that machine. For example, a machine asset can include configuration files for operating speed, PTO power, and other information. As another example, an implementation digital asset can include configuration files for power requirements for operations, speed ratios for task operations, setup dimensions (e.g., travel setup dimensions, operation dimensions), operation limits (e.g., directional requirements for side mowers, one-sided tillage, harvesting equipment, etc.), and additional sensor options.

[0039] In some embodiments, the mission planning system 106 operates on the same server or other structure as the machine information storage 108 and the activity program storage 110. Within the cloud structure 102, the mission planning system 106 may be connected to the machine information storage 108 or the activity program storage 110 via one or more communication systems, depending on the underlying server array structure. For example, the mission planning system 106 may be implemented on a first server using a processor and program memory connected via a wired bus. When evaluating machine information, the mission planning system 106 may use the first server communication card to connect to the machine information storage 108 to access the Internet or other network.

[0040] In some embodiments, processing operations may be shared among multiple processors or separate computers to speed evaluation through parallel processing operations. For example, when identifying applicable reusable assets, mission planning system 106 may perform parallel processing on assigned portions of reusable asset storage 112 to identify potential reusable digital assets related to machine characteristics. As another example, mission planning system 106 may assign separate computers to process two different project requests in parallel.

[0041] In this embodiment, the machine information storage 108 can receive data from the cloud management system 104 based on information from the machine data sources 120. An embodiment of the system may include any number of machine data sources 120. The machine data sources 120 may include external user interfaces, such as phones, computers, server systems, tablets, and other devices used by manufacturers, mechanics, machine users, aftermarket suppliers, and other information sources. Additionally, the machine information storage 108 may receive information directly from the implements 126, 128.

[0042] Activity program storage 110 may receive information from activity program source 122. In this embodiment, cloud management system 104 assists in distributing information to activity program storage 110. In some embodiments, the system may include activity program source 122. Activity program source 122 may be an external user interface, such as a phone, computer, server system, tablet, etc., utilized by any developer, programmer, manufacturer, user, aftermarket supplier, or other entity that may prepare and develop activity scripts for work machines. In some embodiments, machine data source 120 and activity program source 122 may be an operator of cloud management system 102.

[0043] In this embodiment, a single project request source 124 is identified. In other embodiments, the system may have multiple project request sources. The project request source 124 may be an external user interface, such as a phone, computer, server system, tablet, or other device used by any machine user or entity. In some embodiments, the project request source 124 may be an operator of the cloud infrastructure system 102. The cloud management system 104 may receive requests from the project request source 124 and direct the requests to the appropriate mission planning system 106.

[0044] In some embodiments, the mission planning system 106 or the cloud management system 104 can convert the project request into a standard format for the mission planning system 106 to parse and analyze. For example, the project request received from the project request source 124 may be a natural language request from a project manager, such as a request received in a voice format. The cloud management system 104 may convert the voice to text and identify the project definition. In some embodiments, the cloud management system 104 can convert only applicable keywords for the project.

[0045] The mission planning system 106 may analyze project requirements and evaluate project definitions and objectives to identify machine selection criteria (such as machine capabilities, machine locations, machine ownership restrictions, scheduling availability, etc.), other fleet conditions, project operating areas, project timelines and other constraints, project goals, and other project information.

[0046] In some embodiments, the project request may identify one or more machines to be utilized in the project. In such embodiments, the cloud management system 104 may send a query to the machine information storage 108 to obtain machine profile and status information for the specified machines. The cloud management system 104 may include the machine information in the project request sent to the mission planning system 106.

[0047] In other embodiments, the mission planning system 106 can access the machine information storage 108 to review machine profiles and identify machines that fit the project requirements. In some embodiments, the mission planning system 106 can send a query to the machine information storage 108 requesting machine profiles that meet the project requirements. For example, if the project requires machines around a specific area, the machine planning system 106 can send a query to the machine information storage 108 requesting all machines within a specific radius of the project area. In some embodiments, receiving a select group of multiple machine profiles can improve efficiency in the processing analysis to identify which machines are suitable for the project and can reduce processing requirements for other parallel processing requests without overburdening the processor of the machine information storage 108.

[0048] In some embodiments, the mission planning system 106 can receive machine criteria requirements, location information, and other information from the cloud management system 104's project requirements analysis. The mission planning system 106 can use the machine criteria requirements during the analysis of the machine profiles to identify suitable machines for the project. In some embodiments, the mission planning system 106 identifies suitable machines based in part on reusable digital assets associated with the location or other project characteristics. For example, if multiple options exist for the functionality and capabilities required to complete the project, the mission planning system 106 can determine which machines are compatible with the applicable reusable digital assets. In some embodiments, the mission planning system 106 can identify suitable machines based on condition-based machine learning models based on sensor availability and conditions available for a particular machine. For example, the mission planning system 106 can identify a machine with a sensor array and machine learning model designed for a staircase environment to enhance slope safety.

[0049] Mission planning system 106 may then select a reusable digital asset from reusable asset storage 112 that matches the selected machine and is appropriate for the location, operation, or other characteristics of the project. In some embodiments, mission planning system 106 may compile an applicable script from reusable asset storage 112 using the machine information variables and necessary transformations. For example, a reusable digital asset may have base (default) operational settings for machine A to achieve a set speed, and the default operational settings must be transformed for machine B to achieve the same set speed. These transformations may be incorporated into one or more configuration or information files used to compile the script for mission planning.

[0050] Further, mission planning system 106 may select additional operational assets from operational asset storage 114 to accomplish the mission plan. For example, if mission planning system 106 identifies reusable assets for travel between work sites and paths within the work site, but does not identify reusable assets for controlling implement operations, mission planning system 106 may identify and incorporate machine-specific scripts for the implement operations from operational asset storage 114.

[0051] In some embodiments, the machine learning models may be operational assets stored in operational asset storage 114. For example, a machine learning model for controlling operation under specific weather conditions may be a general operational modification rule. As another example, an operational asset may include machine learning models tuned for maintenance assessments via sensor activity during distinct operating conditions. These machine learning models may adapt on demand or based on additional feedback from the machine and the environment. For example, mission planning system 106 may include specific machine learning models based on machine profile information, such as historical information and usage information. The specific machine learning models may be tuned for available sensors, the type of machine, and the specific condition of the machine. For example, a specific sensor reading may indicate maintenance for a machine with a long operating time compared to a newer machine with fewer hours of use.

[0052] Once activity scripts from the reusable digital assets and operational assets have been selected and compiled by the mission planning system 106, the mission planning system 106 can create additional scripts necessary to accomplish the project and associate the various activity scripts required for each operation. If multiple machines are involved, the mission planning system 106 can create individual plans for each selected machine, which are compiled to form a complete mission plan for the project. The mission planning system 106 can then issue the mission plan to each work vehicle 126, 128. Communications of the mission plan can be sent to the communication modules and electronic control units of each work vehicle 126, 128 via one or more communication channels using the communication system network card.

[0053] Work implements 126, 128 may be any number of work implements. Furthermore, work implement 126 and work implement 128 may be the same type of machine. For example, work implements 126, 128 may both be tractors with mowers assigned to a common field and share responsibility for mowing the entire field. In other embodiments, work implement 126 may be a different type of machine than work implement 128. For example, work implement 126 may be a forklift designed to move loads at a job site, and work implement 128 may be a crane designed to lift certain loads at a job site to the upper floors of a building under construction.

[0054] FIG. 2 is a dynamic project map diagram illustrating mission planning options. The map shows an example of a multiple-field project layout, including preparation and completion options. The corresponding mission plan may utilize one or more reusable assets and operational commands to guide the implement through project tasks. Additionally, the corresponding mission plan may specify rules that can be initiated to guide the implement via optional commands configured on the operational or reusable assets.

[0055] The map includes a legend 202 that clearly indicates pre-planned, permanent, and dynamic routes. Mission planning similarly utilizes pre-planned and permanent routes as primary directives, although selectable rule directives allow for some variation in certain permanent and dynamic route options.

[0056] In this embodiment, the map includes a first field 204 and a second field 206. Each field 204, 206 has work assigned to it to complete the project and may be referred to as a work area. The map includes additional areas outside each field 204, 206, namely, a staging area 208, a product supply area (tender area) 210, and an implement shop area (storage area) 212. In this embodiment, the map includes two machines, shown as tractor 214 and tractor 216.

[0057] The map also includes various routes connecting these various areas. In this embodiment, the map includes an approach route 220 from the staging area 208 to the first field 204, which is divided into two work zones. From an approach point into the first field 204, the tractor 214 can select a first approach route 222 to a first work start point or a second approach route 224 to a second work start point. In this embodiment, the first work start point begins work on a first route 226 that covers a first section of the project in the first field 204. Similarly, work operations for a second section of the field 204 begin at a second start point and follow a second route 228. In this embodiment, each work route 226, 228 is illustrated as a parallel, serpentine pattern that bisects the field 204, rotating 180 degrees at each headland. In this embodiment, first working path 226 ends near the start point of second working path 228. Those skilled in the art will recognize that these paths may vary in flow and direction depending on field characteristics, boundaries, operations, and timing. Additionally, field 204 may not be divided in some situations, and may be managed with additional sections in other situations.

[0058] In the illustrated embodiment, first work path 226 terminates on a first exit path 230 that leads from field 204 back to staging area 208 as part of a pre-planned route. Additionally, second work path 228 may terminate at an entry point into field 204, with tractor 214 or tractor 216 leaving entry path 220 toward staging area 208. Alternatively, one of tractors 214 or 216 may travel along first transition path 232 to second field 206 for further work. This disclosure describes tractor 216 traveling along this option.

[0059] Upon entering the second field 206, the tractor 216 may follow a third entry path 234 to a third starting point. In this example, the second field 206 includes a single third work path 236 that follows a pattern of concentric circles that become smaller toward the center of the field. The pre-planned third work path 236 terminates at the work center and continues along a third exit path 238 to the entrance of the field 206. The tractor 216 may follow a semi-permanent return path 244 to the staging area 208.

[0060] In the illustrated embodiment, a dynamic, rules-based path for the field 206 is also illustrated to assist in refueling operations during startup. Refueling operations may include refueling, recharging, replenishing applied products (e.g., seeds, fertilizer, water, pesticides, herbicides, other treatments, etc.), or other refueling options. As an example, in this embodiment, when the tractor 216 reaches a minimum fertilizer threshold, the tractor's electronic control unit pauses its current work operation, exits the field 206 following the dynamic, rules-based path 240, and travels along a resupply path 242 to the product resupply area 210. At the resupply area 210, the tractor 216 receives additional fertilizer to complete the project. Upon receiving the additional fertilizer, the tractor 216 returns along the resupply path 242 and the dynamic, rules-based path 240, and re-enters the field 206 along the third work path 236 where operation was stopped, resuming operation.

[0061] Additionally, this embodiment includes a shop route 246 from staging area 208 to implement shop area 212 and a return shop route 248 from implement shop area 212 back to staging area 208. 212 is illustrated with multiple implement areas where tractors 214 or 216 can pick up or drop off implements for a project. Additionally, this implement storage shop area 212 may be a location where tractors 214 or 216 are maintained or may be stored between projects. In embodiments where tractors 214 and 216 are stored in implement storage shop area 212, shop routes 246 and 248 may be part of a project's mission plan to guide tractors 214 and 216 to staging area 208.

[0062] These paths, along with configured locations, can be incorporated into reusable digital assets to configure mission paths. For example, a setup reusable asset may include instructions to drive path 246 to an implement storage area, install the implement, and return to a staging area via path 248. The reusable asset may be required to include multiple control and motion instructions to guide tractor 214 through a multi-step process. Additionally, the reusable asset may include placeholders that must be filled in with information specific to tractor 214 from a configuration file. For example, machine information for tractor 214 may include a configuration file with speed control definitions, turning definitions, gear control definitions, and additional control scripts or definitions that can be utilized by the reusable asset to implement the reusable asset on tractor 214. Similarly, a separate configuration file for tractor 216 can support the use of the same reusable asset even though the tractor's 216 behavior differs from that of tractor 214. Furthermore, the mission planning system uses the same reusable asset with pre-configured modifications to direct tractors 214 and 216 to different execution locations.

[0063] The additional reusable asset may provide instructions for the approach path 220 to move along the first approach path 222 or the second approach path 224 to the operation start point. Similarly, the mission plan may include rules for identifying and selecting additional operations that may be built on the reusable assets. For example, if the mission plan incorporates a first exit path 230, the reusable asset may include a movement command for the first exit path 230 with a trigger-based rule for determining whether to return to the staging area 208 or transition to the second field 206 via the transition path 232. In some embodiments, the trigger may be based on communication with other tractors to determine whether the other tractor has progressed into the second field 206. In other embodiments, the mission plan may pre-select the tractor to proceed to the second field 206. The mission plan may pre-select an option to use the same reusable asset for the first exit path 230 to reach the transition path 232.

[0064] In addition to the possible paths and combinations of reusable digital assets, additional reusable assets may include terrain adjustments, condition adjustments, and other controls and adjustments. For example, the system may include a reusable digital asset for slope adjustment to control driving on slopes in combination with PTO power adjustments and correlate driving speed and angle. Additionally, the adjustments may include adjusting deck height or angle for specific conditions or terrain. In some embodiments, reusable digital assets may be implemented by correction rules triggered by communications, mission planning commands, or sensor readings. For example, if a sensor indicates that the tractor 214 is on a slope above a threshold, the tractor 214 may initiate a slope correction provided by the reusable digital asset.

[0065] 3 is a flowchart for developing a mission plan using reusable digital assets. In box 302, the system receives a project request including project parameters. In some embodiments, the mission planning system may receive the request directly. In other embodiments, the project request may go through other systems before reaching the mission planning system, such as a project management system or a cloud management system. The project request may be initiated by a project manager, a field or equipment owner, an authorized user, or others. In some embodiments, the project request may be initiated through a computer system, which may have a calendared set of projects or an automated system for identifying when to execute a particular project.

[0066] In box 304, the project request is analyzed by the system to identify project characteristics and required actions. This analysis may occur within the mission planning system or in a separate system that prepares the mission plan. The analysis may involve categorizing the request into information categories applicable to the mission planning process. For example, a request to mow a field for hay may be broken down into an identification of the field, the identified tractor and implement, whether it requires mustering, and other information. This information may be further broken down based on information already known in the system related to information from the project request. For example, the system may include a machine profile corresponding to the identified tractor and field details (e.g., entry location, physical boundaries, terrain, dimensions, etc.) corresponding to the identified field.

[0067] In addition to the work specified in the project request, the required actions may include obtaining the appropriate implements, moving them to a destination location, loading them with fuel or product, or other ancillary actions necessary to prepare the project. Additionally, the system may identify project steps or needs that can be assisted by a human. For example, a machine may be transported from a long distance in a truck or other delivery vehicle. As another example, a machine may require maintenance before it can operate.

[0068] In box 306, the system identifies existing reusable digital assets that fit the project's characteristics and operations and satisfy the project's parameters. In this step, the system can identify related reusable digital assets based on one or more applicable characteristics. The system can identify through one or more parallel perspectives corresponding to the types of potential relationships tracked in the reusable digital asset identification information. For example, the system can include one or more index files that associate each reusable asset with associated location, machine, and operational information. Some embodiments of the system can include more or less distinctions for indexing reusable assets. In some embodiments, the index system can be bypassed for a full database search. In other embodiments, reusable assets can be indexed based on all provided characteristics.

[0069] For example, the system may begin by identifying reusable assets for the location. The system may identify reusable assets including identifying characteristics related to the project's fields, such as field location, longitude and latitude, corresponding field size and constraints, suitable topography, and / or other characteristics. In some embodiments, the system may select reusable assets based on season, weather, or other information indicative of current field conditions. For example, the system may identify a machine learning model for a sensor system to improve functional operation of a sloping wet or dry field. The machine learning model may be trained for different conditions and control sensor settings, such as light settings for a perception camera, evaluation protocols, such as threshold settings for analyzing sensor array feedback, and response operations tailored to field conditions.

[0070] As another example, the system may identify reusable digital assets for the identified machine and compatible machines, which may include identifying reusable digital assets for the specific machine, other machines having the same make and model, and / or machines having compatible driving and operating characteristics.

[0071] As a further example, the system may identify reusable digital assets available for compatible operations. For example, the system may identify reusable assets for compatible driving speeds, PTO rates, transition patterns, deck heights, and / or other operational characteristics.

[0072] As one skilled in the art will appreciate, the ability to identify compatible reusable assets depends on the available details for a project and the identifying characteristics associated with the reusable digital asset file. Furthermore, the system may process all identification options to identify a suitable selection of options for further consideration and potential implementation. For example, the system may identify all options from location-based identification, machine-based identification, and operation-based identification to form a global subset of options from the reusable asset database. The system may then identify or prioritize reusable digital assets from the global subset of options that are common to all three categories. In some embodiments, a set of secondary options may be identified that do not satisfy all three categories but are not incompatible with any of the categories. This may occur if the reusable digital asset does not contain matching specific identifying information. For example, if the reusable digital asset does not include location-specific identifying information related to the size of the field as an identifying characteristic, the reusable digital asset may satisfy the machine and operation requirements, but the process may not be able to confirm whether the field information is compatible. In such cases, if a reusable digital asset becomes the preferred option, the system may perform a secondary review, which checks the configuration and script files to determine if the field size is scalable and applicable to the project.

[0073] In box 308, the mission planning system selects specific reusable digital assets that cover (are responsible for) the operation of the project without violating the constraints of the project. In some embodiments, the mission planning system selects reusable digital assets from the specific reusable digital assets based on an analysis to determine which is best suited for the project. The best suited may be selected based on project compatibility, the scope of the project covered using the reusable digital assets, application reliability, and / or other information.

[0074] Project compatibility may be based on one or more of identity or similarity with the project's machines, implements, operating locations, and other project characteristics. For example, reusable digital assets for the same project field and machine type and implements with similar operations have high project compatibility. Alternatively, reusable digital assets for selected fields among compatible fields and similar machines with matching operations may have low project compatibility because the system requires estimation to cover the entire project field.

[0075] The amount of project coverage that a single reusable digital asset can have may influence the selection. For example, a reusable digital asset that only covers driving commands and requires other assets to include driving, route layout, and other information will have a narrower project coverage than a reusable digital asset that includes route information, including field navigation and corresponding actions. The mission planning system may be configured to prioritize more complete reusable digital assets, if applicable.

[0076] In addition to considering project compatibility and coverage, the mission planning system may determine a confidence level with which a reusable digital asset can be used in a project. This confidence level may increase in importance depending on the number of changes and modifications required to apply the reusable digital asset to the project's mission plan. For example, reusable digital assets for related tasks using the same machine in the same field may have a high likelihood level of compatibility. In contrast, a reusable digital asset for a different task using a different machine in a similarly sized field may have a lower confidence level, even if transformations to certain characteristics make the reusable digital asset compatible.

[0077] Those skilled in the art will recognize that some or all of these considerations may overlap. They are included to illustrate perspectives regarding the consideration of relevant factors that influence optimal selections for a project. In some embodiments, an asset storage system may include multiple executable reusable digital assets that lead to a successful project mission plan. For example, if the reusable digital asset storage includes an operational reusable digital asset that performs tasks as a machine enters a field, traverses the field, and exits to a storage location, and a series of reusable digital assets, each covering a portion of the process, selecting a single combined asset or a series of individual assets may equally lead to a successful project mission plan.

[0078] In some embodiments, the selection analysis may evaluate one or more factors to determine a compatibility score for the project. The compatibility score may be utilized to select reusable digital assets in the project mission plan. For example, the mission planning system may provide scores for (1) machine similarity, (2) project location similarity, (3) operation similarity, (4) project coverage, and (5) similarity of other characteristics relevant to the evaluation. These scores may be combined into a compatibility score for the reusable digital asset. In some embodiments, the mission planning system may assign scores to multiple reusable digital assets in a particular selection of projects to identify a set of reusable digital assets that can be combined to cover a broader scope of the project mission plan.

[0079] In box 310, the mission planning system determines missing project control steps that are not covered by the selected reusable digital assets. The mission planning system may identify project characteristics or required actions and operations that are not covered by the reusable digital asset or set of reusable digital assets selected for the project. This identification may be performed by analyzing and comparing the required actions and operations identified from the start to the end of the project with the coverage provided by the reusable digital assets. For example, the mission planning system may analyze the required actions and operations using the reusable digital assets for the project. During the analysis, the mission planning system may determine that a set of transition actions from completing a task in the field to exiting the field is not provided. These transition actions may include a PTO disengagement action, a safety check action, an implement repositioning action, and / or a transmission power adjustment action to change from a work operation to a drive-only operation.

[0080] In box 312, the mission planning system selects a plurality of appropriate operational and activity assets to cover the mission project management steps. For example, the mission planning system may access or query activity program storage to select various activity and operational scripts. When moving a machine to a new location, the mission planning system may select operational assets to assist with travel control and create an appropriate path to a staging area for travel control. The operational assets or activity scripts may include travel safety settings for the machine and any implements, driving actions configured to set safe speeds and turns along the identified path, and staging commands to position the machine in place for the next step in the process, which may be reusable digital assets or scripts of additional operational assets.

[0081] In box 314, the mission planning system generates a project activity program for the machine using the selected reusable digital assets and operational assets. The project activity program directs the machine's operations for the project. During program generation, the instructions are sequenced and associated with an executable program. For example, the mission planning system can generate scripts that form the basis for the reusable digital assets and operational assets. In some embodiments, the scripts are compiled into a single mission script for the mission. In other embodiments, the mission planning system can further associate asset scripts with operational sequences through script invocation. Using invocation, a single script can be used multiple times throughout the mission. For example, a first script may provide an operational travel path for performing a task along a straight section, while a second script may provide a headland turn. The mission script alternately calls the first and second scripts to direct the machine to traverse a field.

[0082] In some embodiments, a script may include variables that must be provided for precise operational characteristics tailored to scripting a set of operational instructions. For example, a script may be designed for specified driving and operational speeds and associate operations with distances. For such scripts, machine operation instructions may be provided through input variables or subroutine calls within the script. In this example, the machine characteristics may include operational instructions to achieve a particular speed. At creation time, operational instructions for a specified driving speed may be provided by the machine characteristics. For example, a mission planning system may use a project machine configuration file to load multiple machine characteristic scripts into the correct section of the mission planning script.

[0083] In some embodiments, the mission planning system may generate tailored corrections to relate machine-specific commands to script specifications. For example, if the machine travel distance specified in the script for a run is longer than the project machine's operation commanded distance, the mission planning system may increase the machine speed to achieve the specified distance consistent with the script timing.

[0084] Similarly, a mission planning system may utilize configuration files to provide project location information, motion adjustments, etc. for a script. For example, a reusable digital asset may include a variable defining a distance to travel if providing a driving maneuver for linear path movement. In such a case, the same reusable digital asset may be applied to multiple linear path movements.

[0085] In some embodiments, one or more steps may be compiled into a single action sequence. As an example, the mission planning system may identify missing operations, identify operational assets, and create a mission plan from the operational assets and selected reusable digital assets in a generation phase. The mission planning system may begin the mission plan from a specified machine start point and select applicable assets from the start point through movement and task actions until the machine reaches a specified end point at the end of the project. For each required action, the mission planning system may determine whether the selected reusable digital assets cover the particular operation. If not, the mission planning system selects or creates an operational asset for that particular action. This may be repeated for each required action throughout the project. In this way, the mission planning system performs multiple steps to create a mission plan for each required action of the project.

[0086] In box 316, the mission planning system identifies operational rules for potentially applicable secondary protocols from the reusable digital assets and operational assets. In some embodiments, the operational rules may include one or more triggers that cause a machine to perform an action. In some embodiments, the triggered action is part of a project activity program for the primary operation. For example, a reusable digital asset may include an operational rule that is triggered by a position sensor and indicates a branch point in a path. As another example, the primary protocol may include an implement control trigger that changes navigation during an implement operation, such as wrapping or dropping a hay bale.

[0087] In this step, the mission planning system identifies operational rules for secondary protocols. These secondary operational rules relate to actions that modify primary operations from the project activity program. The modifications can be minor or significant, depending on the operational rule that triggers them. For example, an obstacle safety protocol may identify an obstacle and adjust or pause a path to avoid the obstacle based on an obstacle trigger. As another example, weather sensor readings may identify unsafe conditions, leading to an action-triggering rule that halts operations and potentially moves to an identified safe location.

[0088] The secondary protocols may include necessary operational considerations such as refueling, recharging, product replenishment, fleet assignment and communication, and other necessary or possible operational functions. Additionally, the secondary protocols may include safety triggers and rules to address safety concerns. For example, the system may include grade operation modification to prevent rollover, collapse, or damage to the machine or implement. Grade operation modification may be triggered by a grade sensor and the machine's travel direction, with rules being triggered when the grade exceeds a threshold for the current and expected travel direction.

[0089] In some embodiments, a series of secondary protocols may be included. For example, a grade sensor may be used to initiate an alternative action to adjust the driving and implement operation relative to the grade, such as increasing driving speed or reducing implement power to maintain the appropriate ratio for the implement application. This grade adjustment may be initiated when the grade sensor value reaches a first threshold. If the grade sensor value reaches a second threshold, the adjustment may be designed to safely change the route rather than adjust to continue operation properly.

[0090] The mission planning system may identify operational rules for secondary protocols by analyzing project parameters, operations, and characteristics, including the project's machines, locations, implements, selected reusable digital assets, and operational assets. In some embodiments, the selected reusable digital asset may identify potential secondary protocols along with indicators for the system to consider. The indicators may include features other than the reusable digital asset's operation. For example, if a reusable digital asset provides approach path operations to hard surfaces, the asset may indicate a secondary protocol required to prevent getting stuck on a wet or sloped path. The mission planning system may analyze location information to determine whether the approach options (approach paths) are likely to be hard or soft. If the path is likely to be soft or difficult to navigate, the mission planning system selects the secondary protocol to be available as needed.

[0091] In some embodiments, the mission planning may include machine learning models that configure the sensor array to monitor for specific conditions and initiate secondary protocols when the conditions are detected. The mission planning system may also incorporate machine learning models that respond to sensor behavior for detected conditions on all machines traveling to the same location.

[0092] In some embodiments, safety protocols may be associated with a machine, location, and / or operation and automatically included in the mission plan. In other embodiments, safety protocols may be selectively included based on an evaluation of known information about the machine, location, and operation. For example, the mission planning system may only include applicable grade adjustments if it has access to the location's terrain (i.e., can collect terrain information). As another example, the mission planning system may avoid incorporating safety protocols that are redundant with the machine's existing safety systems or that may interfere with safety systems within the machine. As another example, the mission planning system may identify operational models for sensor management and operational control adjusted to expected conditions based on external field condition information, such as recent weather conditions, seasonal information, or user or machine feedback information from the location. The operational models may be machine learning models trained based on past information corresponding to similar expected conditions. These operational models can adjust or modify one or more safety systems to improve safety for given conditions. Improvements and adjustments to the machine learning models may improve safety responses and reaction times based on adjusted sensor management and sensor evaluation.

[0093] The operational rules for the secondary protocols, in some embodiments, may be selected from known reusable digital assets. For example, the mission planning system may identify the secondary protocols and invoke reusable digital assets that correspond to those protocols. If reusable digital assets do not correspond to the secondary protocols, the mission planning system may determine the operations required for the secondary protocols and incorporate a set of reusable digital assets to implement the secondary protocols. In some embodiments, the mission planning system may need to incorporate operational assets and activities into the secondary protocols.

[0094] In some embodiments, the operational rules may include autonomous guidance that allows the machine to operate according to sensors and on-board configuration while maintaining a reusable plan. In such embodiments, the on-board configuration can control movement and adaptation to the environment without having to change the mission plan or secondary operations. The operational rules may also provide threshold flexibility for operation by the autonomous machine, redirecting to the mission plan only when the threshold is reached.

[0095] In box 318, the mission planning system creates a mission plan that includes a primary activity program and triggers (start requests) for secondary protocols. The mission planning system may include a script that instructs the machine to follow the primary activity program as a default while monitoring for possible triggers. The control script may be configured to pause the primary activity program if a trigger initiates a change in primary behavior. The control script may resume once the modification is complete. In some embodiments, the control script is configured to resume the primary program at the same point. In other embodiments, the control script may need to modify the execution of the primary script to accommodate the change.

[0096] The created mission plan may be stored in the system for later use or transmitted to the machine for application. The machine loading process depends on the machine's capabilities and the system. In some embodiments, the mission planning system may support wireless communication over a cellular or other wireless communication network if the machine includes a compatible network communication card and service. In some embodiments, the mission plan may be loaded into the machine using a physical connection, such as a portable memory drive or a wired connection to a computer or Internet interface. In some embodiments, indirect communication over a communication network may be utilized by implementing a combination of transmission techniques to load the mission plan. For example, a computer or mobile device near the machine may receive a mission plan packet over the Internet (via a wired or cellular connection), and then the mission plan may be transmitted over a local communication network, such as a WiFi network, a Bluetooth network, or other local network compatible with the machine's communication capabilities. As another example, one machine may receive mission plans from multiple machines over a communication network and then forward applicable mission plans to each of the additional machines over the local communication network.

[0097] FIG. 4 shows a flowchart for generating a reusable digital asset. This illustrates options for generating a reusable digital asset. Those skilled in the art will understand from this description alternative options for generating a reusable digital asset. For example, a reusable digital asset can be generated from a live recording of machine operations converted into instruction sets and parameters. In this embodiment, the reusable digital asset is generated afresh or created from a machine-provided project plan after implementation.

[0098] In box 402, the system receives a project plan including location parameters, travel parameters, and operational parameters. The project plan may provide overall operational guidance and operational parameters that are not converted into machine instructions for implementation. In some embodiments, the project plan may include a mission plan that includes operational guidance and operational parameters and is provided to one or more machines. In some embodiments, the system may be a cloud management system or mission planning system. In other embodiments, the asset review (analysis) system may be a standalone system within a cloud structure. The analysis system may be connected to or incorporated into activity program storage in some embodiments.

[0099] In some embodiments, the system may receive the project plan from the mission planning system as an edited mission plan and identify the operation guidance and operation parameters from the edited mission plan. In some embodiments, the system may receive the project plan at the same time that the corresponding mission plan is sent to the machine for execution.

[0100] In some embodiments, the system may receive a project plan from an operating machine, which may be sent to a cloud structure for storage as a repeatable plan for that machine, and simultaneously received for analysis by an analysis system.

[0101] In box 404, the system analyzes the project plan to identify subsections of the project plan to determine whether any operations or behaviors are repeatable. During this analysis step, the system is identifying portions of the project plan that may be repeatable not only within the complete project plan, but also for broader applications.

[0102] In this embodiment, the system may distinguish project plan features by location distinctions, operational changes, machine requirement changes, and other feature points. For example, the system may identify subsections based on identifiable location changes or movement shifts. This may reflect transitions between types of paths, such as transition paths to entry paths or work paths to entry paths. In this example, the system may identify subsections for each type of path.

[0103] In some embodiments, the system may identify behavioral changes to identify alternative rules or subsections. For example, the system may identify a subsection of a project plan that reflects a trigger action, such as a replenishment action. In this example, the replenishment subsection may reflect multiple routes for the replenishment action. At the same time, the route-based subsection may identify each route utilized during the replenishment process as a separate subsection.

[0104] Additionally, the system may identify project plan actions associated with selected sensor readings as part of independent subsections. For example, if a selection in the plan depends on a grade sensor reading, the system may identify it as a subsection.

[0105] In box 406, the system determines whether the requested parameters or characteristics are applicable to other machines. In this step, the system evaluates the operational parameters of the project plan to determine whether the other machines fit the project scope. The system may also determine whether the operational parameters can be transformed to make them compatible with the other machines. In some embodiments, the system compares the machine characteristics for which the project plan was designed with the characteristics of other machines to determine whether the characteristics are compatible.

[0106] In some embodiments, the system may identify project constraints or other requirements that may affect the scope of compatibility. For example, if a project plan identifies driving conditions (constraints) that dictate a maximum width along a route, the system determines whether such constraints are limited to the project machine or whether it is compatible with other machines. Similar considerations can be given to multiple characteristics, including speed, height, clearance, weight, and other potential constraints. In addition to driving considerations, the project plan may include functional requirements that constitute maximum and minimum capabilities for compatibility. For example, a hay-moving job may require a compatible machine to lift a certain weight.

[0107] If the system determines that the subsection is applicable to a compatible machine, the system determines applicability parameters in box 408 by analyzing any restrictions on the identified applicable subsections based on the required characteristics. In this step, the system identifies the machine or location applicability of the reusable digital asset by narrowing the compatibility possibilities to generate parameters. The system may evaluate machine constraints to determine machine identification parameters for the reusable digital asset. Similarly, the system may evaluate location or operation constraints to determine identification parameters related to locations or operations compatible with the reusable digital asset. In some embodiments, the determined parameters are part of the reusable digital asset's identification characteristics and are subsequently utilized by a mission planning system in identifying potential reusable digital assets for a project.

[0108] To determine applicability parameters, the system may analyze the project plan and identify or determine machine limitations from the project plan. These identified machine constraints may be inferred to identify constraints on one or more machine capabilities. For example, if the project plan identifies a path travel constraint indicating a maximum width between fences on the path, the system will require any compatible machine to meet the path width dimensional requirements. Similar considerations may be made for multiple characteristics, including speed, height, clearance, weight, and other potential constraints. In addition to travel considerations, the project plan may include functional requirements that may constitute maximum and minimum characteristics of applicable machines. For example, a reusable digital asset for identifying and moving hay may require a minimum lift load.

[0109] In some embodiments, the system may determine whether the operation of a selected subsection can be scaled up or down to allow additional machines to perform the selected section of the plan. For example, if a tractor and mower are designed with a specified power and ground speed to mow a field, the system may identify other machine and mower combinations that can mow the field with a lower power and ground speed. These attributes may be convertible to ensure compatibility with the overall project plan. If the attributes are convertible, the system may determine the associated parameters required by the machine for the identified parameters. For example, the identified parameters may include the ground speed and power ratio of the implement that must be achievable. Those skilled in the art will recognize that this relationship can be expressed in multiple ways, allowing for a variable, fixed, or other relationship between the parameters.

[0110] In some embodiments, the analysis may determine that certain machine limitations from the project plan are preferable for identification parameters associated with the reusable digital asset. For example, if the project plan specifies a minimum lift height for storage, reusable digital assets that store items in a similar structure may require the same minimum lifting capability.

[0111] In some embodiments, the identified parameters are variable and can be configured to work with the reusable digital asset through action calls and property constraints. For example, if the system identifies a compatible machine or location, the system may modify the project plan to generate a reusable digital asset for variable use based on the machine-specific information. This project plan modification may be performed using a mission plan modification script designed for the machine. In some embodiments, this information is built into the machine configuration file.

[0112] In some embodiments, the system evaluates the project plan to identify variable inputs that apply to other locations. For example, linear variations may allow distances to vary so that the same reusable digital asset can be applied to different travel paths. Those skilled in the art will recognize that for straight-line paths connected by corner turns, the variations may be straightforward, but for more complex paths, additional details may be required to be variable. Similar variability may apply to other location-based configurations and characteristics, such as speed, torque, vehicle height, and other characteristics.

[0113] In box 410, the system stores each reusable digital asset in activity program storage along with its application identifying characteristics. In this step, the reusable digital assets generated from the project plan and analysis are stored for future use. The reusable digital assets may be modified subsections of the project plan, incorporating variables that allow for applicability to other machines, locations, or operations. Additionally, the reusable digital assets are associated with identifying characteristics so that the mission planning system can efficiently evaluate each reusable digital asset's applicability to future projects.

[0114] The identifying characteristics may include a name or description of the asset, determined applicable parameters for the machine, location, and / or operation, and other information that may be utilized to identify the reusable digital asset. In some embodiments, the identifying characteristics are also incorporated into the storage index for efficient identification by a mission planning system.

[0115] In some embodiments, a stored reusable digital asset may include configuration file requirements that specify necessary information from a mission planning system about a machine or location to facilitate the use of the reusable digital asset. For example, if a reusable digital asset has a variable for a PTO rotation speed requirement for an implement in an operation script, the associated configuration file requirements will list PTO rotation speed as a data point required to utilize the reusable digital asset. The mission planning system may check these configuration file requirements to ensure that the appropriate information is available for the project before selecting a reusable digital asset for a project.

[0116] This embodiment illustrates additional optional actions to further generate reusable digital assets in boxes 412, 414, and 416. These further generation takes into account evaluation of actual actions to refine the reusable digital assets.

[0117] In box 412, the machine records the mission plan actions of executing the project plan and returns a project plan report. Those skilled in the art will recognize that these steps related to the project plan may occur at any point in the process, including before the project plan is received by the analysis system or concurrently with the analysis. Additionally, this recording and reporting step may be applied to the implementation of one or more generated reusable digital assets.

[0118] In this example, a project plan may be sent to a machine to execute the corresponding mission plan, and at the same time, sent to an analytics system to identify reusable assets. During execution, the machine records operational activity and sensor readings as it performs project operations. In addition to project plan operations, it may record operational changes, obstacle detection, and / or other unexpected information. Sensor feedback may be used to identify field conditions and operational responses. Multiple recordings over time may be used to correlate types of field conditions with operational responses through machine learning analysis or other evaluation.

[0119] In some embodiments, the entire record is returned as a project plan report. In other embodiments, the project plan report may be limited to information related to specific actions or sensor readings. For example, a record of actions taken may be sent, including transitioning from one path to another, turning a task behavior change on or off, performing a reconfiguration (raising or lowering a deck, raising a travel extension, etc.), or other actions. Additionally, if the sensor reading is unexpected, the machine may include snippets of the record surrounding the sensor reading in the report. Once the project plan report is generated or constructed by the machine, it is returned to the cloud management system.

[0120] In box 414, an analysis system for generating and managing reusable digital assets analyzes the project plan report to identify parameter limitations and applicable characteristics. In some embodiments, the analysis identifies actual feedback regarding one or more characteristics of the operation. For example, if a sensor indicates a physical barrier along an entry or transition path, the analysis system determines the space available for traveling along that path. From the travel space, the analysis system may determine limitations on machine and implement size. These may be compared to the parameters of the corresponding reusable digital asset to verify whether the parameters of the reusable digital asset are accurate.

[0121] In some embodiments, the project planning report may provide new information for evaluation. For example, the report may provide previously unknown, more detailed terrain information based on grade sensor readings. The terrain information may also improve the machine characteristics necessary or preferred to account for the terrain. For example, the system may identify weight distribution parameters to limit the likelihood of rollover or other damage.

[0122] In box 416, the system analyzes the project planning report to identify planned modifications or secondary protocols to the operating rules. The system may consider operational modifications that occurred during implementation, warning sensor readings, and / or other indicators that a modified or secondary protocol may be warranted.

[0123] As an example, terrain information may be utilized by the analysis system to further adjust operation to improve machine operation and coordination with the implement. In fertilizer application, this adjustment may improve consistent and even distribution of fertilizer across the field.

[0124] As another example, the report may identify modified behavior for the obstacle. Based on the analysis and / or other feedback, the system may determine that the obstacle is permanent and identify potential suitable modifications to account for the obstacle. For example, the system may construct an adjusted path for the reusable digital asset. Additionally, the system may adjust the reusable digital asset to modify implement deposition operations for herbicide spraying operations. In other embodiments, the system may insert specific triggers for known obstacles in specific locations to utilize secondary protocols for obstacle avoidance. Use of the trigger option may apply the reusable digital asset to other locations that do not contain such obstacles. In some embodiments, the obstacle may be flagged for further review by the system or an operator to confirm the nature of the obstacle as a permanent or temporary obstacle.

[0125] In some embodiments, analysis of the project planning report may indicate that a better operational plan is needed. This report and flagged new information may be provided to a mission planning system to generate an alternative plan for completing the project at that location. For example, if the project planning report indicates that the machine will be climbing or descending across stepped terrain, the analysis system may identify operational challenges and send a report requesting changes. Upon receiving the report, the mission planning system may recognize that the area is suitable for an alternate route that would benefit from the stepped terrain.

[0126] In addition to project planning reports, the system may periodically receive machine reports that share operational information and feedback related to the implementation application of the reusable digital asset. In some embodiments, the analysis system reviews the reports to determine whether the reusable digital asset can be modified or improved based on the feedback. Over time, the system may optimize the reusable digital asset as a whole. In some embodiments, the system may identify alternative optimizations for specific machine or location characteristics. In such embodiments, the identification data and configuration file structure may enable the reusable digital asset to be applicable to multiple optimizations depending on the anticipated implementation.

[0127] In some embodiments, reusable digital assets may be generated from human-operated machine actions. The human-operated machine actions may be recorded and sent to an analysis system to identify reusable assets. In some embodiments, an operator may indicate the start and end points of the reusable information. The analysis system may review and evaluate the report and determine that portions of the program can be converted into reusable digital assets.

[0128] In some embodiments, development of reusable digital assets may be generated based on a combination of rules applied to various applications. For example, an entry / exit rule may dictate that the entry / exit path must be within X feet of the field boundary. Refinement to the rule may require utilizing existing furrows or avoiding crop zones. In such embodiments, a modification rule may adjust the path to adapt the machine to the appropriate furrow path.

[0129] Additionally, fleet operations may require matching entry and exit directions to avoid congestion. Similarly, fleet operation rules may include triggers that allow information from one machine to trigger secondary protocols in another machine. For example, if a first machine identifies an obstacle and sends an obstacle notification to another machine, the second machine may adjust to a secondary path to avoid the obstacle. Furthermore, inter-fleet communication may be based on rules to coordinate path selection to avoid unnecessary interactions and ensure segmented working conditions are maintained. For example, entry path selection may be associated with a defined working path such that once a machine selects an entry path, other machines will not utilize that entry path or working path.

[0130] In some embodiments, machine learning may be implemented to evaluate and generate one or more aspects of reusable digital assets. For example, a machine learning system may be trained using existing project plans, machine characteristics, location information, operational reports, etc. Once trained, the machine learning system may identify reusable digital assets that are broadly applicable and likely to be successfully reused. Furthermore, the machine learning system may identify appropriate operational rules and triggers to improve the usability of the reusable digital assets. Similarly, machine learning may be implemented to create mission plans using reusable digital assets and operational assets.

[0131] In some embodiments, a machine learning system may be trained to control the sensor system to improve performance under specific conditions. Machine learning models may be created for the sensor system to improve environmental awareness for characteristic operating conditions, which may be related to weather conditions, field soil condition, color, season, topography, and other conditions. As an example, one machine learning model may be used when the implement is operating in a snowy field, and another machine learning model may be used when the implement is operating in a colorful spring field. The machine learning model may include lighting settings for sensor operation tailored to the situation and may evaluate imagery and other sensory feedback that takes into account the effects of snow and colorful vegetation.

[0132] In some embodiments, different machine learning models for sensor control and feedback evaluation may be used for different implement-implement combinations. For example, machine learning models may be utilized for real-time analysis of vibration sensor data for an implement, monitoring for abnormal vibrations that may indicate concern, error, impact, etc. The machine learning models may include operational responses based on characteristic abnormal vibrations, such as an emergency stop or pausing to reposition the implement. Different machine learning models may be used for characteristic vibration characteristics, abnormal reactions, and implements that receive appropriate responses. In some embodiments, the machine learning models may be further tailored to the specific task or operation being performed by the implement-implement combination. For example, an implement equipped with a posthole auger may be assigned a machine learning model appropriate for the particular posthole auger model and field soil characteristics.

[0133] Most of the devices described above are comprised of hardware and associated software. For example, a typical work machine includes one or more processors and software executable on those processors to perform the operations described above. The term software is used herein in its commonly understood sense to refer to programs or routines (e.g., subroutines, objects, plug-ins, etc.) and data available to a machine or processor. As is well known, computer programs generally consist of instructions stored on a machine-readable or computer-readable storage medium. Some embodiments of the present invention may include executable programs or instructions stored on a machine-readable or computer-readable storage medium, such as a digital memory. The term "computer" in the traditional sense is not intended to imply that a particular embodiment requires a "computer." For example, various processors, both embedded and not, may be used in devices such as the components described herein.

[0134] Memory for storing software is well known. In some embodiments, memory associated with a given processor may be stored on the same physical device as the processor ("on-board" memory), such as RAM or FLASH memory located within an integrated circuit microprocessor. In other examples, memory may include a separate device, such as an external disk drive, a storage array, or a portable flash key fob. In such cases, memory is "associated" with a digital processor when the two are operatively coupled or able to communicate with each other, such as by an I / O port or a network connection, so that the digital processor can read files stored on the memory. Associated memory may or may not be "read-only" by design (ROM) or permission settings. Other examples include, but are not limited to, WORM, EPROM, EEPROM, and FLASH. These technologies are often implemented in solid-state semiconductor devices. Other memory may consist of moving parts, such as a conventional rotating disk drive. All such memory is "machine-readable" or "computer-readable" and may be utilized to store executable instructions for performing the functions described herein.

[0135] By "software product" is intended a memory device on which a set of executable instructions are stored in machine-readable form, such that a suitable machine or processor having suitable access to the software product can execute the instructions to perform the process implemented by the instructions. Software products may also be used to distribute software. Any type of machine-readable memory can be used to create a software product, including but not limited to those described above. However, it is also known for software to be distributed by electronic transmission ("download"), in which case there is typically a software product associated with the sender, receiver, or both.

[0136] While the invention has been described above and is further claimed, it will be apparent that the same may be varied in numerous ways. Such variations are not to be regarded as departing from the spirit and scope of the invention, and all such modifications which would be obvious to those skilled in the art are intended to be included within the scope of the described apparatus.

Claims

1. a networked server system; A management system for automated work comprising: a work machine; The networked server system comprises: a server communications card configured to communicate over a communications network; a server memory including reusable digital asset storage; a server controller operatively connected to the server communication card and the server memory and configured to control a server memory drive and communications via the server communication card; The working machine is an application gateway having a first communication card configured to communicate with the server communication card over the communication network; a machine control unit including a machine processor and a machine memory for storing machine operation instructions; a machine actuator system including a machine control actuator; the server controller receives a project request via the server communication card and determines a project action by analyzing the project request; the server controller selecting, from the reusable digital asset storage, a reusable digital asset that meets the requirements of the project operation; a mission planning system of the networked server system that creates a mission plan for the work machine; The mission plan includes machine commands and additional operational commands from selected reusable digital assets.

2. The management system of claim 1 , wherein the additional operational instructions are selected from a second reusable digital asset in the reusable digital asset storage.

3. The management system according to claim 1 , wherein the mission plan includes operational rules for guiding the execution of the mission plan by the work machine.

4. The management system of claim 3 , wherein the operational rules are selected from other reusable digital assets in the reusable digital asset storage.

5. The management system of claim 1 , wherein the mission plan includes operational rules based on a start command for modifying execution of the mission plan by the work machine.

6. The management system according to claim 5 , wherein the operation rule based on the start command is selected from another reusable digital asset in the reusable digital asset storage.

7. the reusable digital assets from the reusable digital asset storage are generated based on an analysis of a project plan by an analysis system; The management system of claim 1 , wherein the analysis identifies subsections of the project plan that are reusable for other project activities.

8. The management system of claim 1 , wherein the reusable digital assets include machine learning models.

9. The management system of claim 8 , wherein the machine learning model is configured to be executed by the machine control unit to manage the sensor array system of the work machine.

10. the work machine has a sensor array system connected to the machine control unit; The management system of claim 1 , wherein the machine control unit manages the sensor array system by applying the machine commands based on the reusable digital assets.

11. the reusable digital asset includes the machine learning model that is incorporated into the mission plan; The management system of claim 9 , wherein the machine control unit executes the machine learning model to configure the sensor array system.

12. The management system of claim 10 , wherein the machine control unit analyzes sensor data from the sensor array system by executing the machine learning model.

13. A work machine for automated work, a network server having a server communication card and a server memory including reusable digital asset storage; and an application gateway including a first communication card configured to communicate over a communication network; a machine control unit including a machine processor and a machine memory for storing machine operation instructions; a machine actuator system including a machine control actuator; the application gateway receives a mission plan from the network server via the communication network, the mission plan being created by the network server for instructing the work machine to execute a project, the mission plan including machine instructions selected from reusable digital assets in the reusable digital asset storage of the network server; The machine control unit executes the machine commands from the mission plan, and the machine actuator system controls the machine in response to the machine commands.

14. The work machine of claim 13 further comprising a sensor array system connected to the machine control unit.

15. The work machine of claim 14 , wherein the reusable digital asset includes a machine learning model incorporated into the mission plan, and the machine control unit configures the sensor array system by executing the machine learning model.

16. The work machine of claim 15 , wherein the machine control unit analyzes sensor data from the sensor array system by executing the machine learning model.

Images