Abstract: An intelligent fill level system includes a material unloading container having an interior and a material entryway and a plurality of perception sensors mounted along a rim of the entryway, each sensor configured to generate perception data representative of a profile of unloaded material in at least a portion of the interior. A data processing unit, which may for example be onboard the material unloading container, determines one or more multidimensional profile characteristics, such as for example a fill level, of the unloaded material within the material unloading container at least via fusion of the perception data from the plurality of perception sensors, and a communications unit, which may also for example be onboard the container, transmits output signals representative of the determined one or more multidimensional profile characteristics to one or more remote data processing units associated with respective material loading work machines.

Abstract: A system and method of automated vehicle to sensor calibration includes, during operation of a work vehicle having sensors located thereon, each sensor having a stored location and/or orientation relative to the vehicle, automatically determining via first sensor inputs an orientation of the ground surface relative to vehicle orientation, and automatically mapping via second sensor inputs one or more persistent external references to a vehicle coordinate frame. At least upon determining that the ground surface orientation and the mapped persistent external references satisfy specified conditions, a vehicle to sensor calibration mode is automatically initiated, including receiving actual inputs from a first (e.g., uncalibrated) sensor, which may be one of the sensors having stored locations and/or orientations prior to calibration, and selectively adjusting parameters of the first sensor based at least in part on the mapped persistent external references with respect to the actual inputs from the first sensor.

Abstract: A computer-implemented system and method are provided for searchable integration of operating images and geospatial data, particularly for agricultural field operations or construction worksites in which visual images may be captured by work vehicles during their normal operation rather than requiring specific trips by employees or agronomists. Captured images are uploaded from sensors associated with a work vehicle traversing a work area, along with associated geospatial data, to a remote data storage device via a communications network. The uploaded images and geospatial data are selectively correlated with respect to a geospatial map. Responsive to user input corresponding to a selected one or more nodes in the geospatial map, at least one of the uploaded images are identified as corresponding to the selected one or more nodes. A display is generated representing the identified at least one of the uploaded images on a display unit associated with the received user input.

Abstract: An agricultural applicator, that applies material to an agricultural field, includes an on-board, real-time image sensor that senses targets for the material to be applied. A controller controls applicators, such as nozzles or other applicators, to apply the material to the sensed targets.

Abstract: An autonomous off-road vehicle, upon encountering an obstruction while navigating a route, can apply a first machine-learned model to identify the obstruction. In the event that the first machine-learned model cannot identify the obstruction, the autonomous off-road vehicle can apply a second machine-learned model configured to determine whether or not the obstruction can be ignored, for instance based on dimensions of the obstruction. If the obstruction can be ignored, the autonomous off-road vehicle can continue navigating the route. If the obstruction cannot be ignored, the autonomous off-road vehicle can modify the route, can stop, can flag the obstruction to a remote human operator, can modify an interface of a human operator to display a notification or a video feed from the vehicle, and the like.

Abstract: A system and method are provided for distributed perception sensing via an object detection station arranged such that an associated one or more object detection sensors have respective fields of perception including at least a portion of a virtually defined perimeter extending at least partially about a working area. The object detection station detects a motion incident corresponding to a violation of the virtually defined perimeter, wherein a detected source of the motion incident is classified with respect to one or more defined source types, and one or more signals at least corresponding to the motion incident are wirelessly communicated to one or more working machines operating within the working area. At least one of the working machines may then be selectively transitioned from a normal operating mode to a hierarchical intervention mode with respect to the detected source and/or a relative position thereof within the working area.

Abstract: An autonomous off-road vehicle, upon encountering an obstruction while navigating a route, can apply a first machine-learned model to identify the obstruction. In the event that the first machine-learned model cannot identify the obstruction, the autonomous off-road vehicle can apply a second machine-learned model configured to determine whether or not the obstruction can be ignored, for instance based on dimensions of the obstruction. If the obstruction can be ignored, the autonomous off-road vehicle can continue navigating the route. If the obstruction cannot be ignored, the autonomous off-road vehicle can modify the route, can stop, can flag the obstruction to a remote human operator, can modify an interface of a human operator to display a notification or a video feed from the vehicle, and the like.

Abstract: An agricultural applicator, that applies material to an agricultural field, includes an on-board, real-time image sensor that senses targets for the material to be applied. A controller controls applicators, such as nozzles or other applicators, to apply the material to the sensed targets.

Abstract: Systems and methods enabling network-based work machine software optimization may be carried-out by a server end in communication with a plurality of work machines over a network. In embodiments, the method includes: (i) storing a software solution database containing a plurality of software solutions corresponding to different work machine task profiles; (ii) receiving, at the server end, a software solution request containing task-specific data from a first work machine in the plurality of work machines; and (iii) searching the software solution database for an optimal-fit software solution corresponding to the task-specific data. If locating an optimal-fit software solution, the server end (iv) avails the first work machine of the optimal-fit software solution via the network. If not locating an optimal-fit software solution within the software solution database, the server end (v) transmits a corresponding message over the network and to the first work machine.

Abstract: An agricultural applicator, that applies material to an agricultural field, includes an on-board, real-time image sensor that senses targets for the material to be applied.

Abstract: An agricultural applicator, that applies material to an agricultural field, includes an on-board, real-time image sensor that senses targets for the material to be applied.

Abstract: An autonomous off-road vehicle, upon encountering an obstruction while navigating a route, can apply a first machine-learned model to identify the obstruction. In the event that the first machine-learned model cannot identify the obstruction, the autonomous off-road vehicle can apply a second machine-learned model configured to determine whether or not the obstruction can be ignored, for instance based on dimensions of the obstruction. If the obstruction can be ignored, the autonomous off-road vehicle can continue navigating the route. If the obstruction cannot be ignored, the autonomous off-road vehicle can modify the route, can stop, can flag the obstruction to a remote human operator, can modify an interface of a human operator to display a notification or a video feed from the vehicle, and the like.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for efficient material application. An example landscape treatment apparatus includes a main carrier tank to store a solvent, a concentrate tank to store a solute, and a first mix tank to receive the solvent and the solute as a first mixture. The example apparatus further includes a second mix tank to receive the solvent and the solute as a second mixture, where the first mix tank is to receive the solvent and the solute in alternation with the second mix tank receiving the solvent and the solute. The example apparatus also includes a boom to apply the first mixture and the second mixture to a landscape via a plurality of nozzles, where the boom is to apply the first mixture and the second mixture in alternation.

Abstract: Methods and apparatus to track a blade are disclosed. A disclosed example apparatus includes a blade that is pivotable, first and second optical targets operatively coupled to the blade, and a first camera for collecting first imaging data of the first optical target within a first field of view. The example apparatus also includes a second camera for collecting second imaging data of the second optical target within a second field of view. The example apparatus also includes a selector to select at least one of the first or second imaging data, and a processor to determine an orientation of the blade based on the selected imaging data.

Abstract: Systems and methods enabling network-based work machine software optimization may be carried-out by a server end in communication with a plurality of work machines over a network. In embodiments, the method includes: (i) storing a software solution database containing a plurality of software solutions corresponding to different work machine task profiles; (ii) receiving, at the server end, a software solution request containing task-specific data from a first work machine in the plurality of work machines; and (iii) searching the software solution database for an optimal-fit software solution corresponding to the task-specific data. If locating an optimal-fit software solution, the server end (iv) avails the first work machine of the optimal-fit software solution via the network. If not locating an optimal-fit software solution within the software solution database, the server end (v) transmits a corresponding message over the network and to the first work machine.

Abstract: An agricultural seeding machine includes a trench closer assembly and a sensing device configured to sense an aspect of the soil without contacting the soil and to output a sensed signal corresponding to the aspect of the soil. A processing device processes the sensed signal to generate a processed sensed signal, and compares a characteristic of the processed sensed signal to a stored signal characteristic representative of a soil condition. A trench closure quality metric is determined and provided via a user interface. Additionally, in response to and based upon the comparison, the processing device may automatically adjust the force applied to the soil by the soil contacting member. In this manner, the seeding machine utilizes a feedback signal to determine how well a trench is closed and can adjust the performance of the trench closer assembly in accordance with that feedback.

Abstract: An agricultural vehicle comprises a left frame and a right frame. A left wheel is rotatable with respect to the left frame and a right wheel is rotatable with respect to the right frame. A first leg extends upward from the left frame and a second leg extends upward from the right frame to connect the legs to the beam. A data processor estimates a reference point on or below the vehicle and an angular orientation or attitude of the beam relative to the reference point based on positions of location-determining receivers associated with the beam. An upper carriage is laterally movable along the beam. A lower carriage is suspended from the upper carriage by a plurality of vertical supports, such that a target lateral position of the upper carriage establishes an actual lateral position of the lower carriage.

Abstract: An agricultural seeding machine includes a trench closer assembly and a sensing device configured to sense an aspect of the soil without contacting the soil and to output a sensed signal corresponding to the aspect of the soil. A processing device processes the sensed signal to generate a processed sensed signal, and compares a characteristic of the processed sensed signal to a stored signal characteristic representative of a soil condition. A trench closure quality metric is determined and provided via a user interface. Additionally, in response to and based upon the comparison, the processing device may automatically adjust the force applied to the soil by the soil contacting member. In this manner, the seeding machine utilizes a feedback signal to determine how well a trench is closed and can adjust the performance of the trench closer assembly in accordance with that feedback.

Abstract: A first leg extends upward from the left frame and a second leg extends upward from the right frame to connect the legs to the beam. One or more satellite navigation receivers are associated with beam to determine a position and an attitude of the beam. One or more row units are suspended from the beam, each row unit having a first nozzle and a second nozzle, wherein the first nozzle and the second nozzle are associated with an adjustable reference position in one or more dimensions with respect to the beam.

Abstract: Methods and apparatus to track a blade are disclosed. A disclosed example apparatus includes a blade that is pivotable, first and second optical targets operatively coupled to the blade, and a first camera for collecting first imaging data of the first optical target within a first field of view. The example apparatus also includes a second camera for collecting second imaging data of the second optical target within a second field of view. The example apparatus also includes a selector to select at least one of the first or second imaging data, and a processor to determine an orientation of the blade based on the selected imaging data.