A work machine for harvesting crop includes a controller and an engine. The controller is configured to command operation of the engine in accordance with various power curves based on sensed factors associated with the harvested crop. The work machine stores the harvested crop in a tank to be unloaded by an unloading auger which is powered by the engine. Prior to activation of the unloading auger, the controller commands the engine to operate in accordance with a power curve associated with a reduced power level to reserve power for operation of the unloading auger.

Embodiments of the disclosed technologies are capable of inputting, to a machine-learned model that has been trained to recognize a horticultural product in digital imagery, digital video data comprising frames that represent a view of the horticultural product in belt-assisted transit from a picking area of a field to a harvester bin; outputting, by the machine-learned model, annotated video data; using the annotated video data, computing quantitative data comprising particular counts of the individual instances of the horticultural product associated with particular timestamp data; using the timestamp data, mapping the quantitative data to geographic location data to produce a digital yield map; causing display of the digital yield map on a field manager computing device.

The disclosed apparatus, systems and methods relate to a physical stalk sensing system comprising at least one resilient member. Sensors having the resilient member or members are able to estimate the size of the stalks of row crops as they pass through a field, such as a corn field. The sensors can be mounted on a corn head and the results can be analyzed and visualized. A system for predicting crop yields in real-time or near real-time. A system for adjusting a stripper plate gap.

A computer-implemented method includes obtaining field data for a field that was generated prior to an agricultural harvesting machine operating on the field, the field data representing an estimated yield, obtaining yield data, that is georeferenced to the field, based on a signal from a yield sensor on the agricultural harvesting machine, applying a flow model to the yield data to generate a yield map, the flow model having a set of parameters that models material flow through a harvesting system of the agricultural harvesting machine, obtaining an adjusted set of parameters based on a correlation between the yield map and the estimated yield, modifying the yield map based on the adjusted set of parameters, and generating a control signal based on the modified yield map.

Compound headers and combine harvesters that include compound headers are disclosed. The compound headers may include two or more crop harvester types that are operable to harvest different crops simultaneously, such as different crops grown in the same field in an intercropped relationship. The simultaneously harvested crops may be separated into individual crop flows that are handled separately from each other.

A biomass estimating system for an agricultural harvester includes a sensor arrangement disposed to sense standing crop adjacent to the agricultural harvester and disposed to sense a portion of ground adjacent to the agricultural harvester that has been previously harvested. An ECU receives signals indicating the standing crop and signals indicating the portion of the ground and calculates an estimated biomass of the standing crop based at least upon the signals indicating the standing crop and the signals indicating the portion of ground.

A combine harvester has at least one header for cutting plants to be harvested with the aid of the combine harvester, a feeder for conveying the cut plants in the direction of a threshing mechanism, and a threshing mechanism, with the aid of which fruits can be removed from the cut plants in such a way that the fruits are then present separately from plant residue of the plants. The feeder comprises a revolvingly driveable conveying unit and a conveyor channel within which the cut plants can be conveyed with the conveying unit. The feeder interacts with a measuring unit in the form of a sensor unit that contactlessly detects material feed height of plants conveyed with the aid of the feeder in the conveyor channel.

An agricultural harvester is disclosed. The agricultural harvester includes a cutting unit that has a cutting table adjustable in its cutting table length, a reel adjustable to a reel vertical position and reel longitudinal position, an inclined conveyor downstream from the cutting unit, and a driver assistance system. The driver assistance system autonomously determines, using at least one input variable, at least one machine parameter and specifies the machine parameter to the cutting unit. The machine parameter can include one or more of the cutting table length, the reel vertical position, or the reel longitudinal position. In particular, the driver assistance system may determine a harvested material throughput and a vibration coefficient describing the fluctuation in the harvested material throughput in a region lying in front of the threshing system and adapt or modify the cutting table length based on the determined vibration coefficient.

A priori geo-referenced vegetative index data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the geo-referenced vegetative index data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.

A detection system for an agricultural header includes a belt that has at least one physical feature driven by a roller at a roller rotational speed. The detection system also includes a sensor that detects a physical feature as it passes the sensor during rotation of the belt. The detection system further includes a controller that receives a signal indicating a first pulse of a first time a physical feature passes the sensor during the rotation of the belt and a second pulse of a second time a physical feature passes the sensor during the rotation of the belt. The controller further determines a pulse frequency based on the first and second times and calculates a belt rotational speed based on the pulse frequency. The controller compares the belt rotational speed to the roller rotational speed and provides an output if the roller rotational speed exceeds a threshold.