Deere + Company

Sebastian Blank

Dohn W Pfeiffer

Noel Wayne Anderson

Mario L Donini

Curtis R Hammer

Gurmukh H Advani

Bhanu Kiran Reddy Palla

Joshua D Hoffman

Tammo Wagner

Charles J Schleusner

Robert A Stevens

James Joseph Phelan

Folker Beck

Colin D Engel

Frank Kneip

Cameron R Mott

Oliver Grüenewald

Kristen A Blank

An agricultural harvesting machine includes crop processing functionality configured to engage crop in a field, perform a crop processing operation on the crop, and move the processed crop to a harvested crop repository, and a control system configured to identify a weed seed area indicating presence of weed seeds, and generate a control signal associated with a pre-emergence weed seed treatment operation based on the identified weed seed area.

Agricultural harvesting machine with pre-emergence weed detection and mitigation system

A user device, that is remote from a combine harvester, receives setting information, indicative of a set of settings on the combine harvester. A display controller controls a display device on the remote computing system to display an interface showing the combine harvester settings, along with an adjustment actuator. A settings adjustment input is received through the settings adjustment actuator on the displayed interface. A settings adjustment message is generated, and a communication system on the remote computing system is controlled to send the settings adjustment message to the combine. A verification notification is received at the remote computing system, showing the adjusted settings on the combine.

Remote control of settings on a combine harvester

Operating conditions corresponding to a harvesting operation being performed by a mobile harvesting machine are detected along with a priority of a first performance pillar metric relative to a second performance pillar metric. An operating characteristic of the mobile harvesting machine is detected and a performance pillar metric value is identified for the first performance pillar metric based on the detected operating characteristic. A performance limitation corresponding to the first performance pillar metric is identified based on the detected operating conditions and an aggressiveness setting is detected that is indicative of an operating settings change threshold. It is then determined whether a settings change is to be performed based on the first performance pillar metric value, the priority of the first performance pillar metric, the first performance limitation and the settings change threshold and if the settings change is to be performed, a settings change actuator is controlled to execute the settings change.

Combine harvester control interface for operator and/or remote user

A computer-implemented method includes obtaining a weed map of a field including a crop, the weed map representing weed plant locations on the field, identifying, based at least in part on the weed map, weed seed locations that represent presence of weed seeds on the field, and generating a control signal for a pre-emergence weed mitigation operation based on the weed seed locations.

Pre-emergence weed detection and mitigation system

Machine data is obtained indicating a number of times that a control rule is triggered on a mobile machine, along with an indication as to whether the control operation corresponding to the control rule was implemented and a performance result of that implementation. Effectiveness analyzer logic identifies an effectiveness of the control rule and machine learning logic generates a rating for the rule, based on its effectiveness. A rule modification engine is automatically controlled to make any control rule modifications, and a synchronization engine updates the modified control rules with control rules on the mobile machine.

Self-learning control system for a mobile machine

One or more techniques and/or systems are disclosed for identifying traversability of a site. Site conditions of a target site affecting traversability can be identified using real-time or historical data. Soil conditions, weather conditions, moisture levels, and other factors may be used to determine whether a target site is traversable by a target piece of equipment. The traversability information can be identified for a target area, that comprises a target site, and a traversability map can be generated for the site. Target equipment specifications can be used to determine whether the target equipment may effectively traverse the target site based on the traversability map. Further, a traversability path may be generated for a piece of target equipment based on the traversability map, site conditions, and the equipment specifications. Additionally, site management may be enhanced using the site condition data to plan traversability of target equipment at the target site.

Systems and methods for site traversability sensing

A method performed by a harvesting machine control system comprises obtaining bias data indicative of a performance bias of a first harvesting machine relative to at least one other harvesting machine, receiving a settings input indicative of a request to set performance of the first harvesting machine to correspond to performance of the at least one other harvesting machine, based on the bias data and machine settings associated with the performance of the at least one other harvesting machine, determining adjusted machine settings for the first harvesting machine, and outputting a control instruction to the first harvesting machine based on the adjusted machine settings.

Control of settings on a combine harvester with bias removal

Worksite data from an unmanned aerial vehicle (UAV) is received and an indication of the worksite data is generated. A quality of the received worksite data is calculated based on quality data within the received worksite data. Control signals are generated and provided to the UAV based on the calculated quality of the received worksite data. Additional worksite data corresponding to a modified surface of a worksite area is received from a plurality of mobile machines at the worksite area. A worksite error is calculated for the modified surface of the worksite area. Control signals are generated and provided to a UAV based on the calculated worksite error for the modified surface of the worksite area.

Unmanned aerial vehicle (UAV)-assisted worksite data acquisition

Systems and methods for geospatial yield mapping by managing and modeling a system-based delay between crop location and crop sensing. The system stores a plurality of yield rate values indicative of crop yield detected by a sensor and a plurality of geospatial location values as time sequence data sets. The system then maps a yield rate value to a geospatial location value by determining an offset indicative of a total delay time from when the crop is cut from the field to when the crop is detected by the yield sensor. In some implementations, the delay value is determined as an integer multiple of a defined sampling frequency and is determined as a sum of a plurality of delay component values each indicative of a portion of the total delay time associated with a different one of a plurality of component systems of the crop harvester.

Delay management for geospatial crop yield mapping

A performance dimension is selected, and a gap in machine performance, according to the selected dimension, is identified. A target value is identified to improve machine control according to the selected dimension. A dependent dimension, which depends on the selected dimension, is selected and a dependency indicator, that indicates a dependency of the dependent dimension on the selected dimension, is accessed to identify a value of the dependent dimension that will change if the machine is controlled so that the value of the selected dimension is moved from a current value to the target value. The change in value of the selected dimension, and the dependent dimension are aggregated to determine whether machine control should be modified so the value of the selected dimension moves toward the target value. If so, a corresponding control operation is identified, and control signals are generated to control the machine to perform the identified control operation.

Cross-dimension performance improvement in machine control

A system and method of controlling an agricultural machine includes successively recording signals from a first sensor sensing an agronomic parameter of a field during an operation of the machine in the field. The system and method of controlling an agricultural machine also includes successively recording signals from a second sensor sensing an operation parameter of the machine during the operation of the machine in the field. The signals of the first sensor and the second sensor are spatially overlaid. A respective zone in the field is determined from the overlaid signals. An actuator of the machine is controlled dependent on the determined zone in which the machine operates.

System for optimizing agricultural machine settings

A sensing system bias is reduced across a first agricultural machine and a second agricultural machine. A collection of agronomic data is accessed, that is indicative of an estimated crop yield. The collection that is accessed, for example, includes at least a first set of data sensed by the first agricultural machine and a second set of data sensed by the second agricultural machine. In addition, the first and second sets of data can be scaled based on a yield correction factor. A bias between the scaled first set of data and the scaled second set of data is determined, and a smoothing operation is performed on the scaled first and second sets of data. For example, performing the smoothing operation can include generating a calibration correction factor based on the determined bias, removing the bias between the scaled first set of data and the scaled second set of data to obtain a corrected set of crop yield data, and using the calibration correction factor in sensing the first set of data on the first agricultural machine and the second set of data on the second agricultural machine.

Growing community of inventors

Bettendorf, IA, United States of America

Sebastian Blank