Abstract: A device for steering an agricultural machine having independently steerable axles includes first and second steerable axle interface to couple with a first steering mechanism of a first steerable axle and a second a second steering mechanism of a second steerable axle. The device includes a planning module having a guidance path for the agricultural machine, and a steering control module to coordinate steering of the steering mechanisms. The steering control module includes a translational comparator to determine a translational difference between a location of the agricultural machine relative to the guidance path, an angular comparator to determine an angular difference between an angular orientation of the agricultural machine relative to the guidance path, and a translation steering controller to actuate the first and second steering mechanisms according to the translational difference.

Abstract: A semi-active suspension system includes a suspension element having a damping coefficient range. The suspension element optionally includes an implement end and a chassis end. The semi-active suspension system includes a suspension control circuit in communication with the suspension element. The suspension control circuit optionally includes a kinematic assessment circuit in communication with one or more sensors. The kinematic assessment circuit is configured to measure or determine kinematic characteristics of one or more of the agricultural implement and the chassis. The suspension control circuit optionally includes a damping control circuit, and the damping control circuit generates a specified damping characteristic based on the measured or determined kinematic characteristics. The damping control circuit optionally directs the suspension element to operate within the damping coefficient range based on the specified damping characteristic.

Abstract: A technology platform includes hardware and software components that enable applications of autonomous agricultural equipment operation in an agricultural or other off-road setting, within a common architecture. The technology platform represents a technology stack that is a modular architecture leveraged across multiple use cases and vehicle types. The technology platform includes a vehicle interface component for the physical interface to agricultural equipment, a telematics component that provides stable in-field communications between all aspects of the technology platform, and a perception component that operates as a safety mechanism and includes object detection and classification. Additionally, a cloud-side application performs account management and field setup and as well as syncing of field equipment and operating systems in a common operating system.

Abstract: A framework for safely operating autonomous machinery, such as vehicles and other heavy equipment, in an in-field or off-road environment, includes detecting, identifying, and tracking objects from on-board sensors configured with the autonomous machinery as it performs activities in either an agricultural setting or a transportation environment. The framework generates commands for navigational control of autonomously-operated vehicles in response to detected objects and predicted tracks thereof for safe operation in the performance of those activities. The framework processes image data and range data in multiple fields of view around the autonomously-operated to discern and track objects in a deep learning to accurately interpret this data for determining and effecting such navigational control.

Abstract: A system and method of controlling agriculture equipment which combines geographical coordinates, machine settings, machine position, path plans, user input, and equipment parameters to generate executable commands based of a variety of different in-field agriculture operation objectives for a vehicle equipped with an automatic or electronically controlled locomotion system capable of reading and executing the commands.

Abstract: In an example, a system for applying an agricultural product includes a valve and a solenoid. For instance, the valve includes a coil that generates a magnetic flux. The system includes a valve controller. The valve controller is configured to measure one or more electrical characteristics of at least one of the coil or a dissipation element. In some examples, the valve controller determines an actual duty cycle of a valve operator of the valve using the measured electrical characteristics. The valve controller determines a magnetic flux correction, for instance based on a difference between the actual duty cycle and a specified duty cycle. The valve controller operates the valve operator according to the specified magnetic flux and the magnetic flux correction to guide the actual duty cycle toward the specified duty cycle.

Abstract: A system is configured for nozzle control. The system includes an overall system pressure valve, configured to adjust the pressure of an agricultural product within a boom. A master node is configured to receive an overall system flow rate measurement, an overall target flow rate, and an overall system pressure measurement, the master node configured to adjust the overall system pressure valve to control the pressure of the agricultural product. A plurality of smart nozzles are configured to dispense the agricultural product, the plurality of smart nozzles each associated with an electronic control unit (ECU) and one or more individual nozzle, the smart nozzle is configured to control a nozzle flow rate of the associated one or more individual nozzles.

Abstract: A localized product injection system includes a composite boom tube having a carrier fluid passage within a tube body, and at least one injection product passage within the tube body isolated from the carrier fluid passage. A plurality of port stations are provided at locations along the tube body. Each of the port stations includes a carrier fluid outlet port and at least one injection product outlet port. A localized injection interface is coupled at a port station. The injection interface includes a carrier fluid input coupled with the carrier fluid outlet port, and at least one injection product input coupled with the at least one injection product outlet port. The injection interface includes at least one throttling element in communication with the at least one injection product input, a mixing chamber, and an injection port configured for localized coupling and injection to a product dispenser.

Abstract: A device to determine a height disparity between features of an image includes a memory including instructions and processing circuitry. The processing circuitry is configured by the instructions to obtain an image including a first repetitive feature and a second repetitive feature. The processing circuitry is further configured by the instructions to determine a distribution of pixels in a first area of the image, where the first area includes an occurrence of the repetitive features, and to determine a distribution of pixels in a second area of the image, where the second area includes another occurrence of the repetitive features. The processing circuitry is further configured by the instructions to evaluate the distribution of pixels in the first area and the distribution of pixels in the second area to determine a height difference between the first repetitive feature and the second repetitive feature.

Abstract: Metering devices for an agricultural implement apply a field input, for example, pneumatically delivered granular product including seed or fertilizer or sprayed liquid product including fertilizer and the like, to an agricultural field. In the applying of the field input, the rate of application of the dispensers of one section of the implement can be collectively varied in relation to the rate of application of the dispensers of a different section of the implement frame.

Abstract: A system and method for sensing an edge of a region includes at least one distance sensor configured to detect a plurality of distances of objects along a plurality of adjacent scan lines. A controller is in communication with the at least one distance sensor and is configured to determine a location of an edge of a region within the plurality of adjacent scan lines. The controller includes a comparator module configured to compare values corresponding to the detected plurality of distances, and an identification module configured to identify the location of the edge of the region according to the compared values. In one example, the values corresponding to the detected plurality of distances include couplets of standard deviations that are analyzed and selected to identify the location of the edge.

Abstract: A computer-implemented method may include receiving, over an API, a command identifying a change in an agricultural task; converting, using a processing unit, the command into an event; based on an event type of the event, retrieving a subset of workflows from a workflow datastore; electronically evaluating conditional expressions in the subset of workflows using data of the event; and based on the evaluating, determining a conditional expression of a workflow of the subset of workflows evaluates to true; and in response to the determining, electronically issuing a command using the API in accordance with an action of the workflow of the subset of workflows.

Abstract: A configurable nozzle includes a nozzle body having a reception chamber configured to receive an application mixture. The nozzle body includes a nozzle orifice. At least one orifice assembly is coupled with the nozzle body, the at least one orifice assembly includes an orifice plate movably coupled with the nozzle body. The orifice plate extends along at least a portion of the nozzle orifice, and movement of the orifice plate changes one or more of the size or shape of the nozzle orifice. An orifice actuator is coupled with the orifice plate, and the orifice actuator is configured to move the orifice plate.

Abstract: A framework for safely operating autonomous machinery, such as vehicles and other heavy equipment, in an in-field or off-road environment, includes detecting, identifying, classifying and tracking objects and/or terrain characteristics from on-board sensors that capture images in front and around the autonomous machinery as it performs agricultural or other activities. The framework generates commands for navigational control of the autonomous machinery in response to perceived objects and terrain impacting safe operation. The framework processes image data and range data in multiple fields of view around the autonomous equipment to discern objects and terrain, and applies artificial intelligence techniques in one or more neural networks to accurately interpret this data for enabling such safe operation.

Abstract: System and techniques for detecting a crop related row from an image are described herein. An image that includes several rows—where the several rows including crop rows and furrows—can be obtained. The image can be segmented to produce a set of image segments. A filter can be shifted across respective segments of the set of image segments to get a set of positions. A line can be fit members of the set of positions, the line representing a crop row or furrow.

Abstract: An agricultural vehicle monitoring system includes first and second noncontact sensors configured for coupling with an agricultural vehicle, where the first and second noncontact sensors are configured to sense respective first and second environmental characteristics for determining a position of the agricultural vehicle in a field. The system further includes a comparative vehicle monitor in communication with the first and second noncontact sensors. The comparative vehicle monitor includes a filter module to filter outputs of the first and second noncontact sensors based on an indicator of a relative quality of the output of each sensor. The comparative vehicle monitor additionally includes an evaluation module to determine a vehicle position of the agricultural vehicle relative to at least one of the first and second environmental characteristics according to filtered outputs of the first and second noncontact sensors.

Abstract: System and techniques for calibrating a crop row computer vision system are described herein. An image set that includes crop rows and furrows is obtained. Models of the field are searched to find a model that best fits the field. A calibration parameter is extracted from the model and communicated to a receiver.

Abstract: An automated implement control system includes one or more distance sensors configured for coupling with an agricultural implement. The one or more distance sensors are configured to measure a ground distance and a canopy distance from the one or more sensors to the ground and crop canopy, respectively. An implement control module is in communication with the one or more distance sensors. The implement control module controls movement of the agricultural implement. The implement control module includes a confidence module configured to determine a ground confidence value based on the measured ground distance and a canopy confidence value based on the measured canopy distance. A target selection module of the implement control module is configured to select one of the measured ground or canopy distances as a control basis for controlling movement of the agricultural implement based on the comparison of confidence values.

Abstract: A sprayer control system includes a plurality of smart nozzles each having at least one control valve with a valve operator, an electronic control unit for the valve operator, and one or more spray nozzles. The at least one control valve and the ECU control a flow rate of liquid agricultural product through the nozzles. A duty cycle modulator is in communication with the ECU and generates an applied duty cycle for the at least one control valve. The duty cycle modulator includes a specified duty cycle input having a specified duty cycle and a pressure monitor associated with the at least one control valve. A pressure comparator compares the valve pressure determined with the pressure monitor with a system pressure and generates a pressure error. An applied duty cycle generator generates the applied duty cycle based on the specified duty cycle modified by the pressure error.

Abstract: A device to determine a height disparity between features of an image includes a memory including instructions and processing circuitry. The processing circuitry is configured by the instructions to obtain an image including a first repetitive feature and a second repetitive feature. The processing circuitry is further configured by the instructions to determine a distribution of pixels in a first area of the image, where the first area includes an occurrence of the repetitive features, and to determine a distribution of pixels in a second area of the image, where the second area includes another occurrence of the repetitive features. The processing circuitry is further configured by the instructions to evaluate the distribution of pixels in the first area and the distribution of pixels in the second area to determine a height difference between the first repetitive feature and the second repetitive feature.