Abstract: A method for plant treatment, including: receiving a first measurement for a plant from a sensor as the sensor moves within a geographic area comprising a plurality of plants; in response to receipt of the first measurement and prior to receipt of a second measurement for a second plant of the plurality, determining a set of treatment mechanism operation parameters for the plant to optimize a geographic area output parameter based on the first measurement and historical measurements for the geographic area; determining an initial treatment parameter for the plant; and operating a treatment mechanism in a treatment mode based on the set of operating parameters in response to satisfaction of the initial treatment parameter.

Abstract: A detection system detects malfunctions in an autonomous farming vehicle during an autonomous routine using one or more models and data from sensors coupled to the autonomous farming vehicle. The models may include machine-learned models trained on the sensor data and configured to identify objects indicative of an operational or malfunctioning component within a tilling assembly such as a tilling shank or sweep. Additionally, a machine-learned model may be trained on sensor data to detect whether debris has plugged the tilling assembly of the autonomous farming vehicle. In response to detecting a malfunction or a plug, the detection system may modify the autonomous routine (e.g., pausing operation) or provide information for the malfunction to be addressed (e.g., the likely location of a malfunctioning sweep that has detached from the tilling assembly).

Abstract: The calibration system of the farming machine receives images from each camera of the camera array. The images comprise visual information representing a view of a portion of an area surrounding the farming machine. To calibrate a pair of cameras including a first camera and second camera, the calibration system determines a relative pose between the pair of cameras by extracting relative position and orientation characteristics from visual information in both an image received from the first camera and an image received from the second camera. The calibration system identifies a calibration error for the pair of cameras based on a comparison of the relative pose with an expected pose between the first pair of cameras. The calibration system transmits a notification to an operator of the farming machine that describes the calibration error and instructions for remedying the calibration error.

Abstract: As a farming machine travels through a field of plants, the farming machine operates in a normal operational state to perform one or more farming operations. The farming machine detects an operational failure of a component of the farming machine using measurements obtained from one or more sensors coupled to and monitoring the farming machine. The operational failure of the component impacts performance of a first farming operation of the farming operations. The farming machine configures the farming machine to operate in a remedial operational state. In the remedial operational state, the farming machine diagnoses the operational failure of the component using the obtained measurements. In the remedial operational state, the farming machine selects a solution operation to address the operational failure of the component based on the diagnosis. The farming machine performs the determined solution operation.

Abstract: A farming machine moves through a field and includes an image sensor that captures an image of a plant in the field. A control system accesses the captured image and applies the image to a machine learned plant identification model. The plant identification model identifies pixels representing the plant and categorizes the plant into a plant group (e.g., plant species). The identified pixels are labeled as the plant group and a location of the pixels is determined. The control system actuates a treatment mechanism based on the identified plant group and location. Additionally, the images from the image sensor and the plant identification model may be used to generate a plant identification map. The plant identification map is a map of the field that indicates the locations of the plant groups identified by the plant identification model.

Abstract: A detection system detects malfunctions in an autonomous farming vehicle during an autonomous routine using one or more models and data from sensors coupled to the autonomous farming vehicle. The models may include machine-learned models trained on the sensor data and configured to identify objects indicative of an operational or malfunctioning component within a tilling assembly such as a tilling shank or sweep. Additionally, a machine-learned model may be trained on sensor data to detect whether debris has plugged the tilling assembly of the autonomous farming vehicle. In response to detecting a malfunction or a plug, the detection system may modify the autonomous routine (e.g., pausing operation) or provide information for the malfunction to be addressed (e.g., the likely location of a malfunctioning sweep that has detached from the tilling assembly).

Abstract: A farming machine identifies and treats a plant as the farming machine travels through a field. The farming machine includes a pair of image sensors for capturing images of a plant. The image sensors are different, and their output images are used to generate a depth map to improve the plant identification process. A control system identifies a plant using the depth map. The control system captures images, identifies a plant, and actuates a treatment mechanism in real time.

Abstract: Described are methods for identifying the in-field positions of plant features on a plant by plant basis. These positions are determined based on images captured as a vehicle (e.g., tractor, sprayer, etc.) including one or more cameras travels through the field along a row of crops. The in-field positions of the plant features are useful for a variety of purposes including, for example, generating three-dimensional data models of plants growing in the field, assessing plant growth and phenotypic features, determining what kinds of treatments to apply including both where to apply the treatments and how much, determining whether to remove weeds or other undesirable plants, and so on.

Abstract: A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses an image captured by the one or more sensors and identifies a distance value associated with each pixel of the image. The distance value corresponds to a distance between a point and an object that the pixel represents. The control system classifies pixels in the image as crop, plant, ground, etc. based on depth information in in the pixels. The control system generates a labelled point cloud using the labels and depth information, and identifies features about the crops, plants, ground, etc. in the point cloud. The control system generates treatment actions based on any of the depth information, visual information, point cloud, and feature values. The control system actuates a treatment mechanism based on the classified pixels.

Abstract: A farming machine is configured to identify and treat plants in a field. The farming machine includes one or more light sensors for measuring a characteristic of light. The one or more light sensors are coupled to the farming machine and are directed a substantially upwards orientation away from the plants. A control system adjusts settings of an image acquisition system based on a characteristic of light measured by the one or more light sensors. The image acquisition system captures an image of a plant using one or more image sensors coupled to the farming machine, the one or more image sensors directed in a substantially downwards orientation towards the plants. The control system identifies a plant in the image and actuates a treatment mechanism to treat the identified plant.

Abstract: A system for plant parameter detection, including: a plant morphology sensor having a first field of view and configured to record a morphology measurement of a plant portion and an ambient environment adjacent the plant, a plant physiology sensor having a second field of view and configured to record a plant physiology parameter measurement of a plant portion and an ambient environment adjacent the plant, wherein the second field of view overlaps with the first field of view; a support statically coupling the plant morphology sensor to the physiology sensor, and a computing system configured to: identify a plant set of pixels within the physiology measurement based on the morphology measurement; determine physiology values for each pixel of the plant set of pixels; and extract a growth parameter based on the physiology values.

Abstract: A plant treatment platform uses a plant detection model to detect plants as the plant treatment platform travels through a field. The plant treatment platform receives image data from a camera that captures images of plants (e.g., crops or weeds) growing in the field. The plant treatment platform applies pre-processing functions to the image data to prepare the image data for processing by the plant detection model. For example, the plant treatment platform may reformat the image data, adjust the resolution or aspect ratio, or crop the image data. The plant treatment platform applies the plant detection model to the pre-processed image data to generate bounding boxes for the plants. The plant treatment platform then can apply treatment to the plants based on the output of the machine-learned model.

Abstract: A treatment system for spraying treatment fluid onto plants in a field is described. The treatment system includes a highly configurable treatment mechanism including an array of nozzles and valve assemblies coupled into manifolds, and manifold assemblies. The manifolds of the manifold assemblies can be oriented in an open state or a nested state, the open state with no overlap between nozzles of adjacent manifolds and the nested state with overlap between nozzles of adjacent manifolds. The manifolds can have multiple configurations, examples of which include a tube manifold and an offset manifold. The nozzles of the system can have multiple configurations, examples of which include a tri-spray nozzle, a bar nozzle, a fan nozzle, and a deflected fan nozzle. The system can be controlled by a system controller which detects plant material and instructs a nozzle or combination of nozzles to spray treatment fluid.

Abstract: A detection system detects malfunctions in an autonomous farming vehicle during an autonomous routine using one or more models and data from sensors coupled to the autonomous farming vehicle. The models may include machine-learned models trained on the sensor data and configured to identify objects indicative of an operational or malfunctioning component within a tilling assembly such as a tilling shank or sweep. Additionally, a machine-learned model may be trained on sensor data to detect whether debris has plugged the tilling assembly of the autonomous farming vehicle. In response to detecting a malfunction or a plug, the detection system may modify the autonomous routine (e.g., pausing operation) or provide information for the malfunction to be addressed (e.g., the likely location of a malfunctioning sweep that has detached from the tilling assembly).

Abstract: A modular system includes a hub and a set of modules removably coupled to the hub. The modules are physically coupled to the frame relative to each other so that each module can operate with respect to a different row of a field. An individual module includes a sensor for capturing field measurement data of individual plants along a row as the modular system moves through the geographic region. An individual module further includes a treatment mechanism for applying a treatment to the individual plants of the row based on the field measurement data before the modular system passes by the individual plants. An individual module further includes a computing device that determines the treatment based on the field measurement data and communicates data to the hub. The hub is communicatively coupled to the modules, so that it may exchange data between the modules and with a remote computing system.

Abstract: A system for plant parameter detection, including: a plant morphology sensor having a first field of view and configured to record a morphology measurement of a plant portion and an ambient environment adjacent the plant, a plant physiology sensor having a second field of view and configured to record a plant physiology parameter measurement of a plant portion and an ambient environment adjacent the plant, wherein the second field of view overlaps with the first field of view; a support statically coupling the plant morphology sensor to the physiology sensor, and a computing system configured to: identify a plant set of pixels within the physiology measurement based on the morphology measurement; determine physiology values for each pixel of the plant set of pixels; and extract a growth parameter based on the physiology values.

Abstract: A farming machine is configured to identify and treat plants in a field. The farming machine includes one or more light sensors for measuring a characteristic of light. The one or more light sensors are coupled to the farming machine and are directed a substantially upwards orientation away from the plants. A control system adjusts settings of an image acquisition system based on a characteristic of light measured by the one or more light sensors. The image acquisition system captures an image of a plant using one or more image sensors coupled to the farming machine, the one or more image sensors directed in a substantially downwards orientation towards the plants. The control system identifies a plant in the image and actuates a treatment mechanism to treat the identified plant.

Abstract: A farming machine moves through a field and includes an image sensor that captures an image of a plant in the field. A control system accesses the captured image and applies the image to a machine learned plant identification model. The plant identification model identifies pixels representing the plant and categorizes the plant into a plant group (e.g., plant species). The identified pixels are labeled as the plant group and a location of the pixels is determined. The control system actuates a treatment mechanism based on the identified plant group and location. Additionally, the images from the image sensor and the plant identification model may be used to generate a plant identification map. The plant identification map is a map of the field that indicates the locations of the plant groups identified by the plant identification model.

Abstract: Described are methods for identifying the in-field positions of plant features on a plant by plant basis. These positions are determined based on images captured as a vehicle (e.g., tractor, sprayer, etc.) including one or more cameras travels through the field along a row of crops. The in-field positions of the plant features are useful for a variety of purposes including, for example, generating three-dimensional data models of plants growing in the field, assessing plant growth and phenotypic features, determining what kinds of treatments to apply including both where to apply the treatments and how much, determining whether to remove weeds or other undesirable plants, and so on.

Abstract: Methods and apparatus for using a controllable filter, e.g., an liquid crystal panel, in front of a camera are described. The filter is controlled based on the luminosity of object in a scene being captured by the camera to reduce or eliminate luminosity related image defects such as flaring, blooming or ghosting. Multiple cameras and filters can be used to capture multiple images as part of a depth determination processes where pixel values captured by cameras at different locations are matched to determine the depth, e.g., distance from the camera or camera system to object in the environment. Pixel values are normalized in some embodiments based on the amount of filtering applied to a sensor region and sensor exposure time. The filtering allows for regional sensor exposure control at an individual camera even though the overall exposure time of the pixel sensors may be and often will be the same.