Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: The disclosure includes embodiments for an analysis system. A method according to some embodiments is executed by a graphics processing unit. The method includes generating input data including image data captured with a monocular camera operating in a field environment wherein the image data describes a two-dimensional image of the field environment. The method includes analyzing the input data to generate output data describing a three-dimensional graphic of the field environment depicted in the two-dimensional image. In some embodiments, the output data localizes objects, such as a mobile field device upon which the monocular camera is mounted, within the field environment. In some embodiments, the output data localizes any tangible object located within the field environment with an accuracy that satisfies a threshold for accuracy. The method includes modifying an operation of an autonomous control system of a mobile field device based on the output data.

Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.

Abstract: The disclosure includes embodiments for an analysis system. A method according to some embodiments is executed by a graphics processing unit. The method includes generating input data including image data captured with a monocular camera operating in a field environment wherein the image data describes a two-dimensional image of the field environment. The method includes analyzing the input data to generate output data describing a three-dimensional graphic of the field environment depicted in the two-dimensional image. In some embodiments, the output data localizes objects, such as a mobile field device upon which the monocular camera is mounted, within the field environment. In some embodiments, the output data localizes any tangible object located within the field environment with an accuracy that satisfies a threshold for accuracy. The method includes modifying an operation of an autonomous control system of a mobile field device based on the output data.

Abstract: A rear perception module is utilized in conjunction with a work vehicle having a work vehicle cabin and a cabin roof. In an embodiment, the rear perception module includes an environmental depth perception (EDP) sensor system including a first EDP device having a field of view encompassing an environmental region to a rear of the work vehicle, a rear module housing mounted to an upper trailing edge portion of the cabin roof, and vents formed in exterior walls of the rear module housing to facilitate airflow through the rear module housing along a cooling airflow path. A heat-generating electronic component is electrically coupled to the first EDP device and positioned in or adjacent the cooling airflow path such that excess heat generated by the heat-generating electronic component is dissipated by convective transfer to airflow conducted along the cooling airflow path during operation of the rear perception module.

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 disclosure includes embodiments for an analysis system. A method according to some embodiments is executed by a graphics processing unit. The method includes generating input data including image data captured with a monocular camera operating in a field environment wherein the image data describes a two-dimensional image of the field environment. The method includes analyzing the input data to generate output data describing a three-dimensional graphic of the field environment depicted in the two-dimensional image. In some embodiments, the output data localizes objects, such as a mobile field device upon which the monocular camera is mounted, within the field environment. In some embodiments, the output data localizes any tangible object located within the field environment with an accuracy that satisfies a threshold for accuracy. The method includes modifying an operation of an autonomous control system of a mobile field device based on the output data.

Abstract: A front perception module is utilized in conjunction with a front ballast system, which is included in a work vehicle and which has a laterally-extending hanger bracket supporting a number of removable ballast weights. In various embodiments, the front perception module includes an environmental depth perception (EDP) sensor system including a first EDP device having a field of view (FOV) encompassing an environmental region forward of the work vehicle, a mounting base attached to the work vehicle, and a front module housing containing the EDP sensor system and joined to the work vehicle through the mounting base. The front module housing is positioned over and vertically spaced from the laterally-extending hanger bracket in a manner enabling positioning of the removable ballast weights beneath the front module housing.

Abstract: A front perception module is utilized in conjunction with a front ballast system, which is included in a work vehicle and which has a laterally-extending hanger bracket supporting a number of removable ballast weights. In various embodiments, the front perception module includes an environmental depth perception (EDP) sensor system including a first EDP device having a field of view (FOV) encompassing an environmental region forward of the work vehicle, a mounting base attached to the work vehicle, and a front module housing containing the EDP sensor system and joined to the work vehicle through the mounting base. The front module housing is positioned over and vertically spaced from the laterally-extending hanger bracket in a manner enabling positioning of the removable ballast weights beneath the front module housing.

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 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 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 moves through a field and performs one or more farming actions (e.g., treating one or more plants) in the field. Portions of the field may include moisture, such as puddles or mud patches. A control system associated with the farming machine may include a traversability model and/or a moisture model to help the farming machine operate in the field with the moisture. In particular, the control system may employ the traversability model to reduce the likelihood of the farming machine attempting to traverse an untraversable portion of the field, and the control system may employ the moisture model to reduce the likelihood of the farming machine performing an action that will damage a portion of the field.

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 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 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).