Abstract: An agricultural system includes a target vehicle configured to harvest crops and a work vehicle. The work vehicle includes a controller. The controller includes a memory and a processor, and the controller is configured to receive or determine a plurality of vehicle paths as well as a location of the target vehicle. The controller is also configured to identify an active path of the plurality of vehicle paths based on the location of the target vehicle. The target path is a path traversed by the target vehicle.

Abstract: A vehicle control system for an off-road vehicle including a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to receive a first parameter associated with a characteristic of the off-road vehicle, receive a second parameter associated with a characteristic of an environment of the off-road vehicle, generate, based on the first and second parameters, a perception zone for the off-road vehicle, control the off-road vehicle to avoid an obstacle using the perception zone, receive an indication of a change in at least one of the first parameter or the second parameter, and update the perception zone based on the change in the at least one of the first parameter or the second parameter.

Abstract: A control system includes one or more processing circuits comprising one or more memory devices coupled to one or more processors. The one or more memory devices are configured to store instructions thereon that, when executed by the one or more processors, cause the one or more processors to acquire speed data regarding current speeds of tractive elements of the vehicle from tractive element speed sensors of the vehicle, determine speed references for the tractive elements to perform autonomous driving operations where the speed references indicate speeds at which each of the tractive elements should rotate to accommodate the autonomous driving operations, and control at least one of a driveline or a brake system of the vehicle to selectively alter the current speeds of the tractive elements of the vehicle based on the current speeds and the speed references to accommodate the autonomous driving operations.

Abstract: Low carbon hydrogen will play a crucial role in decarbonization of chemical complexes and manufacturing facilities. Depending on the application, different grades of low carbon hydrogen might be required—fuel grade (90-99% H2 purity) or chemical grade (>99% H2 purity). The current invention describes a hydrogen production process based on autothermal reforming and CO2 capture to produce low carbon hydrogen with hydrogen rich offgas as part of the feedstock.

Abstract: Identifying table joins includes obtaining respective casting similarities between pairs of columns of a first table and a second table. Each pair of columns includes a first column of the first table and a second column of the second table. Ones of the pairs of columns not satisfying a casting similarity condition are discarded to obtain first join candidates. Respective string similarities for the first join candidates are obtained. Ones of the first join candidates not satisfying a string similarity condition are discarded to obtain second join candidates. Final join candidates are obtained using the respective casting similarities and the respective string similarities of the second join candidates. A selected join candidate of the final join candidates is received from a user.

Abstract: Computer vision systems and methods for automatic parcel alignment are provided. The system receives a geotagged aerial image, parcel information, and semantic information where each of the parcel and semantic information are overlaid on the geotagged aerial image. The system cleans the parcel information and the semantic information. The system optimizes the parcel information by grouping geo-registered parcels present in the geotagged aerial image into a plurality of islands and generating a plurality of parcel alignment solutions for each island of the plurality of islands. The system refines the plurality of parcel alignment solutions for each island and regularizes each island. The system generates a composite parcel alignment solution based on the refined plurality of parcel alignment solutions for each regularized island to align the geo-registered parcels of each regularized island with the geotagged aerial image.

Abstract: The invention relates to an object positioning system including an actuator system and a measurement system. The actuator system includes an actuator made of a material with predominantly electrostrictive properties and substantially no net polarization in absence of an electric field. The actuator system is configured to apply an electric field to the actuator, which electric field includes a bias electric field and an actuation electric field superimposed on the bias electric field, a field strength of the actuation electric field being equal to or smaller than a field strength of the bias electric field. The measurement system is configured to measure an electrical property of the actuator which is representative for a mechanical state of the actuator. The measurement system includes a bridge circuit including an actuator and a reference element having electrical properties matched to the electrical properties of the actuator.

Abstract: Example positioning systems and methods are described. In one implementation, a landing platform includes a base having an aperture and multiple positioning arms attached to the base. Each of the multiple positioning arms can rotate between an unlocked position and a locked position. Additionally, each of the multiple positioning arms are configured to engage a positioning ring on an unmanned aerial vehicle (UAV) and further configured to reposition the UAV on the base.

Abstract: Computer vision systems and methods for automatic parcel alignment are provided. The system receives a geotagged aerial image, parcel information, and semantic information where each of the parcel and semantic information are overlaid on the geotagged aerial image. The system cleans the parcel information and the semantic information. The system optimizes the parcel information by grouping geo-registered parcels present in the geotagged aerial image into a plurality of islands and generating a plurality of parcel alignment solutions for each island of the plurality of islands. The system refines the plurality of parcel alignment solutions for each island and regularizes each island. The system generates a composite parcel alignment solution based on the refined plurality of parcel alignment solutions for each regularized island to align the geo-registered parcels of each regularized island with the geotagged aerial image.

Abstract: A work vehicle includes a computing system is configured to access a swath line corresponding to a pass to be made across a field by the work vehicle. Furthermore, the computing system is configured to receive the input indicative of an operating parameter of the work vehicle or the associated implement from at least one of a sensor, a user interface, or an associated memory device of the computing system. Additionally, the computing system is configured to determine the operating parameter based on the received input. Moreover, the computing system is configured to adjust a portion of the swath line based on the determined operating parameter prior to making the pass across the field. In addition, the computing system is configured to control an operation of the plurality of components such that the work vehicle travels along the adjusted portion of the swath line.

Abstract: A work vehicle includes a computing system is configured to access a swath line corresponding to a pass to be made across a field by the work vehicle. Furthermore, the computing system is configured to control the operation of the work vehicle such that the vehicle travels along the swath line to make the pass across the field. Additionally, the computing system is configured to determine an operating parameter of the work vehicle as the vehicle travels along the swath line. Moreover, the computing system is configured to adjust a portion of the swath line positioned forward of the work vehicle relative to a direction of travel of the vehicle based on the determined operating parameter as the vehicle travels along the swath line.

Abstract: A method for determining an as-driven path of an agricultural work vehicle includes receiving position data indicative of a position of the agricultural work vehicle in a field during a first pass of the agricultural work vehicle in the field, receiving inertial movement data of the agricultural work vehicle during the first pass, and receiving operational data indicative of at least one of a steering angle of a wheel of the agricultural work vehicle, a wheel speed of the wheel of the agricultural work vehicle, or a transmission speed of the agricultural work vehicle during the first pass. Moreover, the method includes generating an as-driven path of the agricultural work vehicle during the first pass based at least in part on the position data, the inertial movement data, and the operational data. Additionally, the method includes performing a control action based on the as-driven path.

Abstract: Systems and methods for operating an agricultural system are provided herein. The method can include presenting an image of a field on a display of an electronic device. The method can also include detecting a geographic position of the electronic device and an imager direction of the imager. In addition, the method can include determining a tilt orientation of the electronic device. The method can further include determining a field of view based on the geographic position, the tilt orientation, and the imager direction. The method can also include determining one or more features of an object within the image of the field and comparing the one or more features to stored feature data. Lastly, the method can include detecting a change in the one or more features of the object.

Abstract: A work vehicle includes a frame configured to support a plurality of components of the work vehicle. Furthermore, the work vehicle includes a location sensor configured to capture data indicative of a location of the work vehicle within a field. Additionally, the work vehicle includes a computing system communicatively coupled to the location sensor. The computing system is configured to control an operation of the plurality of components as the work vehicle makes a first pass across the field. Moreover, the computing system is configured to record a travel path of the work vehicle as the work vehicle make the first pass across the field based on data captured by the location sensor. In addition, the computing system is configured to generate a continuous swath line formed from a plurality of line segments such that the continuous swath line corresponds to the recorded travel path of the work vehicle.

Abstract: A method for an agricultural operation can include presenting a captured image of a field on a display of an electronic device. The image can be captured by an imager operably coupled with the electronic device. The method can further include detecting a geographic position of the electronic device, an imager direction of the imager, and a tilt orientation of the electronic device. The method also can include determining a field of view based on the geographic position, the tilt orientation, and the imager direction. Further, the method can include identifying whether one or more portions of the field within the field of view is a processed segment of the field or an unprocessed segment of the field. Lastly, the method can include visually augmenting the captured image with graphics based at least in part on the identification of the one or more portions of the field.

Abstract: A work vehicle includes a location sensor configured to capture data indicative of a location of the work vehicle within a field. Additionally, the work vehicle includes a computing system communicatively coupled to the location sensor. In this respect, the computing system is configured to control an operation of the plurality of components as the work vehicle makes a pass across the field. Moreover, the computing system is configured to record a travel path of the work vehicle as the work vehicle makes the pass across the field based on data captured by the location sensor. In addition, the computing system is configured to analyze the recorded travel path to determine one or more geometric primitives of the recorded travel path. Furthermore, the computing system is configured to generate a swath line for the pass based on the determined one or more geometric primitives.

Abstract: Example landing platform systems and methods are described. In one implementation, a landing platform includes a top plate configured to support an unmanned aerial vehicle (UAV), where the top plate has a plurality of slots therethrough. A rotating plate is located adjacent the top plate and includes multiple centering pins extending therefrom and extending through the plurality of slots in the top plate. A motor is capable of rotating the rotating plate, which causes the multiple centering pins to center the UAV on the top plate.

Abstract: Embodiments provide methods and systems for removing temporal biases in classification tasks. Method performed by server system includes accessing a transaction graph associated with a particular time duration and determining a set of local features and aggregate features associated with each node based on labeled data. Method includes generating via a machine learning model, a set of intermediate node representations associated with each of the plurality of nodes based on the set of local features and the set of aggregate features. Method includes generating via a fraud model and a timestep model, a fraud classification loss, and a timestep classification loss based on the set of intermediate node representations. Method includes determining an adversarial loss value based on the fraud classification loss and the timestep classification loss. Method includes determining a set of optimized parameters for the machine learning model based on the adversarial loss value.

Abstract: A control system includes a controller configured to determine a target speed between a first target position of a haul vehicle relative to a harvester and a second target position of the haul vehicle relative to the harvester based on a flow rate of agricultural product through a conveyor of the harvester. The haul vehicle is coupled to a storage compartment, an outlet of the conveyor is aligned with a first unloading point within the storage compartment while the haul vehicle is positioned at the first target position, and the outlet of the conveyor is aligned with a second unloading point within the storage compartment while the haul vehicle is positioned at the second target position. Furthermore, the controller is configured to output a control signal indicative of instructions to direct the haul vehicle from the first target position to the second target position at the target speed.

Abstract: Identifying table joins includes obtaining respective casting similarities between pairs of columns of a first table and a second table. Each pair of columns includes a first column of the first table and a second column of the second table. Ones of the pairs of columns not satisfying a casting similarity condition are discarded to obtain first join candidates. Respective string similarities for the first join candidates are obtained. Ones of the first join candidates not satisfying a string similarity condition are discarded to obtain second join candidates. Final join candidates are obtained using the respective casting similarities and the respective string similarities of the second join candidates. A selected join candidate of the final join candidates is received from a user.