A view-based method for controlling the driving of agricultural machinery includes collecting ground information from images; identifying a target operation area according to the ground image information; determining a navigation route for the agricultural machinery within the target operation area; and determining whether the navigation route is reliable; detecting manual driving signal of the user and allowing manual driving of the agricultural machinery according to the manual driving signal if the navigation route is not reliable; and determining driving adjustment parameters for the navigation route and current driving attitude if the navigation route is found reliable. A system for driving agricultural machinery, a device applying the method, and a non-volatile storage medium are also disclosed.

Disclosed are an indoor navigating system and an indoor navigating method based on vision. The indoor navigating method comprises capturing a material channel image; segmenting the material channel image to obtain a material pushing machine and a walkable area from the material channel image, and determining boundaries of the material pushing machine and boundaries of the walkable area; obtaining a distance between a left boundary of the material pushing machine and a left rail of a material channel and/or a distance between a right boundary of the material pushing machine and a right rail of the material channel; obtaining a lateral deviation distance of the material pushing machine, and determining a course angle; and adjust an actual moving direction of the material pushing machine according to the course angle.

A vehicle row follow system may include a vehicle comprising at least one sensor to output signals serving as a basis for a three-dimensional (3D) point cloud and to output signals corresponding to a two-dimensional (2D) image of a region forward the vehicle. The system may further include a non-transitory computer readable medium containing instructions to direct a processor to: determine plan row lines in a 2D image; determine a yaw of the vehicle based upon a slope of a heading line relative to a centerline between the plant row lines in the 2D image; determine a lateral offset of the vehicle from the centerline between the consecutive plant rows based upon an identity of the consecutive plant rows in the 3D point cloud; and output steering control signals based upon the determined yaw and lateral offset of the vehicle.

An obstruction avoidance system may include a agronomy vehicle, at least one sensor configured to output signals serving as a basis for a three-dimensional (3D) point cloud and to output signals corresponding to a two-dimensional (2D) image, and instructions to direct a processor to capture a particular 2D image and to obtain signals serving as a basis for a particular 3D point cloud; identify an obstruction candidate in the particular 2d image; correlate the obstruction candidate to a portion of the particular 3D point cloud to determine a value for a parameter of the obstruction candidate; classify the obstruction candidate as an obstruction based upon the parameter; and output control signals to alter a state of the agronomy vehicle in response to the obstruction candidate being classified as an obstruction.

A method for assisting a coupling procedure at an agricultural implement interface includes determining via a control unit whether a set-down procedure associated with unhitching the implement is being executed, determining cartographically via the control unit in communication with a position detection unit a set-down location of the implement and a driving trajectory travelled by the agricultural tractor from the set-down location along a defined route, storing via the control unit the set-down location and the driving trajectory as an associated dataset in a memory unit together with type information about the implement provided by an information unit, retrieving via the control unit the associated dataset to re-hitch the implement, and guiding via the control unit the agricultural tractor back from a defined start position along the driving trajectory to the set-down location by issuing associated control commands.

A method for assisting a coupling operation to be carried out at a three-point powerlift of an agricultural tractor includes determining via a control unit in communication with an imaging device using image capture and analysis a spatial actual position of implement-side coupling points of the implement interface relative to the tractor-side coupling points, steering via the control unit the agricultural tractor along a predetermined trajectory into an end position provided for the attachment of the implement, and activating via the control unit the actuator arrangement in accordance with the course of the predetermined trajectory such that the tractor-side coupling points take up a spatial desired position provided for attaching the implement-side coupling points.

A method and system provide the ability to autonomously navigate an orchard cart in an orchard. Data is received from a sensor suite of the orchard cart into a computer. The sensor suite includes two or more sensors with at least one positional sensor and at least one perception sensor. Based on the data, the computer detects objects in the orchard. A row in the orchard consists of the objects. The orchard cart is autonomously navigated, via the computer, through the orchard. The navigation includes autonomously positioning the orchard cart a defined distance from the detected objects with respect to the row, and autonomously maintaining a defined speed of the orchard cart as the orchard cart is navigated down the row, such that the orchard cart avoids the detected object.

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.

A row vision system modifies automated operation of a vehicle based on edges detected between surfaces in the environment in which the vehicle travels. The vehicle may be a farming vehicle (e.g., a tractor) that operates using automated steering to perform farming operations that track an edge formed by a row of field work completed next to the unworked field area. A row vision system may access images of the field ahead of the tractor and apply models that identify surface types and detect edges between the identified surfaces (e.g., between worked and unworked ground). Using the detected edges, the system determines navigation instructions that modify the automated steering (e.g., direction) to minimize the error between current and desired headings of the vehicle, enabling the tractor to track the row of crops, edge of field, or edge of field work completed.

In a steering method for an agricultural machine, the agricultural machine is steered by track steering action independent of GNSS position data along an initial travel track in a working region until a headland adjoining the working region is reached at an exit point of the initial travel track. The agricultural machine is automatically steered by turn steering action, steering it based on an actual position determined based exclusively on GNSS position data, through the headland until an entry point of a target travel track in the working region is reached. The agricultural machine is steered by track steering action along the target travel track. The agricultural machine automatically detects a transition from a travel track of the working region into the headland and/or a transition from the headland into a travel track of the working region and switches accordingly between turn steering action and track steering action.