An apparatus for efficient targeting or removal of weeds or other plants. The apparatus may include a vehicle having a frame, a motor and a plurality of ground engaging members adapted to propel the vehicle over a surface. It may also include a robotic arm comprising a distal portion and a proximal portion coupled to the frame, and an implement, such as a tool or hoe connected to the distal portion of the robotic arm. The implement can be raised and lowered, and also moved relative to the surface by the robotic arm by pivoting or rotating the robotic arm at or near the proximal portion.

An agricultural device associated with reduced tillage techniques in a field includes a frame and at least one mower module supported by the frame, the at least one mower module positionable to cut plant matter between adjacent crop rows in the field. The plant matter has penetrated a previously formed mat of at least partially crushed residual plant matter.

The disclosure relates to a method for processing plants in a field in which a specific type of crop is planted, said method having the following steps: selecting a processing tool for processing plants; acquiring an image of the field, the image being correlated with position information; determining a position of a plant to be processed in the field using a neural network into which the acquired image is input, the neural network having a plurality of heads and in particular one of the heads being evaluated according to the processing tool and/or the type of crop grown; guiding the processing tool to the position of the plants; and processing the plants using the processing tool.

The disclosure relates to a method for processing plants in a field in which a specific type of crop is planted, said method having the following steps: selecting a processing tool for processing plants; acquiring an image of the field, the image being correlated with position information; determining a position of a plant to be processed in the field using a neural network into which the acquired image is input, the neural network having a plurality of heads and in particular one of the heads being evaluated according to the processing tool and/or the type of crop grown; guiding the processing tool to the position of the plants; and processing the plants using the processing tool.

A soil-working device (1) for row crops, comprising: a frame (2) which extends transversely with respect to the direction of travel (F) in a working position and which has a base segment (2A) and at least one boom (2B) which is able to be folded with respect to the base segment (2A); a folding device (3) for moving the at least one foldable boom (2B) between the working position and transport position in which it is folded by at least approximately 90 degrees; and a plurality of tool carriers (6a-6i) which are arranged on the frame via in each case a remotely adjustable height-guiding device (7a-7i), wherein soil-working tools (9a) assigned to individual plant rows (8) are arranged on the tool carriers (6a-6i). To provide a soil-working device which can be moved reliably between the working position and the transport position, there is provision that the folding device (3) and at least the height-guiding devices (7d-7f) of tool carriers (6d-6f) arranged on the base segment (2A) are coupled to one another by means of a, preferably hydraulic, coupling control device in such a way that, for each movement of a boom (2B) from the working position into the transport position, the height-guiding devices (7d-7f) of tool carriers (6d-6f) arranged on the base segment (2A) move the tool carriers (6d-6f) into a position in which they are lowered relative to the frame (2).

A soil-working device (1) for row crops, comprising: a frame (2) which extends transversely with respect to the direction of travel (F) in a working position and which has a base segment (2A) and at least one boom (2B) which is able to be folded with respect to the base segment (2A); a folding device (3) for moving the at least one foldable boom (2B) between the working position and transport position in which it is folded by at least approximately 90 degrees; and a plurality of tool carriers (6a-6i) which are arranged on the frame via in each case a remotely adjustable height-guiding device (7a-7i), wherein soil-working tools (9a) assigned to individual plant rows (8) are arranged on the tool carriers (6a-6i). To provide a soil-working device which can be moved reliably between the working position and the transport position, there is provision that the folding device (3) and at least the height-guiding devices (7d-7f) of tool carriers (6d-6f) arranged on the base segment (2A) are coupled to one another by means of a, preferably hydraulic, coupling control device in such a way that, for each movement of a boom (2B) from the working position into the transport position, the height-guiding devices (7d-7f) of tool carriers (6d-6f) arranged on the base segment (2A) move the tool carriers (6d-6f) into a position in which they are lowered relative to the frame (2).

The invention relates to a method for cultivating row crops (200), comprising the following steps: sensor and satellite based recording of locations and/or courses of rows of plants (202a-202l ) while a first cultivation measure is carried out on a row crop (200) by means of an agricultural plant cultivation device (10) and controlling the movement and/or operation of an agricultural plant cultivation device (10) while a second cultivation measure is carried out on the row crop (200) based on the recorded locations and/or courses of the rows of plants (202a-2021).

Implementations are described herein for analyzing vision data depicting undesirable plants such as weeds to detect various attribute(s). The detected attribute(s) of a particular undesirable plant may then be used to select, from a plurality of available candidate remediation techniques, the most suitable remediation technique to eradicate or otherwise eliminate the undesirable plants.

Implementations are described herein for analyzing vision data depicting undesirable plants such as weeds to detect various attribute(s). The detected attribute(s) of a particular undesirable plant may then be used to select, from a plurality of available candidate remediation techniques, the most suitable remediation technique to eradicate or otherwise eliminate the undesirable plants.

Methods and systems for controlling robotic actions for agricultural tasks are disclosed which use a spacing-aware plant detection model. A disclosed method, in which all steps are computer-implemented, includes receiving, using an imager moving along a crop row, at least one image of at least a portion of the crop row. The method also includes using the at least one image, a plant detection model, and an average inter-crop spacing for the crop row to generate an output from the plant detection model. The plant detection model is spacing aware in that the output of the plant detection model is altered or overridden based on the average inter-crop spacing. The method also includes outputting a control signal for the robotic action based on the output from the biased plant detection model. The method also includes conducting the robotic action for the agricultural task in response to the control signal.