Spacing-aware plant detection model for agricultural task control

A system for controlling a robotic action for an agricultural task comprising:

• a vehicle;
• an agricultural implement on the vehicle, wherein the robotic action is conducted by the agricultural implement;
• an imager;
• one or more processors;
• and
• one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to:
• receive an initial average inter-crop spacing;
• generate, using a plant detection model and the initial average inter-crop spacing, a pair of outputs from the plant detection model;
• determine a measured inter-crop spacing for a crop row using the pair of outputs;
• move the vehicle along the crop row;
• receive, using the imager moving along the crop row with the vehicle, at least one image of at least a portion of the crop row;
• using the at least one image, the plant detection model, and an average inter-crop spacing for the crop row to generate an output from the plant detection model, wherein the average inter-crop spacing for the crop row is based on the measured inter-crop spacing for the crop row;
• output a control signal for the robotic action based on the output from the plant detection model;
• and
• conduct the robotic action for the agricultural task in response to the control signal;
• wherein the plant detection model includes a neural network;
• and
• wherein the robotic action is one of precision harvesting of the crop row, precision weeding of an intercrop area of the crop row, precision watering on the crop row, precision thermal treatment of the intercrop area of the crop row, and precision chemical application on the crop row.

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a system to execute a method for controlling a robotic action for an agricultural task, in which the robotic action is conducted by an agricultural implement on a vehicle comprising:

• receiving an initial average inter-crop spacing;
• generating, using a plant detection model and the initial average inter-crop spacing, a pair of outputs from the plant detection model;
• determining a measured inter-crop spacing for a crop row using the pair of outputs;
• receiving, using an imager moving along the crop row with the vehicle, at least one image of at least a portion of the crop row;
• using the at least one image, the plant detection model, and an average inter-crop spacing for the crop row to generate an output from the plant detection model, wherein the average inter-crop spacing for the crop row is based on the measured inter-crop spacing for the crop row;
• outputting a control signal for the robotic action based on the output from the plant detection model;
• and
• conducting the robotic action for the agricultural task in response to the control signal;
• wherein the plant detection model includes a neural network;
• and
• wherein the robotic action is one of precision harvesting of the crop row, precision weeding of an intercrop area of the crop row, precision watering on the crop row, precision thermal treatment of the intercrop area of the crop row, and precision chemical application on the crop row.