Implementations set forth herein relate to using fiducial markings on one or more localized portions of an agricultural apparatus in order to generate local and regional data that can be correlated for planning and executing agricultural maintenance. An array of fiducial markings can be disposed onto plastic mulch that surrounds individual crops, in order that each fiducial marking of the array can operate as a signature for each individual crop. Crop data, such as health and yield, corresponding to a particular crop can then be stored in association with a corresponding fiducial marking, thereby allowing the certain data for the particular crop to be tracked and analyzed. Furthermore, autonomous agricultural devices can rely on the crop data, over other sources of data, such as GPS satellites, thereby allowing the autonomous agricultural devices to be more reliable.

A mobile crop monitoring and treatment system includes a vehicle with a propulsion system and multiple sensors mounted on the vehicle. Each sensor is configured to capture data pertaining to at least one plant-related parameter when the sensor is positioned proximate to a plant in a crop. The system also includes a storage system configured to house multiple treatment agents, including at least one chemical pesticide and at least one biological control agent, on-board the vehicle. The system further includes an application system configured to apply one or more of the treatment agents to the plant. In addition, the system includes a controller configured to control movement of the vehicle and operation of the sensors and application system. The controller is configured to cause the application system to apply one or more treatment agents to the plant in response to one or more signals from one or more sensors.

A multi-axis linkage for use with a collapsible boom of an agricultural vehicle is disclosed. The collapsible boom includes a first boom segment having a first truss and a second boom segment having a second truss. The multi-axis linkage includes a first linear motor, a second linear motor, and a multipoint winged link. The first linear motor has a piston rod. An end of the piston rod is coupled to the first truss. The second linear motor has a second piston rod. An end of the second piston rod is coupled to the second truss. The multipoint winged link connects to the first linear motor, the second linear motor, the first boom segment, and the second boom segment.

A precision agriculture implementation method by UAV systems and artificial intelligence image processing technologies provides an unmanned aerial vehicle (UAV), a wireless communication device, a central control unit, and a spray device and a multispectral camera installed to the UAV. The farming area is divided into an array of blocks. The central control unit controls the UAV to fly over the blocks according to navigation parameters and the multispectral camera to capture a multispectral image of each block. A projected leaf area index (PLAI) and a normalized difference vegetation index (NDVI) of each block are calculated by the multispectral image, and a spray control mode of the spray device of the corresponding block is set according to the PLAI and NDVI. The spray device is controlled to spray a water solution, salt solution, fertilizer solution, and/or pesticide solution to the corresponding block according to the spray control mode.

A farming machine includes one or more image sensors for capturing an image as the farming machine moves through the field. A control system accesses an image captured by the one or more sensors and identifies a distance value associated with each pixel of the image. The distance value corresponds to a distance between a point and an object that the pixel represents. The control system classifies pixels in the image as crop, plant, ground, etc. based on the visual information in the pixels. The control system generates a labelled point cloud using the labels and depth information, and identifies features about the crops, plants, ground, etc. in the point cloud. The control system generates treatment actions based on any of the depth information, visual information, point cloud, and feature values. The control system actuates a treatment mechanism based on the classified pixels.

A spray system and method for testing the flow rate of individual nozzles in the spray system are disclosed. The spray system can include a spray tank for holding a fluid to be sprayed, a pump in fluid communication with the spray tank, a manifold in fluid communication with the pump, a plurality of spray nozzles in fluid communication with the manifold, a main flow meter located in a first branch line in fluid communication with the pump and the manifold, a nozzle check flow meter located in a second branch line in fluid communication with the pump and the manifold, and a valve assembly for operating the spray system between a normal operation mode and a nozzle test mode, wherein in the normal operation mode, the valve assembly directs flow to the main flow meter, wherein in the nozzle test mode, the valve assembly directs flow to the nozzle check flow meter.

Implementations are disclosed for a cooling system for cooling sensor packages disposed on an agricultural vehicle, robot, etc. In various implementations, the cooling system includes: a reservoir containing a coolant; one or more sprayers to dispense the coolant from the reservoir at a target; a conduit that fluidly couples the reservoir with the one or more sprayers; and a sensor package that includes at least one processor. At least a portion of the sensor package is in contact with the conduit so that heat is dissipated from the sensor package by the coolant flowing through the conduit.

Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an agricultural observation and treatment system and method of operation. The agricultural treatment system may receive captured sensor data of an agricultural environment by one or more image capture devices, generate a first image from the captured sensor data, detect a first real-world agricultural object from the first image, determine a first pose of the first real-world agricultural object, identify the detected first real-world agricultural object as a new agricultural object or a preidentified agricultural object, and determine a treatment policy associated with the first real-world agricultural object.

The present disclosure provides an agricultural plant protection machine. The machine includes a frame, a liquid storage tank for storing liquid, a pipeline connected to the liquid storage tank, a nozzle, and a pump for pumping the liquid in the liquid storage tank to the nozzle. The pump includes a pump body including a liquid inlet, a liquid outlet, and a pressure relief port; a pressure relief device disposed at the pressure relief port, the pressure relief device including a valve and an elastic reset member, the valve being disposed corresponding to the pressure relief port for sealing the valve. In response to a hydraulic pressure in the pump body exceeding a preset pressure threshold, the valve is separated from the pressure relief port under the force of the liquid and the liquid flows out of the pressure relief port.

A method to reduce bag rupture in an agricultural spray dispensed from a nozzle is disclosed. The method comprises dispensing the agricultural spray from the nozzle. The agricultural spray comprises water, at least one polymer, and at least one perforation-aid type adjuvant. The agricultural spray exhibits fewer fine droplets exhibiting a diameter less than about 150 m formed via the bag rupture approach to droplet formation.