Verdant Robotics, Inc.

Various embodiments relate generally to computer vision and automation to autonomously survey an agricultural environment. In some examples, a system can receive sensor data of a geographic boundary from one or more sensors onboard of the agricultural observation system, detect a plurality of external dynamic objects, a plurality of external static objects, one or more agricultural objects, or a combination thereof from the sensor data, determine a position of a component of the agricultural observation system relative to the plurality of external dynamic objects, the plurality of external static objects, the one or more agricultural objects, or a combination thereof, and generate a local map, in real time, via one or more processing units.

Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include identifying an agricultural object being associated with a subset of agricultural objects, identifying an action corresponding to a subset of agricultural objects responsive, selecting an emitter with which to perform an action associated with the agricultural object, configuring an agricultural projectile delivery system to activate an emitter to propel an agricultural projectile to intercept an agricultural object.

A method of processing agricultural images includes comparing object detections performed by multiple image processing schemes to determine a set of ground truth images from which at least one machine learning (ML) models used by at least one ML algorithm included in the multiple image processing schemes is trained, wherein the multiple image processing schemes include two or more of (a) an image processing scheme that includes a cascade of multiple ML algorithms; (b) an image processing scheme that includes image annotation based on user feedback; or (c) an image processing scheme that includes a cascade of an ML algorithm or a computer vision (CV) algorithm and a user feedback.

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.

A method includes traversing, by the treatment system, along a path in an agricultural environment, receiving, by the treatment system, one or more sensor readings comprising one or more agricultural objects, identifying one or more objects of interest from the one or more agricultural objects by analyzing the one or more sensor readings, determining a first target object of the one or more objects of interest for treatment, selecting a treatment policy to treat the first target object, and activating the treatment mechanism to treat the first target object with the treatment policy.

Various embodiments of apparatuses, methods, systems, and computer program products described herein are directed to a treatment system. An example apparatus includes a treatment apparatus having a first fluid source, one or more channels for delivering a first fluid of the first fluid source, and a treatment unit, the treatment unit having one or more fluid regulators, including a first fluid regulator configured to regulate a flow of the first fluid received by the treatment unit, a movable treatment head unit having one or more spraying tips, a first channel fluidly coupling the one or more spraying tips with the first fluid regulator, wherein the first fluid regulator controls a volume of fluid emitted from the one or more spraying tips, an one or more controllers disposed in the treatment unit configured to control the one or more fluid regulators.

An agricultural treatment system can include one or more motor assemblies, linkage assemblies coupled to the motor assemblies, and a treatment head assembly coupled to the linkage assemblies. Each motor assembly can rotate about a motor assembly rotational axis and each linkage assembly can move in a direction in response to motor assembly rotation about a motor assembly rotational axis. Portions of the treatment head assembly can rotate about one or more treatment head assembly rotational axes in response to linkage assembly movement. The treatment head assembly can include a treatment head, a fluid port that delivers a fluid into the treatment head, spraying tip(s) that spray the fluid onto an agricultural target object, and a fluid regulator that delivers the fluid from the fluid port to the spraying tip(s). The fluid regulator can be coupled to and can rotate with the treatment head, which can be movable.

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. Fluid may be provided through a first pressurized fluid line from a fluid source within an agricultural treatment system to a fluid port of a treatment head assembly of the agricultural treatment system. The fluid may be delivered from the fluid port to one or more spraying tips when the fluid regulator is actuated when in a desired position.

A method includes traversing, by the treatment system, along a path in an agricultural environment, receiving, by the treatment system, one or more sensor readings comprising one or more agricultural objects, identifying one or more objects of interest from the one or more agricultural objects by analyzing the one or more sensor readings, determining a first target object of the one or more objects of interest for treatment, selecting a treatment policy to treat the first target object, and activating the treatment mechanism to treat the first target object with the treatment policy.

Various embodiments of methods, systems, and computer program products described herein are directed to a treatment system. An example method includes identifying a type of a first target agricultural object, based on the identified type of the first target agricultural object, determining a first spray profile for treating the first target agricultural object, sending instructions of a first treatment parameter to a treatment unit, and based on the first spray profile, activating the treatment unit to emit a first fluid at the first target agricultural object, wherein the first fluid regulator is moved to an opened position for an amount of time such that the first fluid is emitted, via the first spraying tip, as a first fluid projectile at the first target agricultural object for a first spray duration.