Systems and methods for autonomous crop thinning

Abstract

The present invention provides a system and method for autonomously thinning crops in an agricultural field. The autonomous plant targeting system identifies individual crops in an area, evaluates parameters such as spacing, health, and size, and selects specific crops for thinning based on these parameters. The system can designate crop boundaries around individual crops and select target crops for removal or eradication, such as by laser irradiation, without affecting surrounding plants.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Provisional Application No. 63 / 444,862, filed February 10, 2023, the contents of which are incorporated herein in their entirety.

[0002] All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference.

[0003] The present disclosure relates to systems and methods for autonomous crop removal. [Background technology]

[0004] As technology advances, tasks previously performed by humans are increasingly being automated. Tasks performed in highly controlled environments, such as factory assembly lines, can be automated by instructing machines to perform the task the same way every time, while tasks performed in unpredictable environments, such as agricultural environments, rely on dynamic feedback and adaptation to perform the task. Autonomous systems often struggle with identifying and locating objects in unpredictable environments. Improved methods of object tracking would advance automation technology and increase the ability of autonomous systems to react and adapt to unpredictable environments. Summary of the Invention [Means for solving the problem]

[0005] Summary of the Disclosure In various aspects, the present disclosure provides a method for autonomous crop thinning, the method including: receiving, by a processor, one or more images of a crop field including crops; processing, by the processor, the images using a machine learning model to identify one or more individual crops; determining, by the processor, locations and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the locations, parameters, or both of each of the one or more identified crops; and selecting target crops for removal based on their individual parameters, location relative to the crop boundary, or both.

[0006] In some aspects, the method further includes guiding an autonomous vehicle equipped with a targeting system capable of removing selected target crops. In some aspects, the targeting system includes a laser capable of illuminating the selected target crops. In some aspects, the method further includes removing the selected target crops using the targeting system. In some aspects, removing the selected target crops includes illuminating the target crops using a laser. In some aspects, the method further includes updating the crop boundaries based on real-time feedback from the targeting system. In some aspects, the selection of target crops for removal is based at least on predetermined crop spacing within the crop field. In some aspects, the machine learning model is a convolutional neural network trained to recognize crop characteristics. In some aspects, the parameters of each identified crop include at least one of health, size, or growth stage. In some aspects, the crop boundaries are specified as a geometric shape selected from the group consisting of a rectangle, an ellipse, and a polygon that closely matches the outline of the crop. In some aspects, determining the location of each crop may include generating a virtual representation of an area around each individual crop.

[0007] In various aspects, the present disclosure provides an autonomous plant targeting system comprising: a processor; and a memory having stored thereon instructions that, when executed by the processor, cause the system to perform operations including: receiving, by the processor, one or more images of a crop field including crops; processing, by the processor, the images using a machine learning model to identify one or more individual crops; determining, by the processor, locations and parameters of each of the one or more identified crops; generating, by the processor, a crop boundary around each identified crop based on the locations, parameters, or both of each of the one or more identified crops; and selecting, by the processor, target crops for removal based on their individual parameters, location relative to the crop boundary, or both.

[0008] In some aspects, the machine learning model is a convolutional neural network trained to recognize crop characteristics. In some aspects, the targeting system includes a laser capable of illuminating selected target crops. In some aspects, the system further includes guiding, by a processor, an autonomous vehicle equipped with the targeting system to remove the selected target crops. In some aspects, the autonomous vehicle includes a detection system that dynamically updates a virtual representation of the crop field as the vehicle moves through the field. In some aspects, the autonomous vehicle collects environmental data from the crop field and adjusts removal operations based on the collected data. In some aspects, selecting target crops for removal is further based on predetermined crop spacing within the crop field. In some aspects, the parameters of each identified crop include at least one of health, size, or growth stage. In some aspects, the crop boundary is specified as a geometric shape selected from the group consisting of a rectangle, an ellipse, and a polygon that closely matches the outline of the crop. In some aspects, determining the location of each crop may include generating a virtual representation of an area around each individual crop.

[0009] In various aspects, the present disclosure provides a non-transitory computer-readable medium including computer-executable instructions that, when executed by a computer hardware arrangement, cause the computer hardware arrangement to perform a procedure including receiving one or more images of a crop field including crops; processing the images using a machine learning model to identify one or more individual crops; determining locations and parameters for each of the one or more identified crops; generating crop boundaries around each identified crop based on the locations, parameters, or both of each of the one or more identified crops; and selecting target crops for removal based on their individual parameters, locations relative to the crop boundaries, or both.

[0010] In some aspects, techniques described herein relate to a method for autonomous crop thinning that includes receiving, by a processor, one or more images of a crop field including crops; processing, by the processor, the images using a machine learning model to identify one or more individual crops; determining, by the processor, locations and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the determined locations and parameters of each of the one or more identified crops; and selecting a target crop for removal based on the individual locations and parameters of the one or more identified crops relative to the crop boundary.

[0011] In some aspects, the techniques described herein relate to an autonomous plant targeting system that includes a processor and a memory including stored instructions that, when executed by the processor, cause the system to perform operations including: receiving, by the processor, one or more images of a crop field including crops; processing, by the processor, the images using a machine learning model to identify one or more individual crops; determining, by the processor, locations and parameters of each of the one or more identified crops; generating, by the processor, a crop boundary around each identified crop based on the determined locations and parameters of each of the one or more identified crops; and selecting, by the processor, target crops for removal based on the individual locations and parameters of the one or more identified crops relative to the crop boundary.

[0012] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium including computer-executable instructions that, when executed by a computer hardware arrangement, cause the computer hardware arrangement to perform a procedure including receiving one or more images of a crop field including crops; using a machine learning model to process the images and identify one or more individual crops; determining locations and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the determined locations and parameters of each of the one or more identified crops; and selecting target crops for removal based on the individual locations and parameters of the one or more identified crops relative to the crop boundary. [Brief explanation of the drawings]

[0013] The novel features of the invention are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present invention will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the invention are utilized, and the accompanying drawings.

[0014] [Figure 1] FIG. 1 illustrates an isometric view of an autonomous vehicle for vegetation removal or eradication, according to one or more embodiments herein.

[0015] [Figure 2] FIG. 2 illustrates a top view of an autonomous laser plant targeting vehicle navigating a field of crops while implementing various techniques described herein.

[0016] [Figure 3] FIG. 3 illustrates a side view of a detection system positioned on an autonomous system for plant removal or eradication, according to one or more embodiments herein.

[0017] [Figure 4] FIG. 4 is a block diagram depicting components of a prediction and targeting system for identifying, locating, targeting, and manipulating objects according to one or more embodiments herein.

[0018] [Figure 5] FIG. 5 is a block diagram illustrating components of a detection terminal according to an embodiment of the present disclosure.

[0019] [Figure 6] FIG. 6 is an example block diagram of a computing device architecture of a computing device that may implement various techniques described herein.

[0020] [Figure 7A] FIG. 7A illustrates a boundary region-based plant detection method.

[0021] [Figure 7B] FIG. 7B illustrates a mask-based plant detection method.

[0022] [Figure 8A] FIG. 8A illustrates a virtual representation of a field with crops identified and selected for targeting.

[0023] [Figure 8B] FIG. 8B illustrates a virtual representation of a field including crops identified and selected for targeting, according to one or more embodiments herein.

[0024] [Figure 9A] FIG. 9A is a flow diagram illustrating a method for autonomously thinning crops according to an exemplary embodiment of the present disclosure.

[0025] [Figure 9B] FIG. 9B is a flow diagram illustrating a method for autonomous removal according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0026] Detailed Description Described herein are systems and methods for autonomously thinning and maintaining crops. Crop thinning may include targeting and removing or eradicating selected crops to maintain crop density at a desired level. Reducing crop density may improve the growth or viability of the remaining crops. Crop thinning may be used to offset overplanting practices, which may be performed to compensate for a percentage of planted seeds that fail to germinate. The autonomous crop thinning method of the present disclosure may include identifying and targeting selected crops based on parameters including plant spacing, plant health, plant size, growth stage, or a combination thereof. As described herein, an autonomous plant targeting system may identify and locate crops within an area, evaluate crop parameters (e.g., spacing, health, size, or a combination thereof), select crops for thinning based on one or more of the parameters, and remove or eradicate the selected crops (e.g., by irradiating the crops with a laser). In some embodiments, removal or eradication may include killing the crop, heating the crop, burning the crop, irradiating the crop, cutting the crop, moving the crop, or spraying the crop. Examples of crops that may be thinned using the methods described herein include onions, peppers, strawberries, carrots, corn, soybeans, barley, oats, wheat, alfalfa, cotton, hay, tobacco, rice, sorghum, tomatoes, potatoes, grapes, rice, lettuce, beans, peas, sugar beets, or brassicas (e.g., broccoli, cauliflower, mustard, kale, or Brussels sprouts). In some embodiments, thinning may be performed in parallel with weeding. For example, an autonomous plant targeting system may perform both crop thinning and weeding as it moves through a crop field.

[0027] The technology described in this patent document for autonomous crop thinning represents a substantial advancement over previous agricultural automation technologies. Traditional methods of crop thinning are primarily manual and require substantial human labor, which can be both time-consuming and costly. The system and method described in this patent document address these limitations by introducing a high degree of autonomy and precision in identifying, selecting, and targeting individual crops for thinning. Unlike previous technologies, this autonomous crop thinning system utilizes advanced imaging and predictive analytics to create a virtual representation of the crop field, which allows for dynamic feedback and real-time adaptation to the field's specific conditions. The system's ability to specify crop boundaries and select target crops based on a combination of location, health, and size parameters is a significant improvement over less advanced systems that may not consider such a comprehensive range of factors. Furthermore, the use of laser illumination to target selected crops provides a level of precision that minimizes damage to surrounding crops, a common drawback of bulkier mechanical thinning equipment.

[0028] This technology provides a solution to several technical problems associated with automated crop thinning in unpredictable agricultural environments. One of the primary challenges in automating agricultural tasks is the variability and unpredictability of natural growth patterns and environmental conditions. The autonomous crop thinning system addresses this by incorporating advanced object tracking and identification methods that can adapt to the dynamic nature of crop fields. By generating and continuously updating a virtual representation of the area as the autonomous system moves through the field, this technology ensures that decisions about which crops to thin are based on the most current data, thereby optimizing crop density and health. Another technical problem that this system solves is the difficulty of selectively targeting individual crops without affecting surrounding vegetation. The high-precision targeting enabled by laser technology ensures that the system can remove or eradicate undesirable crops without collateral damage. This level of precision is a technical solution that manual or mechanical methods cannot easily replicate. Additionally, the system's ability to dynamically update average crop size and make thinning decisions based on real-time deviations from this average represents an advanced approach to maintaining crop uniformity and optimizing field yield. In short, the autonomous crop thinning technology described in this patent document provides a comprehensive and precise solution to the challenge of automating crop management tasks in variable and unpredictable environments. Its integration of advanced imaging, predictive analytics, and precision targeting methods represents a significant improvement over past technologies and provides a clear technical solution to the problems facing modern agriculture.

[0029] Described herein are systems and methods for autonomously thinning and maintaining crops. Crop thinning may include targeting and removing or eradicating selected crops to maintain crop density at a desired level. Reducing crop density may improve the growth or viability of the remaining crops. Crop thinning may be used to offset overplanting practices, which may be performed to compensate for a percentage of planted seeds that fail to germinate. The autonomous crop thinning method of the present disclosure may include identifying and targeting selected crops based on parameters including plant spacing, plant health, plant size, growth stage, or a combination thereof. As described herein, an autonomous plant targeting system may identify and locate crops within an area, evaluate crop parameters (e.g., spacing, health, size, or a combination thereof), select crops for thinning based on one or more of the parameters, and remove or eradicate the selected crops (e.g., by irradiating the crops with a laser). Examples of crops that may be thinned using the methods described herein include onions, peppers, strawberries, carrots, corn, soybeans, barley, oats, wheat, alfalfa, cotton, hay, tobacco, rice, sorghum, tomatoes, potatoes, grapes, rice, lettuce, beans, peas, sugar beets, or brassicas (e.g., broccoli, cauliflower, mustard, kale, or Brussels sprouts). In some embodiments, thinning may be performed in parallel with weeding. For example, an autonomous plant targeting system may perform both crop thinning and weeding as it moves through a crop field.

[0030] As used herein, "image" may refer to a representation of an area or object. For example, an image may be a visual representation of an area or object formed by electromagnetic radiation (e.g., light, x-rays, microwaves, or radio waves) scattered from the area or object. In another example, an image may be a point cloud model formed by a light detection and ranging (LIDAR) or radio detection and ranging (RADAR) sensor. In another example, an image may be an ultrasound image produced by detecting sound waves, infrasound, or ultrasound waves reflected from an area or object. As used herein, "imaging" may be used to describe the process of collecting or producing a representation (e.g., an image) of an area or object.

[0031] As used herein, a position, such as the position of an object or the position of a sensor, may be expressed relative to a frame of reference. Exemplary frames of reference include a surface frame of reference, a vehicle frame of reference, a sensor frame of reference, or an actuator frame of reference. Position may be readily converted between frames of reference, for example, by using conversion factors or calibration models. It should be understood that while a position, position change, or offset may be expressed in one frame of reference, a position, position change, or offset may be expressed in any frame of reference or readily converted between frames of reference.

[0032] As used herein, a "sensor" may refer to a device capable of detecting or measuring an event, a change in an environment, or a physical property. For example, a sensor may detect light, such as visible, ultraviolet, or infrared light, and generate an image. Examples of sensors include a camera (e.g., a charge-coupled device (CCD) camera or a complementary metal-oxide semiconductor (CMOS) camera), a LIDAR detector, an infrared sensor, an ultraviolet sensor, or an X-ray detector.

[0033] As used herein, an "object" may refer to an item or distinct area that can be observed, tracked, manipulated, or targeted. For example, an object may be a plant, such as a crop or a weed. In another example, an object may be a piece of debris. In another example, an object may be a distinct region or point on a surface, such as a marking or surface irregularity.

[0034] As used herein, "targeting" or "aiming" may refer to pointing or directing a device or action toward a particular location or object. For example, targeting an object may include pointing a sensor (e.g., a camera) or an instrument (e.g., a laser) toward the object. The targeting or aiming may be dynamic, such that the device or action follows an object that moves relative to the targeting system. For example, a device positioned on a movable vehicle may dynamically target or aim at an object located on the ground by following the object as the vehicle moves relative to the ground.

[0035] As used herein, a "weed" may refer to an undesirable plant, such as an undesirable type of plant or a plant growing in an undesirable place or at an undesirable time. For example, a weed may be a wild or invasive plant. In another example, a weed may be a plant within a cultivated crop field that is not a cultivated species. In another example, a weed may be a plant growing outside or between the rows of a crop. As used herein, a "crop" may be a cultivated plant.

[0036] As used herein, "manipulating" an object may refer to performing an action on the object, interacting with the object, or altering the state of the object. For example, manipulating may include illuminating the object, illuminating the object, heating the object, burning the object, killing the object, moving the object, lifting the object, grasping the object, spraying the object, or otherwise modifying the object.

[0037] As used herein, "electromagnetic radiation" may refer to radiation across the electromagnetic spectrum, which may include, but is not limited to, visible light, infrared light, ultraviolet light, radio waves, gamma rays, or microwaves. Autonomous Plant Targeting System

[0038] The object tracking methods described herein may be implemented by an autonomous plant targeting system to target and eliminate selected plants. Such tracking methods may facilitate object tracking for a moving body, such as a mobile vehicle. For example, the autonomous plant targeting system may be used to track an identified plant of interest in images or representations collected over time by a first sensor, such as a predictive sensor, for the autonomous plant targeting system while the system is in motion relative to the plant. The tracking information may be used to determine the plant's predicted location relative to the system at a later time. The autonomous plant targeting system may then use the predicted location to locate the same plant in images or representations collected by a second sensor, such as a targeting sensor. In some embodiments, the first sensor is a predictive camera and the second sensor is a targeting camera. One or both of the first and second sensors may move relative to the plant. For example, the predictive camera may be coupled to the autonomous plant targeting system and move along with it.

[0039] Targeting the plant may include precisely locating the plant using a targeting sensor, targeting the plant with a laser, and removing or eradicating the plant by burning it with laser light, such as infrared light. The prediction sensor may be part of a prediction module configured to determine a predicted location of the object of interest, and the targeting sensor may be part of a targeting module configured to refine the predicted location of the object of interest, determine a target location, and target the object of interest at the target location using a laser. The prediction module may be configured to communicate with the targeting module and coordinate camera handoff using point-to-point targeting, as described herein. The targeting module may target the object at the predicted location. In some embodiments, the targeting module may dynamically target the object using the object's trajectory while the system is in motion, such that the position of the targeting sensor, the laser, or both is adjusted to maintain the target.

[0040] The autonomous plant targeting system may identify targets and remove plants without human input. Optionally, the autonomous plant targeting system may be located on an autonomous or driverless vehicle, or may be a trailer pulled by another vehicle, such as a tractor. As illustrated in FIG. 1 , the autonomous plant targeting system may be part of or coupled to a vehicle 100, such as a tractor or autonomous vehicle. The vehicle 100 may drive through a crop field 200, as illustrated in FIG. 2 . As the vehicle 100 drives through the crop field 200, it may identify targets and remove or eradicate plants in an unmaintained section 210 of the field, leaving a maintained section 220 behind. The object tracking methods described herein may be implemented by the autonomous plant targeting system to identify targets and remove or eradicate plants while the vehicle 100 is under motion. Such highly accurate tracking methods allow for precise targeting of plants, such as with lasers, to remove or eradicate them without damaging nearby crops. U.S. Patent No. 11,602,143 (incorporated by reference) describes an autonomous targeting system that can be used to implement the methods of the present disclosure.

[0041] While the primary focus of this patent application is on plant identification, selection, and targeting for autonomous crop thinning purposes, the underlying technology is not limited to plant detection. The system's advanced imaging and predictive analytics capabilities are designed to identify and locate objects in unpredictable environments, which inherently enables the detection of a wide range of objects other than plants. The described methods and systems are capable of distinguishing and tracking any distinguishable item or area that can be observed within their field of operation. This includes, but is not limited to, debris, infrastructure elements, or other items that may be present in agricultural settings. The flexibility and adaptability of the system's object tracking technology allows it to be applied to a variety of scenarios in which autonomous detection and manipulation of objects is beneficial. Thus, while this application primarily illustrates the system's usefulness in an agricultural context, the object detection and targeting principles and mechanisms it employs can be generalized to other applications in which identifying and interacting with various objects is essential.

[0042] In some embodiments, the object tracking methods described herein may be implemented by a detection system. The detection system may include a prediction system and, optionally, a targeting system. In some embodiments, the detection system may be positioned on or coupled to a vehicle, such as an autonomous plant targeting vehicle or a plant targeting trailer pulled by a tractor. The prediction system may include a prediction sensor configured to image an area of ​​interest, and the targeting system may include a targeting sensor configured to image a portion of the area of ​​interest. The imaging may include collecting a representation (e.g., an image) of the area of ​​interest or a portion of the area of ​​interest. In some embodiments, the prediction system may include two or more prediction sensors, allowing coverage of a larger area of ​​interest. In some embodiments, the targeting system may include two or more targeting sensors.

[0043] The region of interest may correspond to a region of overlap between the targeted sensor field of view and the predicted sensor field of view. Such overlap may be simultaneous or temporally separated. For example, the predicted sensor field of view encompasses the region of interest at a first time, and the targeted sensor field of view encompasses the region of interest at a second time that is not the first time. Optionally, the detection system may move relative to the region of interest between the first time and the second time to facilitate temporally separated overlap of the predicted sensor field of view and the targeted sensor field of view.

[0044] In some embodiments, the predictive sensor may have a wider field of view than the targeting sensor. The predictive system may further comprise an object identification module to identify an object of interest in the predicted image or representation collected by the predictive sensor. The object identification module may distinguish the object of interest from other objects in the predicted image.

[0045] The prediction module may determine a predicted location of the object of interest and may transmit the predicted location to the targeting system. The predicted location of the object may be determined using the object tracking methods described herein.

[0046] The targeting system may direct the targeting sensor toward a desired portion of the region of interest predicted to contain the object based on the predicted location received from the prediction system. In some embodiments, the targeting module may direct an instrument toward the object. In some embodiments, the instrument may perform an action on or manipulate the object. In some embodiments, the targeting module may dynamically target the object using the object's trajectory while the system is in motion, such that the position of the targeting sensor, the instrument, or both, is adjusted to maintain the target. U.S. Patent Application No. 17 / 576,814 (incorporated by reference) describes machine learning models for automated identification, maintenance, control, or targeting of objects.

[0047] An example of a detection system 300 is provided in FIG. 3 . The detection system may be part of or coupled to a vehicle 100, such as an autonomous plant targeting vehicle or a tractor-pulled laser plant targeting system trailer, moving along a surface, such as a crop field 200. The detection system 300 includes a prediction module 310 including a prediction sensor with a predicted field of view 315, and a targeting module 320 including a targeting sensor with a targeting field of view 325. The targeting module may further include an instrument, such as a laser, with a target area that overlaps with the targeting field of view 325. In some embodiments, the prediction module 310 is positioned ahead of the targeting module 320 along the direction of travel of the vehicle 100 such that the targeting field of view 325 overlaps with the predicted field of view 315 with a time delay. For example, the predicted field of view 315 at a first time may overlap with the targeting field of view 325 at a second time. In some embodiments, the predicted field of view 315 at the first time may not overlap with the targeted field of view 325 at the first time.

[0048] The prediction module is primarily responsible for the initial identification and tracking of objects. It utilizes a prediction sensor, which may be a camera or another type of imaging device, to capture an image or representation of the area of ​​interest. This module processes the collected data, generates a virtual representation of the area, and identifies the location and parameters of individual objects, such as crops, within that space.

[0049] Once the object is identified and its trajectory is predicted, the prediction module communicates this information to the targeting module. The targeting module is equipped with a targeting sensor that receives the object's predicted location from the prediction module. Using this data, the targeting module can then precisely aim an instrument, such as a laser, at the object. The targeting sensor ensures that the instrument is accurately aimed toward the object's current or future location, taking into account any movement of the object or the autonomous system itself. The prediction module's ability to predict the object's location allows the targeting module to compensate for any delay between object identification and the moment of action, ensuring that targeting is precise and effective. This coordination is particularly useful when the autonomous system is in motion, as it allows dynamic adjustments to be made in real time and ensures that targeting remains accurate despite any changes in the relative positions of the system and the object.

[0050] In other exemplary embodiments, the system does not require the predictive system to be physically located in front of the targeting system. The primary objective is to ensure that the field of view of the predictive system precedes the field of view of the targeting system in the direction of movement of the system, enabling timely prediction and subsequent targeting of the object. By way of non-limiting example, in other exemplary embodiments, the predictive sensor may be angled in such a way that its field of view extends further forward in the path of travel, even if the sensor itself is not positioned at the forefront point of the system. This flexibility in sensor arrangement is particularly advantageous in scenarios where space constraints or design considerations dictate a more compact or nonlinear configuration of system components.

[0051] The detection systems of the present disclosure may be used to target objects on surfaces such as the ground, soil surface, floor, wall, agricultural surface (e.g., field), lawn, road, embankment, pile, or depression. In some embodiments, the surface may be a non-planar surface such as uneven ground, uneven terrain, or a textured floor. For example, the surface may be uneven ground in a construction site, agricultural field, or mining tunnel, or the surface may be uneven terrain including a field, road, forest, hill, mountain, house, or building. The detection systems described herein may locate objects on non-planar surfaces more accurately, more quickly, or within a larger area than single-sensor systems or systems lacking an object matching module.

[0052] Alternatively, or in addition, the detection system may be used to target objects that may be spaced apart from the surface on which they rest, such as a tree canopy, spaced apart from its base, and / or that may be locatable relative to the surface, e.g., relative to the ground surface in the air or atmosphere. Additionally, the detection system may be used to target objects that may move relative to the surface, such as vehicles, animals, humans, or flying objects.

[0053] FIG. 4 illustrates a detection system including a prediction system 400 and a targeting system 450 for tracking object O when targeting it relative to a moving body, such as vehicle 100 illustrated in FIGS. 1-3 . Prediction system 400, targeting system 450, or both may be positioned on or coupled to the moving body (e.g., the moving vehicle). Prediction system 400 may include a prediction sensor 410 configured to image an area, such as an area of ​​a surface including one or more objects, including object O. Optionally, prediction system 400 may include a velocity tracking module 415. The velocity tracking module may estimate the velocity of the moving body relative to the area (e.g., the surface). In some embodiments, velocity tracking module 415 may include a device for measuring the displacement of the moving body over time, such as a rotary encoder. Alternatively, or in addition, the velocity tracking module may use images collected by prediction system 400 to estimate velocity using optical flow.

[0054] The object identification module 420 may identify objects in images collected by the predictive sensor. For example, the object identification module 420 may identify plants in the images and distinguish the plants from other plants in the images, such as crops. The object localization module 425 may determine the locations of objects identified by the object identification module 420 and compile a set of identified objects and their corresponding locations. Object identification and object localization may be performed over time on a series of images collected by the predictive sensor 410. Sets of identified objects and corresponding locations from two or more images from the object localization module 425 may be sent to the de-duplication module 430.

[0055] In some embodiments, the object identification module 420 may employ a machine learning model, which is trained to identify specific features of objects based on a large dataset of labeled images. The training process involves feeding the model numerous example images containing objects of interest, along with annotations that describe the objects' content and their location within the image. For example, in the context of crop thinning, the model may learn to recognize the shapes, colors, textures, and sizes of various crops and weeds. The model is trained to distinguish between these plants and identify weeds or overgrown crops that can be targeted for removal from crops that should be saved. Once trained, the object identification module 420 can process new images from the predictive sensor, apply learned patterns, and identify objects in real time. This allows it to distinguish objects of interest from the background and other objects not relevant to the task at hand. The module may use various machine learning techniques, such as convolutional neural networks (CNNs).

[0056] The de-duplication module 430 may use object locations in a first image collected at a first time and object locations in a second image collected at a second time to identify objects, such as object O, that appear in both the first image and the second image. The set of identified objects and corresponding locations may be deduplicated by the de-duplication module 430 by assigning object locations that appear in both the first image and the second image to the same object O. In some embodiments, the de-duplication module 430 may use speed estimates from the speed tracking module 415 to identify corresponding objects that appear in both images. The resulting de-duplicated set of identified objects may each include unique objects having one or more corresponding locations determined at one or more time points.

[0057] Machine learning can be applied to this process by using a model that recognizes and matches object features across different images. For example, a machine learning model can be trained on a dataset of sequential images in which an object of interest moves or changes appearance slightly. The model will learn to associate different instances of the same object across these images despite variations in viewpoint, lighting, or partial occlusion. Such a model can use techniques such as feature matching and object tracking algorithms that are robust to changes in the object's environment. By learning the typical movement patterns or changes in appearance of objects within a scene, the deduplication module can more accurately determine when different images feature the same object, thereby reducing the likelihood of counting the object more than once.

[0058] The adjustment module 435 may receive the deduplicated set of objects from the de-duplication module 430 and may adjust the deduplicated set by removing objects. In some embodiments, objects may be removed if they are no longer being tracked. For example, an object may be removed if it has not been identified in a predetermined number of images in a sequence of images. In another example, an object may be removed if it has not been identified within a predetermined period of time. In some embodiments, an object that no longer appears in images collected by the predictive sensor 410 may continue to be tracked. For example, an object may continue to be tracked if it is expected to be within the predicted field of view based on the object's predicted location. In another example, an object may continue to be tracked if it is expected to be within range of a targeting system based on the object's predicted location. The adjustment module 435 may provide the adjusted set of objects to the location prediction module 440.

[0059] The coordination module is responsible for maintaining an accurate and current list of tracked objects. It removes objects that are no longer relevant, such as those that have not been detected for a set period of time or number of frames. Machine learning can aid this process by predicting objects that are likely to reappear based on their last known trajectory and typical behavior of objects in the environment. Predictive machine learning models can analyze objects' movement patterns and predict their future locations. If an object temporarily disappears from view, perhaps due to occlusion or moving out of frame, the model can estimate the likelihood of its return. This will allow the coordination module to make informed decisions about whether to continue tracking an object or remove it from the list, optimizing system resources and attention.

[0060] The location prediction module 440 may determine a predicted location of the object O at a future time from the adjusted set of objects. In some embodiments, the predicted location may be determined from two or more corresponding locations determined from images collected at two or more time points, or from a single location combined with speed information from the speed tracking module 415. The predicted location of the object O may be based on a vector velocity including the speed and direction of the object O relative to the moving body between the location of the object O in a first image collected at a first time and the location of the object O in a second image collected at a second time. Optionally, the vector velocity may take into account the distance of the object O from the moving body along the imaging axis (e.g., the height or elevation of the object relative to the surface). Alternatively, or in addition, the predicted location of the object may be based on the location of the object O in the first image or the second image and the vector velocity of the vehicle determined by the speed tracking module 415.

[0061] Targeting system 450 may receive the predicted location of object O at a future time from prediction system 400 and may use the predicted location to precisely target the object with instrument 475 at a future time. Targeting control module 460 of targeting system 450 may receive the predicted location of object O from location prediction module 440 of prediction system 400 and may instruct targeting sensor 465, instrument 475, or both to point toward the predicted location of the object. Optionally, targeting sensor 465 may collect images of object O, and location refinement module 470 may refine the predicted location of object O based on the location of object O determined from the images. In some embodiments, location refinement module 470 may account for optical distortion in images collected by prediction sensor 410 or targeting sensor 465, or distortion in the angular motion of instrument 475 or targeting sensor 465 due to nonlinearities in the angular motion relative to object O. The targeting control module 460 may command the instrument 475, and optionally the targeting sensor 465, to point towards the refined location of the object O. In some embodiments, the targeting control module 460 may adjust the position of the targeting sensor 465 or the instrument 475 to account for the vehicle's motion while following and targeting the object. An instrument 475, such as a laser, may then manipulate the object O. For example, the laser may direct infrared light towards the predicted or refined location of the object O. The object O may be a plant, and directing infrared light towards the location of the plant may remove or eradicate the plant.

[0062] In some embodiments, the prediction system 400 may further include a scheduling module 445. The scheduling module 445 may select objects identified by the prediction module and schedule them to be targeted using the targeting system. The scheduling module 445 may schedule objects for targeting based on parameters such as object location, relative velocity, instrument activation time, confidence score, or a combination thereof. For example, the scheduling module 445 may prioritize targeting objects predicted to move outside the field of view of a prediction sensor or targeting sensor or outside the range of an instrument. Alternatively, or in addition, the scheduling module 445 may prioritize targeting objects identified or located with high confidence. Alternatively, or in addition, the scheduling module 445 may prioritize targeting objects with short activation times. In some embodiments, the scheduling module 445 may prioritize targeting objects based on user-preferred parameters.

[0063] The targeting system, including the targeting control module and targeting sensor, can be designed to handle multiple targets by scheduling targeting sequences based on various parameters such as object location, relative speed, and instrument activation time. The scheduling module 445 can prioritize objects and organize the targeting sequence to efficiently transition between multiple targets. For the targeting sensor to engage multiple targets at once, it can utilize a high-speed point-to-point movement system to quickly redirect the laser or other instrument from one target to the next. Alternatively, if the technology allows, the instrument can be a multi-beam laser, capable of splitting its focus and targeting several locations in succession, or even simultaneously, depending on the spatial arrangement of the targets and the capabilities of the laser system. Advanced algorithms within the targeting control module will generate precise timing and movement patterns to align the laser with each predicted location of the object. This will allow the targeting sensor to follow a predetermined path that intersects with the object in a timely manner, taking into account the continuous movement of the autonomous plant targeting system through the field. Prediction Module

[0064] A prediction module of the present disclosure may be configured to track an object relative to a moving body using the tracking methods described herein. In some embodiments, the prediction module is configured to use a predictive camera or predictive sensor to capture an image or representation of a region of a surface, identify an object of interest in the image, and determine a predicted location of the object.

[0065] The prediction module may include an object identification module configured to identify an object of interest and distinguish the object of interest from other objects in the predicted image. In some embodiments, the prediction module uses a machine learning model to identify and distinguish objects based on features extracted from a training dataset comprising labeled images of the objects. For example, a machine learning model of or associated with the object identification module may be trained to identify plants and distinguish plants of interest from other plants, such as crops. In another example, a machine learning model of or associated with the object identification module may be trained to identify debris and distinguish debris from other objects. The object identification module may be configured to identify plants and distinguish between different plants, such as between crops and weeds. In some embodiments, the machine learning model may be a deep learning model, such as a deep learning neural network.

[0066] In some embodiments, the object identification module includes using a discriminative machine learning model, such as a convolutional neural network. The discriminative machine learning model may be trained using many images, such as high-resolution images of surfaces, with or without an object of interest. For example, the machine learning model may be trained using images of a field, with or without weeds. Once trained, the machine learning model may be configured to identify a region within the image that contains the object of interest. The region may be defined by a polygon, e.g., a rectangle. In some embodiments, the region is a bounding box. In some embodiments, the region is a polygonal mask that covers the identified region. In some embodiments, the discriminative machine learning model may be trained to determine the location of the object of interest, e.g., a pixel location within a predicted image.

[0067] The prediction module may further comprise a speed tracking module to which the prediction module is coupled to determine the speed of the vehicle. In some embodiments, the positioning system and the detection system may be located on the vehicle. Alternatively, or in addition, the positioning system may be located on the vehicle and spatially coupled to the detection system. For example, the positioning system may be located on the vehicle to tow the detection system. The speed tracking module may comprise a positioning system, such as a wheel encoder or rotary encoder, an inertial measurement unit (IMU), a global positioning system (GPS), a ranging sensor (e.g., laser, sonar, or radar), or an internal navigation system (INS). For example, a wheel encoder in communication with the vehicle's wheels may estimate speed or distance traveled based on angular frequency, rotation frequency, rotation angle, or number of wheel rotations. In some embodiments, the speed tracking module may utilize images from the prediction sensor to determine the vehicle's speed using optical flow.

[0068] The prediction module may comprise a system controller, e.g., a system computer having storage, random access memory (RAM), a central processing unit (CPU), and a graphics processing unit (GPU). The system computer may comprise a tensor processing unit (TPU). The system computer may comprise sufficient RAM, storage space, CPU power, and GPU power to perform operations for detecting and identifying targets. The prediction sensor may provide images with sufficient resolution to perform operations for detecting and identifying objects. In some embodiments, the prediction sensor may be a camera, such as a charge-coupled device (CCD) camera or a complementary metal-oxide semiconductor (CMOS) camera, a LIDAR detector, an infrared sensor, an ultraviolet sensor, an X-ray detector, or any other sensor capable of generating images. Targeting Module

[0069] The targeting module of the present disclosure may be configured to target an object tracked by the prediction module. In some embodiments, the targeting module may point an instrument toward the object to manipulate the object. For example, the targeting module may be configured to point a laser beam toward a plant to burn the plant. In another example, the targeting module may point a gripping tool to grasp the object. In another example, the targeting module may point a spraying tool to spray a fluid at the object. In some embodiments, the object may be a weed, a plant, an insect, a pest, a field, a piece of debris, an obstacle, an area of ​​a surface, or any other object that can be manipulated. The targeting module may be configured to receive a predicted location of the object of interest from the prediction module and point a targeting camera or targeting sensor toward the predicted location. In some embodiments, the targeting module may point an instrument, such as a laser, toward the predicted location. The position of the targeting sensor and the position of the instrument may be coupled. In some embodiments, two or more targeting modules communicate with the prediction module.

[0070] The targeting module may include a targeting control module. In some embodiments, the targeting control module may control the targeting sensor, the instrument, or both. In some embodiments, the targeting control module may include an optical control system including optical components configured to control an optical path (e.g., a laser beam path or a camera imaging path). The targeting control module may include software-driven electrical components capable of controlling the activation and deactivation of the instrument. Activation or deactivation may depend on the presence or absence of an object as detected by the targeting camera. Activation or deactivation may depend on the position of the instrument relative to the target object location. In some embodiments, the targeting control module may activate an instrument, such as a laser emitter, when an object is identified and located by the prediction system. In some embodiments, the targeting control module may activate an instrument when the instrument's range or target area is positioned to overlap the target object location.

[0071] The targeting control module may deactivate the instrument once the object is manipulated, such as grasped, sprayed, burned, or irradiated, an area comprising the object may be targeted with the instrument, the object is no longer identified by the target prediction module, a specified period of time has passed, or any combination thereof. For example, the targeting control module may deactivate the emitter once an area on a surface comprising vegetation has been scanned by the beam, once the vegetation has been irradiated or burned, or once the beam has been activated for a predetermined period of time.

[0072] The prediction module and targeting module described herein may be used in combination to locate, identify, and target an object with an instrument. The targeting control module may comprise an optical control system as described herein. The prediction module and targeting module may be in communication, e.g., electrical or digital communication. In some embodiments, the prediction module and targeting module are coupled directly or indirectly. For example, the prediction module and targeting module may be coupled to a support structure. In some embodiments, the prediction module and targeting module are configured on or coupled to a vehicle, such as the vehicle shown in FIGS. 1 and 2. For example, the prediction module and targeting module may be located on an autonomous vehicle. In another example, the prediction module and targeting module may be located on a trailer towed by another vehicle, such as a tractor.

[0073] The targeting module may include a system controller, e.g., a system computer having storage, random access memory (RAM), a central processing unit (CPU), and a graphics processing unit (GPU). The system computer may include a tensor processing unit (TPU). The system computer may have sufficient RAM, storage space, CPU power, and GPU power to perform operations for detecting and identifying targets. The targeting sensor may provide images of sufficient resolution to match objects to objects identified in the predicted image. Autonomous Crop Thinning

[0074] The autonomous crop thinning method of the present disclosure may include automated targeting and removal of selected crops to reduce crop density to a desired level. The selection of crops for thinning may be based on various plant parameters, such as spacing, health, size, growth stage, or a combination thereof. The autonomous plant targeting system of the present disclosure may be used to identify plants within an area (e.g., a crop field), determine the location of the plants within the area, and determine plant parameters.

[0075] During autonomous crop thinning, plants may be identified and tracked over time as the autonomous plant targeting system moves through the crop field, creating a virtual area that may be updated in real time, as illustrated in FIGS. 8A and 8B. In some embodiments, the virtual area may be generated based on imagery from one or more sensors (e.g., a predictive sensor, a targeting sensor, or a combination thereof). The virtual area may represent the location of the crop relative to the autonomous plant targeting system. Plants identified in the imagery may be combined into the virtual area to replicate the plants to be removed. Crops may be identified and selected for thinning based on the location of the crop within the virtual area, determined parameters of the crop, or both. For example, crops may be thinned to a desired spacing. The desired spacing may depend on the crop type. In another example, crops may be thinned based on crop health, such that unhealthy crops are thinned.

[0076] An example of a method for autonomous crop thinning is described with reference to FIGS. 8A and 8B. FIGS. 8A and 8B illustrate a virtual representation of an area 810 (e.g., a crop field), with the location of a crop 820 marked with a blue circle. In FIGS. 8A and 8B, the crops tend to be along rows corresponding to the crop seeding rows. Crop arrangement and distribution may vary depending on the planting style or arrangement, and the methods described herein are not limited to a particular crop arrangement. As the autonomous plant targeting system moves through the crop field, crops may be identified and added to the virtual representation to be tracked. As crops are tracked, the autonomous plant targeting system may determine whether the crop should be targeted for thinning. The determination may be made based on crop location, proximity to other crops, crop health, growth stage, or crop size. In some embodiments, the evaluation may be performed by a greedy algorithm, which may include tracking the crop until a point in the tracking space is reached (e.g., a location in the virtual region, a location relative to the targeting system, or a tracking duration), and then evaluating whether the crop should be thinned. The evaluation may be based on crop boundary collisions, crop size, or location of the crop within the region of interest. In some embodiments, the evaluation for the crop may be informed by location, parameters, and / or evaluations of previously evaluated crops.

[0077] In some embodiments, the evaluation of whether a crop should be thinned may be performed based on a crop boundary. The boundary may be specified around the crop based on the size of the crop, the type of crop, the shape of the crop, user input, or a combination thereof. The boundary may represent a space surrounding the crop that is sufficient for the crop to grow and reach full maturity. The boundary may be any geometric or irregular shape. For example, as illustrated in FIG. 8B, the crop boundary 830 may be rectangular (e.g., square), or the crop boundary 840 may be oval (e.g., circular). Additional examples of rectangular crop boundaries are provided in FIG. 7A. In some embodiments, the crop boundary may be based on the shape of the crop, for example, as illustrated in FIG. 7B. Crops located within the crop boundary that will not be thinned may be selected for thinning. FIG. 8B illustrates an example of a rectangular boundary around the plant being evaluated (left) and a circular boundary around the plant being evaluated (right). Crops other than the crop being evaluated that fall within the boundary are selected for thinning, indicated by an X. Selected crops may be targeted and killed (eg, by irradiating the selected crops with a laser).

[0078] FIG. 9A is a flow diagram illustrating a method 900 for autonomously thinning crops according to an exemplary embodiment of the present disclosure. Method 900 may begin at step 910. In step 910, an image of a crop field including crops is received (e.g., by an autonomous targeting system). In step 915, the image is processed to identify individual crops. The identified individual crops may be of a single type of crop (e.g., onion, pepper, strawberry, carrot, corn, soybean, barley, oats, wheat, alfalfa, cotton, hay, tobacco, rice, sorghum, tomato, potato, grape, rice, lettuce, green beans, peas, sugar beet, or brassica). In step 920, locations and / or parameters are determined for each identified crop. The determined parameters may include one or more of plant spacing, plant health, plant size, or growth stage. In step 925, a boundary is generated around each of the identified crops. The boundary may be delineated based on crop location, parameters, or both. The boundary may be a geometric shape (e.g., a rectangle, an oval, or a polygon). The boundary may closely match the contours of the crops. In step 930, target crops corresponding to a subset of the identified crops are selected for removal. The selected target crops may be selected based on their individual location, parameters, or both. For example, the target crops selected for removal may be selected to achieve a desired crop density after removal. Alternatively, or in addition, the target crops may be selected to remove crops with poor health. Alternatively, or in addition, the target crops may be selected to achieve a narrow distribution of growth stages after removal. In step 935, the selected crops are removed (e.g., using method 950 provided in FIG. 9B).

[0079] 9B is a flow diagram illustrating a method 950 of autonomous removal according to an exemplary embodiment of the present disclosure. Method 950 may begin at step 952. In step 952, a targeting system is directed toward crops selected for removal (e.g., selected as shown in method 900 provided in FIG. 9A). In step 954, the selected crops are removed using the targeting system. For example, the targeting system may direct a laser beam toward the selected crops and remove the crops by burning them with the laser beam. U.S. Pat. No. 11,602,143 (incorporated by reference) describes an autonomous targeting system that may be used to implement method 950.

[0080] The initial generation of crop boundaries may involve the following steps: images of the target objects may be obtained. High-resolution images or scans of the crop field are captured using cameras or sensors mounted on the autonomous plant targeting system. Machine learning algorithms, such as convolutional neural networks (CNNs), analyze the images and identify individual crops. These algorithms are trained on datasets of labeled images and can recognize crop characteristics such as shape, color, and texture. Once the crops are identified, an initial geometric boundary is estimated. This can be a simple shape, such as a rectangle or oval, that encompasses the visible area of ​​the crop. The initial boundary may also be based on a standard geometric shape that provides a conservative estimate of the space the crop requires to grow and ensures that the crop is not obstructed by neighboring plants. To refine these boundaries and better conform to the actual shape of the plants, the following techniques can be employed: image processing techniques, such as edge detection, can be used to identify the precise outline of each crop. This helps adjust the boundary to match the actual shape of the crop. Additionally, advanced segmentation methods can separate the crop from the background and other plants, allowing for boundaries that follow the silhouette of the crop.

[0081] Algorithms and machine learning can also further adapt the shape of the bounding box to better fit the real-world shape of the object. For example, an algorithm can fit a complex polygon or spline curve around the detected edge of the crop to create a boundary that more accurately represents the occupied space. Machine learning models can also be trained in a feedback loop to improve boundary accuracy over time, learning from instances where the initial boundary was too large or too small. In some systems, a user may provide input and manually adjust the boundary, which can be incorporated into the machine learning model as additional training data. As the autonomous plant targeting system operates over time, it collects more data and can dynamically adapt the boundary, i.e., the system can use real-time feedback from the thinning process to adjust the boundary for subsequent operation. By tracking plant growth over time, the system can adjust the boundary to accommodate changes in plant size and shape.

[0082] In some embodiments, the evaluation of whether a crop should be thinned may be based on crop size. Size may be evaluated against other plants in the area, expected plant size based on crop type and maturity, or a combination thereof. In some embodiments, the evaluation may be based on the average size of previously evaluated plants in the area. The average size may be determined dynamically. For example, the average size may be determined by first sampling a configurable number of crops in the area (e.g., about 50 crops) and establishing a baseline for the average size. Once a baseline average is determined, the size of subsequently evaluated crops may be assessed based on their deviation from the average size. Crops that fall outside an acceptable deviation from the average size may be selected for thinning. For example, if a crop is more than about 20% smaller than the average or more than about 20% larger than the average, the crop may be selected for thinning. The acceptable size deviation may be adjusted based on crop type or other parameters, or based on user preference. Crop sizes determined to be valid (e.g., crops not selected for thinning) may be added to a moving average and used to evaluate future crops.

[0083] In some embodiments, crop assessment and thinning may be limited to an area of ​​interest (e.g., a band). Crops that fall outside the designated band may be ignored by the autonomous plant targeting system and instead maintained by traditional crop maintenance methods.

[0084] Additional methods may be used to determine which crops to target for thinning. In some embodiments, crops may be assessed one at a time. In some embodiments, assessment may be performed for multiple crops based on a global arrangement of crops within a region or sub-region. Optical Control System

[0085] The methods described herein may be implemented by an optical control system, such as a laser optical system, to target an object of interest. For example, the optical system may be used to target an object of interest identified in an image or representation collected by a first sensor, such as a predictive sensor, and to locate the same object in an image or representation collected by a second sensor, such as a targeting sensor. In some embodiments, the first sensor is a predictive camera and the second sensor is a targeting camera. Targeting the object may include using the targeting sensor to precisely locate the object and targeting the object with an instrument.

[0086] Described herein is an optical control system for directing a beam, e.g., a light beam, toward a target location on a surface, such as the location of an object of interest. In some embodiments, the instrument is a laser. However, other instruments are also within the scope of this disclosure, including, but not limited to, a gripping instrument, a spraying instrument, a planting instrument, a harvesting instrument, a pollinating instrument, a marking instrument, a blowing instrument, or a depositing instrument.

[0087] In some embodiments, the emitter is configured to direct the beam along an optical path, e.g., a laser path. In some embodiments, the beam comprises electromagnetic radiation, e.g., light, radio waves, microwaves, or x-rays. In some embodiments, the light is visible light, infrared light, or ultraviolet light. The beam may be coherent. In one embodiment, the emitter is a laser, such as an infrared laser.

[0088] One or more optical elements may be positioned in the path of the beam. The optical elements may include a beam combiner, a lens, a reflective element, or any other optical element that may be configured to direct, focus, filter, or otherwise control light. The elements may be configured around a beam combiner, followed in the direction of the beam path by a first reflective element, followed by a second reflective element. In another example, one or both of the first reflective element or the second reflective element may be configured before the beam combiner in the direction of the beam path. In another example, the optical elements may be configured in the order of the beam combiner, followed in the direction of the beam path by the first reflective element. In another example, one or both of the first reflective element or the second reflective element may be configured before the beam combiner in the direction of the beam path. Any number of additional reflective elements may be positioned in the beam path.

[0089] The beam combiner may also be referred to as a beam combining element. In some embodiments, the beam combiner may be a zinc selenide (ZnSe), zinc sulfide (ZnS), or germanium (Ge) beam combiner. For example, the beam combiner may be configured to transmit infrared light and reflect visible light. In some embodiments, the beam combiner may be a dichroic mirror. In some embodiments, the beam combiner may be configured to pass electromagnetic radiation having a wavelength longer than a cutoff wavelength and reflect electromagnetic radiation having a wavelength shorter than a cutoff wavelength. In some embodiments, the beam combiner may be configured to pass electromagnetic radiation having a wavelength shorter than a cutoff wavelength and reflect electromagnetic radiation having a wavelength longer than a cutoff wavelength. In other embodiments, the beam combiner may be a polarizing beam splitter, a long-pass filter, a short-pass filter, or a band-pass filter.

[0090] The optical control system of the present disclosure may further include a lens positioned in the optical path. In some embodiments, the lens may be a focusing lens, where a focusing lens is positioned to focus the beam, the scattered light, or both. For example, a focusing lens may be positioned in the visible light path to focus the scattered light onto the targeting camera. In some embodiments, the lens may be a defocusing lens, where a defocusing lens is positioned to defocus the beam, the scattered light, or both. In some embodiments, the lens may be a collimating lens, where a collimating lens is positioned to collimate the beam, the scattered light, or both. In some embodiments, two or more lenses may be positioned in the optical path. For example, two lenses may be positioned in series in the optical path to expand or narrow the beam.

[0091] The position and orientation of one or both of the first reflective element and the second reflective element may be controlled by one or more actuators. In some embodiments, the actuators may be motors, solenoids, galvanometers, or servos. For example, the position of the first reflective element may be controlled by a first actuator, and the position and orientation of the second reflective element may be controlled by a second actuator. In some embodiments, a single reflective element may be controlled by two or more actuators. For example, the first reflective element may be controlled along a first axis by a first actuator and along a second axis by a second actuator. Optionally, the mirror may be controlled by a first actuator, a second actuator, and a third actuator to provide multi-axis control of the mirror. In some embodiments, a single actuator may control the reflective elements along one or more axes. In some embodiments, a single reflective element may be controlled by a single actuator.

[0092] The actuator may vary the position of the reflective element by rotating the reflective element, thereby varying the angle of incidence of the beam that encounters the reflective element. Varying the angle of incidence may cause a translation of the location where the beam encounters the surface. In some embodiments, the angle of incidence may be adjusted such that the location where the beam encounters the surface is maintained while the optical system moves relative to the surface. In some embodiments, a first actuator rotates the first reflective element about a first axis of rotation, thereby translating the location where the beam encounters the surface along a first translation axis, and a second actuator rotates the second reflective element about a second axis of rotation, thereby translating the location where the beam encounters the surface along a second translation axis. In some embodiments, the first and second actuators rotate the first reflective element about the first and second rotational axes, thereby translating the location where the beam encounters the surface of the first reflective element along the first and second translational axes. For example, a single reflective element may be controlled by the first and second actuators to provide translation of the location where the beam encounters the surface along the first and second translational axes, and the single reflective element may be controlled by two actuators. In another example, the single reflective element may be controlled by one, two, or three actuators.

[0093] The first translation axis and the second translation axis may be orthogonal. The coverage area on the surface may be defined by the maximum translation along the first translation axis and the maximum translation along the second translation axis. One or both of the first actuator and the second actuator may be servo-controlled, piezoelectrically actuated, piezoelectric inertia-actuated, stepper motor-controlled, galvanometer-driven, linear actuator-controlled, or any combination thereof. One or both of the first reflective element and the second reflective element may be a mirror, e.g., a dichroic mirror, or a dielectric mirror, a prism, a beam splitter, or any combination thereof. In some embodiments, one or both of the first reflective element and the second reflective element may be any element capable of deflecting a beam.

[0094] The targeting camera may be positioned to capture light, e.g., visible light, traveling along the visible light path in a direction opposite to the beam path, e.g., the laser path. The light may be scattered by a surface, such as a surface with an object of interest, or an object, such as an object of interest, and travel along the visible light path toward the targeting camera. In some embodiments, the targeting camera is positioned so that it captures light reflected from the beam combiner. In other embodiments, the targeting camera is positioned so that it captures light transmitted through the beam combiner. Using such light capture, the targeting camera may be configured to image a target field of view on the surface. The targeting camera may be coupled to the beam combiner, or the targeting camera may be coupled to a support structure that supports the beam combiner. In one embodiment, the targeting camera does not move relative to the beam combiner, such that the targeting camera maintains a fixed position relative to the beam combiner.

[0095] The optical control system of the present disclosure may further include an exit window positioned in the beam path. In some embodiments, the exit window may be the last optical element encountered by the beam before exiting the optical control system. The exit window may comprise a material that is substantially transparent to visible light, infrared light, ultraviolet light, or any combination thereof. For example, the exit window may comprise glass, quartz, fused silica, zinc selenide, zinc sulfide, a transparent polymer, or a combination thereof. In some embodiments, the exit window may include a scratch-resistant coating, such as a diamond coating. The exit window may prevent dust, debris, water, or any combination thereof, from reaching other optical elements of the optical control system. In some embodiments, the exit window may be part of a protective casing that surrounds the optical control system.

[0096] After exiting the optical control system, the beam may be directed along the beam path toward a surface. In some embodiments, the surface comprises an object of interest, e.g., a plant. Rotational movement of the reflective element may cause the laser to sweep along a first translational axis and a second translational axis. Rotational movement of the reflective element may control where the beam encounters the surface. For example, rotational movement of the reflective element may move the location where the beam encounters the surface to the location of the object of interest on the surface. In some embodiments, the beam is configured to damage the object of interest. For example, the beam may comprise electromagnetic radiation, and the beam may irradiate the object. In another example, the beam may comprise infrared light, and the beam may burn the object. In some embodiments, one or both of the reflective elements may be rotated such that the beam scans an area surrounding and including the object.

[0097] The predictive camera or predictive sensor may cooperate with an optical control system, such as an optical control system, to identify and locate objects for targeting. The predictive camera may have a field of view that encompasses the coverage area of ​​the optical control system covered by the aimable laser sweep. The predictive camera may be configured to capture an image or representation of an area, including the coverage area, for identifying and selecting objects for targeting. The selected objects may be assigned to the optical control system. In some embodiments, the predicted camera field of view and coverage area of ​​the optical control system may be separated in time such that the predicted camera field of view encompasses the target at a first time and the coverage area of ​​the optical control system encompasses the target at a second time. Optionally, the predictive camera, the optical control system, or both may move relative to the target between the first time and the second time.

[0098] In some embodiments, two or more optical control systems may be combined to increase the coverage area on a surface. Two or more optical control systems may be configured to laser sweep along a translation axis of each optical control system that overlaps with the laser sweep along the translation axis of a neighboring optical control system. The combined laser sweep defines a coverage area that can be reached by at least one beam of two or more beams from the two or more optical control systems. One or more prediction cameras may be positioned such that a predicted camera field of view covered by the one or more prediction cameras completely encompasses the coverage area. In some embodiments, the detection system may include two or more prediction cameras, each having a field of view. The fields of view of the prediction cameras may be combined to form a predicted field of view that completely encompasses the coverage area. In some embodiments, the predicted field of view may not completely encompass the coverage area at a single time point, but may encompass the coverage area over two or more time points (e.g., image frames). Optionally, the predictive camera or cameras may move relative to the coverage area over the course of two or more time points, allowing temporal coverage of the coverage area. The predictive camera or sensors may be configured to capture images or representations of an area, including the coverage area, for identifying and selecting objects for targeting. The selected objects may be assigned to one of the two or more optical control systems based on the object's location and the area covered by the laser sweep of the individual optical control systems.

[0099] Two or more optical control systems may be configured on a vehicle, such as vehicle 100 illustrated in FIGS. 1-3 . For example, the vehicle may be an unmanned vehicle. The unmanned vehicle may be a robot. In some embodiments, the vehicle may be controlled by a human. For example, the vehicle may be driven by a human driver. In some embodiments, the vehicle may be coupled to a second vehicle driven by a human driver, for example, towed behind or pushed by the second vehicle. The vehicle may be controlled remotely by a human, for example, by remote control. In some embodiments, the vehicle may be controlled remotely via long wave signals, optical signals, satellite, or any other telecommunication method. Two or more optical control systems may be configured on a vehicle such that their coverage areas overlap surfaces directly below, behind, in front of, or surrounding the vehicle.

[0100] The vehicle may be configured to navigate a surface including multiple objects, e.g., a crop field, including multiple plants, including one or more plants, including one or more objects of interest. The vehicle may include one or more of wheels, a power source, a motor, a predictive camera, or any combination thereof. In some embodiments, the vehicle has sufficient clearance above the surface to drive over plants, e.g., crops, without damaging the plants. In some embodiments, the space between the inner edge of the left wheel and the inner edge of the right wheel is wide enough to pass over a row of plants without damaging the plants. In some embodiments, the distance between the outer edge of the left wheel and the outer edge of the right wheel is narrow enough to allow the vehicle to pass between two rows of plants, e.g., two rows of crops, without damaging the plants. In one embodiment, a vehicle including wheels, two or more optical control systems, and a predictive camera may navigate the rows of crops and emit two or more beams of light toward targets, e.g., plants, thereby burning or irradiating the plants. Computer system and method

[0101] The methods described herein may be implemented using a computer system. In some embodiments, the systems described herein include a computer system. In some embodiments, the computer system may implement the methods autonomously, without human input. In some embodiments, the computer system may implement the methods based on instructions provided by a human user through a detection terminal.

[0102] FIG. 5 illustrates, in a block diagram, components of a non-limiting exemplary embodiment of a detection terminal 1400 according to various aspects of the present disclosure. In some embodiments, the detection terminal 1400 is a device that displays a user interface for providing access to a detection system. As shown, the detection terminal 1400 includes a detection interface 1420. The detection interface 1420 enables the detection terminal 1400 to communicate with a detection system, such as the detection systems of FIG. 3 or 4. In some embodiments, the detection interface 1420 may include an antenna configured to communicate with the detection system, for example, via a remote control. In some embodiments, the detection terminal 1400 may also include a local communication interface, such as an Ethernet interface, a Wi-Fi interface, or other interface, that enables other devices associated with the detection system to connect to the detection system via the detection terminal 1400. For example, the detection terminal may be a handheld device, such as a mobile phone, that launches a graphical interface that enables a user to remotely operate or monitor the detection system via Bluetooth, Wi-Fi, or a mobile network.

[0103] The detection interface may support various communication protocols to ensure compatibility and interoperability with different devices and systems. These protocols may include cellular networks (e.g., LTE, 5G) for remote communication, allowing users to control and receive updates from the system from virtually any location, and LoRaWAN for long-range, low-power communication, which is particularly useful in rural or extensive agricultural settings. With regard to the hardware associated with the detection interface 1420, the detection interface may include hardware components such as a transceiver capable of both transmitting and receiving signals, a signal amplifier to boost communication range and quality, a microcontroller or processor to manage communication protocols and data handling, and power management circuitry to ensure efficient energy usage, especially when the system is battery-powered. In other exemplary embodiments, the detection interface enables several functional capabilities such as real-time data transmission to allow the user to receive live updates regarding the status of the system and the progress of the crop thinning process; remote control commands to allow the user to start, stop, or adjust the operation of the autonomous plant targeting system from the detection terminal; software updates and configuration changes that can be sent to the autonomous system to improve performance or modify operating parameters; and diagnostic data readout for maintenance and troubleshooting purposes.

[0104] The detection terminal 1400 further includes a detection engine 1410. The detection engine may receive information regarding the status of a detection system, for example, the detection system of Figure 3 or 4. The detection engine may receive information regarding the number of identified objects, the identities of the identified objects, the locations of the identified objects, the trajectories and predicted locations of the identified objects, the number of targeted objects, the identities of the targeted objects, the locations of the targeted objects, the location of the detection system, the elapsed time of a task performed by the detection system, the area covered by the detection system, the battery charge of the detection system, or a combination thereof.

[0105] In other exemplary embodiments, the detection engine may receive additional types of information, including environmental data such as temperature and humidity levels, weather conditions affecting operation such as soil moisture content, wind speed, and precipitation, and light intensity and spectral data for assessing photosynthetic activity. The detection engine may also receive metrics related to the performance and efficiency of the autonomous system, such as energy consumption and battery life estimates, area coverage indicating the speed at which the system is progressing through the field, the number of plants thinned per unit of time, and an operational log detailing system activity and any errors or malfunctions. Additionally, the detection engine may receive data points providing insight into the health and status of the crop, such as spectral analysis results, growth indicators including plant height and leaf area index (LAI), which may indicate plant stress or disease, and image data that may reveal signs of pest damage or nutrient deficiencies. Still further, the detection engine may receive information related to the autonomous system's navigation and location within the field, such as GPS coordinates and path tracking data, obstacle detection and avoidance logs, and alignment with crop rows and accuracy of movement relative to the planned path.

[0106] Actual embodiments of the illustrated devices may have many more components than those included herein, as would be known to those skilled in the art. For example, each illustrated device would have a power source, one or more processors, computer-readable media for storing computer-executable instructions, etc. These additional components are not illustrated herein for clarity.

[0107] In some examples, the procedures described herein may be implemented by a computing device or apparatus, such as a computing device having computing device architecture 1600 shown in FIG. 6 . In one example, the procedures described herein can be implemented by a computing device with computing device architecture 1600. The computing device may include any suitable device, such as a mobile device (e.g., a mobile phone), a desktop computing device, a tablet computing device, a wearable device, a server (e.g., a Software as a Service (SaaS) system or other server-based system), and / or any other computing device with the resource capabilities to perform the processes described herein, including procedures 500 or 600. In some cases, a computing device or apparatus may include various components, such as one or more input devices, one or more output devices, one or more processors, one or more microprocessors, one or more microcomputers, and / or other components configured to perform the steps of the processes described herein. In some examples, a computing device may include a display (in addition to the display or output device, as examples), a network interface configured to communicate and / or receive data, any combination thereof, and / or other components. The network interface may be configured to communicate and / or receive Internet Protocol (IP)-based data or other types of data.

[0108] Components of a computing device may be implemented in circuitry. For example, a component may include and / or be implemented using electronic circuitry or other electronic hardware, which may include one or more programmable electronic circuitry (e.g., microprocessors, graphics processing units (GPUs), digital signal processors (DSPs), central processing units (CPUs), and / or other suitable electronic circuitry), and / or may perform various operations described herein including and / or implemented using computer software, firmware, or any combination thereof.

[0109] Procedures 500 and 600 are illustrated as logical flow diagrams, whose operations represent sequences of operations that may be implemented in hardware, computer instructions, or a combination thereof. In the context of computer instructions, the operations represent computer-executable instructions stored on one or more computer-readable storage media that, when executed by one or more processors, perform the recited operations. Generally, computer-executable instructions include routines, programs, objects, components, data structures, and the like that perform particular functions or implement particular data types. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described operations can be combined in any order and / or in parallel to implement a process.

[0110] Additionally, the processes described herein may be performed under the control of one or more computer systems configured with executable instructions and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or a combination thereof. As noted above, the code may be stored on a computer-readable or machine-readable storage medium, for example, in the form of a computer program comprising instructions executable by one or more processors. The computer-readable or machine-readable storage medium may be non-transitory.

[0111] 6 illustrates an exemplary computing device architecture 1600 of an exemplary computing device, which can implement various techniques described herein. For example, the computing device architecture 1600 can implement the procedures described herein, control the detection system shown in FIG. 3 or FIG. 4, or control the vehicle shown in FIG. 1 and FIG. 2. The components of the computing device architecture 1600 are shown in electrical communication with each other using connections 1605, such as a bus. The exemplary computing device architecture 1600 includes a processing unit (which may include a CPU and / or a GPU) 1610 and computing device connections 1605 that couple various computing device components to the processor 1610, including computing device memory 1615, such as read-only memory (ROM) 1620 and random access memory (RAM) 1625. In some embodiments, the computing device may include a hardware accelerator.

[0112] The computing device architecture 1600 may include a cache of high-speed memory directly, closely connected to, or integrated as part of the processor 1610. The computing device architecture 1600 may copy data from the memory 1615 and / or the storage device 1630 to the cache 1612 for quick access by the processor 1610. In this manner, the cache may provide a performance boost that avoids processor 1610 delays while waiting for data. These and other modules may control or be configured to control the processor 1610 to perform various functions. Other computing device memory 1615 may be available for use as well. The memory 1615 may include multiple different types of memory with different performance characteristics. The processor 1610 may include any general-purpose processor and special-purpose processors in which hardware or software services, such as service 1 1632, service 2 1634, and service 3 1636, stored in the storage device 1630, configured to control the processor 1610, and software instructions are incorporated into the processor design. Processor 1610 may be a self-contained system including multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0113] To enable user interaction with the computing device architecture, input device(s) 1645 can represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, speech, etc. Output device(s) 1635 can also be one or more of several output mechanisms known to those skilled in the art, such as a display, projector, television, speaker device, etc. In some cases, a multi-mode computing device can enable a user to provide multiple types of input and communicate with the computing device architecture 1600. Communications interface 1640 can generally coordinate and manage user input and computing device output. No limitations exist regarding operation on any particular hardware arrangement, and therefore basic features herein may be readily substituted for improved hardware or firmware arrangements as they are developed.

[0114] The storage device 1630 is a non-volatile memory, which can be a hard disk or other type of computer-readable medium capable of storing data accessible by a computer, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cartridge, random access memory (RAM) 1625, read-only memory (ROM) 1620, and hybrids thereof. The storage device 1630 can include services 1632, 1634, 1636 for controlling the processor 1610. Other hardware or software modules are also contemplated. The storage device 1630 can be connected to the computing device connections 1605. In one aspect, hardware modules that perform specific functions can include software components stored in a computer-readable medium in association with the necessary hardware components, such as the processor 1610, connections 1605, output devices 1635, etc., to perform the functions.

[0115] Various examples of embodiments of the present disclosure are discussed in detail below. While specific implementations are discussed, it should be understood that this description is for illustrative purposes only. Those skilled in the art will recognize that other components and configurations may be used without departing from the spirit and scope of the present disclosure. Accordingly, the following description and drawings are illustrative and should not be construed as limiting. Numerous specific details are set forth to provide a thorough understanding of the present disclosure. However, in certain instances, well-known or conventional details are not described to avoid obscuring the description. Reference to one or an embodiment in this disclosure can be a reference to the same embodiment or any embodiment, and such reference means at least one of the exemplary embodiments.

[0116] Reference to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the present disclosure. Appearances of the phrase "in one embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment, nor are separate or alternative exemplary embodiments mutually exclusive of other exemplary embodiments. Furthermore, various features are described that may be exhibited by some exemplary embodiments but not by others. Any feature of one embodiment can be combined or used with any other feature of any other embodiment.

[0117] The terms used herein generally have their ordinary meaning in the art, within the context of this disclosure and in the specific context in which each term is used. Alternative terms and synonyms may be used for any one or more of the terms discussed herein, and no special significance should be placed on whether a term is recited or discussed herein. In some cases, synonyms for a term are provided. The listing of one or more synonyms does not exclude the use of other synonyms. The use of examples anywhere in this specification, including examples of any term discussed herein, is merely illustrative and is not intended to further limit the scope and meaning of the disclosure or any example term. Similarly, the present disclosure is not limited to the various exemplary embodiments provided herein.

[0118] Without intending to limit the scope of the present disclosure, examples of instruments, devices, methods, and their related results according to exemplary embodiments of the present disclosure are provided below. It should be noted that headings and subheadings may be used in the examples for the convenience of the reader and are not intended to limit the scope of the present disclosure in any way. Unless otherwise defined, technical and scientific terms used herein have the meanings commonly understood by those skilled in the art to which the present disclosure pertains. In case of conflict, the present document, including definitions, will control.

[0119] Additional features and advantages of the present disclosure will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the principles disclosed herein. The features and advantages of the present disclosure may be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features of the present disclosure will become more fully apparent from the following description and the appended claims, or may be learned by practice of the principles described herein.

[0120] For clarity of explanation, in some instances, the technology may be presented as including individual functional blocks that represent devices, device components, method steps or routines embodied in software, or combinations of hardware and software.

[0121] In the figures, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Rather, in some embodiments, such features may be arranged in a different manner and / or order than that shown in the illustrative figures. Additionally, the inclusion of a structural or method feature in a particular figure does not mean to imply that such feature is required in all embodiments, and in some embodiments, it may not be included or may be combined with other features.

[0122] While the concepts of the present disclosure are subject to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and will be described in detail herein. It should be understood, however, that there is no intention to limit the concepts of the present disclosure to the particular forms disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives consistent with the present disclosure and the appended claims.

[0123] The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or transporting instructions and / or data. Computer-readable media may also include non-transitory media, which do not include carrier waves and / or transitory electronic signals on which data may be stored and propagated wirelessly or via wired connections. Examples of non-transitory media may include, but are not limited to, magnetic disks or tapes, optical storage media, such as compact discs (CDs) or digital versatile discs (DVDs), flash memory, memory, or other memory devices. A computer-readable medium may have stored code and / or machine-executable instructions, which may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program descriptions. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, or the like.

[0124] In some embodiments, computer-readable storage devices, media, and memories may include cables or wireless signals containing bitstreams and the like. However, when stated, non-transitory computer-readable storage media explicitly excludes media such as energy, carrier signals, electromagnetic waves, and the signals themselves.

[0125] Specific details are provided in the above description to provide a thorough understanding of the embodiments and examples provided herein. However, it will be understood by those skilled in the art that the embodiments may be practiced without these specific details. For clarity of explanation, in some instances, the technology may be presented as including individual functional blocks, including devices, device components, method steps or routines embodied in software, or functional blocks comprising a combination of hardware and software. Additional components other than those shown in the figures and / or described herein may be used. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form so as not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail to avoid obscuring the embodiments.

[0126] Individual embodiments may be described above as a process or method, which is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. While a flowchart may describe operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of operations may be rearranged. A process is terminated when the operations are completed, but may also have additional steps not included in the diagram. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination may correspond to a return of the function to the calling function or the main function.

[0127] The processes and methods according to the embodiments described above can be implemented using computer-executable instructions stored on or otherwise available from a computer-readable medium. Such instructions can include, for example, instructions and data that cause or otherwise configure a general-purpose computer, special-purpose computer, or processing device to perform a certain function or group of functions. Portions of the computer resources used can be accessible via a network. The computer-executable instructions can be, for example, binaries, intermediate format instructions such as assembly language, firmware, source code, etc. Examples of computer-readable media that can be used to store instructions, information used, and / or information created during methods according to the described embodiments include magnetic or optical disks, flash memory, USB devices with non-volatile memory, networked storage devices, etc.

[0128] Devices implementing processes and methods according to these disclosures may include hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof, and may take any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, program code or code segments (e.g., a computer program product) to perform the necessary tasks may be stored in a computer-readable or machine-readable medium. A processor may perform the necessary tasks. Exemplary examples of form factors include laptops, smartphones, mobile phones, tablet devices or other small form factor personal computers, personal digital assistants, rack-mounted devices, stand-alone devices, etc. The functionality described herein may also be embodied in peripheral devices or add-in cards. Such functionality may also be implemented on a circuit board among different chips or among different processes running within a single device, as further examples.

[0129] The instructions, media for carrying such instructions, computing resources for executing them, and other structures for supporting such computing resources are exemplary means for providing the functionality described in this disclosure.

[0130] The various illustrative logic blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as a departure from the scope of the present application.

[0131] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general-purpose computer, a wireless communication device handset, or an integrated circuit device, having multiple uses, including applications in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized, at least in part, by a computer-readable data storage medium comprising program code including instructions that, when executed, perform one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may comprise memory or data storage media, such as random access memory (RAM), such as synchronous dynamic random access memory (SDRAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, and the like. The techniques may additionally, or alternatively, be realized at least in part by a computer-readable communications medium, such as a propagated signal or wave, that carries or communicates program code in the form of instructions or data structures and can be accessed, read, and / or executed by a computer.

[0132] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such a processor may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a DSP and a microprocessor, two or more microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Thus, the term “processor” as used herein may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or apparatus suitable for implementing the techniques described herein.

[0133] While illustrative embodiments have been shown and described, it will be understood that various changes can be made therein without departing from the spirit and scope of the disclosure.

[0134] While the foregoing description describes aspects of the application with reference to specific embodiments thereof, those skilled in the art will recognize that the application is not limited thereto. Accordingly, while exemplary embodiments of the application have been described in detail herein, it should be understood that the inventive concepts may be otherwise embodied and employed in a variety of ways, and the appended claims are intended to be construed to include such variations except insofar as limited by the prior art. Various features and aspects of the application described above may be used individually or in combination. Moreover, the embodiments may be utilized in any number of environments and applications other than those described herein without departing from the broader spirit and scope of the specification. The specification and drawings are therefore to be regarded as illustrative, and not restrictive. For illustrative purposes, the method has been described in a particular order. It should be understood that in alternative embodiments, the method may be performed in an order different from that described.

[0135] Those skilled in the art will understand that the less than ("<") and greater than (">") symbols or terminology used herein can be substituted with the less than or equal to ("≦") and greater than or equal to ("≧") symbols, respectively, without departing from the scope of the present description.

[0136] When a component is described as being "configured to" perform a certain operation, such configuration can be accomplished, for example, by designing electronic circuitry or other hardware to perform the operation, by programming programmable electronic circuitry (e.g., a microprocessor or other suitable electronic circuitry) to perform the operation, or by any combination thereof.

[0137] The phrase "coupled to" refers to any component that is physically connected, either directly or indirectly, to another component and / or that is in communication, either directly or indirectly, with another component (e.g., connected to the other component via a wired or wireless connection and / or other suitable communication interface).

[0138] Claim language or other language reciting "at least one of" a set and / or "one or more of" a set indicates that one member of the set or multiple members of the set (in any combination) fulfills the claim. For example, claim language reciting "at least one of A and B" means A, B, or A and B. In another example, claim language reciting "at least one of A, B, and C" means A, B, C, or A and B, or A and C, or B and C, or A, B, and C. The language "at least one of" a set and / or "one or more of" a set does not limit the set to the items listed in the set. For example, claim language reciting "at least one of A and B" can mean A, B, or A and B, and can additionally include items not listed in the set of A and B.

[0139] As used herein, the terms "about" and "approximately" in reference to numbers are used herein to include numbers within 10%, 5%, or 1% in either direction of that number (greater than or less than 10%, 5%, or 1%), unless otherwise stated or otherwise clear from the context (unless such number would exceed 100% of the possible value).

[0140] While preferred embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the invention. It is understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention. The following claims define the scope of the invention, and it is intended that methods and structures within the scope of these claims and their equivalents be covered thereby.

[0141] While embodiments of the present invention are described herein in the context of particular implementations in particular environments for particular purposes, those skilled in the art will recognize that their usefulness is not limited thereto, and that embodiments of the present invention may also be beneficially implemented in other related environments for similar purposes. The present invention should therefore be limited not by the embodiments, methods, and examples described above, but by all embodiments that are within the scope and spirit of the invention as claimed. The present invention should not be limited in terms of the particular embodiments described herein, which are intended as illustrations of various aspects. Many modifications and variations can be made without departing from its spirit and scope. Functionally equivalent systems, processes, and apparatuses within the scope of the invention, in addition to those recited herein, will be apparent from the representative descriptions herein. Such modifications and variations are intended to be within the scope of the appended claims. The present invention should be limited only by the terms of the appended claims, along with the full range of equivalents to which such representative claims are entitled.

[0142] The preceding description of exemplary embodiments provides non-limiting representative examples with reference to figures, particularly illustrating the features and teachings of different aspects of the present invention. It should be recognized that the described embodiments can be implemented separately or in combination with other embodiments from the description of the embodiments. Upon reviewing the description of the embodiments, one skilled in the art should be able to learn and understand the different described aspects of the present invention. The description of the embodiments is not specifically exhaustive, but should facilitate understanding of the present invention to the extent that other implementations within the knowledge of one skilled in the art upon perusal of the description of the embodiments will also be understood to be consistent with the application of the present invention.

Claims

1. 1. A method for autonomous crop thinning, comprising: a processor receiving one or more images of a crop field including a crop; the processor processing the image using a machine learning model to identify one or more individual crop plants; the processor determining a location and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the location, the parameters, or both, of each of the one or more identified crops; selecting target crops for removal based on individual parameters of the one or more identified crops, their location relative to the crop boundaries, or both; A method comprising:

2. 10. The method of claim 1, wherein the method further comprises guiding an autonomous vehicle equipped with a targeting system capable of removing the selected target crop.

3. The method of claim 2 , wherein the targeting system comprises a laser capable of irradiating the selected target crop.

4. 4. The method of claim 2 or claim 3, further comprising removing the selected target crop with the targeting system.

5. The method of claim 4 , wherein removing the selected target crop comprises irradiating the target crop with a laser.

6. The method of any one of claims 2-5, further comprising updating the crop boundary based on real-time feedback from the targeting system.

7. 7. The method of any one of claims 1-6, wherein the selection of target crops for removal is based at least on predetermined crop spacing within the crop field.

8. 8. The method of claim 1, wherein the machine learning model is a convolutional neural network trained to recognize crop characteristics.

9. The method of any one of claims 1-8, wherein the parameters of each identified crop plant include at least one of health, size, or growth stage.

10. The method of any one of claims 1-9, wherein the crop boundary is specified as a geometric shape selected from the group consisting of a rectangle, an ellipse, and a polygon that closely matches the outline of the crop.

11. The method of any one of claims 1 to 10, wherein determining the location of the individual plant may comprise generating a virtual representation of an area around the individual plant.

12. 1. An autonomous plant targeting system, comprising: a processor; a memory having instructions stored therein that, when executed by the processor, cause the system to: receiving, by the processor, one or more images of a crop field including a crop; the processor processing the image using a machine learning model to identify one or more individual crop plants; the processor determining a location and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the location, the parameters, or both of each of the one or more identified crops; the processor selecting target crops for removal based on individual parameters of the one or more identified crops, their location relative to the crop boundaries, or both; a memory and A system comprising:

13. 13. The system of claim 12, wherein the machine learning model is a convolutional neural network trained to recognize crop characteristics.

14. 14. The system of claim 12 or claim 13, wherein the targeting system comprises a laser capable of irradiating the selected target crop.

15. 15. The system of any one of claims 12-14, wherein the system further comprises the processor guiding an autonomous vehicle equipped with a targeting system to remove the selected target crop.

16. 16. The system of claim 15, wherein the autonomous vehicle includes a detection system that dynamically updates the virtual representation of the crop field as the vehicle moves through the field.

17. 17. The system of claim 15 or claim 16, wherein the autonomous vehicle collects environmental data from the crop field and adjusts the removal action based on the collected data.

18. 18. The system of any one of claims 12-17, wherein said selecting a target crop for removal is further based on a predetermined crop spacing within said crop field.

19. The system of any one of claims 12-18, wherein the parameters of each identified crop plant include at least one of health, size, or growth stage.

20. 20. The system of any one of claims 12-19, wherein the crop boundary is specified as a geometric shape selected from the group consisting of a rectangle, an ellipse, and a polygon that closely matches the outline of the crop.

21. The system of any one of claims 12-20, wherein determining the location of the individual plant may include generating a virtual representation of an area around the individual plant.

22. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by a computer hardware arrangement, cause the computer hardware arrangement to: receiving one or more images of a crop field including a crop; processing the image using a machine learning model to identify one or more individual crop plants; determining the location and parameters of each of the one or more identified crops; generating a crop boundary around each identified crop based on the location, the parameters, or both, of each of the one or more identified crops; selecting target crops for removal based on individual parameters of the one or more identified crops, their location relative to the crop boundaries, or both; A non-transitory computer readable medium for carrying out a procedure including:

Images