Systems and methods for autonomous plant targeting using crop proximity

Abstract

In some variations, a method for autonomous object (e.g., plant) targeting based on proximity to a desired object includes receiving an image of a field, characterizing one or more objects of interest in the image using a pre-trained machine learning model, selecting a first object of the one or more objects of interest, generating a targetable region of the field relative to a location of the first object, and selectively targeting one or more objects of interest for damage based at least in part on their locations being inside the targetable region. The targeted object(s) of interest may, for example, be targeted with an implement such as a laser to damage the targeted object(s) of interest.

Description

Attorney Docket No. : CBN.011 WOSYSTEMS AND METHODS FOR AUTONOMOUS PLANT TARGETING USING CROP PROXIMITYCROSS-REFERNCE TO RELATED APPLICATIONS

[0001] The present application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 682,517, filed August 13, 2024, which is incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] The present technology relates to systems and methods for autonomous plant targeting using crop proximity.BACKGROUND

[0003] As technology advances, tasks that had previously been performed by humans are increasingly becoming automated. While tasks performed in highly controlled environments, such as factory assembly lines, can be automated by directing a machine to perform the task the same way each time, tasks performed in unpredictable environments, such as driving on city streets or vacuuming a cluttered room, depend on dynamic feedback and adaptation to perform the task. Autonomous systems often struggle to identify and locate objects in unpredictable environments. Improved methods of object detection, location, and targeting would advance automation technology and increase the ability of autonomous systems to react and adapt to unpredictable environments.SUMMARY

[0004] The subject technology is illustrated, for example, according to various aspects described below, including with reference to FIGS. 1-12. Various examples of aspects of the subject technology are described as numbered clauses (1, 2, 3, etc.) for convenience. These are provided as examples and do not limit the subject technology.Clause 1. A method comprising: receiving an image of a field; characterizing one or more objects of interest in the image using a pre-trained machine learning model;Attorney Docket No. : CBN.011 WO selecting a first object of the one or more objects of interest; generating a targetable region of the field relative to a location of the first object; and selectively targeting one or more objects of interest for damage based at least in part on their locations being inside the targetable region.Clause 2. The method of clause 1, further comprising instructing an implement to damage the targeted one or more objects of interest.Clause 3. The method of clause 2, wherein the implement comprises a laser capable of irradiating the targeted one or more objects of interest.Clause 4. The method of any one of clauses 1-3, further comprising identifying one or more objects of interest for no action, based at least in part on their locations being outside of the targetable region.Clause 5. The method of any one of clauses 1^1, further comprising selectively targeting one or more objects of interest for damage based at least in part on their locations being outside the targetable region.Clause 6. The method of any one of clauses 1-5, wherein the targetable region is defined at least in part by a perimeter centered around the location of the first object.Clause 7. The method of any one of clauses 1-6, wherein a size of the targetable region corresponds to a property of the first object.Clause 8. The method of any one of clauses 1-7, wherein the targetable region is defined based at least in part by a user input.Clause 9. The method of any one of clauses 1-8, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one object of interest in the image.Clause 10. The method of clause 9, wherein the one or more properties is stored in an embedding associated with the at least one object of interest.Attorney Docket No. : CBN.011 WOClause 11. The method of clause 9 or 10, wherein the one or more properties comprises a first object score representing likelihood that the at least one object of interest is a first object type, and / or a second object score representing likelihood that the at least one object of interest is a second object type.Clause 12. The method of any one of clauses 9-11, wherein selecting a first object of the one or more objects of interest comprises selecting the first object based at least in part on the one or more properties of the first object.Clause 13. The method of any one of clauses 1-12, wherein the first object is a crop.Clause 14. The method of any one of clauses 1-13, wherein at least one of the targeted objects of interest is a weed.Clause 15. The method of any one of clauses 1-14, wherein at least one of the targeted objects of interest is a crop.Clause 16. A system comprising: a processor; and a memory operably coupled to the processor and storing instructions that, when executed by the processor, cause the system to: receive an image of a field; characterize one or more objects of interest in the image using a pre-trained machine learning model; select a first object of the one or more objects of interest; generate a targetable region of the field relative to a location of the first object; and selectively target one or more objects of interest for damage based at least in part on their locations being inside the targetable region.Attorney Docket No. : CBN.011 WOClause 17. The system of clause 16, wherein the instructions, when executed by the processor, cause the system to instruct an implement to damage the targeted one or more objects of interest.Clause 18. The system of clause 17, wherein the implement comprises a laser capable of irradiating the targeted one or more objects of interest.Clause 19. The system of any one of clauses 16-18, wherein the instructions, when executed by the processor, cause the system to identify one or more objects of interest for no action, based at least in part on their locations being outside of the targetable region.Clause 20. The system of any one of clauses 16-19, wherein the instructions, when executed by the processor, cause the system to selectively target one or more objects of interest for damage based at least in part on their locations being outside the targetable region.Clause 21. The system of any one of clauses 16-20, wherein the targetable region is defined at least in part by a perimeter centered around the location of the first object.Clause 22. The system of any one of clauses 16-21, wherein a size of the targetable region corresponds to a property of the first object.Clause 23. The system of any one of clauses 16-22, wherein the targetable region is defined based at least in part by a user input.Clause 24. The system of any one of clauses 16-23, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one object of interest in the image.Clause 25. The system of clause 24, wherein the one or more properties is stored in an embedding associated with the at least one object of interest.Clause 26. The system of clause 24 or 25, wherein the one or more properties comprises a first object score representing likelihood that the at least one object of interest isAttorney Docket No. : CBN.011 WO a first object type, and / or a second object score representing likelihood that the at least one object of interest is a second object type.Clause 27. The system of any one of clauses 24-26, wherein when the instructions cause the system to select a first object, the system selects the first object based at least in part on the one or more properties of the first object.Clause 28. The system of any one of clauses 16-27, wherein the first object is a crop.Clause 29. The system of any one of clauses 16-28, wherein at least one of the targeted objects of interest is a weed.Clause 30. The system of any one of clauses 16-29, wherein at least one of the targeted objects of interest is a crop.Clause 31. A method comprising: receiving an image of a crop field; identifying one or more plants of interest in the image using a pre-trained machine learning model; selecting a desired plant of the one or more plants of interest; generating a targetable region of the crop field relative to a location of the desired plant; and selectively targeting one or more plants of interest for damage based at least in part on their locations being inside the targetable region.Clause 32. The method of clause 31, further comprising instructing an implement to damage the targeted one or more plants of interest.Clause 33. The method of clause 32, wherein the implement comprises a laser capable of irradiating the targeted one or more plants of interest.Attorney Docket No. : CBN.011 WOClause 34. The method of any one of clauses 31-33, further comprising identifying one or more plants of interest for no action, based at least in part on their locations being outside of the targetable region.Clause 35. The method of any one of clauses 31-34, further comprising selectively targeting one or more plants of interest for damage based at least in part on their locations being outside the targetable region.Clause 36. The method of any one of clauses 31-35, wherein the targetable region is defined at least in part by a perimeter centered around the location of the desired plant.Clause 37. The method of any one of clauses 31-36, wherein a size of the targetable region corresponds to a property of the desired plant.Clause 38. The method of any one of clauses 31-37, wherein the targetable region is defined based at least in part by a user input.Clause 39. The method of any one of clauses 31-38, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one plant of interest in the image.Clause 40. The method of clause 39, wherein the one or more properties is stored in an embedding associated with the at least one plant of interest.Clause 41. The method of clause 39 or 40, wherein the one or more properties comprises a crop score representing likelihood that the at least one plant of interest is a crop, and / or a weed score representing likelihood that the at least one plant of interest is a weed.Clause 42. The method of any one of clauses 39-41, wherein the one or more properties comprises at least one of health, size, or growth stage of the plant of interest.Clause 43. The method of any one of clauses 39-42, wherein selecting a desired plant of the one or more plants of interest comprises selecting the desired plant based at least in part on the one or more properties of the desired plant.Attorney Docket No. : CBN.011 WOClause 44. The method of any one of clauses 31-43, wherein the desired plant is a crop.Clause 45. The method of any one of clauses 31-44, wherein at least one of the targeted plants of interest is a weed.Clause 46. The method of any one of clauses 31-45, wherein at least one of the targeted plants of interest is a crop.Clause 47. A system comprising: a processor; and a memory operably coupled to the processor and storing instructions that, when executed by the processor, cause the system to: receive an image of a crop field; identify one or more plants of interest in the image using a pre-trained machine learning model; select a desired plant of the one or more plants of interest; generate a targetable region of the crop field relative to a location of the desired plant; and selectively target one or more plants of interest for damage based at least in part on their locations being inside the targetable region.Clause 48. The system of clause 47, wherein the instructions, when executed by the processor, cause the system to instruct an implement to damage the targeted one or more plants of interest.Clause 49. The system of clause 48, wherein the implement comprises a laser capable of irradiating the targeted one or more plants of interest.Clause 50. The system of any one of clauses 47-49, wherein the instructions, when executed by the processor, cause the system to identify one or more plants of interest for no action, based at least in part on their locations being outside of the targetable region.Attorney Docket No. : CBN.011 WOClause 51. The system of any one of clauses 47-50, wherein the instructions, when executed by the processor, cause the system to selectively target one or more objects of interest for damage based at least in part on their locations being outside the targetable region.Clause 52. The system of any one of clauses 47-51, wherein the targetable region is defined at least in part by a perimeter centered around the location of the desired plant.Clause 53. The system of any one of clauses 47-52, wherein a size of the targetable region corresponds to a property of the desired plant.Clause 54. The system of any one of clauses 47-53, wherein the targetable region is defined based at least in part by a user input.Clause 55. The system of any one of clauses 47-54, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one plant of interest in the image.Clause 56. The system of clause 55, wherein the one or more properties is stored in an embedding associated with the at least one plant of interest.Clause 57. The system of clause 55 or 56, wherein the one or more properties comprises a crop score representing likelihood that the at least one plant of interest is a crop, and / or a weed score representing likelihood that the at least one plant of interest is a weed.Clause 58. The system of any one of clauses 55-57, wherein the one or more properties comprises at least one of health, size, or growth stage of the plant of interest.Clause 59. The system of any one of clauses 55-58, wherein selecting a desired plant of the one or more plants of interest comprises selecting the desired plant based at least in part on the one or more properties of the desired plant.Clause 60. The system of any one of clauses 47-59, wherein the desired plant is a crop.Attorney Docket No. : CBN.011 WOClause 61. The system of any one of clauses 47-60, wherein at least one of the targeted plants of interest is a weed.Clause 62. The system of any one of clauses 47-61, wherein at least one of the targeted plants of interest is a crop.BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Many aspects of the present disclosure can be better understood with reference to the following drawings. The components in the drawings are not necessarily to scale. Instead, emphasis is placed on illustrating clearly the principles of the present disclosure.

[0006] FIG. 1 is a schematic illustration of an example autonomous plant targeting system, in accordance with the present technology.

[0007] FIG. 2 is a schematic illustration of an example autonomous plant targeting system navigating a field of crops while implementing various techniques in accordance with the present technology.

[0008] FIG. 3 is a schematic illustration of an example detection system positioned on an autonomous plant targeting system, in accordance with the present technology.

[0009] FIG. 4 is a block diagram illustrating components of an example prediction system and an example targeting system in accordance with the present technology.

[0010] FIG. 5 is a block diagram depicting components of a detection terminal in accordance with the present technology.

[0011] FIG. 6 is an example block diagram of a computing device architecture of a computing device that can implement various techniques in accordance with the present technology.

[0012] FIG. 7 is a flowchart of an example method for autonomous object targeting using proximity to an identified object, in accordance with the present technology.

[0013] FIG. 8 is a schematic illustration of an example targeting region defined in relation to a first object of interest, in accordance with the present technology.

[0014] FIGS. 9A-9F are schematic illustrations of example targeting regions, in accordance with the present technology.Attorney Docket No. : CBN.011 WO

[0015] FIG. 10 is a schematic illustration of multiple different example targeting regions in the same imaged field, in accordance with the present technology.

[0016] FIG. 11 is a schematic illustration of the targeting of plants based on proximity to crops in an example implementation of a weeding process.

[0017] FIG. 12 is a schematic illustration of the targeting of plants based on proximity to crops in an example implementation of a hybrid weeding and crop thinning process.DETAILED DESCRIPTION

[0018] The present technology relates to systems and methods for autonomous object targeting using proximity to an identified object. Some variations of the present technology, for example, are directed to the autonomous targeting of weeds, crops, and / or other objects based on their proximity to a crop. Specific details of several variations of the technology are described below with reference to FIGS. 1-12.

[0019] An autonomous method of targeting objects of interest based on proximity to an identified object of interest may include automated targeting (e.g., damage, destroy, or otherwise take an action upon) of select objects of interest based on their location relative to the location of an identified object of interest that is intended to be maintained (e.g., not targeted). For example, where the objects of interest are plants, an autonomous plant targeting system can be configured to identify, in one or more images, a desired plant of interest that is to be maintained and not damaged, such as a crop. A targetable region can be defined with respect to that plant of interest, and the system can target one or more plants that are located within the targetable region, such as for damage or otherwise removed (e.g., with an implement such as a laser, as described elsewhere herein). Targeted plants may include, for example, a weed or a crop that is small, unhealthy, or otherwise not desired to be maintained in the field. The autonomous plant targeting system can also refrain from targeting plants outside of the targetable region. Instead, any plants that may be identified as located outside of the targetable region can be damaged or otherwise removed through separate, alternative processes (e.g., chemical plant killer, mechanical plant removal, and / or other conventional crop maintenance techniques, etc.) that may be unsafe to perform within the targetable region without risking damage to the desired plant of interest. In some variations, the targetable region may generally provide a buffer region to enable safe use of such alternative plant-damaging techniques without harming the desired plant of interest. Accordingly, the autonomous plant targeting methods based on proximity to a desired plant of interest, in accordance with the presentAttorney Docket No. : CBN.011 WO technology, can be used in combination with (e.g., before or after) such alternative plantdamaging processes to result in thorough and efficient treatment of a field (e.g., crop field).[00201 In some variations, the methods of the present technology may be implemented by an autonomous plant targeting system to target and eliminate an object of interest, such as a plant of interest (e.g., weed, crop). For example, an autonomous plant targeting system may include a detection system configured to detect and locate a plant of interest identified in images or representations collected by a first sensor, such as a prediction sensor, over time relative to the autonomous plant targeting system. The detection information may be used to determine a predicted location of the plant of interest relative to the system. The autonomous plant targeting system may then locate the same plant in an image or representation collected by a second sensor, such as a targeting sensor, using the predicted location. In some variations, the first sensor is a prediction camera, and the second sensor is a targeting camera. One or both of the first sensor and the second sensor may be moving relative to the plant of interest. For example, the prediction camera may be coupled to and moving with the autonomous plant targeting system.[0021 J Targeting the plant of interest may comprise precisely locating the plant using the targeting sensor, targeting the plant with a laser, and eradicating the plant by burning it with laser light, such as infrared light. For example, in some variations the plant of interest may be a weed, as distinct from a crop that is desired to be maintained alive. As another example, in some variations the plant of interest may be any other suitable unwanted plant (e.g., failing crop, such as a small crop plant, a diseased crop plant, a crop plant located in an undesirable location, etc.). The prediction sensor may be part of a prediction system configured to determine a predicted location of an object of interest (e.g., plant of interest), and the targeting sensor may be part of a targeting system configured to refine the predicted location of the object of interest to determine a target location and target the object of interest with the laser at the target location. The prediction system may be configured to communicate with the targeting system to coordinate a camera handoff using point to point targeting, such as that described in U.S. Patent Publication No. 2022 / 0299635, which is incorporated herein by reference. The targeting system may target the object at the predicted location. In some variations, the targeting system may use the trajectory of the object to dynamically target the object while the system is in motion such that the position of the targeting sensor, the laser, or both is adjusted to maintain the target.Attorney Docket No. : CBN.011 WO

[0022] An autonomous plant targeting system may identify, target, and eliminate certain plants without human input. In some variations, the autonomous plant targeting system may be positioned on a self-driving vehicle or a piloted vehicle or may be pulled by a vehicle such as a tractor. For example, as shown in FIG. 1, an autonomous plant targeting system may be part of or coupled to a vehicle 100, such as a tractor or self-driving vehicle. The autonomous plant targeting system may, for example, be configured to target weeds, though can additionally or alternatively be configured to target any other undesired objects (e.g., undesired plants, pests, etc.). In some variations, the vehicle 100 may drive through a field of crops 200, as illustrated in FIG. 2. As the vehicle 100 drives through field 200 it may identify, target, and eradicate weeds in an unweeded section 210 of the field, leaving a weeded field 220 behind it. The methods in accordance with the present technology may be implemented by the autonomous plant targeting system to identify, target, and eradicate certain objects of interest while the vehicle 100 is in motion. The high precision of such methods enables accurate targeting of objects of interest, such as with a laser, to eradicate the object of interest without damaging nearby objects. The high precision of such methods enables accurate targeting of plants, such as with a laser, to eradicate the plants without damaging nearby crops. U.S. Patent No. 11,602,143, which is incorporated by reference, describes autonomous targeting systems that may be used to perform at least some portion of the methods in accordance with the present technology.

[0023] While the primary focus of the methods described herein is on the identification, selection, and targeting of plants, the applicability of the underlying technology is not limited to plant detection. The system's advanced imaging and predictive analytics capabilities can be designed to identify and locate objects in unpredictable environments, which inherently allows for the detection of a wide range of objects beyond just plants. The methods and systems described are capable of detecting any distinguishable items or areas that can be observed within their operational field. This includes, but is not limited to, debris, infrastructure elements, people, animals, insects, pests, or other items that may be present in an agricultural setting or other suitable setting (e.g., home). The flexibility and adaptability of the system's object detection technology enable it to be applied to various scenarios where autonomous detection and manipulation of objects are beneficial. Therefore, while the application predominantly illustrates the system's utility in an agricultural context, the principles and mechanisms of object detection and targeting it employs can be generalized to other applications where identifying and interacting with various objects is desired.Attorney Docket No. : CBN.011 WOI. Object detection system

[0024] In some variations, the methods in accordance with the present technology may be performed by a detection system configured to identify and target an object of interest. In some variations, the detection system may be positioned on or coupled to a vehicle, such as a self-driving plant targeting vehicle or a plant targeting trailer pulled by a tractor. The detection system may include a prediction system and a targeting system.

[0025] Generally, as further described herein, the prediction system may be configured to identify object(s) of interest in one or more images and / or track the location of such objects relative to a moving body, such as by using the methods described herein. For example, in some variations, the prediction system may be configured to capture an image or representation of a region of a surface using a prediction camera and / or other prediction sensor, identify an obj ect of interest in the image, and / or determine a predicted location of the obj ect. Accordingly, the prediction system may be configured to process image data to generate a virtual representation of the region, identifying the location (that is, current and / or future locations relative to the moving body as the moving body moves) and parameters of individual objects, such as crops, within that space.

[0026] Once an object has been identified and its location predicted, the prediction system communicates this information to the targeting system. The targeting system can apply a decision algorithm to decide whether to perform an action associated with the object. For example, the decision algorithm can generate an instruction for the targeting system to aim an implement, such as a laser, at the object (e.g., to destroy or damage the object). The targeting system may ensure that the implement is accurately directed towards the object's current or future location, accounting for any movement of the object or the autonomous system itself. The prediction system’s ability to forecast the object's location allows the targeting module to compensate for any delays between the identification of the object and the moment of action, ensuring that the targeting is precise and effective. This coordination is particularly useful when the autonomous system is in motion, as it allows for dynamic adjustments to be made in realtime, ensuring that the targeting remains accurate despite any changes in the relative positions of the system and the objects.

[0027] An example of a detection system 300 is shown in the illustrative schematic of FIG. 3. The detection system may be part of or coupled to a vehicle 100, such as a self-driving plant targeting vehicle or a laser plant targeting system trailer pulled by a tractor, that movesAttorney Docket No. : CBN.011 WO along a surface, such as a crop field 200. The detection system 300 includes a prediction system 310, including a prediction sensor with a prediction field of view 315, and a targeting system 320, including a targeting sensor with a targeting field of view 325. The targeting system may further include an implement, such as a laser, with a target area that overlaps with the targeting field of view 325. In some variations, the prediction system 310 is positioned ahead of the targeting system 320, along the direction of travel of the vehicle 100, such that the targeting field of view 325 overlaps with the prediction field of view 315 with a temporal delay. For example, the prediction field of view 315 at a first time may overlap with the targeting field of view 325 at a second time. In some variations, the prediction field of view 315 at the first time may not overlap with the targeting field of view 325 at the first time.

[0028] In other example variations, the system does not require the prediction system to be physically located in front of the targeting system. The primary objective is to ensure that the prediction system's field of view precedes the targeting system's field of view in the direction of the system's movement, allowing for the timely prediction and subsequent targeting of objects. As a non-limiting example, in other example variations the prediction sensor may be angled in such a way that its field of view extends further ahead in the travel path, even if the sensor itself is not positioned at the frontmost point of the system. This flexibility in sensor arrangement is particularly advantageous in scenarios where space constraints or design considerations necessitate a more compact or non-linear configuration of system components.

[0029] The detection system of the present technology may be used to target objects on a surface, such as the ground, a dirt surface, a floor, a wall, an agricultural surface (e.g., a field), a lawn, a road, a mound, a pile, or a pit. In some variations, 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 at a construction site, in an agricultural field, or in a mining tunnel, or the surface may be uneven terrain containing fields, roads, forests, hills, mountains, houses, or buildings. The detection systems in accordance with the present technology may locate an object on a non-planar surface more accurately, faster, or within a larger area than a single sensor system or a system lacking an object matching module.

[0030] Additionally or alternatively, the detection system may be used to target objects that may be spaced from the surface they are resting on, such as a tree top distanced from its grounding point, and / or to target obj ects that may be locatable relative to a surface, for example, relative to a ground surface in air or in the atmosphere. In addition, the detection system mayAttorney Docket No. : CBN.011 WO be used to target objects that may be moving relative to a surface, for example, a vehicle, an animal, a human, or a flying object.

[0031] The prediction system and the targeting system may be used in combination to locate, identify, and target an object with an implement. The prediction system and the targeting system may be in communication, for example electrical or digital communication. The targeting system may comprise an optical control system as described in further detail below. In some variations, the prediction system and the targeting system are directly or indirectly coupled. For example, the prediction system and the targeting system may be coupled to a support structure. In some variations, the prediction system and the targeting system are configured on or coupled to a vehicle, such as the vehicle shown in FIG. 1 and FIG. 2. For example, the prediction system and the targeting system may be positioned on a self-driving vehicle. In another example, the prediction system and the targeting system may be positioned on a trailer pulled by another vehicle, such as a tractor.

[0032] FIG. 4 is a schematic illustration of a detection system comprising a prediction system 400 and a targeting system 450 for tracking at targeting an object O relative to a moving body, such as vehicle 100 illustrated in FIG. 1 - FIG. 3. The prediction system 400, the targeting system 450, or both may be positioned on or coupled to the moving body (e.g., the moving vehicle). The prediction system 400 and the targeting system 450 are described in further detail below. Furthermore, U.S. Patent No. 11,602,143 (which is incorporated herein in its entirety by this reference) describes additional details regarding an example autonomous plant targeting system with which the detection system of the present technology can be used.A. Prediction system

[0033] As described above, the prediction system in accordance with the present technology may be configured to identify object(s) of interest in one or more images and / or track the location of such objects in their trajectories relative to a moving body. In some variations, a prediction system is configured to capture an image or representation of a region of a surface using a prediction camera and / or other prediction sensor, identify an object of interest in the image, and / or determine a predicted location of the object. The prediction system may include a system controller, for example 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 mayAttorney Docket No. : CBN.011 WO comprise sufficient RAM, storage space, CPU power, and GPU power to perform operations to detect and identify a target.[00341 In some variations, the prediction system may include a prediction sensor configured to generate an image for analysis by the prediction system. For example, as shown in FIG. 4, the prediction system 400 may include a prediction sensor 410 configured to image a region, such as a region of a surface, containing one or more objects, including object O. In some variations, the prediction system may include a plurality of prediction sensors, enabling coverage of a larger region of interest. The prediction sensor may provide images of sufficient resolution on which to perform operations to detect and identify an object. In some variations, 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 an image. For example, the image can be a representation of the field and / or object(s) of interest located in the field, such as a visual representation formed by electromagnetic radiation (e.g., light, X-rays, microwaves, or radio waves) scattered off of the field or object, a point cloud model formed by a LIDAR or radar sensor, or a sonogram produced by detecting sonic, infrasonic, or ultrasonic waves reflected off of the field or object.

[0035] The prediction system may further include an object identification module configured to identify an object of interest and differentiate the object of interest from other objects in the prediction image collected by the prediction sensor. For example, as shown in FIG. 4 the prediction system 400 may include an object identification module 420 configured to identify objects and their properties in image(s) collected by the prediction sensor. In some variations, the object identification module uses at least one pre-trained identification machine learning model to identify and differentiate objects, such as by predicting one or more properties of objects in the images. In some variations, visual characteristics of the object may be represented by a numerical representation in the form of an embedding (e.g., feature vector), such that similar-looking objects may have similar embeddings and different-looking objects have dissimilar embeddings. For example, the identification machine learning model may be trained to identify plants and differentiate plants of interest from other plants, such as crops. The identification machine learning model may predict plant properties for the object, such as a weed score (e.g., confidence score representing likelihood that the object is a weed), a crop score (e.g., confidence score representing likelihood that the object is a crop), weed type, crop type, a quantification (e.g., number) of images in which the object is pictured, and / or visualAttorney Docket No. : CBN.011 WO characteristics of the plant (e.g., size, shape, health, growth stage, etc.). Using these properties, the prediction system may be configured to identify a plant and to differentiate between different plants, such as between a crop and a weed. Additionally or alternatively, the prediction system may be configured to differentiate between different subtypes (e.g., genus or species) of plants, such as type of crop or type of week. Examples of crops that the prediction system may be configured to identify include onion, pepper, strawberry, carrot, corn, soybeans, barley, oats, wheat, alfalfa, cotton, hay, tobacco, rice, sorghum, tomato, potato, grape, rice, lettuce, bean, pea, sugar beet, or brassica (e.g., broccoli, cauliflower, mustard, kale, or brussels sprouts).

[0036] The identification machine learning model may be trained with many training images, such as high-resolution images, for example of surfaces with or without objects of interest. For example, the machine learning model may be trained with images of fields with or without weeds. The training of the identification machine learning model can be based on properties (e.g., features) extracted from a training dataset comprising labeled images of objects. The training process involves feeding the model numerous examples of images that contain the objects of interest, along with annotations that describe what the objects are and where they are located within the images. The model is trained to differentiate between these objects. For example, in some variations the model is trained to identify which plants in image(s) are crops that ought to be preserved and which are weeds or excess crops that can be targeted for removal. Once trained, the object identification module 420 can process new images from the prediction sensor and apply the learned patterns to identify objects in realtime. It can differentiate objects of interest from the background and other objects that are not relevant to the task at hand. The object identification module may use various machine learning techniques, such as convolutional neural networks (CNNs), though the identification machine learning model may include any suitable types of machine learning model(s).

[0037] Once trained, the machine learning model may be configured to identify a region in the image containing an object of interest. The region may be defined by a polygon, for example a rectangle. In some variations, the region is a bounding box. In some variations, the region is a polygon mask covering an identified region. In some variations, the identification machine learning model may be trained to determine a location of the object of interest, for example a pixel location within a prediction image.

[0038] In some variations, the prediction system may further include an object location module configured to determine locations of objects identified by the object identificationAttorney Docket No. : CBN.011 WO module. For example, as shown in FIG. 4, the prediction system 400 may include an object location module 425. The object location module 425 may determine locations of the objects identified by the object identification module 420 and to compile a set of identified objects and their corresponding locations. Object identification and object location may be performed on a series of images collected by the prediction sensor 410 over time. The set of identified objects and corresponding locations from in two or more images from the object location module 425 may be sent to a deduplication module, such as deduplication module 430.[00391 The deduplication module (e.g., deduplication 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, appearing in both the first image and the second image. The set of identified objects and corresponding locations may be deduplicated by the deduplication module by assigning locations of an object appearing in both the first image and the second image to the same object O. In some variations, the deduplication module may use a velocity estimate from the velocity tracking module (e.g., velocity tracking module 415), described below, to identify corresponding objects appearing in both images. The resulting deduplicated set of identified objects may contain unique objects, each of which has one or more corresponding locations determined at one or more time points.

[0040] Machine learning can be applied to this process by using models that recognize and match features of objects across different images. For instance, a machine learning model could be trained on a dataset of sequential images where objects of interest move or change appearance slightly. The model would learn to associate different instances of the same object across these images, despite variations in perspective, lighting, or partial occlusions. Such a model could use techniques like feature matching and object tracking algorithms that are robust to changes in the object's environment. By learning the typical motion patterns or changes in appearance of objects within the field, the trained deduplication module can more accurately determine when different images feature the same object, thereby reducing the likelihood of counting an object more than once.

[0041] Furthermore, in some variations the prediction system may include a reconciliation module, which maintains an accurate and current list of objects being tracked. For example, the reconciliation module may remove objects that are no longer relevant, such as those that have not been detected for a set period or number of frames. Machine learning can assist in this process by predicting which objects are likely to reappear based on their last known trajectory and the typical behavior of objects within the environment. A predictiveAttorney Docket No. : CBN.011 WO machine learning model could analyze the movement patterns of obj ects and predict their future positions. If an object temporarily disappears from view (e.g., due to occlusion or moving out of the frame) the model could estimate the likelihood of its return. This would allow the reconciliation module to make informed decisions about whether to keep tracking an object or remove it from the list, optimizing the system's resources and attention. The reconciliation module may provide the reconciled set of objects to the location prediction module, described in further detail below.[00421 For example, as shown in FIG. 4, the prediction system 400 can include a reconciliation module 435. The reconciliation module 435 may receive the deduplicated set of objects from the deduplication module 430 and may reconcile the deduplicated set by removing objects. In some variations, 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 the series of images. In another example, an object may be removed if it has not been identified in a predetermined period of time. In some variations, objects no longer appearing in images collected by the prediction sensor may continue to be tracked. For example, an object may continue to be tracked if it is expected to be within the prediction field of view based on the predicted location of the object. 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 predicted location of the object.

[0043] In some variations, the prediction module may comprise a velocity tracking module to determine a velocity of a vehicle to which the prediction system is coupled. For example, as shown in FIG. 4, the prediction system 400 may include a velocity tracking module 415. The velocity tracking module may estimate a velocity of the moving body relative to the region being imaged (e.g., surface). In some variations, the velocity tracking module 415 may comprise a device to measure the displacement of the moving body over time. For example, the velocity tracking module may include 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 a wheel of the vehicle may estimate a velocity or a distance traveled based on angular frequency, rotational frequency, rotation angle, or number of wheel rotations. In some variations, the positioning system may be positioned on the vehicle. Additionally or alternatively, the positioning system may be positioned on a vehicle that is spatially coupled to the detection system. For example, the positioning system may beAttorney Docket No. : CBN.011 WO located on a vehicle pulling the detection system. Furthermore, in some variations, the velocity tracking module may additionally or alternatively utilize images from the prediction sensor to determine the velocity of the vehicle using optical flow.

[0044] In some variations, the detection system can include a location prediction module configured to determine a predicted location at a future time(s) of object O from the reconciled set of objects (e.g., a trajectory of the object O). For example, as shown in FIG. 4, the prediction system 400 can include a location prediction module 440. In some variations, 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 velocity information from the velocity tracking module. The predicted location of object O may be based on a vector velocity, including speed and direction, of object O relative to the moving body between the location of object O in a first image collected at a first time and the location of object O in a second image collected at a second time. Optionally, the vector velocity may account for a distance of the object O from the moving body along the imaging axis (e.g., a height or elevation of the object relative to the surface). Additionally or alternatively, the predicted location of the object may be based on the location of object O in the first image or in the second image and a vector velocity of the vehicle determined by the from the velocity tracking module.

[0045] In some variations, the prediction system may include a scheduling module configured to select objects identified by prediction module and schedule which objects to target with the targeting system. For example, as shown in FIG. 4, the prediction system 400 may include a scheduling module 445. The scheduling module may schedule objects for targeting based on parameters such as object location, relative velocity, implement activation time, object score (e.g., confidence score representing likelihood that the object is a particular object type), or combinations thereof. For example, the scheduling module 5 may prioritize targeting objects predicted to move out of a field of view of a prediction sensor or a targeting sensor or out of range of an implement. In some variations, the scheduling module may prioritize objects and orchestrate the targeting sequence to efficiently transition between multiple targets. Additionally or alternatively, the scheduling module may prioritize targeting objects identified or located with high confidence. Additionally or alternatively, a scheduling module may prioritize targeting objects with short activation times. In some variations, the scheduling module may prioritize targeting objects based on a user's preferred parameters.Attorney Docket No. : CBN.011 WO

[0046] In some variations, the scheduling module (e.g., scheduling module 445) may use a decision algorithm that is configured to instruct or recommend an action associated with an object of interest in one or more images. The decision algorithm may, for example, include a rule-based algorithm and / or at least one machine learning model utilizing information from other modules of the prediction system to generate an instructed or recommended action to perform on the object of interest in the one or more collected images. The decision algorithm may, for example, determine an action to perform on a detected object based on the object’s properties (e.g., as predicted by the object identification module using an identification machine learning model) and one or more algorithmic parameters. For example, to determine a suitable action, the decision algorithm may utilize one or more thresholds (e.g., a threshold value against which the weed score is compared, a threshold value against which the crop score is compared, a minimum threshold quantity of images in which the plant should be pictured to permit performance of an action associated with the plant) and / or other assessment of the visual characteristics (e.g., health) of the plant.B. Targeting system

[0047] The detection system may include a targeting system configured to decide whether to perform an action associated with an object. For example, based on an instruction from the prediction system, the targeting system of the present technology may be configured to target an object tracked by a prediction system. The targeting system may ensure that the implement is accurately directed towards the object's current or future location, accounting for any movement of the object or the autonomous system itself. FIG. 4 is a schematic illustration of a detection system with a targeting system 450, which is described in further detail herein.

[0048] The targeting system may include a system controller, for example 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 to detect and identify a target.

[0049] The targeting system may include a targeting sensor configured to image a portion of the region of interest. For example, as shown in FIG. 4, the targeting system 450 may include a targeting sensor 475. In some variations, the targeting system may include a plurality of targeting sensors. The targeting system may be configured to receive a predicted location of an object of interest from the prediction system and point the targeting sensorAttorney Docket No. : CBN.011 WO toward the predicted location. In other words, 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. The targeting sensor may provide images of sufficient resolution on which to perform operations to target an object (e.g., to match an object to an object identified in a prediction image). In some variations, the targeting 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 an image. In some variations, the targeting sensor may have a smaller field of view than the prediction sensor.

[0050] The region of interest may correspond to a region of overlap between the targeting sensor field of view and the prediction sensor field of view. Such overlap may be contemporaneous or may be temporally separated. For example, the prediction sensor field of view can encompass the region of interest at a first time and the targeting sensor field of view can encompass the region of interest at a second time but not at the first time. In some variations, the detection system may move relative to the region of interest between the first time and the second time, facilitating temporally separated overlap of the prediction sensor field of view and the targeting sensor field of view.

[0051] In some variations, the targeting module may direct an implement (e.g., implement 475 shown in FIG. 4) toward the object. In some variations, the implement may perform an action on or manipulate the object. In some variations, the targeting module may use the trajectory of the object to dynamically target the object while the system is in motion such that the position of the targeting sensor, the implement, or both is adjusted to maintain the target. U.S. Patent Publication No. 2022 / 0299635, which is incorporated herein in its entirety by this reference, describes machine learning models for automated identification, maintenance, control, or targeting of objects that may be used with the methods of the present technology. The position of the targeting sensor and the position of the implement may be coupled. In some variations, a plurality of targeting systems may be in communication with the prediction system.

[0052] The implement may be or include one or more suitable devices for acting upon or otherwise manipulating an object. The manipulation of the object by the implement may eradicate the object. For example, the targeting system may be configured to direct a laser beam (e.g., infrared laser light beam) toward a plant to damage (e.g., burn) the plant. In anotherAttorney Docket No. : CBN.011 WO example, the targeting system may be configured to direct a grabbing tool to grab the object. In another example, the targeting system may direct a spraying tool to spray fluid (e.g., herbicide, pest repellent, etc.) at the object. In some variations, the object may be a weed, a plant, an insect, a pest, a field, a piece of debris, an obstruction, a region of a surface, or any other object that may be manipulated.

[0053] The targeting system may include a targeting control module. For example, as shown in FIG. 4, the targeting system 450 may include a targeting control module 460. In some variations, the targeting control module may control the targeting sensor, the implement, or both. In some variations, the targeting control module may include an optical control system comprising 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 activation and deactivation of the implement. Activation or deactivation may depend on the presence or absence of an object as detected by the targeting sensor. Activation or deactivation may depend at least in part on the position of the implement relative to the target object location. In some variations, the targeting control module may activate the implement, such as a laser emitter, when an object is identified and located by the prediction system. In some variations, the targeting control module may activate the implement when the range or target area of the implement is positioned to overlap with the target object location.

[0054] The targeting system may receive the predicted location of the object at a future time from the prediction system and may use the predicted location to precisely target the obj ect with an implement at the future time. For example, with reference to FIG. 4, the targeting control module 450 may receive the predicted location of object O from the location prediction module 440 of the prediction system 400, and may instruct the targeting sensor 465, the implement 475, or both to point toward the predicted location of the object.

[0055] In some variations, the targeting system may further include a location refinement module configured to refine the predicted location of an object provided by the prediction system. For example, as shown in FIG. 4, the targeting system 450 may include a location refinement module 470 configured to refine the predicted location of object O based on the location of object O determined from an image collected by the targeting sensor. In some variations, the location refinement module 470 may account for optical distortions in images collected by the prediction sensor 410 or the targeting sensor 465, and / or for distortions in angular motions of the implement 475 or the targeting sensor 465 due to nonlinearity of theAttorney Docket No. : CBN.011 WO angular motions relative to object O. Accordingly, the targeting control module may instruct the implement and / or the targeting sensor to point toward the refined location of object O. In some variations, the targeting control module may additionally or alternatively adjust the position of the targeting sensor and / or the implement to follow the object to account for motion of the vehicle while targeting.

[0056] In some variations, the targeting sensor may be controlled to engage multiple targets substantially simultaneously. For example, it may utilize a rapid point-to-point movement system to quickly redirect the laser and / or other implements from one target to the next. Additionally or alternatively, the implement may include a multi-beam laser capable of splitting its focus to target several locations in quick 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 may generate the precise timing and movement patterns to align the laser with each predicted location of the objects. This may enable the targeting sensor to follow a pre-determined path that intersects with the objects at the right moments, considering the continuous movement of the autonomous plant targeting system through the field.

[0057] The targeting control module may deactivate the implement after the object has been manipulated (e.g., grabbed, sprayed, burned, or irradiated), after the region including the object has been targeted with the implement, when the object is no longer detected and / or otherwise identified by the prediction system, after a designated period of time has elapsed, and / or any combination thereof. For example, the targeting control module may deactivate a laser emitter after a region on the surface comprising a plant has been scanned by the beam, after the plant has been irradiated or burned, or after the beam has been activated for a predetermined period of time.II. Proximity -based targeting

[0058] An autonomous method of targeting objects of interest based on proximity to an identified object of interest may include automated targeting (e.g., damage, destroy, or otherwise take an action upon) of select objects of interest based on their location relative to the location of an identified object of interest that is intended to be maintained (e.g., not targeted). The identified object of interest that is intended to be maintained may also be referred to herein as a “primary object” and the objects of interest intended to be targeted may also be referred to herein as a “secondary object.” For example, an autonomous plant targeting systemAttorney Docket No. : CBN.011 WO can be configured to identify, in one or more images, a desired plant of interest that is to be maintained and not damaged. A first region (also referred to herein as a “targetable region”) can be defined with respect to that plant of interest, and the system can target one or more plants of interest that are located within the targetable region (e.g., with an implement such as a laser, as described elsewhere herein), such as for damage and / or other manipulation. The autonomous plant targeting system can refrain from targeting at least certain plants outside of the targetable region. Instead, those certain plants of interest that may be identified as located outside of the targetable region can be damaged or otherwise removed through separate, alternative processes (e.g., chemical plant killer, mechanical plant removal, etc.) that may be unsafe to perform within the targetable region without risking damage to the desired plant of interest. Accordingly, the autonomous plant targeting methods based on proximity to a desired plant of interest, in accordance with the present technology, can be used in combination with (e.g., before or after) with such alternative processes to result in thorough and efficient treatment of a field (e.g., crop field).A. Methods for targeting based on proximity to object of interest

[0059] FIG. 7 depicts a flowchart of an example method 700 for autonomously targeting objects (e.g., plants) of interest based on proximity to a selected object of interest. Method 700 can include receiving an image of a field 710 (e.g., crop field, other suitable field, surface, 3D volume in space, or other region including object(s) of interest), characterizing one or more objects of interest in the image using a pre-trained machine learning model 720, selecting a first object of the one or more objects of interest 730, generating a targetable region of the field relative to a location of the first object 740, and selectively targeting one or more objects of interest for damage based at least in part on their locations being inside the targetable region 750. Although the method 700 is primarily described herein with respect to targeting plants as objects of interest, it should be understood that in some variations, the method 700 may be performed with respect to targeting any suitable kind of object(s).

[0060] Receiving an image of a field 710 functions to obtain image data that can be analyzed by the prediction system (e.g., prediction system 400) to characterize object(s) of interest in the imaged field, including identifying one or more objects of interest and predicting one or more properties of the objects of interest. In some variations, multiple images of the field may be received, such as multiple images generated by a prediction sensor in an autonomous vehicle as the autonomous vehicle traverses the imaged field. The received image can be any suitable kind of image (e.g., white light or visible image) generated by a predictionAttorney Docket No. : CBN.011 WO sensor (e.g., prediction sensor 410), such as 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 an image. The received image can be a still image and / or a frame of a video feed, for example. In some variations, the field can include a crop field including one or multiple types of crops. However, the field can include any suitable kind of region that may include objects of interest.

[0061] Characterizing one or more obj ects of interest in the received image using a pretrained machine learning algorithm 720 functions to analyze the received image to identify and / or predict one or more properties of objects of interest located in the field. The received image(s) may be analyzed by the prediction system (e.g., prediction system 400) to predict one or more properties of objects of interest in the images. For example, as described in further detail herein, an identification machine learning model may be trained to identify plants and differentiate plants of interest from other plants, such as crops. The identification machine learning model may predict plant properties for the object, such as a weed score (e.g., confidence score representing likelihood that the object is a weed), a crop score (e.g., confidence score representing likelihood that the object is a crop), weed type, crop type, a quantification (e.g., number) of images in which the object is pictured, and / or visual characteristics of the plant (e.g., size, shape, health, growth stage, etc.). Using these properties, the prediction system may be configured to identify a plant and to differentiate between different plants, such as between a crop and a weed. Additionally or alternatively, the prediction system may be configured to differentiate between different subtypes (e.g., genus or species) of plants, such as type of crop or type of week. Examples of crops that the prediction system may be configured to identify include onion, pepper, strawberry, carrot, corn, soybeans, barley, oats, wheat, alfalfa, cotton, hay, tobacco, rice, sorghum, tomato, potato, grape, rice, lettuce, bean, pea, sugar beet, or brassica (e.g., broccoli, cauliflower, mustard, kale, or brussels sprouts).

[0062] Selecting a first object of the one or more objects of interest 730 functions to designate at least one object among the identified object(s) of interest as a primary object around which the targetable region is based. Selection of an object of interest as a primary object (e.g., for maintaining or keeping undamaged) can be based at least in part on one or more predicted properties of that object of interest. For example, in variations in which the objects of interest are plants of interest, a first plant of interest may be selected as a primaryAttorney Docket No. : CBN.011 WO plant if one or more of its predicted properties satisfy one or more predetermined characteristics (e.g., its type is a designated desired plant type such as a crop, its size is above a threshold size, its shape is approximating a prototypical or ideal shape, its health is above a threshold health state, its growth stage is at least a threshold stage, etc.). In some variations, selection of an object of interest as a primary object can additionally or alternatively be based on one or more predicted properties of multiple objects of interest, such as by comparing respective properties of different objects of interest. For example, in variations in which the objects of interest are plants of interest, a first plant of interest out of multiple plants of interest characterized within a certain region can be selected as a primary plant if that first plant of interest is the largest, has the best health, exhibits the furthest developed growth stage, and / or has the most prototypical or ideal shape, etc. compared to the other plants of interest within that region.

[0063] After a first or primary object is selected, a first region (also referred to herein as a “targetable region”) relative to the location of that object may be defined. Generating a targetable region of the field relative to a location of the first object 740 functions to define a targetable region within which objects of interest (other than the primary object) are targeted for an action, such as damage or removal. For example, in variations in which the objects of interest are plants, the primary plant can be a crop that is desired to be maintained, and plants of interest located within the targetable region can be secondary plants such as undesirable weeds or crops (e.g., for crop thinning) that are targeted for damage. In some variations, this targetable region can represent a buffer region around the primary plant, where it may endanger the primary plant to utilize conventional crop maintenance methods (e.g., chemical spray) to plants within the targetable region, but it may be acceptably low risk to utilize conventional crop maintenance methods to plants outside the targetable region.

[0064] FIG. 8 is an illustrative schematic of an example targetable region 810 defined relative to a primary plant 802 (or other object). For example, after the primary plant 802 is identified and selected as a primary plant for maintaining, the targetable region 810 can be defined as a two-dimensional region surrounding the primary plant 802. The targetable region 810 can, for example, be defined by a rectangular (e.g., square) perimeter around the primary plant 802. Outside of this targetable region 810 is a second region 820 (also referred to herein as a “non-targetable region”), within which in some embodiments, any identified objects of interest can be “ignored” (e.g., not targeted). However, it should be understood that in some embodiments, one or more identified objects of interest within the second region 820 (outside of the targetable region 810) can still be targeted. For example, as described below withAttorney Docket No. : CBN.011 WO reference to FIG. 12, in some embodiments a plant of interest can be identified as located in the second region 820 and identified as a secondary plant to be targeted for removal (e.g., for crop thinning).

[0065] The targetable region can have any suitable shape and / or size. In some variations, the targetable region can be defined at least in part by a perimeter, which can be any suitable shape. FIGS. 9A-9F are illustrative schematics of various example targetable regions 810. For example, although FIG. 8 illustrates a targetable region 810 that is generally rectangular (e.g., square), the targetable region 810 can be circular (e.g., FIG. 9A) or elliptical (e.g., FIG. 9B). As another example, the targetable region 810 can have a polygonal perimeter, such as diamond-shaped (e.g., FIG. 9C), pentagonal, hexagonal, and / or any polygon having any suitable number of sides (e.g., six, seven, eight, or more sides). As another example, the targetable region 810 can include a segment of a circle or ellipse (FIG. 9E). As another example, the targetable region 810 can have an irregular perimeter (FIG. 9F). In some variations, the targetable region 810 can be regular or irregular, and / or exhibit symmetry or asymmetry (e.g., radial symmetry, bilateral symmetry, etc.). As yet another example, the targetable region 810 can have a shape resembling the real -world shape of the object. In some variations, machine learning algorithms and / or computer vision algorithms (e.g., edge detection techniques, image segmentation techniques, etc.) can identify edges of the primary object in the image, an algorithm can fit complex polygons or spline curves around the detected edges of the primary object, and the targetable region 810 can be generated to have a perimeter resembling a scaled version modeled real -world shape of the object (e.g., with an added buffer distance offset from the outline of the object’s shape).

[0066] Additionally or alternatively, the targetable region can have one or more predetermined characteristics relative to the primary object. For example, in some variations, the targetable region 810 can be generally centered around the primary object 802 (e.g., FIG. 8, FIG. 9A, FIG. 9B, etc.). As another example, in some variations, the targetable region 810 can be generally off-center from the primary object, such that the primary object 802 is offset from a geometrical center of the targetable region 810 (e.g., FIG. 9B, FIG. 9C).

[0067] The targetable region 810 can, in some variations, be generated based at least in part on user input. For example, in some variations, the targetable region 810 can be based at least in part on a user selection of a desired targetable region 810, such as from a set of prepopulated or predefined types of targetable regions 810 that vary in size, shape, degree of centeredness relative to a primary object, and / or the like. Additionally or alternatively, theAttorney Docket No. : CBN.011 WO shape of the targetable region 810 can be generated based on a manual outline that is drawn or otherwise input by a user (e.g., traced on a display screen, etc.).

[0068] Additionally or alternatively, the targetable region 810 can be generated based at least in part on one or more properties of the primary object. For example, different sizes, shapes, and / or other characteristics of a desired targetable region 810 can be associated with different object types. In variations in which the objects of interest are plants, for example, different types of targetable regions 810 may be associated with different types of primary plants (e.g., crops). For example, a first type of targetable region 810 may be generated for a first type of crop, while a second type of targetable region 810 may be generated for a second type of crop.

[0069] Additionally or alternatively, in some variations, the size of the generated targetable region 810 generated may scale with the size of the primary object 802. For example, a first type of targetable region 810 may be generated for a first size of primary plant, while a second type of targetable region 810 may be generated for a second size of primary plant (e.g., larger crops or other primary plants may generally warrant larger targetable regions 810).

[0070] Additionally or alternatively, in some variations in which the objects of interest are plants, the targetable region 810 can be generated based at least in part on a type of alternative crop maintenance technique to be used outside of the targetable region 810 (e.g., in the non-targetable region 820), as different types of alternative crop maintenance techniques may warrant different sizes and / or shapes (and / or other characteristics) of buffer regions to reduce risk of damage to the primary plant. For example, a first type of targetable region 810 (e.g., particular size, shape, etc.) may be generated for a first type of alternative crop maintenance technique to be used in the non-targetable region 820, while a second type of targetable region 810 may be generated for a second type of alternatively crop maintenance technique to be used in the non-targetable region 820.

[0071] Furthermore, any one or more targetable region types can be stored in memory and selected by a user for use in the method 700. In some variations, a type of targetable region 810 configuration can be saved as associated with a certain object type (e.g., crop type), and / or associated with any other characteristic. For example, a user may save a “lettuce” configuration for targetable regions 810 to be used in instances where the primary plant is lettuce, and a “carrot” configuration different from the “lettuce configuration” for targetable regions 810 to be used in instances where the primary plant is carrot. Such saved targetable regionAttorney Docket No. : CBN.011 WO configurations may be selected by a user, automatically selected upon identification of the primary plant as a particular plant type associated with a particular targetable region configuration, etc.

[0072] In some variations, the method may include generating multiple instances of the same type of targetable region 810 in the field (e.g., in instances in which the field includes one type of primary object, such as one type of crop). However, in some variations the method may include generating different types of targetable regions 810 for multiple primary objects in the field. For example, as shown schematically in FIG. 10, in some variations a field may include a first primary object 802a (e.g., first crop type, first crop size, etc.) for which a first type of targetable region 810a (e.g., square region) is generated, a second primary object 802b (e.g., second crop type, second crop size, etc.) for which a second type of targetable region 810b (e.g., circular region) is generated.

[0073] Selectively targeting one or more objects of interest based at least in part on their locations being inside the targetable region 750 functions to designate objects located within the targetable region 810 that are suitable for damage (e.g., removal). In some variations, certain objects of interest may also be selected for targeting based at least in part on one or more object properties. For example, in variations in which the objects of interest are plants, the method may include targeting plants within the targetable region that have a particular threshold weed score, crop score, health status, size, growth stage, etc. For example, targeted plants in the targetable region may be weeds, crops to be thinned, etc. However, in some variations the method may include targeting any identified plant (e.g., as identified and / or otherwise characterized by the object detection system) that is located within the targetable region 810. Plants located outside of the targetable region may be ignored or otherwise designated as non-targeted plants. FIG. 8 schematically illustrates an example arrangement of a primary object 802 intended to be maintained or kept, targeted objects of interest 804, and non-targeted objects of interest 806, in relation to a targetable region 810 and a non-targetable region 820. In particular, targeted obj ects of interest 810 are located within the targetable region 810, and non-targeted objects of interest 806 are located within the non-targetable region 820.

[0074] Once one or more objects of interest are designed as targeted objects, such targeted objects may be on the receiving end of an action causing damage (e.g., for removal of the targeted object). For example, instructing an implement to damage the targeted objects 760 may involve instructing a targeting system (e.g., targeting system 450) to perform an action on the targeted object, such as to manipulate the targeted object. For example, the targeting systemAttorney Docket No. : CBN.011 WO may be instructed to direct a laser beam toward the targeted objects to irradiate and bum the targeted objects. For example, U.S. Patent No. 11,602,143, which is incorporated herein by reference, describes example autonomous targeting systems that may be used to perform actions to damage targeted objects. Although in some variations targeting one or more objects of interest may involve damaging (e.g., killing) the targeted object(s) of interest (e.g., with a laser, etc.), in some variations targeting may additionally or alternatively include manipulating the targeted object(s) of interest in any suitable manner, including but not limited to improving the health of the targeted object(s) of interest (e.g., applying a beneficial light and / or other substance to the targeted object(s) of interest).B. Examples

[0075] FIG. 11 is a schematic illustration of the targeting of plants based on proximity to crops, in an example implementation of a weeding process. FIG. 11 illustrates a field 1110 including a series of crops (e.g., arranged in a grid). Various plants of interest are identified in images, and one or more properties of the plants of interest are predicted, as crop score, weed score, etc. (e.g., using method 700 performed by an autonomous plant targeting system). Based on these predicted properties, certain plants may be identified as crops 802.

[0076] A targetable zone 810 is defined around each crop 802, and portions of the field 1110 not including the targetable zone 810 and crops 802 are designated collectively or individually as a non-targetable zone 820. The targetable zones 810 are shown in FIG. 11 as square and centered around their respective desired crops 802, but it should be understood that the targetable zones 810 may include a boundary or perimeter of any suitable shape, and may or may not be centered around their respective desired crops 802. Furthermore, while the multiple targetable zones 810 are shown in FIG. 11 as non-overlapping (e.g., with a portion of the non-targetable zone 820 separating adjacent targetable zones 810), in some variations two or more targetable zones 810 may at least partially overlap.

[0077] In this variation of field 1110, certain plants of interest located inside of a targetable zone 810 may be designated as targeted plants of interest 804 (e.g., for damage or other removal), and may receive damage such as with a laser implement on the autonomous plant targeting system. Generally, such targeted plants of interest 804 may include weeds, but may also include any other undesired plant or other undesired object. Meanwhile, plants of interest 806 in the non-targetable zone 820 may be left unaffected by the autonomous plantAttorney Docket No. : CBN.011 WO targeting system, and may be damaged or otherwise removed through alternative crop maintenance techniques, such as chemical- or mechanical-based processes.[00781 FIG. 12 is a schematic illustration of the targeting of plants based on proximity to crops in an example implementation of a hybrid weeding and crop thinning process. FIG. 12 illustrates a field 1210 including a series of crops (e.g., arranged in a grid). Various plants of interest are identified in images, and one or more properties of the plants of interest are predicted, as crop score, weed score, etc. (e.g., using method 700 performed by an autonomous plant targeting system). Based on these predicted properties, certain plants may be identified as crops. However, some crops may be characterized as crops 802 desired to be maintained (e.g., based on size, shape, health state, growth stage, etc.), while other crops may be characterized as crops 804b that are desired to be removed through crop thinning (e.g., based on size, shape, health state, growth stage, proximity to nearby desired crops, etc.).[00791 A targetable zone 810 is defined around each desired crop 802, and portions of the field 1210 not including the targetable zone 810 and desired crops 802 are designated collectively or individually as a non-targetable zone 820. Targetable zones 810 are not defined around the undesired crops 804b, such that undesired crops 804b are located in the nontargetable zone 820. The targetable zones 810 are shown in FIG. 11 as square and centered around their respective desired crops 802, but it should be understood that the targetable zones 810 may include a boundary or perimeter of any suitable shape, and may or may not be centered around their respective desired crops 802. Furthermore, while the multiple targetable zones 810 are shown in FIG. 12 as non-overlapping (e.g., with a portion of the non-targetable zone 820 separating adjacent targetable zones 810), in some variations two or more targetable zones 810 may at least partially overlap.

[0080] In this variation of field 1210, both certain plants of interest located inside of a targetable zone 810 and certain plants of interest located outside of the targetable zone 810 (e.g., in the non-targetable zone 820) may be designated as targeted plants of interest (e.g., for damage or other removal), and may receive damage such as with a laser implement on the autonomous plant targeting system. For example, targeted plants of interest 804a located inside of the targetable zone 810 may include weeds, but may additionally or alternatively include any other undesired plant (e.g., misplaced crop) or other undesired object. Furthermore, targeted plants of interest 804b located outside of the targetable zone 810 (e.g., in the nontargetable zone 820) may include crops to be thinned, but may also include any other undesired plant or object. Meanwhile, other plants of interest 806 (which may include weeds and / or anyAttorney Docket No. : CBN.011 WO other undesired plant or object) in the non-targetable zone 820 may be left unaffected by the autonomous plant targeting system, and may be damaged or otherwise removed through alternative crop maintenance techniques, such as chemical- or mechanical-based processes.III. Computer systems and methods[0081| The methods described herein may be implemented using a computer system. In some variations, the systems described herein include a computer system. In some variations, a computer system may implement the methods autonomously without human input. In some variations, a computer system may implement the methods based on instructions provided by a human user through a detection terminal.[0082| FIG. 5 illustrates components in a block diagram of a non-limiting example variation of a detection terminal 1400 according to various aspects of the present disclosure. In some variations, the detection terminal 1400 is a device that displays a user interface in order to provide access to the detection system. As shown, the detection terminal 1400 includes a detection interface 1420. The detection interface 1420 allows the detection terminal 1400 to communicate with a detection system, such a detection system of FIG. 3 or FIG. 4. In some variations, the detection interface 1420 may include an antenna configured to communicate with the detection system, for example by remote control. In some variations, the detection terminal 1400 may also include a local communication interface, such as an Ethernet interface, a Wi-Fi interface, or other interface that allows other devices associated with detection system to connect to the detection system via the detection terminal 1400. For example, a detection terminal may be a handheld device, such as a mobile phone, running a graphical interface that enables a user to operate or monitor the detection system remotely over Bluetooth, Wi-Fi, or mobile network.[0083| The detection interface may support various communication protocols to ensure compatibility and interoperability with different devices and systems. These protocols could include cellular networks (e.g., LTE, 5G) for remote communication, enabling the user to control and receive updates from the system from virtually anywhere, and LoRaW AN for long range, low-power communication, particularly useful in rural or expansive agricultural settings. Regarding the hardware associated with the detection interface 1420, the detection interface may include hardware components such as: transceivers capable of both transmitting and receiving signals, signal amplifiers to boost communication range and quality, microcontrollers or processors to manage communication protocols and data handling, powerAttorney Docket No. : CBN.011 WO management circuits to ensure efficient energy use, especially when the system is battery powered. In other example variations, the detection interface enables several functional capabilities, such as: real-time data transmission, allowing the user to receive live updates on the system's status and the progress of the object targeting process; remote control commands, enabling the user to start, stop, or adjust the operation of the autonomous object targeting system from the detection terminal; software updates and configuration changes that can be sent to the autonomous system to improve performance or modify operational parameters; and diagnostic data retrieval for maintenance and troubleshooting purposes.[0084| The detection terminal 1400 further includes detection engine 1410. The detection engine may receive information regarding the status of a detection system, for example a detection system of FIG. 3 or FIG. 4. The detection engine may receive information regarding the number of objects identified, the identity of objects identified, the location of objects identified, the trajectories and predicted locations of objects identified, the number of objects targeted, the identity of objects targeted, the location of objects targeted, the location of the detection system, the elapsed time of a task performed by the detection system, an area covered by the detection system, a battery charge of the detection system, or combinations thereof.

[0085] In some example variations, the detection engine may receive additional types of information, including: environmental data such as: temperature and humidity levels; soil moisture content; weather conditions impacting the operation, such as 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 rate, indicating how quickly the system is progressing through the field; number of objects targeted per unit of time; operational logs detailing system activity and any errors or malfunctions. Furthermore, the detection engine may receive data points that provide insights into the health and status of the crops, such as spectral analysis results that may indicate plant stress or disease; growth metrics, including plant height and leaf area index (LAI); imagery data that could reveal signs of pest infestation or nutrient deficiencies. Even further, the detection engine may receive information related to the autonomous system's navigation and positioning 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.Attorney Docket No. : CBN.011 WO

[0086] Actual variations of the illustrated devices may have more components included therein which are known to one of ordinary skill in the art. For example, each of the illustrated devices may have a power source, one or more processors, computer-readable media for storing computer-executable instructions, and so on. These additional components are not illustrated herein for the sake of clarity.

[0087] In some examples, the procedures described herein may be performed by a computing device or apparatus, such as a computing device having the computing device architecture 1600 shown in FIG. 6. In one example, the procedures described herein can be performed by a computing device with the computing device architecture 1600. The computing device can 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., in 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 method 700. In some cases, the 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 component that is configured to carry out the steps of processes described herein. In some examples, the computing device may include a display (as an example of the output device or in addition to the output device), a network interface configured to communicate and / or receive the data, any combination thereof, and / or other component(s). The network interface may be configured to communicate and / or receive Internet Protocol (IP) based data or other type of data.

[0088] The components of the computing device can be implemented in circuitry. For example, the components can include and / or can be implemented using electronic circuits or other electronic hardware, which can include one or more programmable electronic circuits (e.g., microprocessors, graphics processing units (GPUs), digital signal processors (DSPs), central processing units (CPUs), and / or other suitable electronic circuits), and / or can include and / or be implemented using computer software, firmware, or any combination thereof, to perform the various operations described herein.

[0089] Method 700 is illustrated as logical flow diagrams, the operation of which represent a sequence of operations that can 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,Attorney Docket No. : CBN.011 WO 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 the processes.

[0090] 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) executing collectively on one or more processors, by hardware, or combinations 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.

[0091] FIG. 6 illustrates an example computing device architecture 1600 of an example computing device which can implement the 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 vehicles shown in FIG. 1 and FIG. 2. The components of computing device architecture 1600 are shown in electrical communication with each other using connection 1605, such as a bus. The example computing device architecture 1600 includes a processing unit (which may include a CPU and / or GPU) 1610 and computing device connection 1605 that couples various computing device components including computing device memory 1615, such as read only memory (ROM) 1620 and random access memory (RAM) 1625, to processor 1610. In some variations, a computing device may comprise a hardware accelerator.

[0092] Computing device architecture 1600 can include a cache of high-speed memory connected directly with, in close proximity to, or integrated as part of processor 1610. Computing device architecture 1600 can copy data from memory 1615 and / or the storage device 1630 to cache 1612 for quick access by processor 1610. In this way, the cache can provide a performance boost that avoids processor 1610 delays while waiting for data. These and other modules can control or be configured to control processor 1610 to perform various actions. Other computing device memory 1615 may be available for use as well. Memory 1615 can include multiple different types of memory with different performance characteristics.Attorney Docket No. : CBN.011 WOProcessor 1610 can include any general purpose processor and a hardware or software service, such as service 1 1632, service 2 1634, and service 3 1636 stored in storage device 1630, configured to control processor 1610 as well as a special-purpose processor where software instructions are incorporated into the processor design. Processor 1610 may be a self-contained system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

[0093] To enable user interaction with the computing device architecture, input device 1645 can represent any number of input mechanisms, such as a microphone for speech, a touch sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech and so forth. Output device 1635 can also be one or more of a number of output mechanisms known to those of skill in the art, such as a display, projector, television, speaker device, etc. In some instances, multimodal computing devices can enable a user to provide multiple types of input to communicate with computing device architecture 1600. Communication interface 1640 can generally govern and manage the user input and computing device output. There is no restriction on operating on any particular hardware arrangement and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

[0094] Storage device 1630 is a non-volatile memory and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, cartridges, random access memories (RAMs) 1625, read only memory (ROM) 1620, and hybrids thereof. Storage device 1630 can include services 1632, 1634, 1636 for controlling processor 1610. Other hardware or software modules are contemplated. Storage device 1630 can be connected to the computing device connection 1605. In one aspect, a hardware module that performs a particular function can include the software component stored in a computer-readable medium in connection with the necessary hardware components, such as processor 1610, connection 1605, output device 1635, and so forth, to carry out the function.Conclusion

[0095] Although many of the variations are described above with respect to systems, devices, and methods for autonomous plant targeting, the technology is applicable to other applications and / or other approaches. Moreover, other variations in addition to those described herein are within the scope of the technology. Additionally, several other variations of theAttorney Docket No. : CBN.011 WO technology can have different configurations, components, or procedures than those described herein. A person of ordinary skill in the art, therefore, will accordingly understand that the technology can have other variations with additional elements, or the technology can have other variations without several of the features shown and described above with reference to FIGS 1-12.

[0096] The descriptions of variations of the technology are not intended to be exhaustive or to limit the technology to the precise form disclosed above. Where the context permits, singular or plural terms may also include the plural or singular term, respectively. Although specific variations of, and examples for, the technology are described above for illustrative purposes, various equivalent modifications are possible within the scope of the technology, as those skilled in the relevant art will recognize. For example, while steps are presented in a given order, alternative variations may perform steps in a different order. The various variations described herein may also be combined to provide further variations.

[0097] As used herein, the terms “generally,” “substantially,” “about,” and similar terms are used as terms of approximation and not as terms of degree, and are intended to account for the inherent variations in measured or calculated values that would be recognized by those of ordinary skill in the art.

[0098] Moreover, unless the word “or” is expressly limited to mean only a single item exclusive from the other items in reference to a list of two or more items, then the use of “or” in such a list is to be interpreted as including (a) any single item in the list, (b) all of the items in the list, or (c) any combination of the items in the list. Additionally, the term "comprising" is used throughout to mean including at least the recited feature(s) such that any greater number of the same feature and / or additional types of other features are not precluded. It will also be appreciated that specific variations have been described herein for purposes of illustration, but that various modifications may be made without deviating from the technology. Further, while advantages associated with certain variations of the technology have been described in the context of those variations, other variations may also exhibit such advantages, and not all variations need necessarily exhibit such advantages to fall within the scope of the technology. Accordingly, the disclosure and associated technology can encompass other variations not expressly shown or described herein.

Claims

Attorney Docket No. : CBN.011 WOCLAIMSI / We claim:

1. A method comprising: receiving an image of a field; characterizing one or more objects of interest in the image using a pre-trained machine learning model; selecting a first object of the one or more objects of interest; generating a targetable region of the field relative to a location of the first object; and selectively targeting one or more objects of interest for damage based at least in part on their locations being inside the targetable region.

2. The method of claim 1, further comprising instructing an implement to damage the targeted one or more objects of interest.

3. The method of claim 2, wherein the implement comprises a laser capable of irradiating the targeted one or more objects of interest.

4. The method of any one of claims 1-3, further comprising identifying one or more objects of interest for no action, based at least in part on their locations being outside of the targetable region.

5. The method of any one of claims 1-4, further comprising selectively targeting one or more objects of interest for damage based at least in part on their locations being outside the targetable region.

6. The method of any one of claims 1-5, wherein the targetable region is defined at least in part by a perimeter centered around the location of the first object.

7. The method of any one of claims 1-6, wherein a size of the targetable region corresponds to a property of the first object.Attorney Docket No. : CBN.011 WO8. The method of any one of claims 1-7, wherein the targetable region is defined based at least in part by a user input.

9. The method of any one of claims 1-8, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one object of interest in the image.

10. The method of claim 9, wherein the one or more properties is stored in an embedding associated with the at least one object of interest.

11. The method of claim 9 or 10, wherein the one or more properties comprises a first object score representing likelihood that the at least one object of interest is a first object type, and / or a second object score representing likelihood that the at least one object of interest is a second object type.

12. The method of any one of claims 9-11, wherein selecting a first object of the one or more objects of interest comprises selecting the first object based at least in part on the one or more properties of the first object.

13. The method of any one of claims 1-12, wherein the first object is a crop.

14. The method of any one of claims 1-13, wherein at least one of the targeted objects of interest is a weed.

15. The method of any one of claims 1-14, wherein at least one of the targeted objects of interest is a crop.Attorney Docket No. : CBN.011 WO16. A system comprising: a processor; and a memory operably coupled to the processor and storing instructions that, when executed by the processor, cause the system to: receive an image of a field; characterize one or more objects of interest in the image using a pre-trained machine learning model; select a first object of the one or more objects of interest; generate a targetable region of the field relative to a location of the first object; and selectively target one or more objects of interest for damage based at least in part on their locations being inside the targetable region.

17. The system of claim 16, wherein the instructions, when executed by the processor, cause the system to instruct an implement to damage the targeted one or more objects of interest.

18. The system of claim 17, wherein the implement comprises a laser capable of irradiating the targeted one or more objects of interest.

19. The system of any one of claims 16-18, wherein the instructions, when executed by the processor, cause the system to identify one or more objects of interest for no action, based at least in part on their locations being outside of the targetable region.

20. The system of any one of claims 16-19, wherein the instructions, when executed by the processor, cause the system to selectively target one or more objects of interest for damage based at least in part on their locations being outside the targetable region.

21. The system of any one of claims 16-20, wherein the targetable region is defined at least in part by a perimeter centered around the location of the first object.

22. The system of any one of claims 16-21, wherein a size of the targetable region corresponds to a property of the first object.Attorney Docket No. : CBN.011 WO23. The system of any one of claims 16-22, wherein the targetable region is defined based at least in part by a user input.

24. The system of any one of claims 16-23, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one object of interest in the image.

25. The system of claim 24, wherein the one or more properties is stored in an embedding associated with the at least one object of interest.

26. The system of claim 24 or 25, wherein the one or more properties comprises a first object score representing likelihood that the at least one object of interest is a first object type, and / or a second object score representing likelihood that the at least one object of interest is a second object type.

27. The system of any one of claims 24-26, wherein when the instructions cause the system to select a first object, the system selects the first object based at least in part on the one or more properties of the first object.

28. The system of any one of claims 16-27, wherein the first object is a crop.

29. The system of any one of claims 16-28, wherein at least one of the targeted objects of interest is a weed.

30. The system of any one of claims 16-29, wherein at least one of the targeted objects of interest is a crop.Attorney Docket No. : CBN.011 WO31. A method compri sing : receiving an image of a crop field; identifying one or more plants of interest in the image using a pre-trained machine learning model; selecting a desired plant of the one or more plants of interest; generating a targetable region of the crop field relative to a location of the desired plant; and selectively targeting one or more plants of interest for damage based at least in part on their locations being inside the targetable region.

32. The method of claim 31, further comprising instructing an implement to damage the targeted one or more plants of interest.

33. The method of claim 32, wherein the implement comprises a laser capable of irradiating the targeted one or more plants of interest.

34. The method of any one of claims 31-33, further comprising identifying one or more plants of interest for no action, based at least in part on their locations being outside of the targetable region.

35. The method of any one of claims 31-34, further comprising selectively targeting one or more plants of interest for damage based at least in part on their locations being outside the targetable region.

36. The method of any one of claims 31-35, wherein the targetable region is defined at least in part by a perimeter centered around the location of the desired plant.

37. The method of any one of claims 31-36, wherein a size of the targetable region corresponds to a property of the desired plant.

38. The method of any one of claims 31-37, wherein the targetable region is defined based at least in part by a user input.Attorney Docket No. : CBN.011 WO39. The method of any one of claims 31-38, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one plant of interest in the image.

40. The method of claim 39, wherein the one or more properties is stored in an embedding associated with the at least one plant of interest.

41. The method of claim 39 or 40, wherein the one or more properties comprises a crop score representing likelihood that the at least one plant of interest is a crop, and / or a weed score representing likelihood that the at least one plant of interest is a weed.

42. The method of any one of claims 39-41, wherein the one or more properties comprises at least one of health, size, or growth stage of the plant of interest.

43. The method of any one of claims 39-42, wherein selecting a desired plant of the one or more plants of interest comprises selecting the desired plant based at least in part on the one or more properties of the desired plant.

44. The method of any one of claims 31-43, wherein the desired plant is a crop.

45. The method of any one of claims 31-44, wherein at least one of the targeted plants of interest is a weed.

46. The method of any one of claims 31-45, wherein at least one of the targeted plants of interest is a crop.Attorney Docket No. : CBN.011 WO47. A system comprising: a processor; and a memory operably coupled to the processor and storing instructions that, when executed by the processor, cause the system to: receive an image of a crop field; identify one or more plants of interest in the image using a pre-trained machine learning model; select a desired plant of the one or more plants of interest; generate a targetable region of the crop field relative to a location of the desired plant; and selectively target one or more plants of interest for damage based at least in part on their locations being inside the targetable region.

48. The system of claim 47, wherein the instructions, when executed by the processor, cause the system to instruct an implement to damage the targeted one or more plants of interest.

49. The system of claim 48, wherein the implement comprises a laser capable of irradiating the targeted one or more plants of interest.

50. The system of any one of claims 47-49, wherein the instructions, when executed by the processor, cause the system to identify one or more plants of interest for no action, based at least in part on their locations being outside of the targetable region.

51. The system of any one of claims 47-50, wherein the instructions, when executed by the processor, cause the system to selectively target one or more objects of interest for damage based at least in part on their locations being outside the targetable region.

52. The system of any one of claims 47-51, wherein the targetable region is defined at least in part by a perimeter centered around the location of the desired plant.

53. The system of any one of claims 47-52, wherein a size of the targetable region corresponds to a property of the desired plant.Attorney Docket No. : CBN.011 WO54. The system of any one of claims 47-53, wherein the targetable region is defined based at least in part by a user input.

55. The system of any one of claims 47-54, wherein the pre-trained machine learning model is configured to predict one or more properties of at least one plant of interest in the image.

56. The system of claim 55, wherein the one or more properties is stored in an embedding associated with the at least one plant of interest.

57. The system of claim 55 or 56, wherein the one or more properties comprises a crop score representing likelihood that the at least one plant of interest is a crop, and / or a weed score representing likelihood that the at least one plant of interest is a weed.

58. The system of any one of claims 55-57, wherein the one or more properties comprises at least one of health, size, or growth stage of the plant of interest.

59. The system of any one of claims 55-58, wherein selecting a desired plant of the one or more plants of interest comprises selecting the desired plant based at least in part on the one or more properties of the desired plant.

60. The system of any one of claims 47-59, wherein the desired plant is a crop.

61. The system of any one of claims 47-60, wherein at least one of the targeted plants of interest is a weed.

62. The system of any one of claims 47-61, wherein at least one of the targeted plants of interest is a crop.

Images