Autonomous laser weed eradication

Abstract

The application relates to autonomous laser weed eradication, and provides a system for damaging or killing plants, the system comprising: a first camera, a second camera, a light source, a control system, and a computing system, the computing system is configured to: receive, at a first time, a first image of at least one plant in the field captured by the first camera; identifying a plant in the first image; predicting the position of the plant based on the first image; causing the second camera to capture a second image of an area of the field including the predicted position; predicting a target position of the plant in the second image at a second time after the first time, wherein movement of the second camera relative to the surface during the elapsed time is taken into account; causing the control system to direct an optical path of the light beam toward the predicted target position; the light source is caused to emit a light beam toward the predicted target location of the plant for a length of time sufficient to damage or kill the plant.

Description

[0001] This is a divisional application, with its parent application number being 202080079695.0, the international application date being September 16, 2020, and the invention title being Autonomous Laser Weed Eradication.

[0002] Cross-references to related applications This application claims the benefit of U.S. Provisional Application No. 62 / 901,641, filed September 17, 2019, which is incorporated herein by reference in its entirety. Background Technology

[0003] Global agricultural output is worth trillions of dollars annually. Agriculture is a vital component of food production and encompasses the cultivation of both livestock and plants. Population growth and declining crop yields due to climate change threaten global food security. Methods to increase agricultural production by improving crop yields and labor efficiency may help alleviate food shortages. Summary of the Invention

[0004] This disclosure provides various methods, apparatuses, modules, and systems that can be adopted for the automated identification, maintenance, control, or targeting of plants. For example, the methods, apparatuses, modules, and systems disclosed herein can be used to autonomously identify and eradicate weeds located in crop fields. These methods, apparatuses, modules, and systems can be used as alternatives to manual cultivation or chemical herbicides. For example, these methods, apparatuses, modules, and systems can be used for crop management or for home weed control.

[0005] In various aspects, this disclosure provides an optical control system comprising: a transmitter configured to emit a beam along an optical path toward a target location on a surface, wherein the target location is determined by autonomously positioning a target on the surface; a first reflective element positioned to intersect the optical path and deflect the beam; a first aiming actuator connected to the first reflective element and configured to rotate the first reflective element and deflect the beam toward the target location; and a combining element positioned in the optical path between the transmitter and the first reflective element and configured to differentially deflect the beam and scattered light from the target location traveling along the optical path in a direction opposite to the beam.

[0006] In some aspects, the optical control system further includes a targeting camera optically connected to the combined elements and configured to receive scattered light reflected off the first reflective element and image a targeting field of view including the target position. In some aspects, the optical control system is configured to guide a beam toward the target position while the optical control system moves relative to a surface. In some aspects, the optical control system further includes a targeting system computer configured to detect pixel movement in the targeting field of view relative to the target position and convert the pixel movement of the targeting field of view into rotation of the first reflective element.

[0007] In some aspects, the conversion from pixel movement to rotation of the first reflective element involves a reference calibration function. In other aspects, the calibration function is obtained by associating the position of a reference mark on a calibration surface with the camera pixel movement.

[0008] In some aspects, the optical control system also includes an inertial measurement unit coupled to the optical control system, wherein the inertial measurement unit is configured to measure the acceleration of the optical control system, the rotation of the optical control system relative to the surface, or a combination thereof. In some aspects, the aiming system computer is configured to adjust the target position based on the amount of time since imaging, the acceleration of the optical control system, the rotation of the optical control system relative to the surface, or a combination thereof.

[0009] In some aspects, the optical control system is enclosed in a housing that includes an exit window capable of transmitting emitted and visible light and positioned in an optical path between the first reflective element and the surface. In some aspects, the optical control system is completely enclosed in the housing. In some aspects, the optical control system also includes an air source configured to guide the incoming airflow. In some aspects, the housing also includes a wall opposite the aperture configured to control the direction of the airflow and reduce turbulence without obstructing the beam.

[0010] In some aspects, the first reflecting element is a mirror. In some aspects, the combined element transmits the beam and reflects visible light. In some aspects, the emitter is a laser emitter. In some aspects, the laser emitter is selected from the group consisting of infrared lasers, ultraviolet lasers, and visible light lasers. In some aspects, the optical control system further includes a second aiming actuator connected to the first reflecting element and configured to rotate the first reflecting element and deflect the beam toward a target position. In some aspects, the optical control system further includes: a second reflecting element positioned to intersect the optical path and deflect the beam deflected by the first reflecting element; and a second aiming actuator connected to the second reflecting element and configured to rotate the second reflecting element and deflect the beam toward a target position. In some aspects, the first aiming actuator deflects the beam along a first axis, and the second aiming actuator deflects the beam along a second axis, wherein the first axis and the second axis are orthogonal. In some respects, the combining element is positioned behind the transmitter, the first reflective element is positioned behind the combining element, and the second reflective element is positioned behind the first reflective element, relative to the direction of the beam. In some respects, the weeds are positioned at the target location.

[0011] In various aspects, this disclosure provides a weed eradication method comprising: capturing an image of a predicted field of view using a predictive camera; locating a target in the predicted field of view; assigning the target to one of a plurality of aiming modules, the plurality of aiming modules including an aiming camera having an aiming field of view overlapping the location of the target; capturing an image of the aiming field of view using the aiming camera; locating the target in the aiming field of view; and guiding a beam toward the location of the target.

[0012] In some aspects, locating a target in a predicted field of view also includes identifying the target's orientation within the predicted field of view. In some aspects, the weeding method also includes identifying a region containing the target, wherein the region is defined by a polygon. In some aspects, the weeding method also includes converting the orientation into a predicted surface position. In some aspects, the weeding method also includes determining the expected movement within the aiming field of view. In some aspects, the weeding method also includes converting the expected movement into an actuator orientation change. In some aspects, locating a target includes identifying the target using a trained neural network. In some aspects, the trained neural network is capable of providing a bounding box, a polygon mask, or a combination thereof around the target. In some aspects, the trained neural network is trained using images of the field.

[0013] In some aspects, locating a target within the aiming field of view also includes referencing a calibration function obtained by associating the position of a reference mark on a calibration surface with camera pixel coordinates and correcting the target's position. In some aspects, assigning a target to one of a plurality of aiming modules includes providing the target's position to one of the multiple aiming modules. In some aspects, guiding the beam toward the target's position also includes referencing a calibration function obtained by associating the pixel movement of a reference mark on the calibration surface with an actuator tilt value and correcting the actuator tilt value. In some aspects, the weed eradication method also includes deactivating the beam once the target has been damaged or killed.

[0014] In some applications, the aiming camera is used to capture images of the aiming field of view, locate the target within the aiming field of view, and guide the beam toward the target with high precision. In other applications, the target is weeds.

[0015] In some aspects, weed eradication methods also include damaging or killing the weeds. In some aspects, damaging or killing the weeds includes irradiating them. In some aspects, damaging or killing the weeds includes burning them. In some aspects, targeting involves distinguishing between weeds and intended plants.

[0016] In various aspects, this disclosure provides a targeting system including a prediction module, a targeting module, and an optical control module; the prediction module includes: a prediction camera configured to image a predicted field of view on a surface and locate a target in the predicted field of view; and a prediction module controller configured to convert the position of the target in the predicted field of view into a predicted position on the surface and assign the target to the targeting module; the targeting module includes: a targeting module controller configured to convert the predicted position into the azimuth of a targeting actuator; and the optical control module includes: a transmitter configured to emit a beam toward the target along an optical path; and a targeting actuator configured to receive azimuth information from the targeting module controller and deflect the beam toward the target.

[0017] In some aspects, the aiming system also includes an aiming camera configured to image an aiming field of view on a surface and locate a target within the aiming field of view. In some aspects, the optical control module also includes: a first reflective element controlled by the aiming actuator and positioned to intersect the optical path and deflect the beam; and a combining element positioned in the optical path between the transmitter and the first reflective element and configured to differentially deflect the beam and scattered light from the aiming field of view traveling along the optical path in the opposite direction to the beam.

[0018] In some aspects, the optical control module is configured to guide the beam toward the target while the aiming system moves relative to the surface. In other aspects, the aiming module is configured to detect pixel movement of the aiming field of view relative to the target and convert that pixel movement into motion of the aiming actuator.

[0019] In some aspects, the aiming system further includes an inertial measurement unit configured to measure the acceleration of the aiming system and the rotation of the aiming system relative to the surface. In some aspects, the aiming module is configured to adjust the predicted position based on the amount of time since imaging, the acceleration of the aiming system, the rotation of the aiming system relative to the surface, or a combination thereof. In some aspects, the aiming system further includes a second aiming module comprising: a second aiming camera configured to image a second aiming field of view on the surface and locate a target within the second aiming field of view; and an aiming module controller configured to convert the position of the target in the second aiming field of view into the orientation of a second aiming actuator. In some aspects, the predicted field of view includes the aiming field of view.

[0020] In some aspects, the targeting system also includes a vehicle that transports the predictive camera and optical control module. In some aspects, the vehicle is autonomous. In some aspects, the vehicle includes multiple wheels.

[0021] In some aspects, the optical control module is enclosed in a housing that includes an vent window capable of transmitting emitted and visible light and positioned in an optical path between the first reflective element and the surface. In some aspects, the optical control module is completely enclosed in the housing. In some aspects, the aiming system also includes an air source configured to direct airflow from an aperture in the outer surface of the housing toward the outer surface of the vent window. In some aspects, the housing also includes a wall opposite the aperture configured to control the direction of the airflow and reduce turbulence without obstructing the beam.

[0022] In some aspects, the first reflecting element is a mirror. In some aspects, the combined element transmits the beam and reflects visible light. In some aspects, the transmitter is a laser transmitter. In some aspects, the laser transmitter is selected from the group consisting of infrared lasers, ultraviolet lasers, and visible light lasers. In some aspects, the optical control module further includes a second aiming actuator connected to the first reflecting element and configured to rotate the first reflecting element and deflect the beam toward the target. In some aspects, the optical control module further includes: a second reflecting element positioned to intersect the optical path and deflect the beam deflected by the first reflecting element; and a second aiming actuator connected to the second reflecting element and configured to rotate the second reflecting element and deflect the beam toward the target. In some aspects, the first aiming actuator deflects the beam along a first axis, and the second aiming actuator deflects the beam along a second axis, wherein the first axis and the second axis are orthogonal. In some aspects, the combined element is positioned after the transmitter, the first reflecting element is positioned after the combined element, and the second reflecting element is positioned after the first reflecting element, relative to the direction of the beam.

[0023] Additional aspects and advantages of this disclosure will become readily apparent to those skilled in the art from the following detailed description, in which only illustrative embodiments of the disclosure are shown and described. As will be appreciated, this disclosure is capable of other and different embodiments, and certain details thereof can be modified in various obvious ways without departing from this disclosure. Therefore, the drawings and description should be considered illustrative in nature and not restrictive.

[0024] All publications, patents and patent applications mentioned in this specification are incorporated herein by reference to the extent that each individual publication, patent or patent application is specifically and individually indicated as incorporated herein by reference. Attached Figure Description

[0025] A better understanding of the features and advantages of this disclosure will be obtained by referring to the following detailed description and accompanying drawings, which illustrate illustrative embodiments in which the principles of this disclosure are utilized, and the accompanying drawings: Figure 1A The figures are isometric views of a laser aiming system according to one or more embodiments herein; Figure 1B The illustration shows an isometric view of a laser aiming system having indicated laser paths and visible light paths according to one or more embodiments herein; Figure 2 The figure shows a top view of a laser aiming system having indicated laser paths and visible light paths according to one or more embodiments herein; Figure 3A The figure shows a side view of a laser aiming system according to one or more embodiments herein; Figure 3B The figure shows a side cross-sectional view of a laser aiming system with an indicated clean air path according to one or more embodiments herein; Figure 4 illustrates a targeting laser and a targeting coverage area of ​​the targeting laser according to one or more embodiments herein; Figure 4A The figure shows a side view of a targeting laser and the targeting coverage area of ​​the targeting laser according to one or more embodiments herein; Figure 4B The figure shows a front view of a targeting laser and the targeting coverage area of ​​the targeting laser according to one or more embodiments herein; Figure 5 The illustration shows an isometric view of a prediction camera, a plurality of aiming lasers, a prediction view area of ​​the prediction camera, and an aiming coverage area of ​​the aiming lasers according to one or more embodiments herein. Figure 6The illustration shows a front view of the coverage area of ​​an autonomous laser weed eradication robot, a predictive camera, and multiple aiming lasers according to one or more embodiments herein. Figure 7 The illustration shows an isometric view of the coverage area of ​​an autonomous laser weed eradication robot, a predictive camera, and multiple aiming lasers according to one or more embodiments herein. Figure 8 Methods for identifying, allocating, and targeting targets according to one or more embodiments herein are described; Figure 9 Methods for identifying, allocating, targeting, and eradicating weeds in fields according to one or more embodiments herein are described. Detailed Implementation

[0026] Crop cultivation is crucial for food and textile production. A vital component of crop management is the control or elimination of unwanted plant species, commonly known as weeds. Weeds reduce crop yields by depriving the intended plant of resources, including water, nutrients, sunlight, and space. Weeds can further interfere with crop growth by harboring pests or parasites that harm the intended plant. Traditional weed control and eradication methods include manual cultivation or chemical herbicides. Manual cultivation is labor-intensive, leading to increased crop production costs and higher food and textile prices. The use of chemical herbicides can have negative environmental impacts, including groundwater contamination, acute toxicity, or long-term health effects such as cancer.

[0027] Developing eco-friendly and low-cost weed control and eradication methods is crucial for higher crop yields, lower food prices, and long-term environmental stability. Reducing or eliminating the need for herbicides can mitigate many negative environmental side effects of crop production, including toxic runoff and groundwater pollution. Reducing the need for manual labor can significantly lower agricultural costs and improve labor standards.

[0028] This disclosure provides various methods, devices, modules, and systems for the automated identification, maintenance, control, or targeting of plants. In some embodiments, the methods, devices, modules, and systems disclosed herein can be used to autonomously identify and eradicate weeds located in crop fields. For example, specific methods are disclosed herein for autonomously locating, identifying, and targeting objects, such as weeds, using beams including electromagnetic radiation. Devices configured to locate, identify, and autonomously target objects using beams are also disclosed herein. These devices can be used, for example, to control or eliminate weeds. For example, the device can be used to burn or irradiate weeds. Modules disclosed herein can be used for the autonomous control of the devices and systems disclosed herein to implement the methods disclosed herein, such as locating, identifying, targeting, and controlling or eliminating weeds. Systems disclosed herein may include devices, modules, and methods configured to autonomously control or eliminate objects (e.g., weeds) by locating, identifying, and targeting objects using projectiles. Sometimes, these methods, devices, modules, and systems can be used for crop management or for home weed control. These methods, devices, modules, and systems can be used as alternatives to manual cultivation or chemical herbicides.

[0029] Optical control system This paper describes an optical control system for guiding a beam (e.g., a light beam) toward a target location on a surface. Figure 1AAn isometric view of an embodiment of the optical control system 100 disclosed herein is illustrated. A transmitter 101 is configured to guide a beam along an optical path 102. In some embodiments, the beam comprises electromagnetic radiation, such as light, radio waves, microwaves, or X-rays. In some embodiments, the light is visible light, infrared light, or ultraviolet light. The beam may be coherent. In a preferred embodiment, the transmitter is a laser, such as an infrared laser. In some embodiments, the transmitter emits a beam having wavelengths of about 1 m, about 100 mm, about 10 mm, about 1 mm, about 100 μm, about 10 μm, about 1.5 μm, about 1 μm, about 900 nm, about 800 nm, about 700 nm, about 600 nm, about 500 nm, about 400 nm, about 300 nm, about 100 nm, about 10 nm, or about 1 nm. In some embodiments, the transmitter emits a beam having a wavelength ranging from about 1 m to about 100 mm, from about 100 mm to about 10 mm, from about 10 mm to about 1 mm, from about 1 mm to about 100 μm, from about 100 μm to about 10 μm, from about 10 μm to about 1.5 μm, from about 1.5 μm to about 1 μm, from about 1 μm to about 900 nm, from about 900 nm to about 800 nm, from about 800 nm to about 700 nm, from about 700 nm to about 600 nm, from about 600 nm to about 500 nm, from about 500 nm to about 400 nm, from about 400 nm to about 300 nm, from about 300 nm to about 100 nm, from about 100 nm to about 10 nm, or from about 10 nm to about 1 nm. In some embodiments, the transmitter may be capable of emitting electromagnetic radiation up to 10 mW, up to 100 mW, up to 1 W, up to 10 W, up to 100 W, up to 1 kW, or up to 10 kW. In some embodiments, the transmitter may be capable of emitting electromagnetic radiation from 10 mW to 100 mW, from 100 mW to 1 W, from 1 W to 10 W, from 10 W to 100 W, from 100 W to 1 kW, or from 1 kW to 10 kW.

[0030] Figure 1B It shows Figure 1A An isometric view of an embodiment of the optical control device 100 is shown, further illustrating the orientation and direction of the beam path 102. Reference numerals are in... Figure 1A and Figure 1BThe arrangement is consistent. One or more optical elements may be positioned in the beam path. The optical elements may include one or more of a beam combiner 103, a first reflective element 105, and a second reflective element 106. These elements may be configured in the direction of the beam path in the order of beam combiner 103, then the first reflective element 105, and then the second reflective element 106. In another example, one or both of the first or second reflective elements may be configured sequentially before the beam combiner in the direction of the beam path. In another example, the optical elements may be configured in the direction of the beam path in the order of beam combiner 103, then the first reflective element 105. In another example, one or both of the first or second reflective elements may be configured in the direction of the beam path before the beam combiner. Any number of additional reflective elements may be positioned in the beam path.

[0031] A beam combiner may also be referred to as a beam combining element. In some embodiments, beam combiner 103 may be a zinc selenide (ZnSe), zinc sulfide (ZnS), or germanium (Ge) beam combiner. For example, a beam combiner may be configured to transmit infrared light and reflect visible light. In some embodiments, beam combiner 103 may be dichroic. In some embodiments, a beam combiner may be configured to allow electromagnetic radiation having a wavelength longer than the cutoff wavelength to pass through and reflect electromagnetic radiation having a wavelength shorter than the cutoff wavelength. In some embodiments, a beam combiner may be configured to allow electromagnetic radiation having a wavelength shorter than the cutoff wavelength to pass through and reflect electromagnetic radiation having a wavelength longer than the cutoff wavelength. In some embodiments, the cutoff wavelength may be about 1 m, about 100 mm, about 10 mm, about 1 mm, about 100 μm, about 10 μm, about 1.5 μm, about 1 μm, about 900 nm, about 800 nm, about 700 nm, about 600 nm, about 500 nm, about 400 nm, about 300 nm, about 100 nm, about 10 nm, or about 1 nm. In some embodiments, the cutoff wavelength may be from about 1 m to about 100 mm, from about 100 mm to about 10 mm, from about 10 mm to about 1 mm, from about 1 mm to about 100 μm, from about 100 μm to about 10 μm, from about 10 μm to about 1.5 μm, from about 1.5 μm to about 1 μm, from about 1 μm to about 900 nm, from about 900 nm to about 800 nm, from about 800 nm to about 700 nm, from about 700 nm to about 600 nm, from about 600 nm to about 500 nm, from about 500 nm to about 400 nm, from about 400 nm to about 300 nm, from about 300 nm to about 100 nm, from about 100 nm to about 10 nm, or from about 10 nm to about 1 nm. In other embodiments, the beam combiner may be a polarization beamsplitter, a long-pass filter, a short-pass filter, or a band-pass filter.

[0032] The orientation and orientation of one or both of the first reflecting element 105 and the second reflecting element 106 can be controlled by an actuator. In some embodiments, the actuator may be a motor, solenoid, ammeter, or servo mechanism. For example, the orientation of the first reflecting element may be controlled by a first actuator, and the orientation and orientation of the second reflecting element may be controlled by a second actuator. In some embodiments, a single reflecting element may be controlled by multiple actuators. For example, the first reflecting element may be controlled by a first actuator along a first axis and a second actuator along a second axis. In some embodiments, a single actuator may control the reflecting element along multiple axes. The actuator can change the orientation of the reflecting element by rotating the reflecting element, thereby changing the angle of incidence of the beam encountering the reflecting element. Changing the angle of incidence can cause a translation of the orientation of the beam encountering the surface. In some embodiments, the angle of incidence can be adjusted such that the orientation of the beam encountering the surface is maintained as the optical system moves relative to the surface. In some embodiments, a first actuator rotates a first reflecting element about a first rotation axis, thereby translating the azimuth of the beam encountering the surface along a first translation axis, and a second actuator rotates a second reflecting element about a second rotation axis, thereby translating the azimuth of the beam encountering the surface along the second translation axis. In some embodiments, the first and second actuators rotate the first reflecting element about the first and second rotation axes, thereby translating the azimuth of the beam encountering the surface of the first reflecting element along the first and second translation axes. For example, a single reflecting element may be controlled by the first and second actuators to provide translation of the azimuth of the beam encountering the surface along the first and second translation axes, wherein the single reflecting element is controlled by two actuators. The first and second translation axes may be orthogonal. The coverage area on the surface may be defined by the maximum translation along the first translation axis and the maximum translation along the second translation axis. One or both of the first and second actuators may be servo-controlled, piezoelectric-actuated, piezoelectric-inertial-actuated, stepper motor-controlled, ammeter-driven, linear actuator-controlled, or any combination thereof. One or both of the first and second reflecting elements may be a mirror; for example, a dichroic mirror or a dielectric mirror; a prism; a beam splitter; or any combination thereof. In some embodiments, one or both of the first and second reflecting elements may be any element capable of deflecting a beam.

[0033] Figure 2 As shown Figure 1A and Figure 1B A top view of an embodiment of the optical control system 100 shown. Figure 1A , Figure 1B and Figure 2The reference numerals are consistent throughout. The aiming camera 104 is positioned to capture light 152, such as visible light, traveling along an optical path in the opposite direction to the beam combiner 151. The light may be scattered by a surface, such as the surface including the target. In some embodiments, the aiming camera is positioned such that it captures light reflected away from the beam combiner 103. In other embodiments, the aiming camera is positioned such that it captures light transmitted through the beam combiner. The aiming camera may be configured to image the target field of view on the surface. The aiming camera may be coupled to the beam combiner, or the aiming camera may be coupled to a support structure supporting the beam combiner. In a preferred embodiment, the aiming camera does not move relative to the beam combiner.

[0034] Figure 3A and Figure 3B A side view of an embodiment of the optical control device disclosed herein is shown. Reference numerals are consistent between Figures 1 to 3. Figure 3B The illustration depicts a mechanism for preventing dust and debris from accumulating on the optical elements of the optical control device shown in Figures 1 through 3. In some embodiments, the optical element may include a hard stop 351 on a reflector to prevent the beam from striking areas of the optical control device outside a predetermined boundary on the surface. The optical element (e.g., a beam combining element and one or both reflective elements) may be protected by a housing. The optical element may be enclosed by a housing. In some embodiments, the housing is sealed to prevent dust, debris, water, or any combination thereof from contacting the optical element. Figure 3B As shown, the housing may include a laser escape window 107. In some embodiments, the laser escape window is positioned to intersect the beam following the second reflecting element in the beam path, or the laser escape window is positioned to intersect the beam following the first reflecting element in the beam path. In some embodiments, the laser escape window is the last element in the beam path. The laser escape window prevents dust, debris, water, or any combination thereof from reaching the optical element. In some embodiments, the laser escape window comprises a material that is substantially transparent to electromagnetic radiation (such as light). For example, the laser escape window may comprise glass, quartz, fused silica, zinc selenide, a transparent polymer, or a combination thereof.

[0035] The housing may also include a self-cleaning device configured to prevent dust or debris from accumulating on the surface of the laser exit window or to remove dust or debris already accumulated on the surface of the laser exit window. In some embodiments, the self-cleaning device includes an orifice 352 in the outer surface of the housing configured to discharge clean air 353. The clean air prevents debris from damaging the laser exit window. In some embodiments, the clean air may be filtered. The orifice may be configured to direct airflow toward the outer surface of the exit window. The orifice may be configured such that clean air is directed across the surface of the laser exit window. In some embodiments, the housing is configured to direct clean air without obstructing the beam 102. For example, the housing may include an opening 354 in the beam path after the laser exit window, the opening 354 having a gap that allows the beam to pass through unobstructed. In some embodiments, the opening includes a wall opposite the orifice. The wall may be configured to control the direction of the airflow and reduce turbulence without obstructing the beam. The opening may encompass both the laser exit window and the beam path, and is configured such that the opening is narrower near the laser exit window and wider away from the laser exit window in the direction of the beam path. In some embodiments, the opening has a smooth corner 355 to allow clean air to pass through while preventing turbulence.

[0036] After leaving the optical control system, the beam 102 can be guided toward the surface, such as... Figure 4A and Figure 4B As shown in the illustration. In some embodiments, the surface includes a target, such as weeds. Figure 2 As shown, the rotational motion of one or both of the reflective elements 105 and 106 can generate laser sweeping along the first translation axis 401 and laser sweeping along the second translation axis 402, respectively as follows: Figure 4A and Figure 4B As shown in views 400 and 450. Rotational movement of one or both of the reflecting elements controls the position where the beam encounters the surface. For example, rotational movement of one or both of the reflecting elements can move the position where the beam encounters the surface to the orientation of the target on the surface. In some embodiments, the beam is configured to damage the target. For example, the beam may include electromagnetic radiation and may irradiate the target. In another example, the beam may include infrared light and may burn the target. In some embodiments, one or both of the reflecting elements are rotatable such that the beam scans the area surrounding and including the target.

[0037] Composite System In some embodiments, multiple optical control systems may be combined to increase the coverage area on the surface. Figure 5The illustration shows a composite system 500 comprising multiple optical control systems 100. The multiple optical control systems are configured such that a laser sweep along the translation axis 402 of each optical control system overlaps with a laser sweep along the translation axis of an adjacent optical control system. The combined laser sweep defines a coverage area 503 reachable by at least one beam from a plurality of beams from the multiple optical control systems. A predictive camera 501 is positioned such that a predictive camera field of view 502 completely covers the coverage area 503.

[0038] Multiple optical control systems can be configured on vehicle 601, such as Figure 6 View 600 and Figure 7 As shown in view 700. For example, the vehicle may be an autonomous vehicle. An autonomous vehicle may be a robot. In some embodiments, the vehicle may be controlled by a human. For example, the vehicle may be driven by a human driver. In some embodiments, the vehicle may be coupled to a second vehicle driven by a human driver, for example, towed behind a second vehicle or pushed by a second vehicle. The vehicle may be remotely controlled by a human, for example, via a remote controller. In some embodiments, the vehicle may be remotely controlled via long-wave signals, optical signals, satellite, or any other telecommunication method. Multiple optical control systems may be configured on the vehicle such that the coverage area overlaps with surfaces below, behind, in front of, or around the vehicle. The vehicle may be configured to navigate over surfaces including multiple targets (e.g., a crop field including multiple weeds). The vehicle may include one or more of multiple wheels, power sources, motors, predictive cameras 501, or any combination thereof. In some embodiments, the vehicle has sufficient clearance above the surface to travel over plants (e.g., crops) without damaging them. In some embodiments, the space between the inner edges of the left and right wheels is wide enough to pass over a row of plants without damaging them. In some embodiments, the distance between the outer edges of the left and right wheels is narrow enough to allow the vehicle to pass between two rows of plants (e.g., two rows of crops) without damaging them. In a preferred embodiment, a vehicle comprising multiple wheels, multiple optical control systems, and predictive cameras can navigate over rows of crops and fire one of multiple beams toward a target (e.g., weeds) to burn or irradiate the weeds.

[0039] Prediction module This paper discloses a prediction module configured to locate targets on a surface. Figure 8A prediction module 810 configured to identify, assign, and aim at targets is illustrated. In some embodiments, a target prediction system 811 is configured to use a prediction camera 501 to capture an image of a prediction field of view including a surface, identify targets in the image, and locate the targets within the prediction field of view. A camera-to-control conversion system 812 may be configured to convert the position of a target in the prediction field of view into an orientation on the surface. For example, the camera-to-control conversion system may establish multiple interpolation functions that provide a conversion from the position in the prediction field of view to one or more actuator orientations (e.g., translation and tilt orientations) of one or more actuators controlling one or more reflective elements 105 and 106, as shown in Figures 1 through 3.

[0040] Figure 8 The prediction module 810 shown may also include an attitude and motion correction system 813. The attitude and motion correction system may include a positioning system, such as an inertial measurement unit (IMU), a global positioning system (GPS), or an internal navigation system (INS). The attitude and motion correction system may utilize an inertial measurement unit (IMU) that may be directly or indirectly coupled to the prediction camera. For example, the prediction camera and the IMU may be mounted to a vehicle. The IMU may collect motion readings from the IMU and anything directly or indirectly coupled to the IMU, such as the prediction camera. For example, the IMU may collect readings including three-dimensional acceleration and three-dimensional rotation information that can be used to determine the magnitude and direction of motion over an elapsed time. The attitude and motion correction system may include a global positioning system (GPS). GPS may be directly or indirectly coupled to the aiming camera. For example, GPS may communicate with a satellite-based radio navigation system to measure a first azimuth of the aiming camera at a first time and a second azimuth of the aiming camera at a second time. The attitude and motion correction system may include an internal navigation system (INS). The INS may be directly or indirectly coupled to the aiming camera. For example, the INS may include motion sensors (e.g., accelerometers) and rotation sensors (e.g., gyroscopes) to measure the azimuth, orientation, and velocity of the aiming camera. The attitude and motion correction system may or may not use external references to determine changes in the azimuth of the aiming camera. The attitude and motion correction system may determine changes in the azimuth of the aiming camera from a first azimuth and a second azimuth. In some embodiments, after the target prediction system locates the target in an image, the attitude and motion correction system determines the amount of time that has elapsed since the image was captured and the magnitude and direction of the predicted camera's motion that has occurred during that time. The attitude and motion correction system may integrate the target position, the elapsed time, and the magnitude and direction of the motion to determine the corrected position of the target on the surface.

[0041] The prediction module may also include an image detection module. The imaging detection module can be configured to locate and identify targets in an image. For example, the imaging detection module can be configured to distinguish between two types of plants, such as crops and weeds. In some embodiments, the imaging detection module includes the use of a convolutional neural network. The neural network can be trained using numerous images of surfaces with or without targets, such as images from a prediction camera or a targeting camera. For example, the neural network can be trained using images of fields with or without weeds. Once trained, the neural network can be configured to identify regions in an image that include targets. This region can be defined by a polygon (e.g., a rectangle). In some embodiments, the region is a bounding box. In some embodiments, the region is a polygonal mask covering the identified region.

[0042] Based on the target's location, the target allocation system 814 can assign the target to an aiming module 820 among multiple aiming modules. The target's location can be corrected based on the amplitude and direction of movement over an elapsed time period, or the location can be within a region defined by a polygon, or both. The future target location can be determined based on the predicted amplitude and direction of movement over a future time period. The target allocation module can assign the target to an aiming module having a coverage area that overlaps with the target location, the corrected target location, or the future target location.

[0043] The prediction module may include a system controller, such as a system computer with storage devices, random access memory (RAM), a central processing unit (CPU), and a graphics processing unit (GPU). The system computer may include a tensor processing unit (TPU). The system computer should include sufficient RAM, storage space, CPU processing power, and GPU processing power to perform the operation of detecting and recognizing targets. The prediction camera should provide images with sufficient resolution to perform the operation of detecting and recognizing targets on them.

[0044] Aiming module This article discloses an aiming module configured to guide a beam toward a target location on a surface. Figure 8A targeting module 820 is illustrated, configured to predict the position of a target and move one or more optical elements to guide a beam toward the target position. Multiple targeting modules may communicate with a prediction module 810. The targeting modules include an optical control system as described herein. For example, as shown in Figures 1 through 3, the targeting module may include: a transmitter 101 that emits a beam 102 along an optical path; and a beam combining element 103; optionally a targeting camera 104; a first reflective element 105 configured to deflect the beam controlled by a first actuator; and a second reflective element 106 optionally positioned in the optical path, configured to deflect the beam controlled by a second actuator. One or both of the actuators may be configured to rotate one or both of the reflective elements about a first rotation axis and optionally a second rotation axis, thereby altering the deflection of the beam path and translating the beam's orientation toward the surface along a first translation axis and optionally along a second translation axis. In some embodiments, the first and second actuators can rotate a single reflective element about a first and a second rotation axis, thereby providing the orientation of the point where the beam encounters the surface along the first and second translation axes. The predictive camera should have a sufficiently large field of view to image the area covered by the beam path.

[0045] like Figure 8 As shown, the target prediction system 821 captures an image of a region on a surface. This region can be predicted to contain a target, as predicted by the prediction module 810. The target prediction system can identify the pixel location of the target in the image. The camera-to-control conversion system 822 can convert the pixel location of the target image into the orientation of a first reflecting element and optionally a second reflecting element. The orientation of the reflecting elements can be controlled by actuators, as described herein. For example, the camera-to-control conversion system can convert the pixel location of the target into translation or tilt values ​​for one or both actuators corresponding to the predicted mirror orientation that deflects the beam to the target location.

[0046] In some embodiments, the target prediction system further includes an image detection module. The image detection module can be configured to locate and identify targets in an image. For example, the image detection module can be configured to distinguish between two types of plants, such as crops and weeds. In some embodiments, the image detection module includes the use of a convolutional neural network. The neural network can be trained using numerous images of surfaces with or without targets, such as images from a prediction camera or a targeting camera. For example, the neural network can be trained using images of fields with or without weeds. Once trained, the neural network can be configured to identify regions in an image that include targets. This region can be defined by a polygon (e.g., a rectangle). In some embodiments, the region is a bounding box. In some embodiments, the region is a polygonal mask covering the identified region.

[0047] The target position can be further corrected using an attitude and motion correction system 823. The attitude and motion correction system can use a positioning system (e.g., IMU, GPS, or INS) to determine the magnitude and direction of the aiming camera's motion. In some embodiments, acceleration and rotation readings from an IMU directly or indirectly coupled to the aiming camera are used to determine the magnitude and direction of the motion. For example, the prediction camera and IMU can be mounted to a vehicle. The IMU can collect motion readings from the IMU itself and anything directly or indirectly coupled to it, such as the aiming camera. For example, the IMU can collect readings including three-dimensional acceleration and three-dimensional rotation information that can be used to determine the magnitude and direction of the motion over an elapsed time. In some embodiments, the attitude and motion correction system can use GPS to determine the magnitude and direction of the aiming camera's motion. For example, GPS can be mounted to a vehicle. GPS can communicate with a satellite-based radio navigation system to measure a first azimuth of the aiming camera at a first time and a second azimuth of the aiming camera at a second time. In some embodiments, the attitude and motion correction system can use an INS to determine the magnitude and direction of the aiming camera's motion. For example, the INS can measure the aiming camera's azimuth, orientation, and velocity. In some embodiments, after the target prediction system 821 locates the target in the image, the attitude and motion correction system determines the amount of time that has elapsed since the image was captured, as well as the magnitude and direction of the aiming camera's motion that has occurred during that time. The attitude and motion correction system may integrate the target position, the elapsed time, and the magnitude and direction of the motion to determine the corrected position of the target on the surface. In some embodiments, the positioning system used by the attitude and motion correction system of the aiming module 823 and the positioning system used by the attitude and motion correction system of the prediction module 813 are the same. The future target position may be determined based on the predicted magnitude and direction of the motion during a future time period. In some embodiments, the positioning system used by the attitude and motion correction system of the aiming module and the positioning system used by the attitude and motion correction system of the prediction module are different.

[0048] The actuator control system 824 includes software-driven electrical components capable of providing signals to a first actuator and optionally a second actuator to control a first reflecting element and optionally a second reflecting element. For example, the actuator control system sends signals including actuator pantilt values ​​to the first and second actuators. The actuators use the pantilt azimuth indicated by the signals to move the first and second reflecting elements about a first and a second rotation axis to an azimuth such that the beam is deflected to a target position, a corrected target position, or a future target position.

[0049] The laser control system 825 includes software-driven electrical components capable of controlling the activation and deactivation of the transmitter. Activation or deactivation may depend on the presence or absence of a target detected by the targeting camera 104. Activation or deactivation may depend on the orientation of the beam path guided toward the surface relative to the target location. In some embodiments, the laser control system may activate the transmitter when the target is identified by the prediction system. In some embodiments, the laser control system may activate the transmitter when the beam path is positioned to overlap with the target location. In some embodiments, the laser control system may activate the transmitter when the beam path is within a region of the surface including the target (e.g., a bounding box or a polygonal mask covering the identified area). Once the target has been eliminated, the region including the target has been scanned by the beam, the target is no longer identified by the target prediction module, a specified time period has elapsed, or any combination thereof, the laser control system may deactivate the transmitter. For example, once an area on the surface including weeds has been scanned by the beam, or once the weeds have been irradiated or burned, the laser control system may deactivate the transmitter.

[0050] The prediction and aiming modules described herein can be used in combination to utilize beam localization, identification, and aiming at targets. The aiming control module may include an optical control system as described herein. The prediction and aiming modules can communicate, for example, via electrical or digital communication. In some embodiments, the prediction and aiming modules are directly or indirectly coupled. For example, the prediction and aiming modules may be coupled to a support structure. In some embodiments, the prediction and aiming modules are constructed on a vehicle (e.g., vehicle 601), such as... Figure 6 and Figure 7 As shown in the image.

[0051] The targeting module may include a system controller, such as a system computer with storage devices, random access memory (RAM), a central processing unit (CPU), and a graphics processing unit (GPU). The system computer may include a tensor processing unit (TPU). The system computer should include sufficient RAM, storage space, CPU processing power, and GPU processing power to perform the operation of detecting and identifying targets. The targeting camera should provide images with sufficient resolution to perform the operation of detecting and identifying targets on them.

[0052] Calibration method The prediction module disclosed herein may also include a calibration step. In some embodiments, the camera-to-control transition system of the prediction module 812 is calibrated. In some embodiments, a calibration surface is positioned within the field of view of the prediction camera. The calibration surface includes known markers at known orientations. The prediction camera may collect multiple images of the calibration surface at different orientations relative to the calibration surface. The prediction module may then correlate the pixel orientations of the known markers with the known orientations on the surface. An interpolation function may be constructed from the multiple associated pixel orientations and the known surface orientations. In some embodiments, the interpolation function may be saved to a hard disk and loaded from the hard disk by the prediction module.

[0053] The aiming module disclosed herein may also include a calibration step. In some embodiments, the camera-to-control conversion system of the aiming module 812 is calibrated. In some embodiments, a calibration surface is positioned within the field of view of the aiming camera. The calibration surface includes known markers at known azimuths. The aiming module may collect multiple images of the calibration surface and multiple actuator azimuths, such that the multiple images include different fields of view. For example, the aiming module may collect multiple images at multiple randomly selected translation tilt values ​​of the first and second actuators. The calibration map may be constructed from multiple sampling points. Each sampling point is collected by identifying the pixel position of a known marker in an image collected at a known actuator azimuth and associating the known position with the actuator azimuth and the pixel position. In some embodiments, the map is fitted to a spline smoothing algorithm to construct a smooth curve, thereby allowing accurate estimation of the positions between sampling points. In some embodiments, the spline smoothing algorithm may be saved to a hard disk and loaded from the hard disk by the aiming module.

[0054] Weed eradication system Figure 9 A process 900 for an embodiment of the apparatus and methods disclosed herein is illustrated. The following examples are illustrative and do not limit the scope of the apparatus, systems, and methods described herein. The process includes identifying, distributing, targeting, and eradicating weeds in a field. In this example, the weed eradication system includes a prediction module 810 communicating with a plurality of targeting modules 820. The prediction and targeting modules are controlled by a system controller (e.g., a computer including storage devices, RAM, CPU, and GPU). Each targeting module includes an optical control system 100, as shown in Figures 1 through 3. The prediction and targeting modules are coupled to a solid support. Figure 6 and Figure 7 As shown, the solid support is positioned on vehicle 601.

[0055] like Figure 9As shown, iterative operations 920, 930, 940, 950, and 960 continue until the field of interest is completely scanned 910. First, the prediction module runs operation 920. The prediction camera collects images of the field surface in the area around or in front of the vehicle. The system controller processes the images and identifies weeds in the images. In step 921, the prediction model predicts the location of one or more weeds identified in the image. In step 922, the camera-to-control system transforms the pixel coordinates of the weeds in the image to ground locations. At 922, the system controller instructs the vehicle to adjust its orientation and speed 923 based on the vehicle's motion measured by the IMU. Based on the ground locations of the weeds and the coverage area of ​​the targeting module, each of the one or more weeds is assigned to the targeting module 924.

[0056] Iterative operations 930, 940, 950, and 960 are performed for each target module 925. Iterative operations 940, 950, and 960 are performed for each weed. The aiming module among the multiple aiming modules performs operation 940. The aiming camera captures a target image of the field, and the system controller identifies weeds in the target image 941. The system controller converts the pixel positions of the weeds in the target image into translation and tilt values ​​942 for controlling the translation and tilt of each actuator in the optical control system controlled by the aiming module. At 943, the system controller applies attitude and motion corrections to the actuator translation and tilt values ​​based on the vehicle's motion measured by the IMU, and plans a route 944 for the transmission beam path controlled by the actuator translation and tilt azimuth. Once the actuator reaches the determined azimuth, the transmitter is activated 945.

[0057] Repeat operation 950 while implementing the planned route 946. Weeds are identified in the images collected by the aiming camera, and the route plan is updated 952 based on the observed orientation of the weeds. In 953, the system controller applies attitude and motion corrections to the actuator translation and tilt values ​​based on the vehicle's motion measured by the IMU. Based on the updated route plan 954, the actuator is moved into position. Once the planned route is complete, the transmitter is deactivated 960.

[0058] While preferred embodiments of the present disclosure have been shown and described herein, it will be apparent to those skilled in the art that these embodiments are merely illustrative. Many variations, modifications, and substitutions will now occur to those skilled in the art without departing from the present disclosure. It should be understood that various alternatives to the embodiments of the present disclosure described herein may be employed in the practice of this disclosure.

Claims

1. A system for damaging or killing plants, the system comprising: A first camera, configured to capture images of plants in a field; A second camera, configured to capture images of plants in the field; A light source configured to emit a light beam; A control system, comprising one or more actuators, wherein the control system is configured to guide the optical path of the light beam; and Computing system The computing system is configured to perform operations, including: Receive a first image of at least one plant in the field captured by the first camera at the first moment; Identify plants in the first image, wherein the identification of the plants is performed using an algorithm configured to distinguish between weeds and crops; Predict the location of the plant based on the first image; The second camera captures a second image of the area of ​​the field including the predicted location; Predict the target location of the plant in the second image at a second time after the first time, wherein the prediction of the target location takes into account the motion of the second camera relative to the surface during the elapsed time between the first time and the second time. The control system guides the optical path of the light beam toward the predicted target position; and The light source emits a beam of light toward the predicted target location of the plant for a duration sufficient to damage or kill the plant.

2. The system according to claim 1, wherein, Plant identification in the first image is performed using a neural network.

3. The system according to claim 2, wherein, The neural network is configured to distinguish between weeds and crops.

4. The system according to claim 2, wherein, The neural network includes a convolutional neural network, which is trained using images of weeds and crops.

5. The system according to claim 1, wherein, The operation also includes tracking the motion of the system over an elapsed period of time.

6. The system according to claim 5, wherein, The motion is tracked using one or more of the following: an inertial measurement unit (IMU), a global positioning system (GPS), or an internal navigation system (INS).

7. The system according to claim 5, wherein, The operation also includes adjusting the predicted target position based on the tracked motion.

8. The system according to claim 1 further includes a framework supporting the first camera, the second camera, the light source, the control system, and the computing system.

9. The system according to claim 8, wherein, The frame is configured to move on the field.

10. The system according to claim 9, wherein, The frame is configured to move autonomously or by a driver.

11. The system according to any one of claims 1-10, wherein, The beam is a laser beam.

12. The system according to any one of claims 1-11, wherein, The light beam has a wavelength ranging from 300 nm to 100 μm.

13. The system according to any one of claims 1-12, wherein, The beam has a power range from 10W to 10kW.

14. The system according to any one of claims 1-13, wherein, The control system includes one or more mirrors for guiding the optical path of the light beam.

15. The system according to any one of claims 1-14, further comprising a housing containing an optical control system, wherein, The housing includes an escaping portion configured for the passage of the light beam.

16. The system according to any one of claims 1-15, wherein, The optical control system is configured to direct the light beam toward the weeds as the system moves relative to the field.

17. The system according to any one of claims 1-16, wherein, The light source is selected from a group consisting of infrared lasers, ultraviolet lasers, and visible lasers.

18. An aiming system, comprising: A first camera, configured to image a surface; A transmitter configured to emit a beam toward the surface; as well as A computing system, which communicates with the first camera and the transmitter, is configured to perform operations including: Receive a target image of the surface from the first camera at a first time, the target image including the target on the surface; Identify regions in the target image that include the target. The target position on the surface is determined based on the region identified in the target image at a second time after the first time, wherein the determination of the target position takes into account the motion of the first camera relative to the target during the elapsed time between the first time and the second time. The optical path of the beam is aligned based on the determined target position of the target; When at least a portion of the optical path is aligned with the target position of the determined target, the transmitter emits a beam toward the target; and The transmitter is deactivated.

19. The system according to claim 18, wherein, Identifying regions in the target image that include the target is performed using a neural network.

20. The system according to claim 19, wherein, The neural network is configured to distinguish between weeds and crops.

21. The system according to claim 19, wherein, The neural network includes a convolutional neural network, which is trained using images of weeds and crops.

22. The system according to claim 18, wherein, The operation also includes tracking the motion of the system over an elapsed period of time.

23. The system according to claim 22, wherein, The motion is tracked using one or more of the following: an inertial measurement unit (IMU), a global positioning system (GPS), or an internal navigation system (INS).

24. The system according to claim 22, wherein, The operation also includes adjusting the predicted target position based on the tracked motion.

25. The system of claim 18, further comprising a frame supporting the first camera, the second camera, the light source, the control system, and the computing system.

26. The system according to claim 25, wherein, The frame is configured to move on the field.

27. The system according to claim 25, wherein, The frame is configured to move autonomously or by a driver.

28. The system according to any one of claims 18-27, wherein, The beam is a laser beam.

29. The system according to any one of claims 18-28, wherein, The light beam has a wavelength ranging from 300 nm to 100 μm.

30. The system according to any one of claims 18-29, wherein, The beam has a power range from 10W to 10kW.

31. The system according to any one of claims 18-30, wherein, The control system includes one or more mirrors for guiding the optical path of the light beam.

32. The system according to any one of claims 18-31, further comprising a housing containing an optical control system, wherein, The housing includes an escaping portion configured for the passage of the light beam.

33. The system according to any one of claims 18-32, wherein, The optical control system is configured to direct the light beam toward the weeds as the system moves relative to the field.

34. The system according to any one of claims 18-33, wherein, The light source is selected from a group consisting of infrared lasers, ultraviolet lasers, and visible lasers.

35. A targeting system for autonomous plant eradication, comprising: A first camera, configured to image a surface; A transmitter configured to emit a beam toward the surface; as well as A computing system, which communicates with the first camera and the transmitter, is configured to perform operations including: Receive a target image of the surface from the first camera at a first time, the target image including plants on the surface; Identifying regions in the target image that include the plant, wherein the identification of regions in the target image is performed using an algorithm configured to distinguish between weeds and crops; At a second time after the first time, the target position of the plant on the surface is determined based on the region identified in the target image, wherein the determination of the target position takes into account the motion of the first camera relative to the plant during the elapsed time between the first time and the second time. The optical path of the beam is aligned based on the determined target location of the plant; and When at least a portion of the optical path is aligned with the target location of the determined plant, the transmitter emits a beam toward the plant.

36. The aiming system of claim 35, further comprising a second camera in communication with the computing system.

37. The aiming system according to claim 36, wherein, The operation also includes: A predicted image is received from the second camera, the predicted image including the surface; Identify regions in the predicted image that include the plant; The predicted location of the plant is projected based on the predicted image and the region identified in the predicted image; and Align the first camera with the projected predicted position.

38. The aiming system according to claim 37, wherein, The target image includes the predicted location of the projection.

39. The aiming system according to any one of claims 35 to 38, further comprising an actuator configured to align the optical path of the transmitter with the determined target position, wherein, The actuator is also configured to align the first camera with the projected predicted position, control a mirror in the optical path, or perform both.

40. The aiming system according to any one of claims 35 to 39, wherein, The target system is positioned on the framework.

41. The aiming system according to claim 40, wherein, The frame is configured to move on the field.

42. The aiming system according to claim 41, wherein, The frame is configured to move autonomously or by a driver.

43. The aiming system according to any one of claims 35-41, wherein, The transmitter is a laser.

44. The aiming system according to claim 43, wherein, The laser is selected from the group consisting of infrared lasers, ultraviolet lasers, and visible lasers.

45. A method for autonomously killing plants, the method comprising: Receive a target image of the surface from a first camera at a first time, the target image including plants on the surface; Identifying regions in the target image that include the plant, wherein the identification of regions in the target image is performed using an algorithm configured to distinguish between weeds and crops; At a second time after the first time, the target position of the plant on the surface is predicted based on the region identified in the target image, wherein the predicted target position takes into account the motion of the first camera relative to the weed during the elapsed time between the first time and the second time. The optical path of the beam is aligned based on the target position of the plant; and When at least a portion of the optical path is aligned with the target location of the plant, the transmitter emits a beam toward the plant, wherein the beam emitted toward the plant kills or damages the plant.

46. ​​The method of claim 45, further comprising: Receive a predicted image of the surface; Identify the regions in the predicted image that include the plant; And project the predicted location of the plant based on the predicted image and the region identified in the predicted image; The target image includes the predicted location of the projection.

47. The method according to claim 45 or 46, wherein, The transmitter moves relative to the surface.

48. The method according to any one of claims 45 to 47, further comprising deactivating the beam of the transmitter after the plant has been damaged or killed.

49. The method according to any one of claims 45 to 48, wherein, Aligning the optical path with the projected target position includes a reference calibration function.

50. A system for autonomous plant eradication, the system comprising: processor; as well as A memory having program instructions stored thereon, which, when executed by the processor, cause the system to perform operations, including: Receive a target image of the surface from the camera at the first moment, the target image including plants on the surface; Identifying regions in the target image that include the plant, wherein the identification of regions in the target image is performed using an algorithm configured to distinguish between weeds and crops; At a second time after the first time, the target position of the plant on the surface is determined based on the region identified in the target image, wherein the determination of the target position takes into account the motion of the camera relative to the plant during the elapsed time between the first time and the second time. Provide instructions to align the optical path of the beam from the transmitter with the target location of the plant; and Instructions are given to the transmitter to emit a beam toward the weed when at least a portion of the optical path is aligned with the plant, wherein the emitted beam kills or damages the weed.

51. The system according to claim 50, wherein, The operation also includes: Receive a predicted image of the surface; Identify regions in the predicted image that include the plant; and The predicted location of the plant is projected based on the predicted image and the region identified in the predicted image; The target image includes the predicted location of the projection.

52. The system according to claim 51, wherein, The operation also includes providing instructions to the transmitter to deactivate the beam once the plant has been damaged or killed.

53. An optical control system, comprising: A transmitter configured to emit a beam along an optical path toward a target on a surface, wherein the target is autonomously determined; A first reflective element is positioned to intersect the optical path and deflect the beam; An actuator, connected to the first reflective element and configured to rotate the first reflective element and deflect the beam toward the target; and A beam combiner is positioned in the optical path between the transmitter and the first reflective element and configured to differentially deflect the beam and scattered light from the target traveling along the optical path in the opposite direction to the beam.

54. The optical control system of claim 53 further includes a targeting camera, optically connected to the beam combiner and configured to receive scattered light reflected from the first reflective element and to image a targeting field of view including the target.

55. The optical control system according to claim 53 or 54, wherein, The optical control system is configured to guide the beam toward the target while the optical control system moves relative to the surface.

56. The optical control system according to any one of claims 53 to 55, further comprising a targeting system computer configured to detect pixel movement of the targeting field of view relative to the target position and convert the pixel movement of the targeting field of view into rotation of the first reflective element.

57. The optical control system according to claim 56, wherein, The conversion of the movement into rotation of the first reflective element includes a reference calibration function.

58. The optical control system according to claim 57, wherein, The calibration function is obtained by associating the position of the reference marks on the calibration surface with camera movement.

59. The optical control system according to any one of claims 53 to 58, further comprising an inertial measurement unit coupled to said optical control system, wherein, The inertial measurement unit is configured to measure the acceleration of the optical control system, the rotation of the optical control system relative to the surface, or a combination thereof.

60. The optical control system of claim 59 further includes a targeting system computer configured to adjust the position of the target based on a time elapsed since imaging, the acceleration of the optical control system, the rotation of the optical control system relative to the surface, or a combination thereof.

61. The optical control system according to any one of claims 53 to 60, wherein, The optical control system is enclosed in a housing that includes an exit window capable of transmitting beams and visible light, wherein the exit window is positioned in the optical path between the first reflective element and the surface.

62. The optical control system according to claim 61, wherein, The optical control system is completely enclosed within the housing.

63. The optical control system of claim 61 or 62 further includes an air source configured to direct airflow from an opening in the outer surface of the housing toward the outer surface of the escaping window.

64. The optical control system according to claim 63, wherein, The housing also includes a wall opposite the orifice, the wall being configured to control the direction of the airflow and reduce turbulence without obstructing the beam.

65. The optical control system according to any one of claims 53 to 64, wherein, The first reflective element is a mirror.

66. The optical control system according to any one of claims 53 to 65, wherein, The beam combiner transmits the beam and reflects the visible light.

67. The optical control system according to any one of claims 53 to 66, wherein, The transmitter is a laser transmitter.

68. The optical control system according to claim 67, wherein, The laser emitter is selected from a group consisting of infrared lasers, ultraviolet lasers, and visible lasers.

69. The optical control system according to any one of claims 53 to 68, further comprising a second actuator connected to the first reflective element and configured to rotate the first reflective element and deflect the beam toward the target position.

70. The optical control system according to any one of claims 53 to 68, further comprising: A second reflective element is positioned to intersect the optical path and deflect the beam deflected by the first reflective element; A second actuator, which is connected to the second reflective element and configured to rotate the second reflective element and deflect the beam toward the target position.

71. The optical control system according to claim 69 or 70, wherein, A first aiming actuator deflects the beam along a first translation axis, and a second actuator deflects the beam along a second translation axis, wherein the first translation axis and the second translation axis are orthogonal.

72. The optical control system according to claim 70, wherein, The beam combiner is positioned behind the transmitter relative to the direction of the beam, the first reflective element is positioned behind the beam combiner, and the second reflective element is positioned behind the first reflective element.

73. The optical control system according to any one of claims 53 to 72, wherein, The target is weeds.

Images