Agricultural output is valued at trillions of dollars annually worldwide. Agriculture is an essential component of food production and includes cultivation of both livestock and plants. Rising population and decreased crop yield due to changing climate threaten global food security. Methods for increasing agricultural production by improving crop yield and boosting labor efficiency may help mitigate food shortages.
The present disclosure provides various methods, devices, modules, and systems which may be employed for automated identification, maintenance, control, or targeting of plants. For example, the methods, devices, modules, and systems disclosed herein may be used to autonomously identify and eradicate weeds located within a field of crops. The methods, devices, modules, and systems may be used as alternatives to hand cultivation or chemical herbicides. For instance, the methods, devices, modules, and systems may be used for agricultural crop management or for at-home weed control.
In various aspects, the present disclosure provides an optical control system comprising: an emitter configured to emit a beam along an optical path toward a target location on a surface, wherein the target location is determined by autonomously locating a target on the surface; a first reflective element positioned to intersect the optical path and deflect the beam; a first targeting 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 emitter and the first reflective element and configured to differentially deflect the beam and a scattered light from the target location traveling along the optical path in a direction opposite the beam.
In some aspects, the optical control system further comprises a targeting camera optically connected to the combining element and configured to receive the scattered light reflected off the first reflective element and image a targeting field of view including the target location. In some aspects, the optical control system is configured to direct the beam toward the target location while the optical control system is moving relative to the surface. In some aspects, the optical control system further comprises a targeting system computer configured to detect a pixel movement of the targeting field of view relative to the target location and convert from the pixel movement of the targeting field of view to a rotation of the first reflective element.
In some aspects, conversion from the pixel movement to the rotation of the first reflective element comprises referencing a calibration function. In some aspects, the calibration function is obtained by correlating locations of fiducial markers on a calibration surface to camera pixel movements.
In some aspects, the optical control system further comprises an inertial measurement unit coupled to the optical control system, wherein the inertial measurement unit is configured to measure an acceleration of the optical control system, a rotation of the optical control system relative to the surface, or a combination thereof. In some aspects, the targeting system computer is configured to adjust the target location based on an 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.
In some aspects, the optical control system is enclosed in an enclosure, the enclosure comprising an escape window capable of transmitting the emission and the visible light and positioned in the optical path between the first reflective element and the surface. In some aspects, the optical control system is fully enclosed in the enclosure. In some aspects, the optical control system further comprises an air source configured to direct an air stream from an In some aspects, the enclosure further comprises a wall opposite the aperture configured to control the direction of the air stream and reduce turbulent flow without obstructing the beam.
In some aspects, the first reflective element is a mirror. In some aspects, the combining element transmits the beam and reflects the visible light. In some aspects, the emitter is a laser emitter. In some aspects, the laser emitter is selected from the group consisting of an infrared laser, an ultraviolet laser, and a visible laser. In some aspects, the optical control system further comprises a second targeting actuator connected to the first reflective element and configured to rotate the first reflective element and deflect the beam toward the target location. In some aspects, the optical control system further comprises a second reflective element positioned to intersect the optical path and deflect the beam deflected by the first reflective element, and a second targeting actuator connected to the second reflective element and configured to rotate the second reflective element and deflect the beam toward the target location. In some aspects, the first targeting actuator deflects the beam along a first axis and the second targeting actuator deflects the beam along a second axis, wherein the first axis and the second axis are orthogonal. In some aspects, the combining element is positioned after the emitter, the first reflective element is positioned after the combining element, and the second reflective element is positioned after the first reflective element relative to the direction of the beam. In some aspects, a weed is positioned at the target location.
In various aspects, the present disclosure provides a weed eradication method comprising: capturing an image of a prediction field of view with a prediction camera; locating a target in a prediction field of view; assigning the target to one of a plurality of targeting modules comprising a targeting camera having a targeting field of view overlapping with a location of the target; capturing an image of the targeting field of view with the targeting camera; locating the target in the targeting field of view; and directing a beam toward a location of the target.
In some aspects, locating the target in the prediction field of view further comprises identifying a position of the target in the prediction field of view. In some aspects, the weed eradication method further comprises identifying a region containing the target, wherein the region is defined by a polygon. In some aspects, the weed eradication method further comprises converting the position to a predicted surface location. In some aspects, the weed eradication method further comprises determining a desired movement in the targeting field of view. In some aspects, the weed eradication method further comprises converting the desired movement to an actuator position change. In some aspects, locating the target comprises identifying a target using a trained neural net. In some aspects, the trained neural net is capable of providing a bounding box, a polygon mask, or a combination thereof around the target. In some aspects, the trained neural net is trained with images of fields.
In some aspects, locating the target in the targeting field of view further comprises referencing a calibration function obtained by correlating locations of fiducial markers on a calibration surface to camera pixel coordinates and correcting the location of the target. In some aspects, assigning the target to one of the plurality of targeting modules comprises providing the location of the target to one of the plurality of targeting modules. In some aspects, directing a beam toward the location of the target further comprises referencing a calibration function obtained by correlating pixel movements of fiducial markers on a calibration surface to actuator tilt values and correcting the actuator tilt values. In some aspects, the weed eradication method further comprises deactivating the beam once the target has been damaged or killed.
In some aspects, capturing an image of the targeting field of view with the targeting camera, locating the target in the targeting field of view, and directing a beam toward a location of the target are performed with high accuracy. In some aspects, the target is a weed.
In some aspects, the weed eradication method further comprises damaging or killing the weed. In some aspects, damaging or killing the weed comprises irradiating the weed. In some aspects, damaging or killing the weed comprises burning the weed. In some aspects, locating the target comprises differentiating between the weed and a desired plant.
In various aspects, the present disclosure provides a targeting system comprising a prediction module, a targeting module, and an optical control module; the prediction module comprising: a prediction camera configured to image a prediction field of view on a surface and to locate a target in the prediction field of view, and a prediction module controller configured to convert a location of the target in the prediction field of view to a predicted location on the surface and assign the target to the targeting module; the targeting module comprising: a targeting module controller configured to convert the predicted location to a position of a targeting actuator; and the optical control module comprising: an emitter configured to emit a beam along an optical path toward the target, and the targeting actuator configured to receive position information from the targeting module controller and deflect the beam toward the target.
In some aspects, the targeting system further comprises a targeting camera configured to image a targeting field of view on the surface and to locate the target in the targeting field of view. In some aspects, the optical control module further comprises: a first reflective element controlled by the targeting actuator and positioned to intersect the optical path and deflect the beam, and a combining element positioned in the optical path between the emitter and the first reflective element and configured to differentially deflect the beam and a scattered light from the targeting field of view traveling along the optical path in a direction opposite the beam.
In some aspects, the optical control module is configured to direct the beam toward the target while the targeting system is moving relative to the surface. In some aspects, the targeting module is configured to detect a pixel movement of the targeting field of view relative to the target and convert from the pixel movement of the targeting field of view to a motion of the targeting actuator.
In some aspects, the targeting system further comprises an inertial measurement unit configured to measure an acceleration of the targeting system and a rotation of the targeting system relative to the surface. In some aspects, the targeting module is configured to adjust the predicted location based on an amount of time since imaging, an acceleration of the targeting system, a rotation of the targeting system relative to the surface, or a combination thereof. In some aspects, the targeting system further comprises a second targeting module comprising: a second targeting camera configured to image a second targeting field of view on the surface and to locate the target in the second targeting field of view, and a targeting module controller configured to convert a location of the target in the second targeting field of view to a position of a second targeting actuator. In some aspects, the prediction field of view comprises the targeting field of view.
In some aspects, the targeting system further comprises a vehicle transporting the prediction camera and the optical control module. In some aspects, the vehicle is an autonomous vehicle. In some aspects, the vehicle comprises a plurality of wheels.
In some aspects, the optical control module is enclosed in an enclosure, the enclosure comprising an escape window capable of transmitting the emission and the visible light and positioned in the optical path between the first reflective element and the surface. In some aspects, the optical control module is fully enclosed in the enclosure. In some aspects, the targeting system further comprises an air source configured to direct an air stream from an aperture in an external surface of the enclosure toward an exterior surface of the escape window. In some aspects, the enclosure further comprises a wall opposite the aperture configured to control the direction of the air stream and reduce turbulent flow without obstructing the beam.
In some aspects, the first reflective element is a mirror. In some aspects, the combining element transmits the beam and reflects the visible light. In some aspects, the emitter is a laser emitter. In some aspects, the laser emitter is selected from the group consisting of an infrared laser, an ultraviolet laser, and a visible laser. In some aspects, the optical control module further comprises a second targeting actuator connected to the first reflective element and configured to rotate the first reflective element and deflect the beam toward the target. In some aspects, the optical control module further comprises a second reflective element positioned to intersect the optical path and deflect the beam deflected by the first reflective element, and a second targeting actuator connected to the second reflective element and configured to rotate the second reflective element and deflect the beam toward the target. In some aspects, the first targeting actuator deflects the beam along a first axis and the second targeting actuator deflects the beam along a second axis, wherein the first axis and the second axis are orthogonal. In some aspects, the combining element is positioned after the emitter, the first reflective element is positioned after the combining element, and the second reflective element is positioned after the first reflective element relative to the direction of the beam.
Additional aspects and advantages of the present disclosure will become readily apparent to those skilled in this art from the following detailed description, wherein only illustrative embodiments of the present disclosure are shown and described. As will be realized, the present disclosure is capable of other and different embodiments, and its several details are capable of modifications in various obvious respects, all without departing from the disclosure. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference.
The novel features of the disclosure are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present disclosure will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the disclosure are utilized, and the accompanying drawings of which:
Cultivation of crops is essential for food and textile production. One important component of crop management is the control or elimination of undesirable plant species, commonly referred to as weeds. Weeds may decrease crop yield by depriving a desired plant of resources including water, nutrients, sunlight, and space. Weeds may further interfere with crop growth by harboring pests or parasites that damage the desired plants. Traditional weed control and eradication methods include hand cultivation or chemical herbicides. Hand cultivation is labor intensive, leading to increased cost of crop production and higher food and textile prices. Use of chemical herbicides may have negative environmental impacts including ground water contamination, acute toxicity, or long-term health effects such as cancer.
Development of eco-friendly and low-cost weed control and eradication methods is important for higher crop yield, lower food prices, and long-term environmental stability. Reducing or eliminating the need for herbicides may decrease many of the negative environmental side-effects of crop production, including toxic run-off and ground water contamination. Decreasing the need for manual labor may substantially lower farming costs and improve labor standards.
The present disclosure provides various methods, devices, modules, and systems which may be employed for automated identification, maintenance, control, or targeting of plants. In some embodiments, the methods, devices, modules, and systems disclosed herein may be used to autonomously identify and eradicate weeds located within a field of crops. For example, disclosed herein are particular methods for autonomously locating, identifying, and targeting objects, for example weeds, with a beam comprising electromagnetic radiation. Also disclosed herein are devices configured to locate, identify, and autonomously target the objects with a beam. The devices may be used, for example, to control or eliminate weeds. For example, the devices may be used to burn or irradiate weeds. The modules disclosed herein may be used for autonomous control of the devices and systems disclosed herein to implement the methods disclosed herein, for example to locate, identify, target, and control or eliminate weeds. The systems disclosed herein may comprise devices, modules, and methods configured to autonomously control or eliminate an object, for example a weed, by locating, identifying, and targeting the object with an emission. Sometimes, the methods, devices, modules, and systems may be used for agricultural crop management or for at-home weed control. The methods, devices, modules, and systems may be used as alternatives to hand cultivation or chemical herbicides.
Described herein are optical control systems for directing a beam, for example a light beam, toward a target location on a surface.
The beam combiner may also be referred to as a beam combining element. In some embodiments, the beam combiner 103 may be a zinc selenide (ZnSe), zinc sulfide (ZnS), or germanium (Ge) beam combiner. For example, the beam combiner may be configured to transmit infrared light and reflect visible light. In some embodiments, the beam combiner 103 may be a dichroic. In some embodiments, the beam combiner may be configured to pass electromagnetic radiation having a wavelength longer than a cutoff wavelength and reflect electromagnetic radiation having a wavelength shorter than the cutoff wavelength. In some embodiments, the beam combiner may be configured to pass electromagnetic radiation having a wavelength shorter than a cutoff wavelength and reflect electromagnetic radiation having a wavelength longer than 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 polarizing beam splitter, a long pass filter, a short pass filter, or a band pass filter.
The positions and orientations of one or both of the first reflective element 105 and the second reflective element 106 may be controlled by actuators. In some embodiments, an actuator may be a motor, a solenoid, a galvanometer, or a servo. For example, the position of the first reflective element may be controlled by a first actuator 110, and the position and orientation of the second reflective element may be controlled by a second actuator 111. In some embodiments, a single reflective element may be controlled by a plurality of actuators. For example, the first reflective 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 a reflective element along a plurality of axes. An actuator may change a position of a reflective element by rotating the reflective element, thereby changing an angle of incidence of a beam encountering the reflective element. Changing the angle of incidence may cause a translation of the position at which the beam encounters the surface. In some embodiments, the angle of incidence may be adjusted such that the position at which the beam encounters the surface is maintained while the optical system moves with respect to the surface. In some embodiments, the first actuator rotates the first reflective element about a first rotational axis, thereby translating the position at which the beam encounters the surface along a first translational axis, and the second actuator rotates the second reflective element about a second rotational axis, thereby translating the position at which the beam encounters the surface along a second translational axis. In some embodiments, a first actuator and a second actuator rotate a first reflective element about a first rotational axis and a second rotational axis, thereby translating the position at which the beam encounters the surface of the first reflective element along a first translational axis and a second translational axis. For example, a single reflective element may be controlled by a first actuator and a second actuator, providing translation of the position at which the beam encounters the surface along a first translation axis and a second translation axis with a single reflective element controlled by two actuators. The first translational axis and the second translational axis may be orthogonal. A coverage area on the surface may be defined by a maximum translation along the first translational axis and a maximum translation along the second translation axis. One or both of the first actuator and the second actuator may be servo-controlled, piezoelectric actuated, piezo inertial actuated, stepper motor-controlled, galvanometer-driven, linear actuator-controlled, or any combination thereof. One or both of the first reflective element and the second reflective element may be a mirror; 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 reflective element and the second reflective element may be any element capable of deflecting the beam.
The enclosure may further comprise a self-cleaning device configured to prevent accumulation of dust or debris on the surface of the laser escape window or to remove dust or debris that has accumulated on the surface of the laser escape window. In some embodiments, the self-cleaning device comprises an aperture 352 in an external surface of the enclosure 361 configured to discharge clean air 353. The clean air may prevent debris from damaging the laser escape window. In some embodiments, the clean air may be filtered. The aperture may be configured to direct an air stream from toward an exterior surface of the escape window 362. The aperture may be configured such that the clean air is directed across the surface of the laser escape window. In some embodiments, the enclosure is configured to guide the clean air without obstructing the beam 102. For example, the enclosure may comprise an opening 354 after the laser escape window in the beam path having clearance such that the beam may pass unobstructed. In some embodiments, the opening comprises a wall opposite the aperture. The wall may be configured to control the direction of the air stream and reduce turbulent flow without obstructing the beam. The opening may encompass the laser escape window and the beam path, and be configured so that the opening is narrower close to the laser escape window and wider farther from the laser escape window in the direction of the beam path. In some embodiments, the opening has smooth corners 355 to allow passage of the clean air while preventing turbulent flow.
After exiting the optical control system, the beam 102 may be directed toward a surface, as shown in
In some embodiments, a plurality of optical control systems may be combined to increase a coverage area on a surface.
The plurality of optical control systems may be configured on a vehicle 601, as shown in view 600 of
Disclosed herein is a prediction module configured to locate targets on a surface.
The prediction module 810 shown in
The prediction module may further comprise an image detection module. The imaging detection module may be configured to locate and identify a target in an image. For example, the imaging detection module may be configured to differentiate between two plants, such as between a crop and a weed. In some embodiments, the imaging detection module comprises using a convolutional neural net. The neural net may be trained with many images, such as images from the prediction camera or the targeting camera, of surfaces with or without targets. For example, the neural net may be trained with images of fields with or without weeds. Once trained, the neural net may be configured to identify a region in the image comprising a target. The region may be defined by a polygon, for example a rectangle. In some embodiments, the region is a bounding box. In some embodiments, the region is a polygon mask covering an identified region.
Based on the location of the target, a target assignment system 814 may assign the target to a targeting module 820 of a plurality of targeting modules. The location of the target may be corrected based on a magnitude and direction of motion during an elapsed time, or the location may be within a region defined by a polygon, or both. A future target location may be determined based on a predicted magnitude and direction of motion during future time period. The target assignment module may assign the target to the targeting module having a coverage area that overlaps with the target location, the corrected target location, or the future target location.
The prediction module may comprise 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 should comprise sufficient RAM, storage space, CPU power, and GPU power to perform operations to detect and identify a target. The prediction camera should provide images of sufficient resolution on which to perform operations to detect and identify a target.
Disclosed herein are targeting modules configured to direct a beam toward a target location on a surface.
As shown in
In some embodiments, the target prediction system further comprises an image detection module. The imaging detection module may be configured to locate and identify a target in an image. For example, the imaging detection module may be configured to differentiate between two plants, such as between a crop and a weed. In some embodiments, the imaging detection module comprises using a convolutional neural net. The neural net may be trained with many images, such as images from the prediction camera or the targeting camera, of surfaces with or without targets. For example, the neural net may be trained with images of fields with or without weeds. Once trained, the neural net may be configured to identify a region in the image comprising a target. The region may be defined by a polygon, for example a rectangle. In some embodiments, the region is a bounding box. In some embodiments, the region is a polygon mask covering an identified region.
The target location may be further corrected using the pose and motion correction system 823. The pose and motion correction system may use a positioning system, for example an IMU, a GPS, or an INS, to determine a magnitude and direction of motion of the targeting camera. In some embodiments, acceleration and rotation readings from an IMU coupled directly or indirectly to the targeting camera are used to determine a magnitude and direction of motion. For example, the prediction camera and the IMU may be mounted to a vehicle. The IMU may collect motion readings of the IMU, and anything directly or indirectly coupled to the IMU, such as the targeting camera. For example, the IMU may collect readings comprising three-dimensional acceleration and three-dimensional rotation information which may be used to determine a magnitude and a direction of motion over an elapsed time. In some embodiments, the pose and motion correction system may use GPS to determine a magnitude and direction of motion of the targeting camera. For example, the GPS may be mounted to the vehicle. The GPS may communicate with a satellite-based radionavigation system to measure a first position of the targeting camera at a first time and a second position of the targeting camera at a second time. In some embodiments, the pose and motion correction system may use an INS to determine a magnitude and direction of motion of the targeting camera. For example, the INS may measure the position, the orientation, and the velocity of the targeting camera. In some embodiments, after the target prediction system 821 locates a target in an image, the pose and motion correction system determines an amount of time that has elapsed since the image was captured and the magnitude and direction of motion of the targeting camera that has occurred during the elapsed time. The pose and motion correction system may integrate the target location, time elapsed, and magnitude and direction of motion to determine a corrected location of the target on the surface. In some embodiments, the positioning system used by the pose and motion correction system of the targeting module 823 and the positioning system used by the pose and motion correction system of the prediction module 813 are the same. A future target location may be determined based on a predicted magnitude and direction of motion during future time period. In some embodiments, the positioning system used by the pose and motion correction system of the targeting module and the positioning system used by the pose and motion correction system of the prediction module are different.
The actuator control system 824 comprises software-driven electrical components capable of providing signals the first actuator, and optionally the second actuator, controlling the first reflective element, and optionally the second reflective element. For example, the actuator control system sends a signal comprising actuator pan tilt values to the first actuator and the second actuator. The actuators adopt the signaled pan tilt positions and move the first reflective element and the second reflective element around a first rotational axis and a second rotational axis to positions such that the beam is deflected to the target location, the corrected target location, or the future target location.
The laser control system 825 comprises software-driven electrical components capable of controlling activation and deactivation of the emitter. Activation or deactivation may depend on the presence or absence of a target as detected by the targeting camera 104. Activation or deactivation may depend on the position of the beam path directed toward the surface relative to a target location. In some embodiments, the laser control system may activate the emitter when a target is identified by the target prediction system. In some embodiments, the laser control system may activate the emitter when the beam path is positioned to overlap with the target location. In some embodiments, the laser control system may fire the emitter when the beam path is within a region of the surface comprising a target defined by a polygon, for example a bounding box or a polygon mask covering the identified region. The laser control system may deactivate the emitter once the target has been eliminated, the region comprising the target has been scanned by the beam, the target is no longer identified by the target prediction module, a designated period of time has elapsed, or any combination thereof. For example, the laser control system may deactivate the emitter once a region on the surface comprising a weed has been scanned by the beam, or once the weed has been irradiated or burned.
The prediction modules and the targeting modules described herein may be used in combination to locate, identify, and target a target with a beam. The targeting control module may comprise an optical control system as described herein. The prediction module and the targeting module may be in communication, for example electrical or digital communication. In some embodiments, the prediction module and the targeting module are directly or indirectly coupled. For example, the prediction module and the targeting module may be coupled to a support structure. In some embodiments, the prediction module and the targeting module are configured on a vehicle, for example the vehicle 601, as shown in
The targeting module may comprise 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 an tensor processing unit (TPU). The system computer should comprise sufficient RAM, storage space, CPU power, and GPU power to perform operations to detect and identify a target. The targeting camera should provide images of sufficient resolution on which to perform operations to detect and identify a target.
The prediction modules disclosed herein may further comprise calibration step. In some embodiments, the camera to control translation system of the prediction module 812 is calibrated. In some embodiments, a calibration surface is positioned within a field of view of a prediction camera. The calibration surface comprises known marks at known positions. The prediction camera may collect a plurality of images of the calibration surface at different positions relative to the calibration surface. The prediction module may then correlate a pixel position of a known mark to the known position on the surface. An interpolation function may be built from a plurality of correlated pixel positions and known surface positions. In some embodiments, the interpolation function may be saved to a hard drive and loaded from the hard drive by the prediction module.
The targeting modules disclosed herein may further comprise calibration step. In some embodiments, the camera to control translation system of the targeting module 812 is calibrated. In some embodiments, a calibration surface is positioned within a field of view of a targeting camera. The calibration surface comprises known marks at known positions. The targeting module may collect a plurality of images of the calibration surface and a plurality of actuator positions, such that the plurality of images comprises different fields of view. For example, the targeting module may collect a plurality of images at a plurality of randomly selected pan tilt values of a first actuator and a second actuator. A calibration map may be built from a plurality of sample points. Each sample point may be collected by identifying a pixel location of a known mark in an image collected at a known actuator position, and correlating the known location with the actuator position and the pixel location. In some embodiments, the map is fitted to a spline smoothing algorithm to build smooth curves to allow for accurate estimation of locations between the sample points. In some embodiments, the spline smoothing algorithm may be saved to a hard drive and loaded from the hard drive by the targeting module.
As shown in
Operations 930, 940, 950, and 960 are iterated for each target module 925. Operations 940, 950, and 960 are iterated for each weed. A targeting module of the plurality of targeting modules runs operation 940. The targeting camera captures a target image of the field, and the system controller identifies the weed in the target image 941. The system controller translates a pixel location of the weed in the target image into pan and tilt values for each actuator controlling each reflective element in an optical control system controlled by targeting module 942. The system controller applies a pose and motion correction to the actuator pan and tilt values based on motion of the vehicle measured by the IMU at 943 and plans a route for an emitted beam path controlled by the actuator pan and tilt positions 944. Once the actuators reach a determined position, an emitter is activated 945.
Operation 950 is repeated while the planned route is implemented 946. The weed is identified in an image collected by the targeting camera, and the route plan is updated based on an observed position of the weed 952. The system controller applies a pose and motion correction to the actuator pan and tilt values based on motion of the vehicle measured by the IMU at 953. The actuators are moved into position based on the updated route plan 954. Once the planned route has been completed the emitter is deactivated 960.
While preferred embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the disclosure. It should be understood that various alternatives to the embodiments of the disclosure described herein may be employed in practicing the disclosure. It is intended that the following claims define the scope of the disclosure and that methods and structures within the scope of these claims and their equivalents be covered thereby.
This application is a continuation of U.S. application Ser. No. 18/106,026, filed on Feb. 6, 2023, which is a continuation of U.S. application Ser. No. 17/022,483, filed Sep. 16, 2020, now U.S. Pat. No. 11,602,143, which claims the benefit of U.S. Provisional Application No. 62/901,641, filed Sep. 17, 2019, which applications are incorporated herein by reference in their entirety.
Number | Date | Country | |
---|---|---|---|
62901641 | Sep 2019 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 18106026 | Feb 2023 | US |
Child | 18382294 | US | |
Parent | 17022483 | Sep 2020 | US |
Child | 18106026 | US |