Unmanned aerial vehicle

Abstract

The present invention relates to an unmanned aerial vehicle (UAV) for agricultural weed management. The UAV comprises a control and processing unit (20) and a camera (30). The control and processing unit is configured to control the UAV to fly to a position within a canopy of crops and below a vertical height of the crops and / or between a row of multiple crops and below a vertical height of the multiple crops. The control and processing unit is configured to control the camera to acquire at least one image relating to the ground at a position within a canopy of crops and below a vertical height of the crops and / or between a row of multiple crops and below a vertical height of the multiple crops. The control and processing unit is configured to analyze the at least one image to determine a presence of at least one weed and its position on the ground.

Description

Technical Field

[0001] This invention relates to an unmanned aerial vehicle (UAV) for agricultural weed management, a base station, a system and method for agricultural weed management, and a computer program product. Background Technology

[0002] The general background of this invention is the assessment and management of farmland in terms of weeds. Currently, remote sensing and unmanned aerial vehicles (UAVs) (such as drones) cannot acquire images with the required resolution and quality to perform the necessary image diagnostics.

[0003] WO2019 / 076758A1 proposes a UAV configured to hover in a stationary position above the crop, then lower the camera towards the crop and into the crop canopy to acquire images. A drawback of this solution is that the downwash of the UAV's propellers creates noticeable leaf movement within the crop canopy at the imaging point. Furthermore, the camera can easily become entangled in dense canopy. Additionally, raising and lowering the camera from the UAV slows down the field survey process, making the acquisition of necessary image data very time-consuming. Summary of the Invention

[0004] Having improved methods for managing agricultural weeds would be beneficial.

[0005] The object of the invention is achieved through the subject matter of the independent claims, wherein further embodiments are incorporated in the dependent claims. It should be noted that the aspects and embodiments of the invention described below are also applicable to unmanned aerial vehicles for agricultural weed management, base stations, systems and methods for agricultural weed management, and computer program products.

[0006] According to a first aspect, an unmanned aerial vehicle (UAV) for agricultural weed management is provided. The UAV includes a first control and processing unit and a camera. The first control and processing unit is configured to control the UAV to fly to a position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit is configured to control the camera to acquire at least one image relative to the ground at the position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit is configured to analyze the at least one image to determine the presence of at least one weed and its location on the ground.

[0007] In other words, UAVs fly close to crops to allow for proximity sensing of weeds. In this way, UAVs are able to generate precise and accurate weed maps of agricultural crop fields.

[0008] UAVs can acquire data by randomly scouting around the field. The UAVs themselves can also determine their location to acquire data through image processing, or they can be guided to a location by the user. Because UAVs can fly through the canopy to acquire more information in a shorter time compared to other technologies proposed in WO2019 / 076758A1, UAVs (or multiple similar UAVs) can acquire weed images and economically generate weed maps for the entire field.

[0009] In one embodiment, the at least one image comprises a plurality of images, and wherein the processing and control unit is configured to control a camera to acquire the plurality of images at corresponding multiple different locations relative to the ground within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops.

[0010] In other words, the granularity of the weed map is increased by acquiring images at various heights and locations within the crop canopy and / or between multiple crops in a row.

[0011] In one embodiment, the first control and processing unit is configured to analyze at least one image to determine a weed map, wherein the weed map classifies the presence of weeds on the ground based on the density and spatial distribution of the weeds.

[0012] In other words, the images are used to analyze the frequency and banding of weeds in crop fields. This helps to identify whether weeds are evenly distributed, present in patches, or whether individual weed plants are randomly distributed in the field.

[0013] In one embodiment, the UAV has a size on the order of 1cm to 20cm, preferably 2cm to 10cm, more preferably 4cm to 8cm, and a weight equal to or less than 200g, preferably equal to or less than 100g, more preferably equal to or less than 50g.

[0014] Therefore, UAVs are small in size to allow for optimal freedom of movement within the canopy and between crop rows below the vertical height of the crop. When flying within the canopy, such UAVs are less susceptible to wind disturbance because the crop at least partially protects them from such influences. Furthermore, their small size and light weight contribute to greater safety, for example, in the event of an unintended accidental collision.

[0015] In one embodiment, the UAV includes a propeller guard. The propeller guard is configured to at least partially surround the UAV's propeller and preferably completely surround the propeller.

[0016] In this way, for example, the propeller is protected from being struck by the blades, which could otherwise potentially intercept the propeller's rotational motion.

[0017] In one embodiment, the UAV includes at least one weed control unit. The at least one weed control unit is configured to be activated at a location determined by the first control and processing unit based on image analysis of the presence and location of at least one weed.

[0018] Therefore, UAVs can acquire images, analyze images, and control weeds, for example, by applying appropriate herbicides in an operational sequence. This is more efficient than the solution proposed in WO2019 / 076758A1. Furthermore, UAVs with at least one weed control unit get closer to the target weeds, which provides greater accuracy in applying herbicides to the target. A second advantage is that the ground effect reduces the energy required for flight and increases the UAV's range.

[0019] In one embodiment, the UAV includes a location determining device. The location determining device is configured to provide a first control and processing unit with at least one location associated with a camera when at least one image related to the ground is acquired.

[0020] In one embodiment, the UAV includes a first transceiver. A first control and processing unit is configured to utilize the first transceiver to transmit image analysis of at least one ground-related image and / or at least one ground-related image, as well as information about at least one location associated with a camera when the at least one ground-related image is acquired. The first control and processing unit is configured to receive a command to fly to at least one location where at least one type of weed has been identified and to activate at least one weed control unit at said at least one location. This command is based on image analysis of the at least one ground-related image and / or at least one ground-related image transmitted by the first transceiver.

[0021] In other words, the UAV sends information about the acquired images and the locations of those images to another processing unit, such as a base station (e.g., a vehicle). The base station is larger and has greater processing power, and is capable of receiving image information from multiple UAVs in the field. The base station coordinates the flight paths of multiple UAVs and sends commands to them to fly to the locations where weeds need to be controlled. The optimal flight path is calculated by considering various aspects of the UAVs, such as their energy level, the type of control unit, the remaining capacity of the control unit to control a particular weed problem, the location of the UAV, and the distance between the location of the identified weed problem. In this way, when calculating the appropriate flight path, the base station's second control and processing unit can also consider the "specialization" of different UAVs in the crop field (e.g., one UAV specifically dedicated to detecting weeds on the ground, another specifically dedicated to weed control, etc.).

[0022] According to a second aspect, a base station for multiple UAVs is provided. The base station includes: a UAV parking unit comprising at least one UAV, a second control and processing unit, and at least one second transceiver. The at least one UAV includes a first control and processing unit, a camera, and a first transceiver. The UAV parking unit of the base station is configured to carry multiple UAVs. The second control and processing unit is configured to control the UAVs to fly from the base station to a position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit of the UAVs is configured to control the camera to acquire at least one image related to the ground at the position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit of the UAVs is configured to transmit information about the at least one image related to the ground to the base station using the first transceiver. The second control and processing unit of the base station is configured to receive information about the at least one image related to the ground from the at least one UAV using the second transceiver. The base station's second control and processing unit is configured to analyze at least one image received from at least one UAV to determine the presence of at least one type of weed and its location on the ground.

[0023] Therefore, if a UAV has a small size and limited processing capabilities for the acquired image information, it can transmit the image information to a base station via wireless communication. The base station has greater processing power. It receives image data from the small UAV and is capable of performing in-depth image analysis, such as using artificial intelligence algorithms to identify weed problems in crop fields.

[0024] In one embodiment, a base station for multiple UAVs includes at least one UAV. The at least one UAV further includes a location determination device. The location determination device is configured to provide a first control and processing unit of the UAV with at least one location associated with a camera upon acquisition of at least one image relating to the ground. The first control and processing unit of the UAV is configured to transmit information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a first transceiver. A second control and processing unit of the base station is configured to receive information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a second transceiver. The second control and processing unit of the base station is configured to analyze at least one image received from the at least one UAV to determine the presence of at least one type of weed on the ground at the at least one location.

[0025] In one embodiment, a base station for multiple UAVs includes at least one UAV. The at least one UAV also includes at least one weed control unit. A second control and processing unit of the base station is further configured to determine instructions for the at least one UAV to fly to at least one location where the presence of at least weeds has been determined, and to activate the at least one weed control unit at said at least one location.

[0026] In one embodiment, a base station for multiple UAVs includes a UAV parking unit with the multiple UAVs. A second control and processing unit of the base station is configured to analyze at least one image received from at least one UAV to determine a weed map. The weed map classifies the presence of weeds on the ground according to their density and spatial distribution. The second control and processing unit of the base station is also configured to determine a flight path map for the multiple UAVs based on the weed map and the classification of weeds according to their density and spatial distribution on the ground. The second control and processing unit of the base station is further configured to determine instructions for the multiple UAVs to fly to at least one location where the presence of at least weeds has been determined, and to activate at least one weed control unit at said at least one location according to the determined flight path map.

[0027] Therefore, the base station's second control and processing unit coordinates the activities of multiple UAVs. Depending on the weeds present in the farmland and the corresponding weed map, it can instruct the multiple UAVs to control the weeds in different ways. For example, application can be done in patches, as parallel strips, or via a target-to-target approach. A large, evenly distributed distribution of weeds favors a strip application strategy, while a small number of weeds favors a target-to-target application strategy. Furthermore, the presence of weed patches allows for a patch-based strategy, in which the UAV's weed control unit treats only certain areas of the field. The base station's second control and processing unit determines which strategy is optimal and establishes flight plans for the multiple UAVs to optimally manage the farmland.

[0028] In one embodiment, a base station for multiple UAVs includes a second control and processing unit configured to control the multiple UAVs to operate in alternating groups, such that when one group is out flying, another group is on a UAV parking unit.

[0029] In other words, while one group of UAVs is flying over the crop field and controlling weeds, another group is at the base station and preferably receives services from the service unit (such as recharging the battery and / or refilling the spray can).

[0030] According to a third aspect, a system for agricultural weed management is provided. The system includes a base station for multiple UAVs. The base station includes: a UAV parking unit comprising at least one UAV, a second control and processing unit, and at least one second transceiver. The at least one UAV includes a first control and processing unit, a camera, and a first transceiver. The UAV parking unit is configured to carry multiple UAVs. The first control and processing unit of the UAVs is configured to cause the UAVs to fly from the base station to a position within the canopy of crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit of the UAVs is configured to control the camera to acquire at least one image related to the ground at the position within the canopy of crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit of the UAVs is configured to transmit information including information about the at least one image related to the ground to the base station using the first transceiver. The second control and processing unit of the base station is configured to receive information about the at least one image related to the ground from the at least one UAV using the second transceiver. The base station's second control and processing unit is configured to analyze at least one image received from at least one UAV to determine the presence of at least one type of weed and its location on the ground.

[0031] According to the fourth aspect, a method for agricultural weed management is provided, comprising:

[0032] a) Flying the UAV into the canopy of a crop and below the vertical height of the crop and / or between multiple crops in a row and below the vertical height of the multiple crops;

[0033] b) Acquire at least one ground-related image by a camera at a position within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops;

[0034] c) Analyze at least one image to determine at least one type of weed and its location on the ground.

[0035] In a fifth aspect, a computer program product for controlling a UAV of the first aspect is provided, the computer program product being configured, when executed by a processor, to perform the method of the fourth aspect.

[0036] Advantageously, the benefits provided by any of the above aspects also apply to all other aspects, and vice versa.

[0037] The above aspects and embodiments will become apparent and will be illustrated with reference to the implementation schemes described below. Attached Figure Description

[0038] An exemplary implementation scheme will now be described with reference to the following figures:

[0039] Figure 1 A schematic setup of an embodiment of a UAV for agricultural weed management is shown;

[0040] Figure 2 A schematic setup of an embodiment for a base station used for multiple UAVs is shown;

[0041] Figure 3 A schematic embodiment of a system for agricultural weed management is shown;

[0042] Figure 4 A schematic embodiment of a method for agricultural weed management is shown;

[0043] Figure 5 A schematic representation of detailed embodiments of a base station (UAV vehicle) and multiple UAVs on farmland is shown;

[0044] Figures 6a) to 6c) Illustrative embodiments of multiple UAVs applying herbicides to agricultural crop fields based on different weed maps are shown. Detailed Implementation

[0045] Figure 1 An embodiment of an unmanned aerial vehicle (UAV) 10 for agricultural weed management is shown. The UAV includes a first control and processing unit 20 and a camera 30. The first control and processing unit is configured to control the UAV to fly to a position within the canopy of crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit is configured to control the camera to acquire at least one image related to the ground at the position within the canopy of crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit is configured to analyze the at least one image to determine the presence of at least one weed and its position on the ground.

[0046] In one embodiment, the term "agricultural weed management" refers to field survey activities to identify weeds on the ground in farmland. Where at least one weed control unit 50 is present, the term also includes control activities for the identified weeds.

[0047] In one embodiment, a location within the crop canopy and below the vertical height of the crop refers to a location within and / or beside the spatial arrangement (three-dimensional geometry) of the aboveground portion of the crop plant, but not at a height above the crop plant.

[0048] In one embodiment, a position between multiple rows of crops and below the vertical height of said crops refers to a position at a height between the crop canopies of different rows but not above the crop plants. It is possible that the crop canopies partially overlap at the top, while the UAV flies below.

[0049] In one embodiment, the camera includes a conventional imaging sensor that can be used to image the ground at a certain resolution, so that image processing can identify at least one type of weed.

[0050] In one embodiment, the camera is a 360-degree omnidirectional camera, or a camera capable of imaging essentially 360 degrees.

[0051] In one embodiment, the camera is configured to operate in the visible wavelength range. In one embodiment, the camera is configured to operate in the near-infrared range. In one embodiment, the camera is monochrome. In one embodiment, the camera is configured to acquire color information such as RGB. In one embodiment, the camera is configured to acquire hyperspectral information. This improves image analysis for the automatic detection of at least one type of weed.

[0052] In one embodiment, the camera also includes a light source, which may also be multispectral to support image acquisition.

[0053] In one embodiment, the first control and processing unit is configured to analyze at least one image to determine at least one type of weed.

[0054] In one embodiment, image analysis of at least one image includes the use of machine learning algorithms. This is applicable to image processing to identify at least one type of weed.

[0055] In one embodiment, the machine learning algorithm includes a decision tree algorithm.

[0056] In one embodiment, the machine learning algorithm includes an artificial neural network.

[0057] In one embodiment, the machine learning algorithm has been trained on multiple images. In another embodiment, the machine learning algorithm has been trained on multiple images, which include images of at least one type of weed on the ground.

[0058] In one embodiment, the machine learning algorithm has been taught based on multiple images containing such images.

[0059] Therefore, the first control and processing unit can run image processing software including a machine learning analyzer. For example, it acquires images of specific weeds on the ground, along with information related to the size of the weeds, the geographical location of the weeds to be found globally, and the time of year in which the weeds are to be found. The name of the weed can also be labeled using the image of the weed. The machine learning analyzer is then trained on the acquired image; the machine learning analyzer can be based on an artificial neural network or a decision tree analyzer. Thus, when a new image of the ground is presented to the analyzer, the analyzer determines the specific type of weed in the image by comparing the image of the weeds found in the new image with images of different weeds that have been trained on the analyzer, where such images may have associated timestamps (such as the time of year) and geographical locations labeled to the image. The images of different weeds trained on the analyzer may also take into account the size of the weeds and the location and time of their growth. Therefore, the specific location and size of the weed type on the ground can be determined. The first control and processing unit can access a database containing different weed types. This database is compiled based on experimentally determined data.

[0060] In one embodiment, image analysis includes identifying nesting sites of birds or small mammals and their locations (for their future protection).

[0061] In one embodiment, the term "crop" refers to orchard crop plants and / or arable crop plants, and preferably arable crop plants. Orchard crops are selected from apples, pears (European and Asian), grapevines, stone fruits (such as peaches, nectarines, plums, apricots, apricot plums, prunes, persimmons, cherries), subtropical crops (such as mangoes, avocados, olives, citrus fruits, oranges, lemons, limes, tangerines, grapefruits, kiwifruits, pomelos, kumquats, Calimonic oranges, Javanese pomelos, figs, dates), and nut crops (such as almonds, pecans, pistachios, walnuts, hazelnuts, chestnuts, and chestnuts). Arable crops refer to grain crops (such as wheat, corn, rice, barley, millet, oats, rye), legumes (such as lentils, kidney beans, peas), oilseed crops (such as rapeseed, soybeans, sunflowers, flaxseeds), fiber crops (such as cotton, jute, flax), vegetable crops (such as tomatoes, peppers, potatoes, pumpkins, garlic, onions, leeks, carrots, celery, beets, beetroot, spinach, lettuce, clover, cabbage, Brussels sprouts, broccoli, cauliflower, turnips, cucumbers), fruit crops (such as melons, watermelons, strawberries, raspberries, blueberries, pineapples, bananas), flower crops (such as lilies, orchids, tulips), and other crops (such as peanuts, sugarcane, cocoa, coffee, tea).

[0062] More preferred crops are those planted in rows, such as sugarcane, corn, soybeans, rapeseed, sunflowers, cotton, potatoes, tomatoes, peppers, cucumbers, onions, wheat, barley, rice, grapevines, peanuts, bananas, cocoa, and coffee.

[0063] In one embodiment, the width (distance) between the two rows of planted crops is between 10cm and 2m, more preferably between 50cm and 1.5m.

[0064] In one embodiment, the crop has a height between 20cm and 10m, preferably between 20cm and 5m, and more preferably between 50cm and 3.5m.

[0065] According to one embodiment, the at least one image includes multiple images, and the processing and control unit is configured to control a camera to acquire the multiple images at corresponding multiple different locations relative to the ground, within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops.

[0066] According to one embodiment, the first control and processing unit is configured to analyze at least one image to determine a weed map, wherein the weed map classifies the presence of weeds on the ground according to the density and spatial distribution of the weeds.

[0067] In one embodiment, at least one image acquired from a UAV above the crop canopy can also be used to determine a weed map.

[0068] In one embodiment, the first control and processing unit is configured to analyze at least one image to determine a weed map, wherein the weed map classifies the presence of weeds on the ground based on weed density, spatial distribution, and their typology.

[0069] In one embodiment, weed density refers to the number of weed plants per square meter.

[0070] In one embodiment, the spatial distribution of weeds refers to the degree of aggregation of weeds in certain locations within a field. For example, the spatial pattern of weeds can be dispersed (individual plants randomly distributed across the field) or clustered (weeds forming patches on the field). Furthermore, the spatial distribution of weeds can be dense and uniform, for example, between multiple crops in a row.

[0071] According to one embodiment, the UAV has a size on the order of 1cm to 20cm, preferably 2cm to 10cm, more preferably 4cm to 8cm, and a weight equal to or less than 200g, preferably equal to or less than 100g, more preferably equal to or less than 50g.

[0072] According to one embodiment, the UAV includes a propeller guard 40. The propeller guard is configured to at least partially surround the UAV's propeller, preferably completely surrounding the propeller.

[0073] In one embodiment, the propeller protection device may be made of a robust, lightweight material and may be molded into a three-dimensional shape or assembled from thin strips of material into a three-dimensional structure.

[0074] In one embodiment, the UAV's propeller is a counter-rotating propeller.

[0075] In one embodiment, the camera is mounted on an extendable and retractable bracket on the UAV. The bracket is configured to change the distance between the camera and the UAV body.

[0076] In one embodiment, the camera is mounted on a telescopic, extendable, and retractable bracket on the UAV.

[0077] In one embodiment, the UAV includes a distance sensor configured to measure the distance of the extendable and retractable support relative to the weeds.

[0078] In one embodiment, the first control and processing unit of the UAV is configured to use information from a distance sensor to avoid the UAV, whereby the UAV's extendable and retractable support collided with weeds and / or crop plants.

[0079] In one embodiment, the UAV includes a distance sensor, which is preferably selected from LiDAR sensors, parallax laser rangefinder sensors, stereo vision sensors, IR reflection sensors, time-of-flight sensors, ultrasonic sensors, and radar sensors.

[0080] In one embodiment, the UAV includes a LiDAR sensor as a distance sensor. The distance sensor is used to guide the UAV, particularly in areas with very limited space, such as within the canopy of crop plants, and to help avoid collisions.

[0081] According to one embodiment, the UAV includes at least one weed control unit 50. The at least one weed control unit is configured to be activated at a location determined by a first control and processing unit based on image analysis of the presence and location of at least one weed.

[0082] In one embodiment, at least one weed control unit includes at least one spraying unit. The at least one spraying unit is configured to spray liquid.

[0083] In one embodiment, the spraying unit is positioned (or can be positioned using a extendable bracket) in front of the descending airflow from the UAV's propeller to avoid interference.

[0084] In one embodiment, in the context of a spraying unit, the term "activation" refers to the start of the spraying process.

[0085] In one embodiment, the spraying unit includes at least one liquid atomizer (such as a hydraulic nozzle) and / or at least one atomizing disc (such as a rotating disc).

[0086] In one embodiment, at least one weed control unit includes a liquid atomizer, a liquid tank, and at least one feed tube. The liquid tank is configured to contain chemicals. The feed tube is configured to deliver liquid from the liquid tank to the liquid atomizer. The liquid atomizer is configured to spray the liquid.

[0087] In one embodiment, the liquid container has a liquid volume capacity of 0.1 ml to 800 ml, preferably 0.5 ml to 100 ml.

[0088] In one embodiment, the term "liquid" refers to a liquid comprising chemically and / or biologically based agricultural herbicides.

[0089] In one embodiment, the term "liquid" also includes one or more adjuvants to be applied by at least one spraying unit to enhance the retention and biodelivery of the chemical- and / or biological agricultural herbicide on target weeds. These may be combined with the chemical- and / or biological agricultural herbicide before or within the spraying unit.

[0090] In one embodiment, the first control and processing unit is configured to control the UAV to fly at a flight altitude of less than 0.8m (more preferably less than 0.4m) above the ground when at least one spraying unit has been activated.

[0091] In one embodiment, the first control and processing unit is configured to activate at least one spraying unit to apply liquid as a spray of fine droplets, a single jet, a single droplet, or a combination thereof, depending on the preferred type of deposit.

[0092] In one embodiment, the first control and processing unit is configured to adjust the volume of liquid to be applied to the target by at least one spraying unit according to the size of the target.

[0093] In one embodiment, the first control and processing unit is configured to control the flight of the UAV and activate at least one spraying unit to achieve strip, patch, and target-to-target spraying application, or a combination thereof, on farmland.

[0094] In one embodiment, the first control and processing unit is configured to control the flight of the UAV and activate at least one spraying unit to apply liquid in a spray application mode within the crop to minimize the spread of weeds.

[0095] In one embodiment, at least one weed control unit is mounted on at least one extendable and retractable bracket on the UAV. The at least one bracket is configured to change the distance between the at least one weed control unit and the UAV body.

[0096] In one embodiment, at least one weed control unit is mounted on at least one telescopic, extendable, and retractable bracket on the UAV.

[0097] In one embodiment, the UAV includes a distance sensor configured to measure the distance between the extendable and retractable support and the weeds. Useful distance sensors have been discussed in more detail above.

[0098] In one embodiment, the first control and processing unit of the UAV is configured to use information from a distance sensor to avoid the UAV, whereby the UAV's extendable and retractable support collided with the weed target.

[0099] According to one embodiment, the UAV includes a position determination device 60. The position determination device 60 is configured to provide a first control and processing unit 20 with at least one position associated with a camera when at least one image related to the ground is acquired.

[0100] Location can be a geographic location relative to a precise location on the ground, or it can be a location on the ground that references another location or multiple locations on the ground, such as the boundary of a field or the location of a base station. In other words, an absolute geographic location can be used, or a location on the ground that does not need to be known in an absolute sense but references a known location can be used.

[0101] In one embodiment, the location is an absolute geographic location.

[0102] In one embodiment, the location is a location determined with reference to one or more known locations.

[0103] In other words, it is possible to determine that an image is associated with a specific location on the ground without knowing its precise geographic location. Instead, the location of the acquired image can be recorded by knowing the location of the image relative to a known location on the ground. In other words, the absolute GPS-derived location of the imagery acquired by the UAV can be provided, and / or the location of the acquired imagery relative to a known location (such as a field boundary or the location of a base station used by the UAV) can be provided. This again enables the first control and processing units to determine the exact location of the acquired imagery, as they will know the absolute location of the field boundary or charging station.

[0104] In one embodiment, the GPS unit is used to determine location (such as the location of the camera when a particular image is acquired) and / or is used in determining location (such as the location of the camera when a particular image is acquired).

[0105] In one embodiment, an inertial navigation unit is used alone or in combination with a GPS unit to determine location (such as the position of a camera when a particular image is acquired). Thus, for example, an inertial navigation unit including, for example, one or more laser gyroscopes is calibrated or zeroed at a known location (such as a base station), and as it moves with at least one camera, movement away from that known location in x, y, and z coordinates can be determined, thereby determining the position of at least one camera when an image is acquired.

[0106] According to one embodiment, the UAV includes a first transceiver 70. A first control and processing unit is configured to utilize the first transceiver to transmit image analysis of at least one ground-related image and / or at least one ground-related image, as well as information about at least one location associated with a camera when the at least one ground-related image is acquired. The first control and processing unit is configured to receive instructions to fly to at least one location where at least one type of weed has been identified and to activate at least one weed control unit 50 at said at least one location. These instructions are based on image analysis of the at least one ground-related image and / or at least one ground-related image transmitted by the first transceiver.

[0107] Therefore, the UAV acquires images that are sent (optionally along with basic image analysis) to one or more processors outside the UAV, where in-depth image analysis is performed. The external processor can receive images from multiple different UAVs (and locations) and can calculate multiple flying targets and the optimal flight path to the identified flying target while minimizing interference between adjacent UAVs. Flight path information is provided to individual UAVs, which use this information to fly towards the identified target and activate at least one weed control unit.

[0108] In one embodiment, the UAV includes a multispectral light source. This light source can help identify weeds (where less light is available within the canopy) and aid in navigation during flight, including at dawn, dusk, and night.

[0109] In one embodiment, the UAV includes at least one additional sensor, such as a thermal camera, a sensor for measuring soil moisture, and a sensor for measuring soil temperature. Data from such sensors can be used to plan weed control operations, as these factors affect weed and crop growth. Other sensors may include orientation sensors, location sensors, height sensors, battery level sensors, and position sensors relative to a base station, sound sensors, etc.

[0110] Figure 2 An embodiment of a base station 100 for multiple UAVs 10 is shown. The base station includes: a UAV parking unit 110 comprising at least one UAV 10, a second control and processing unit 120, and at least one second transceiver 130. The at least one UAV includes a first control and processing unit 20, a camera 30, and a first transceiver 70. The UAV parking unit is configured to carry multiple UAVs. The first control and processing unit 20 is configured to cause the UAVs to fly from the base station to a position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit 20 is configured to control the camera to acquire at least one ground-related image at the position within the canopy of crops and below the vertical height of the crops, and / or between a row of multiple crops and below the vertical height of the crops. The first control and processing unit 20 is configured to transmit information about the at least one ground-related image to the base station using the first transceiver 70. The second control and processing unit 120 is configured to receive information about at least one image relating to the ground from at least one UAV using a second transceiver 130. The second control and processing unit 120 is configured to analyze the at least one image received from at least one UAV to determine the presence of at least one type of weed and its location on the ground.

[0111] In one embodiment, a base station refers to a vehicle, such as an unmanned ground vehicle (UGV), a UAV, or a tractor.

[0112] In one embodiment, the base station is a UAV vehicle.

[0113] In one embodiment, the UAV carrier typically has dimensions from 0.5m to 2m and the capacity to carry a payload of several kilograms, preferably greater than 2kg. This would allow for a payload of, for example, 40 UAVs each weighing 50g, or 80 UAVs each weighing 25g. The carrier can carry a mixture of different-sized UAVs for different purposes (e.g., different-sized UAVs for field surveying and dedicated UAVs for weed control).

[0114] In one embodiment, the UAV vehicle includes at least one outrigger, preferably multiple outriggers. In one embodiment, the outriggers are extendable. Therefore, the UAV vehicle can land, for example, in the middle or at the boundary of a crop field without disturbing the growing crops.

[0115] In one embodiment, image analysis is performed by the processing unit 120 of the base station 100. Since there are no size limitations similar to those of UAVs flying within crop canopies, the base station can have extensive processing capabilities and analyze images from multiple UAVs. This is accomplished in the same manner discussed above.

[0116] In one embodiment, the base station includes a service unit. The service unit is configured to recharge a power unit (battery), refill at least one liquid tank (if any) with liquid, replace at least one liquid tank with a partially filled liquid tank, clean a spraying unit, and / or provide other necessary services to the UAV.

[0117] According to one embodiment, base station 100 includes a plurality of UAVs 10. Each UAV also includes a location determination device 60. The location determination device 60 is configured to provide a first control and processing unit 20 with at least one location associated with a camera upon acquisition of at least one image relating to the ground. The first control and processing unit 20 is configured to transmit information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a first transceiver 70. A second control and processing unit 120 of the base station is configured to receive information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a second transceiver 130. The second control and processing unit 120 is configured to analyze at least one image received from at least one UAV to determine the presence of at least one type of weed on the ground at the at least one location.

[0118] According to one embodiment, base station 100 includes a plurality of UAVs 10. At least one UAV also includes at least one weed control unit 50. A second control and processing unit 120 is further configured to determine instructions for the at least one UAV to fly to at least one location where the presence of at least one weed has been determined, and to activate the at least one weed control unit at said at least one location.

[0119] In one embodiment, the second control and processing unit 120 is configured to analyze the previous liquid treatment history of the farmland to select a suitable liquid for spraying application, the liquid having a different mode of action than the immediate previous treatment, to minimize the development of resistance and to determine instructions to give at least one UAV to fly to at least one location where the presence of at least one weed has been identified, and to activate at least one spraying unit at said at least one location.

[0120] In one embodiment, the second control and processing unit 120 is configured to identify locations where the liquid cannot work effectively, thereby selecting a suitable liquid for high-resistance spraying application, and determining instructions to give at least one UAV to fly to at least one location and activate at least one spraying unit at said at least one location.

[0121] In one embodiment, the second control and processing unit 120 is configured to identify a UAV that fails to spray liquid to a target location and determine instructions to give at least one additional UAV to fly to at least one target location and activate at least one spraying unit at the at least one target location.

[0122] In one embodiment, a base station 100 for multiple UAVs includes a UAV parking unit 110 with multiple UAVs. A second control and processing unit 120 is configured to analyze at least one image received from at least one UAV to determine a weed map. The weed map classifies the presence of weeds on the ground according to their density and spatial distribution (and preferably also according to their typology). The second control and processing unit 120 is also configured to determine a flight path map for the multiple UAVs based on the weed map and the classification of weeds according to their density and spatial distribution on the ground. The second control and processing unit 120 is also configured to determine instructions for the multiple UAVs to fly to at least one location where the presence of at least weeds has been determined, and to activate at least one weed control unit 50 at said at least one location according to the determined flight path map.

[0123] In one embodiment, the flight path map includes information on the activation and deactivation of at least one weed control unit of the UAV.

[0124] In one embodiment, the activation / deactivation of the flight path map and at least one weed control unit along the UAV's flight path map includes information about strips, patches, and target-to-target weed control operations, or combinations thereof.

[0125] According to one embodiment, a base station 100 for multiple UAVs 10 includes UAVs, wherein a second control and processing unit 120 is configured to control the multiple UAVs to operate in alternating groups, such that when one group is flying outside, another group is on a UAV parking unit.

[0126] In one embodiment, the UAV on the parking unit receives services from the base station's service unit.

[0127] In one embodiment, the parking unit is an open landing module configured to enable multiple UAVs to take off and land.

[0128] In one embodiment, the parking unit is configured to park and lock / unlock multiple UAVs. For example, it may be necessary to lock UAVs during base station relocation.

[0129] In one embodiment, a base station 100 for multiple UAVs includes at least one UAV equipped with a multispectral camera configured to observe farmland before the UAV 10 takes off. The observation includes identifying targets for reconnaissance. The observation also includes calculating how to effectively deploy the UAV 10 to manage the farmland.

[0130] In one embodiment, a base station 100 for multiple UAVs includes at least one retrieval UAV configured to retrieve any UAV 10 that is unable to return to the base station on its own. The retrieval UAV may include a robotic arm configured to transport any UAV 10 back to the base station.

[0131] Figure 3A system 200 for agricultural weed management is shown. System 200 includes a base station 100 for multiple UAVs 10. Base station 100 includes: a UAV parking unit 110 including at least one UAV, a second control and processing unit 120, and at least one second transceiver 130. At least one UAV 10 includes a first control and processing unit 20, a camera 30, and a first transceiver 70. The UAV parking unit is configured to carry multiple UAVs. The first control and processing unit 20 is configured to cause the UAVs to fly from the base station to a position within the canopy of crops and below the vertical height of the crops and / or between rows of crops and below the vertical height of the crops. The first control and processing unit 20 is configured to control the camera to acquire at least one image related to the ground at the position within the canopy of crops and below the vertical height of the crops and / or between rows of crops and below the vertical height of the crops. The first control and processing unit 20 is configured to transmit information including information about the at least one image related to the ground to the base station using the first transceiver 70. The second control and processing unit 120 is configured to receive information about at least one image relating to the ground from at least one UAV using a second transceiver 130. The second control and processing unit 120 is configured to analyze the at least one image received from at least one UAV to determine the presence of at least one type of weed and its location on the ground.

[0132] In one embodiment, system 200 includes a base station 100 for at least one UAV 10. The UAV also includes a location determination device 60. The location determination device 60 is configured to provide a first control and processing unit 20 with at least one location associated with a camera upon acquisition of at least one image relating to the ground. The first control and processing unit 20 is configured to transmit information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a first transceiver 70. A second control and processing unit 120 is configured to receive information about the at least one location associated with the camera upon acquisition of at least one image relating to the ground using a second transceiver 130. The second control and processing unit 120 is configured to analyze at least one image received from at least one UAV to determine the presence of at least one type of weed at said at least one location.

[0133] In one embodiment, system 200 includes a base station 100 for a plurality of UAVs 10. At least one UAV also includes at least one weed control unit 50. A second control and processing unit 120 is further configured to determine instructions given to the at least one UAV to fly to at least one location where at least one weed has been identified, and to activate the at least one weed control unit 50 at said at least one location.

[0134] Figure 4An embodiment of a method 300 for agricultural weed management is shown. The method includes a flight step 310, also referred to as step a), flying a UAV to a position within the canopy of crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops;

[0135] In step 320, also known as step b), at least one image relating to the ground is acquired by a camera at a position within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops.

[0136] In analysis step 330, also known as step c), at least one image is analyzed to determine at least one type of weed and its location on the ground.

[0137] In one embodiment, in step b), multiple images are acquired, wherein the processing and control unit is configured to control the camera to acquire the multiple images at corresponding multiple different locations relative to the ground within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops.

[0138] In one embodiment, in step c), at least one image is analyzed to determine a weed map, wherein the weed map classifies the presence of weeds on the ground based on the density and spatial distribution of the weeds.

[0139] In one embodiment, in step a), the UAV is flown into the canopy of the crop and below the vertical height of the crop and / or between a row of crops and below the vertical height of the crops, wherein the UAV has a size on the order of 1 cm to 20 cm, preferably 2 cm to 10 cm, more preferably 4 cm to 8 cm, and a weight equal to or less than 200 g, preferably equal to or less than 100 g, more preferably equal to or less than 50 g.

[0140] In one embodiment, in step a), the UAV is flown into the canopy of a crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops, wherein the UAV includes a propeller guard that is configured to at least partially surround the propeller of the UAV, preferably completely surrounding the propeller.

[0141] In one embodiment, in activation step 340, also known as step d), at least one weed control unit of the UAV is activated at a location determined by the first control and processing unit based on image analysis of at least one image related to the ground.

[0142] In one embodiment, in step a), the UAV is flown to a position within the canopy of a crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops, wherein the UAV includes a position determination device.

[0143] In step 321, also known as step b1), at least one image related to the ground is acquired, and at least one position associated with the camera when the at least one image related to the ground is acquired is provided to the first control and processing unit.

[0144] In one embodiment, in step a), the UAV is flown to a position within the canopy of a crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops, wherein the UAV includes a first transceiver and a position determination device.

[0145] In step 322, also known as step b2), at least one image related to the ground is acquired, and at least one position associated with the camera when the at least one image related to the ground is acquired is provided to the first control and processing unit.

[0146] In transmission step 323, also known as step b3), image analysis of at least one image related to the ground and / or at least one image related to the ground is transmitted, along with information about at least one location associated with the camera when the at least one image related to the ground is acquired.

[0147] In receiving step 324, also known as step b4), a receiving instruction is sent to at least one location where at least one weed has been identified, and at said at least one weed control unit is activated, wherein the instruction is based on image analysis of at least one ground-related image and / or at least one ground-related image transmitted by a first transceiver.

[0148] Figure 5 A schematic representation of a detailed embodiment of multiple UAVs at a base station and on farmland is shown. In this figure, the base station is a UAV carrier carrying multiple small UAVs. The carrier is capable of flying the UAVs to the farmland and landing, parking, or hovering. Once in the farmland, the UAV carrier can launch the small UAVs, which can fly over the field in an optimized flight pattern to detect weeds on the ground. The UAVs can locally apply herbicides as needed. The small UAVs fly both above and inside the crop canopy, or between multiple rows of crops, such as in a vineyard, identifying weeds on the ground and locally applying herbicides to control them. Figure 5In the image, the UAV on the right (equipped with a camera; propeller protected by a propeller guard) acquires images of weeds on the ground. Two smaller UAVs (equipped with spraying units; propellers protected by a propeller guard) in the middle of the image apply herbicide to the weeds on the ground through spot spraying. A first control and processing unit determines the appropriate herbicide to apply based on information received from the camera and associated sensors (e.g., depending on the type of weed detected). A particular advantage of this invention is that a fleet of UAVs can very quickly survey and autonomously apply herbicide to areas of farmland, benefiting the ability to treat an entire field in a relatively short time. The work rate depends on the number of UAVs; a fleet of twenty UAVs can simultaneously treat twenty different areas within a target field, while a fleet of forty can treat forty different areas, achieving twice the work rate. Another advantage of this invention is that it allows for rapid treatment of farmland with herbicides applied only to the target areas, thereby minimizing application to non-target areas. This is a more efficient method of applying herbicides to targets and significantly reduces the amount of herbicide applied to farmland without compromising performance. This is beneficial for both the environment and reducing residue levels in agricultural products. Another benefit is the reduction in the amount of herbicide that needs to be transported by application equipment, for example, from the range of liters per hectare to approximately 100 to 10 ml per hectare, amounts that are easily transported by a fleet of several UAVs. Furthermore, since weed problems occur continuously throughout the growing season, an advantage of this invention is that it allows for rapid revisiting of farmland for repeated treatments, for example, on a 5-10 day cycle, to ensure that target weeds are treated at their optimal growth stage (e.g., the 2-5 leaf stage). This further reduces the need for active ingredients, as weeds in earlier growth stages are easier to control than those in later stages. Moreover, successful biocontrol of weeds typically requires close monitoring of the application window. In addition, spraying fields with boom sprayers mounted on tractors has high processing costs, including driver time; high energy consumption with correspondingly high carbon dioxide emissions; and can cause soil compaction damage, especially when repeated treatments are required when new weeds appear.

[0149] Figures 6a) to 6c) (From a top-down view) illustrative examples of multiple UAVs applying herbicides to agricultural crop fields based on different weed maps are shown. Figure 6a In this embodiment, the density and spatial distribution of weeds identified in the field necessitate a patch spraying application pattern. In this embodiment, a UAV flies to identified weed patches within a row of multiple crops (shown as black dots) to apply the herbicide only to the weeds within those patches. In the next row, a second UAV flies to the identified weed patches within that row and applies the herbicide in a similar manner as discussed previously. In the third row, a third UAV operates in a similar manner. Figure 6b In this embodiment, a large number of weeds facilitates a strip application strategy. Here, for each row, the UAV activates its weed control unit to spray herbicide along the entire strip (row). Figure 6c In this embodiment, a small number of weeds facilitates a target-to-target application strategy, in which the UAV flies within a row and applies herbicides specifically to the identified weeds within that row. Depending on the weed growth in the field, these three strategies may also be combined. Furthermore, the UAV does not necessarily need to fly within multiple crops in a row and apply herbicides within that row. Other flight paths and herbicide application paths, such as between different rows, are also possible.

[0150] In another exemplary embodiment, a computer program or computer program product is provided, characterized in that it is configured to perform method steps of the method according to one of the foregoing embodiments on a suitable system.

[0151] Therefore, the computer program product can be stored on a computer unit, which can also be part of the implementation scheme. This computing unit can be configured to perform or induce the execution of the steps of the methods described above. Furthermore, it can be configured to operate components of the UAV, base station, and / or system described above. The computing unit can be configured to automatically operate and / or execute user commands. The computer program can be loaded into the working memory of the data processor. The data processor can therefore be equipped to execute the methods according to one of the foregoing implementation schemes.

[0152] This exemplary embodiment of the invention covers computer programs that use the invention from the outset and computer programs that convert existing programs into programs using the invention through updates. Furthermore, computer program products may be able to provide all the necessary steps to complete the steps of the exemplary embodiment of the methods described above.

[0153] According to another exemplary embodiment of the invention, a computer-readable medium, such as a CD-ROM, a USB memory stick, etc., is presented, wherein the computer-readable medium has a computer program product stored thereon, which is / may be the computer program product described in the preceding section. The computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium provided with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0154] However, computer programs can also be presented through networks like the World Wide Web and can be downloaded from such networks into the working memory of a data processor.

[0155] According to another exemplary embodiment of the present invention, a medium is provided for making a computer program product available for download, the computer program product being configured to perform a method according to one of the embodiments previously described according to the present invention.

[0156] It should be noted that embodiments of the present invention are described with reference to different subject matter. In particular, some embodiments are described with reference to method-type claims, while other embodiments are described with reference to UAV, base station, and / or system-type claims. However, those skilled in the art will understand from the above and below description that, unless otherwise stated, any combination of features related to different subject matter is also considered to be disclosed with this application, in addition to any combination of features belonging to one type of subject matter.

[0157] Although the invention has been illustrated and described in detail in the accompanying drawings and the foregoing description, such illustrations and descriptions should be considered illustrative or exemplary rather than limiting. The invention is not limited to the disclosed embodiments. Other variations of the disclosed embodiments can be understood and implemented by those skilled in the art in practicing the claimed invention through study of the drawings, the disclosure, and the dependent claims.

[0158] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude multiple. A single processor or other unit can perform the functions of several items recited in the claims. The mere fact that certain measures are recited in different dependent claims does not imply that a combination of these measures cannot be used to gain an advantage. No reference numerals in the claims should be construed as limiting the scope.

Claims

1. An unmanned aerial vehicle (UAV; 10) for agricultural weed management, comprising: - First control and processing unit (20); as well as - Camera (30); The first control and processing unit is configured to control the unmanned aerial vehicle to fly to a position within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops; The first control and processing unit is configured to control the camera to acquire at least one image related to the ground at a position within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops; The first control and processing unit is configured to analyze the at least one image to determine the presence of at least one type of weed and its location on the ground. The first control and processing unit is configured to analyze the at least one image to determine a weed map, wherein the weed map classifies the presence of weeds on the ground according to their density and spatial distribution. The flight path map of the unmanned aerial vehicle (UAV) is determined based on a weed map and the classification of weeds according to their density and spatial distribution on the ground. The flight path map includes information on the activation and deactivation of at least one weed control unit of the UAV. The activation / deactivation of the flight path map and at least one weed control unit along the flight path map of the unmanned aerial vehicle includes information about strips, patches, and target-to-target weed control operations, or combinations thereof.

2. The unmanned aerial vehicle of claim 1, wherein the at least one image comprises a plurality of images, and wherein the processing and control unit is configured to control the camera to acquire the plurality of images at corresponding plurality of different locations relative to the ground within the canopy of the crops and below the vertical height of the crops and / or between a row of plurality of crops and below the vertical height of the plurality of crops.

3. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle has a size on the order of 1 cm to 20 cm and a weight equal to or less than 200 g.

4. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle has a size on the order of 2 cm to 10 cm and a weight equal to or less than 100 g.

5. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle has a size on the order of 4 cm to 8 cm and a weight equal to or less than 50 g.

6. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle comprises: - Propeller protection device (40); The propeller protection device is configured to at least partially surround the propeller of the unmanned aerial vehicle.

7. The unmanned aerial vehicle of claim 6, wherein the propeller protection device is configured to completely surround the propeller.

8. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle comprises: - At least one weed control unit (50); The at least one weed control unit is configured to be activated at a location determined by the first control and processing unit based on image analysis of the presence and location of at least one weed.

9. The unmanned aerial vehicle according to any one of claims 1 to 2, wherein the unmanned aerial vehicle includes a position determination device (60). The location determination device (60) is configured to provide the first control and processing unit (20) with at least one location associated with the camera when the at least one image related to the ground is acquired.

10. The unmanned aerial vehicle according to claim 8, wherein the unmanned aerial vehicle includes a first transceiver (70). The first control and processing unit is configured to use the first transceiver to transmit image analysis of at least one ground-related image and / or at least one ground-related image, as well as information about at least one location associated with the camera when the at least one ground-related image is acquired. The first control and processing unit is configured to receive instructions to fly to at least one location where at least one weed has been identified and to activate the at least one weed control unit (50) at the at least one location. The instructions are based on image analysis of at least one ground-related image and / or at least one ground-related image transmitted by the first transceiver.

11. A base station (100) for multiple unmanned aerial vehicles. The base station includes: - Unmanned aerial vehicle (UAV) parking unit (110), the UAV parking unit comprising at least one UAV. - Second control and processing unit (120). - At least one second transceiver (130). The at least one unmanned aerial vehicle mentioned above includes: - First control and processing unit (20); - Camera (30); and - First transceiver (70); The unmanned aerial vehicle (UAV) parking unit is configured to carry multiple UAVs. The first control and processing unit (20) is configured to control the unmanned aerial vehicle to fly from the base station to a position within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops; The first control and processing unit (20) is configured to control the camera to acquire at least one image related to the ground at a position within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops. The first control and processing unit (20) is configured to transmit information about at least one image related to the ground to a base station using the first transceiver (70). The second control and processing unit (120) is configured to receive information about at least one image relating to the ground from at least one unmanned aerial vehicle using the second transceiver (130). The second control and processing unit (120) is configured to analyze at least one image received from the at least one unmanned aerial vehicle to determine the presence of at least one type of weed and its location on the ground. The second control and processing unit (120) is configured to analyze at least one image received from at least one unmanned aerial vehicle to determine a weed map, wherein the weed map classifies the presence of weeds on the ground according to the density and spatial distribution of the weeds. The second control and processing unit is further configured to determine a flight path map for the unmanned aerial vehicle (UAV) based on a weed map and a classification of weeds according to their density and spatial distribution on the ground. The flight path map includes information regarding the activation and deactivation of at least one weed control unit of the UAV. The activation / deactivation of the flight path map and at least one weed control unit along the flight path map of the unmanned aerial vehicle includes information about strips, patches, and target-to-target weed control operations, or combinations thereof.

12. The base station for multiple unmanned aerial vehicles according to claim 11, wherein... The at least one unmanned aerial vehicle also includes a position determination device (60). The location determining device (60) is configured to provide the first control and processing unit (20) with at least one location associated with the camera when the at least one image related to the ground is acquired. The first control and processing unit (20) is configured to transmit information about at least one location associated with the camera when the at least one image related to the ground is acquired using the first transceiver (70), wherein the second control and processing unit (120) is configured to receive information about at least one location associated with the camera when the at least one image related to the ground is acquired using the second transceiver (130). The second control and processing unit (120) is configured to analyze at least one image received from the at least one unmanned aerial vehicle to determine the presence of at least one type of weed on the ground at the at least one location.

13. A base station for a plurality of unmanned aerial vehicles according to any one of claims 11 to 12, wherein the at least one unmanned aerial vehicle further comprises at least one weed control unit (50). The control and processing unit (120) is further configured to determine instructions to at least one unmanned aerial vehicle to fly to at least one location where the presence of at least weeds has been determined, and to activate the at least one weed control unit (50) at the at least one location.

14. The base station for multiple unmanned aerial vehicles according to claim 13, comprising an unmanned aerial vehicle parking unit (110) with multiple unmanned aerial vehicles. The second control and processing unit (120) is further configured to determine instructions to a plurality of unmanned aerial vehicles to fly to at least one location where the presence of at least weeds has been determined, and to activate the at least one weed control unit (50) at the at least one location according to a determined flight path map.

15. A base station for a plurality of unmanned aerial vehicles according to any one of claims 11 to 12, wherein the second control and processing unit (120) is configured to control the plurality of unmanned aerial vehicles to operate in alternating groups such that when one group is out flying, another group is on the unmanned aerial vehicle parking unit.

16. A system (200) for agricultural weed management, comprising: - Base stations (100) for multiple unmanned aerial vehicles, including: - Unmanned aerial vehicle (UAV) parking unit (110), the UAV parking unit comprising at least one UAV; - Second control and processing unit (120); - At least one second transceiver (130); - At least one unmanned aerial vehicle (10), including: - First control and processing unit (20); - Camera (30); and - First transceiver (70); The unmanned aerial vehicle (UAV) parking unit is configured to carry multiple UAVs. The first control and processing unit (20) is configured to control the unmanned aerial vehicle to fly from the base station to a position within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops; The first control and processing unit (20) is configured to control the camera to acquire at least one image related to the ground at a position within the canopy of the crops and below the vertical height of the crops and / or between a row of multiple crops and below the vertical height of the multiple crops. The first control and processing unit (20) is configured to transmit information, including information about at least one image related to the ground, to the base station using the first transceiver (70). The second control and processing unit (120) is configured to receive information about the at least one image relating to the ground from at least one unmanned aerial vehicle using the second transceiver (130). The second control and processing unit (120) is configured to analyze at least one image received from the at least one unmanned aerial vehicle to determine the presence of at least one type of weed and its location on the ground, and to determine a weed map, wherein the weed map classifies the presence of weeds on the ground according to their density and spatial distribution. The second control and processing unit is further configured to determine a flight path map for the unmanned aerial vehicle (UAV) based on a weed map and a classification of weeds according to their density and spatial distribution on the ground. The flight path map includes information regarding the activation and deactivation of at least one weed control unit of the UAV. The activation / deactivation of the flight path map and at least one weed control unit along the flight path map of the unmanned aerial vehicle includes information about strips, patches, and target-to-target weed control operations, or combinations thereof.

17. A method (300) for agricultural weed management, comprising: a) Flying the unmanned aerial vehicle (310) to a position within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops; (b) Acquire (320) at least one image relating to the ground by a camera at a location within the canopy of the crop and below the vertical height of the crop and / or between a row of multiple crops and below the vertical height of the multiple crops; c) Analyze the at least one image of (330) to determine at least one type of weed and its location on the ground, and determine a weed map, wherein the weed map classifies the presence of weeds on the ground according to the density and spatial distribution of the weeds. The flight path map of the unmanned aerial vehicle (UAV) is determined based on a weed map and the classification of weeds according to their density and spatial distribution on the ground. The flight path map includes information on the activation and deactivation of at least one weed control unit of the UAV. The activation / deactivation of the flight path map and at least one weed control unit along the flight path map of the unmanned aerial vehicle includes information about strips, patches, and target-to-target weed control operations, or combinations thereof.

18. A computer program product for controlling an unmanned aerial vehicle according to any one of claims 1 to 10, wherein the computer program product, when executed by a processor, is configured to perform the method of claim 17.

Images