Unmanned aerial vehicle-based payload management

Abstract

A drone-based payload management system includes at least one drone and a drone controller, the drone (s) having a first payload compartment and a second payload compartment configured to store a first payload and a second payload, respectively. The drone controller may be coupled with the payload compartment and include at least one processor and at least one computer-readable memory. The memory (s) may store software instructions executable by the processor (s) to perform operations including: obtaining a location of the drone (s) when deploying the drone (s); determining a ground attribute value of the ground surface associated with the location; deriving a payload ratio of a first amount of the first payload relative to a second amount of the second payload based on the ground attribute value; and causing the first payload compartment and the second payload compartment to release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

Description

Cross-references to related applications

[0001] not applicable

[0002] not applicable Background Technology

[0003] Technical Field: The technical field of this disclosure is based on payload delivery for unmanned aerial vehicles (UAVs).

[0004] In the agricultural sector, drone technology has provided new mechanisms for sowing and spraying crops. The use of unmanned aerial vehicles (UAVs) has not only begun to automate the application of seeds and fertilizers but has also introduced ways to collect data about the ground, which is being used to make informed spraying decisions. However, this conventional technology does not provide an effective means of deploying soil additives, such as oolitic aragonite, which exhibit complex interactions with other payloads and require high flexibility and control in their relative amounts and other deployment parameters. Summary of the Invention

[0005] This disclosure contemplates various systems and methods for overcoming the aforementioned drawbacks in known related technologies. One aspect of an embodiment of this disclosure is a drone-based payload management system. The system may include at least one drone and a drone controller. The at least one drone may have a first payload bay and a second payload bay configured to store a first payload and a second payload, respectively. The drone controller may be coupled to the first payload bay and the second payload bay and may include at least one processor and at least one computer-readable storage device. The at least one computer-readable storage device stores software instructions executable by the at least one processor to perform operations including: obtaining the location of the at least one drone when deploying the at least one drone; determining ground attribute values ​​of the ground associated with the location; deriving a payload ratio of a first amount of the first payload to a second amount of the second payload based on the ground attribute values; and causing the first payload bay and the second payload bay to release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

[0006] The system may include one or more sensors. The ground attribute values ​​can be determined based on the output of at least one of the one or more sensors. The one or more sensors may include one or more types of sensors selected from the group consisting of: GPS sensors, accelerometers, LiDAR sensors, RADAR sensors, cameras, thermometers, magnetometers, gyroscopes, inertial measurement units (IMUs), and spectrometers, and / or may include other types of sensors. The one or more sensors may be incorporated into the at least one UAV. The ground attribute values ​​may conform to a ground attribute namespace or ontology. The ground attribute values ​​may be directly or indirectly quantified by one or more attributes selected from the group consisting of: chemical attributes, elevation attributes, slope attributes, physical attributes, optical attributes, and geographic attributes. The ground attribute values ​​may be derived at least partially from image descriptors. The ground attribute values ​​may be determined in real time based on a digital representation of the surface. The ground attribute values ​​may be determined at least partially by referencing previously characterized attributes of the surface associated with the location.

[0007] The payload ratio can be derived from the ground attribute values ​​via one or more of the following: lookup tables, functions, and machine learning models. One or both of the first and second payload compartments may include a controllable payload opening coupled to the UAV controller. At least one of the first and second quantities may include the amount released per unit time, or the amount released per unit area, or another quantitative measure. The first and second quantities can be measured by weight. The first and second quantities can be measured by volume. The payload ratio may be in the range of 1:100 to 1:1, or in other ranges that may be practical for a particular use case. One or both of the first and second payloads may include seeds. One or both of the first and second payloads may include spores. One or both of the first and second payloads may include one or more payloads selected from the following: seeds, spores, fertilizers, pesticides, liquids, regulators, worms, biological products, powders, slurries, and mycorrhizal fungi. The second payload may include calcium carbonate (e.g., oolitic aragonite).

[0008] The location may include one or more selected from the group consisting of: geographic location, postal code, geofence area, Schneider 2 (S2) cell, grid location, fixed location, relative location, landmark, simultaneous localization and mapping (SLAM) location, visual simultaneous localization and mapping (vSLAM) location, wireless triangulation point, and / or location relative to one or more beacons. Obtaining the location may include: obtaining the location of the at least one UAV while the at least one UAV is in flight.

[0009] The operation may further include: determining the dispersion of one or both of the first payload and the second payload on the ground surface. The operation may further include: performing a test release of one or both of the first payload capsule and the second payload capsule, and then releasing the first and second quantities, the dispersion being determined based on the test release. Determining the dispersion may include: measuring the time from release to the arrival of one or both of the first payload and the second payload on the ground. The operation may further include: adjusting the release of one or both of the first payload and the second payload based on the dispersion.

[0010] At least one drone may include at least one unmanned aerial vehicle (UAV). At least one drone may include at least one autonomous drone. The at least one drone may include a swarm of two or more drones that may operate in concert. The at least one drone may also have a third payload bay. The first payload bay and the second payload bay may be included in the same drone among the at least one drone.

[0011] Another aspect of the embodiments of this disclosure is a payload management method based on unmanned aerial vehicles (UAVs). The method may include: obtaining the location of at least one UAV when deploying it. The at least one UAV may have a first payload bay and a second payload bay. The first payload bay may be configured to store a first payload, and the second payload bay may be configured to store a second payload. The method may further include: determining ground attribute values ​​of a surface associated with the location; deriving a payload ratio based on the ground attribute values, a first amount of the first payload relative to a second amount of the second payload; and causing the first payload bay and the second payload bay to release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

[0012] Another aspect of embodiments of this disclosure is a computer program product comprising one or more non-transitory program storage media, on which instructions are stored, executable by one or more processors or programmable circuits to perform operations for payload management based on unmanned aerial vehicles (UAVs). The operations may include: obtaining the location of at least one UAV when deploying at least one UAV. The at least one UAV may have a first payload bay and a second payload bay. The first payload bay may be configured to store a first payload, and the second payload bay may be configured to store a second payload. The operations may further include: determining ground attribute values ​​of a surface associated with the location; deriving a payload ratio based on the ground attribute values, a first amount of the first payload relative to a second amount of the second payload; and causing the first payload bay and the second payload bay to release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio. Attached Figure Description

[0013] These and other features and advantages of the various embodiments disclosed herein will be better understood with reference to the following description and accompanying drawings, in which the same reference numerals always denote the same parts, and wherein: Figure 1 A system for drone-based payload management according to one or more embodiments of the present disclosure is shown; Figure 2 This is a perspective view of a single drone in the system; Figure 3 This is a front view of the drone; Figure 4 This is an exploded perspective view of the drone; Figure 5 It is a functional block diagram of the system; Figure 6 Example operational flows are shown according to one or more embodiments of this disclosure; and Figure 7 This is a high-level block diagram of an exemplary apparatus that can be used to implement the systems and methods described herein. Detailed Implementation

[0014] This disclosure covers various embodiments of systems, apparatus, and methods for UAV-based payload management. The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of several currently contemplated embodiments and is not intended to represent the only form in which the disclosed subject matter can be developed or utilized. Functions and features are illustrated in conjunction with the described embodiments. However, it should be understood that the same or equivalent functionality may be implemented by different embodiments, which are also intended to be included within the scope of this disclosure. It should also be understood that the use of related terms such as "first" and "second" is only for distinguishing one entity from another and does not necessarily require or imply any actual such relationship or order between these entities.

[0015] Figure 1 A system 100 for drone-based payload management according to an embodiment of the present disclosure is illustrated. System 100 may include at least one drone 110, such as an unmanned aerial vehicle (UAV). In the illustrated embodiment, for example, two or more drones 110 are provided (in... Figure 1 The view shows a swarm of four drones, but any actual number of drones 110 can be used, including 1, 2, 3, 4, 5, 10, 15, 20, 50, 100 or more, depending on the size of the payload delivery operation. In this respect, the drone swarm 110... Figure 1The drone is depicted flying over farmland 10 and dropping a first payload 20-1 (such as seeds) and a second payload 20-2 (such as oolitic aragonite) (generally or collectively referred to as payload 20). As shown, each individual drone 110 may drop both the first payload 20-1 and the second payload 20-2. Alternatively, one drone 110 may drop the first payload 20-1 while another drone drops the second payload 20-2, such that the drone swarm 110 collectively drops payloads 20-1 and 20-2 onto farmland 10. The payload management system 100 may also include a drone controller 120 configured to obtain the location of one or more drones 110 in flight or otherwise deployed, determine ground attribute values ​​of farmland 10 or other land surfaces associated with the location, and derive a payload ratio based on the ground attribute values ​​of a first amount of the first payload 20-1 relative to a second amount of the second payload 20-2. Then, one or more drones 110 can release a first payload 20-1 and a second payload 20-2 in a first amount and a second amount, respectively, according to the payload ratio. Therefore, advantageously, the system 100 can adjust the relative amounts of payloads 20-1 and 20-2 and / or other parameters (e.g., deployment mechanism, drop height, etc.) in real time based on the ground properties of a particular field 10 or its area 12. In this way, the system 100 enables the effective and efficient deployment of complex soil additives and other payloads, which can benefit from fine-tuning of delivery parameters based on precise location, time, or other conditions.

[0016] As a soil additive, aragonite (e.g., oolitic aragonite) advantageously provides calcium to support pH buffering, while also providing micronutrients and viable microorganisms, all without increasing the magnesium content in the soil, as might happen with limestone. Furthermore, aragonite effectively reduces the amount of fertilizer required by keeping nutrients readily available to crops and other plants in the soil. Simultaneously, because the calcium in aragonite decomposes relatively quickly in the soil, it can be advantageously used to address immediate needs in the short term. Thus, by analyzing current conditions (re-analyzing and revisiting the same area at arbitrary time intervals, e.g., daily), different amounts of aragonite can be adaptively added to the soil according to the needs of any small area of ​​field 10. This characteristic makes real-time fine-tuning of the amount of aragonite based on the current conditions of field 10 particularly important for efficiency and effectiveness. Moreover, since the ideal amount of other additives, such as fertilizers, can depend on the amount of aragonite added, and the amount of aragonite and other additives can depend on the amount of seeds planted or thrown in a given area, it is important to derive the relative amounts of multiple payloads to be combined based on real-time conditions.

[0017] Figure 2 , Figure 3and Figure 4 This is a close-up view of a single drone 110 of system 100. Drone 110 is described as an unmanned aerial vehicle (UAV) with a hexacopter design and six propeller units 112 surrounding a central control unit 114. For example, drone 110 could be a heavy-duty lifting drone. The propeller units 112 may include motors and propellers, and the central control unit 114 may include a flight controller, power supply, fuel tank, engine, sensors, and other systems for controlling the operation of drone 110. The propeller units 112 and central control unit 114 can be designed and arranged according to well-known multi-rotor helicopter design principles. Other multi-rotor helicopter designs (e.g., quadcopters, octocopters, Y6, etc.) can also be used, and non-multi-rotor helicopter designs are also considered. An exemplary source of drones may include those provided by Toofon Corporation and described in U.S. Patent Application US2022 / 0297822, filed March 17, 2022, entitled “Systems and Method for Efficient Cruise and Hover in VTOL,” the entire contents of which are incorporated herein by reference.

[0018] As shown in the figure, the UAV 110 may include a first payload bay 116-1 and a second payload bay 116-2 (generally or collectively referred to as payload bay 116), which can be configured to store the first payload 20-1 and the second payload 20-2 respectively (see figure). Figure 3 Payload bays 116-1 and 116-2 may be supported by the UAV 110 in a suspended configuration. For example, the UAV 110 may include a support frame 118 into which payload bays 116-1 and 116-2 may be inserted. It is conceivable that the structure of the payload bays 116 and the support frame 118 may allow the payload bays 116 to be easily inserted into and removed from the support frame 118, or otherwise detachably coupled to the support frame 118 (see [link to relevant documentation]). Figure 4 This allows the payload bay to be refilled or easily exchanged with a full payload bay when it is empty. In some cases, the structure of the payload bay 116 and the support frame 118 allows for a modular configuration of the UAV 110, in which multiple different payload bays 116 storing different payloads 20 can be alternately loaded onto the UAV 110 to suit the user's specific needs.

[0019] Payload bays 116-1 and 116-2 may each include a UAV controller 120 as described herein (see [link]). Figure 1The corresponding payload openings 117-1 and 117-2 (generally or collectively referred to as payload opening 117) are controlled by the drone controller 120. In this regard, it is conceivable that the drone controller 120 may be located on the same drone 110 having the payload bay 116 in question, such as in its central control unit 114, or may be remotely located relative to the drone 110, such as in a different drone 110 (e.g., a master drone 110 responsible for controlling and guiding the operation of other drone 110s) or in a fixed structure (e.g., a control tower). In either case, the drone controller 120 may be communicatively coupled to the first payload bay 116-1 and the second payload bay 116-2, for example, via a wired or wireless connection. It is also conceivable that the drone controller 120 may include multiple physical devices, some of which perform functions on the drone 110 while others perform functions elsewhere, and / or it is also conceivable that, such as when the control of the drone 110 is switched from one remote device to another as the drone 110 flies from one location to another, the devices(s) acting as the drone controller 120 may change over time. Payload openings 117-1, 117-2 can be controllable to allow the release of payloads 20-1, 20-2 in different amounts and / or at different flow rates, thereby enabling the delivery of different relative amounts of payloads 20-1, 20-2 as described herein. In the case of simultaneous delivery of multiple payloads 20-1, 20-2, proper mixing can be achieved in some cases after the payloads 20-1, 20-2 leave the UAV 110 and fall through the air below the UAV 110. In this regard, the propeller can advantageously enhance the mixing of payloads 20-1, 20-2 by positioning it to generate wind near the payload opening 117. Alternatively, mixing can be achieved by providing a mixing manifold or chute below the payload opening 117, ultimately dispersing the resulting mixture of payloads 20-1, 20-2 from a single combined opening through the mixing manifold or chute. It is also envisioned that the payload compartment 116 (or the outlet of any such manifold or spur) could be positioned sufficiently below the propeller or outside the propeller's downwash, such that the deployment of (one or more) payloads 20 is unaffected by the propeller's operation. With this design, the effect of the propeller's downwash on the dispersion of (one or more) payloads 20 may not need to be considered for deployment parameters.

[0020] As described above, the drone controller 120 (whether on or away from the drone 110) can be configured to determine ground attribute values ​​of farmland 10 or other land surfaces associated with the location of the drone 110. The ground attribute values ​​can be determined based on the output of at least one sensor 119, which can be mounted on, for example... Figure 2The ground attribute values ​​may be mounted on or otherwise disposed of on the UAV 110, or located at a location remote from the UAV 110 (e.g., on another UAV or a fixed structure). Typically, ground attribute values ​​can quantify one or more attributes, such as chemical attributes (e.g., the presence / amount of pH, nitrogen, phosphorus, or potassium), physical attributes (e.g., surface roughness, temperature, ground cover, foliage, vegetation, whether the ground has been plowed, whether payload 20 is present, etc.), optical attributes (e.g., the amount of light hitting the ground, surface reflectivity, etc.), and / or geographic attributes (e.g., location, geology, hardness, irrigation, presence of floodplains, or runoff, etc.). The use of one or more ground attribute values ​​allows for the standardization of surface features for input into machine learning models and other computer-based systems. In this respect, ground attribute values ​​may conform to a ground attribute namespace or ontology, and their definitions may be stored in a local database on the UAV 110 or in other structures embodying the UAV controller 120, or may be stored and accessed remotely.

[0021] Various types of sensors 119 are conceived, including, for example, GPS sensors, accelerometers, LiDAR sensors, RADAR sensors, cameras, thermometers, magnetometers, gyroscopes, and / or inertial measurement units (IMUs), any of which can be replicated and / or combined to define a sensor array. For example, image data collected from a camera can be used as input to a computer vision model (e.g., using OpenCV) that determines ground attribute values ​​based on various image features. For instance, the RGB channels of the image data can be used to determine the color of the ground, where a low G relative to R and B can indicate a brown color consistent with soil where payload 20 has not yet been deployed, while a large number of predetermined colors matching the payload coloring can indicate the location where payload 20 has been deployed, and thus can help determine the spread of previous payload drops or currently ongoing payload drops. Typically, ground attribute values ​​can be derived at least partially from one or more image descriptors, and in some cases, image descriptors can be mapped to ground attribute values ​​(e.g., an image descriptor quantifying the amount of green relative to the background color can represent the amount of ground cover). Ground attribute values ​​can be measured in real time from a digital representation of the ground, which can be constructed from different image descriptors captured simultaneously from (in some cases, on different drones 110 or fixed structures) different types of cameras or other sensors 119. For this purpose, system 100 can utilize the technology described in U.S. Patent No. 11,210,573, the entire contents of which are incorporated herein by reference.

[0022] Based on one or more ground attribute values ​​associated with the location of UAV 110, UAV controller 120 can derive the payload ratio and accordingly coordinate the release of payload 20 from payload bay 116. In a relatively simple implementation, the payload ratio can be derived via a mapping from ground attribute values ​​(including combinations of different ground attribute values) to payload ratios, such as by using one or more lookup tables (e.g., for discrete or coarsely adjustable payload ratios) or functions (e.g., for continuous or finely adjustable payload ratios). Alternatively or additionally, the payload ratio can be derived via a machine learning model. In this case, various data features (including ground attribute values ​​determined using sensor 119, time information, wind and other weather-related data (sensed / predicted or reported from remote weather services), and location information of UAV 110 including altitude, attitude, velocity, and acceleration, etc.) can be input into a model that has been trained using historical data. The output of the model can be an appropriate payload ratio determined by the model, along with other parameters as described herein. Regardless of how the payload ratio is derived, it is conceivable that the payload ratio can specify the relative amounts of different payloads 20 as a proportion or percentage (e.g., one part seed, one part aragonite, two parts fertilizer) or as the mass, weight, or volume of each individual payload 20 (e.g., total amount or amount released per unit time, which may be based on the size of the area to be covered). In either case, it should be noted that the derived payload ratio can advantageously take into account the interdependencies of multiple different payloads 20, thereby allowing for the efficient and effective delivery of complexly interacting soil additives in a manner not possible using conventional systems. In some embodiments, the controller may utilize a location-indexed lookup table stored in computer-readable storage. Based on location, the lookup table may return instructions regarding what payload ratio(s) should be used at that location or otherwise how the delivery should be performed.

[0023] A typical payload ratio can depend on the nature of the payload 20, which can include various substances that can be transported and deployed by the UAV 110 for different purposes. For example,

[0024] Agricultural and other uses of System 100 may require one or both of the payloads 20, which include seeds (e.g., vegetables, corn, wheat, wildflowers, trees, grass, bamboo, berries, etc.), projectiles / stuffs / pointers containing seeds or seedlings (e.g., balls that burst upon impact or aerodynamic containers designed to reduce drag and increase ground penetration speed), spores, fertilizers, pesticides, liquids (e.g., water, etc.), powders, regulators, animals (e.g., worms, ladybugs, etc.), biological agents, mycorrhizae or other fungi (e.g., for decomposing wood, growing mushrooms, etc.), bacteria, materials for erosion control (e.g., bamboo, compost, biostimulants, boron, algae, etc.), materials for carbon sequestration, soil, and / or calcium carbonate, which may advantageously be in the form of aragonite (e.g., oolitic aragonite). For example, when deploying payload 20 for erosion control, bamboo seeds can be deployed in areas with high slopes, while grass seeds can be deployed in areas with gentler slopes, with the relevant ground property values ​​including the slope of the ground. In some cases, a single payload 20 may include two or more such materials, for example, when a payload compartment 116 contains seeds coated with calcium carbonate. For example, the payload ratio, expressed as a proportion, may range from 1:100 to 1:1, but other ratios may also be derived. In cases where one or more UAVs 110 commonly have three or more payload compartments 116 (e.g., on a single UAV 110 or distributed among several UAVs 110), it is conceivable that three or more different payloads 20 may also exist (e.g., four payloads, five payloads, etc.). Thus, the payload ratio is not limited to specifying the relative amounts of two different payloads 20, but may specify the relative amounts of three or more different payloads 20 depending on the specific circumstances.

[0025] In embodiments that utilize machine learning (e.g., machine vision for color analysis as described above) to determine ground attribute values, it is conceivable that such a machine learning model for determining ground attribute values ​​could be included within the same machine learning model that can be used to derive the load ratio, where only a single combined model is implemented. For illustration, in the above example where RGB channel data collected by a camera can be input into a machine vision algorithm to determine ground attribute values ​​such as vegetation volume, the machine learning model deriving the load ratio could, in principle, use vegetation volume as input, but could alternatively use the raw RGB channel data. In the latter case, the RGB channel data, rather than the vegetation volume (which may never be explicitly determined), can be considered as the relevant ground attribute value from which the load ratio is derived. The training of the machine learning model can be based on existing satellite maps with marked areas, possibly including satellite maps available via Google® Maps or OpenStreetMap™ (see URL OpenStreetPMAP org).

[0026] With the payload ratio already derived, the UAV controller 120 can continue to actuate the payload opening 117 or otherwise cause the first payload bay 116-1 and the second payload bay 116-2 (or more payload bays) to release corresponding payloads 20-1, 20-2 of the first and second quantities according to the payload ratio. For example, each payload opening 117 can be opened for a specified time period and / or can be opened to a specified degree (i.e., open a specified opening size) to release the desired quantity. For this purpose, control signals can be sent to appropriate actuators via a wired connection (e.g., via a communication bus) between the central control unit 114 and the payload bay 116 or wirelessly via radio frequency communication. Simultaneous release of payloads 20 as described above can be permitted when payload bays 116-1, 116-2 are on the same UAV 110 or on two or more UAVs 110 flying close to each other. Machine learning models or other processing that derives payload ratios can additionally derive delivery parameters, such as the delivery timing of each payload 20, the delivery location (including altitude) of each payload 20, which of the multiple delivery mechanisms / subsystems to use (e.g., droppers, predetermined loads of discrete quantities, projectiles / particle dispensers for different sizes of payload particles, different rotation speed settings for dispensers, etc., different projectiles / fillers / pointers for ground penetration in the case of hard ground determined based on ground property values), and whether / how payload mixing is achieved. For example, in strong winds, the UAV controller 120 may determine that one or both payloads 20-1, 20-2 should be delivered from a lower altitude and / or should be laterally offset from the target area on the ground. This can depend on the properties of each individual payload 20, such as its size, shape, humidity, etc., which may affect wind resistance (e.g., fine powder can be delivered closer to the ground, while larger chunks of payload 20 can be delivered from a higher altitude to reduce dispersion). Another proposed deployment parameter is the control of the configuration of the shield around the propeller of the UAV 110, which can be changed in real time for the dispersion of the payload 20.

[0027] Following the same route, to improve delivery accuracy, it is also envisioned that the UAV controller 120 may perform a test release of one or both of the first payload bay 116-1 and the second payload bay 116-2, followed by the release of the first and second quantities. The test release may include releasing a small quantity of one or both payloads 20-1, 20-2, after which it can be directly observed whether the payload(s)20 were successfully delivered to the target area of ​​the farmland 10 or other areas of the ground and / or whether some corrections should be made to the position or delivery parameters of the UAV(s)110 to more accurately deliver the payload(s)20. For example, after the test release (or after the actual delivery, for future delivery and record keeping), the UAV controller 120 may determine the dispersion of one or both of the first payload 20-1 and the second payload 20-2 on the ground. Determining dispersion may include, for example, measuring the time from release to the arrival of one or both of the first payload 20-1 and the second payload 20-2 on the ground, based on which the assumed area of ​​the actual delivery can be estimated. Alternatively or additionally, one or more sensors 119 (e.g., cameras as described above) may be used to determine dispersion. These sensors 119 may be used to detect payload coloration or ultraviolet (UV) characteristics, which indicate the location where payload 20 has been deployed and thus indicate dispersion. Based on the dispersion, the UAV controller 120 may adjust the release of one or both of the first payload 20-1 and the second payload 20-2.

[0028] Figure 5 This is a functional block diagram of system 100. Besides one or more drones 110 ( Figure 5 In addition to the two shown in the diagram, system 100 may include a hub 130, which may include a fixed structure (e.g., a control tower) or a mobile drone deployment truck, which may serve as a control center for system 100 and / or as part of a sensor array used by system 100, without necessarily being directly involved in the deployment of payload 20. In this regard, it is conceivable that implementations regarding [specific details about hub 130 and its processing unit 132] can be performed within hub 130. Figure 1 The drone controller 120 is described. Alternatively or additionally, the drone controller 120 may be implemented in one or more drones 110 (e.g., in a drone processing unit 152 of the drone 110). Generally, the drone processing unit 152 may be connected to one or more cameras or other sensors 119 (see also...). Figures 1 to 4This includes, for example, load cells, altimeters, accelerometers, gyroscopes, inertial measurement units (IMUs), compasses, tilt sensors, etc.; a Global Positioning System (GPS) receiver 154; and one or more payload bays 116 including one or more payload openings 117. The UAV processing unit 152 can also be connected to a flight controller 156 (in the case of an unmanned aerial vehicle (UAV) or other aerial drone) or other motion controller, and a UAV communication interface 158 for communicating with other UAVs 110 via the UAV communication interface 158 or with a hub station 130 via the hub station communication interface 134 of the UAV 110. This can be on the UAV 110, for example, in the central control unit 114 of the UAV 110 (see...). Figures 2 to 4 This includes any such component of the drone 110, or otherwise installed inside or outside the drone. The drone processing unit 152 can be responsible for various processing tasks and can, for example, control the overall operation of the drone 110. For example, if the drone processing unit 152 is used as the drone controller 120, the drone processing unit 152 can, alone or in cooperation with other drones 110 and / or hub station 130, obtain the location of the drone 110, determine ground attribute values, derive payload ratios, and cause (one or more) payload bays 116 to release (one or more) payloads 20, as described above. Figure 5 The features shown are not exhaustive, and the drone 110 may include various other features not specifically shown, such as noise suppression systems, power systems, etc.

[0029] In the case of the aerial drone 110, the flight controller 156 can control the propeller unit 112, for example, in response to commands issued by the drone processing unit 152 (see...). Figures 2 to 4 The flight controller 156, in combination with the drone processing unit 152 and sensors 119, controls the flight of the drone 110 to avoid known obstacles such as trees and forests. The drone 110 can use, for example, a depth sensor provided by PrimeSense to detect the distance to objects in order to avoid them, and can use web mapping services such as Google Maps to navigate the local landscape.

[0030] The UAV communication interface 158 (and similarly, the hub station communication interface 134) can support communication via any conventional communication method, such as supporting communication via: radio frequency in the form of a cellular network such as GSM (Global System for Mobile Communications), CDMA, etc., or a local area network such as WiFi (e.g., 802.11, WiGig, etc.), or any other communication means known in the art (e.g., infrared, microwave, laser, and / or ultrasonic communication). As described above, one or more sensors 119 may be on the UAV 110 together with the UAV processing unit 152, which may act as the UAV controller 120 to determine ground attribute values ​​and derive the payload ratio of the payload 20 (e.g., using one or more processors and memories of the UAV processing unit 152 on the UAV 110). In this regard, it is conceivable that the UAV 110 can operate independently without external commands, thereby making its own decisions regarding where to open the payload opening 117 of the onboard payload bay 116, when to open the payload opening 117 of the onboard payload bay 116, and to what relative extent the payload opening 117 of the onboard payload bay 116 is opened, while simultaneously issuing commands to the flight controller 156 to locate the UAV 110 based on the real-time conditions of the farmland 10 or its area 12 (e.g., through a machine learning model) to most effectively and efficiently deploy (one or more) payloads 20.

[0031] Even when the drone controller 120 is entirely on one or more drones 110, it can still be advantageous to employ some central or at least external decision-making functions, for example, via a swarm manager controller. For instance, the determination of ground attribute values ​​may not be the only relevant factor deriving the payload ratio or determining the flight direction of one or more drones 110. Other factors may include, for example, the presence of another high-priority farmland 10 or other delivery target or its area 12, which is unknown to an individual drone 110; additional information about the ground, including aspects that are undetermined by the drone 110; the presence of other drones 110 that have already delivered payload 20 to the same delivery target en route; priority orders issued to drones 110 or swarms including drones 110 to return to a charging station or other base and cease payload delivery activities; relevant weather forecasts unknown to the drone 110; physical obstacles unknown to the drone 110, etc. Given these factors, UAV 110 can transmit signals via UAV communication interface 158 to a fixed hub station 130 or a second UAV 110 located outside UAV 110, indicating one or more ground attribute values ​​and / or a derived payload ratio determined by UAV processing unit 152, and receive flight control signals from hub station 130 or the second UAV 110. In response to receiving the flight control signals, UAV processing unit 152 can issue commands to flight controller 156 and / or payload bay 116 / opening 117 to guide UAV 110 to release payload(s) 20 accordingly. Therefore, in response to receiving control signals via UAV communication interface 158, flight controller 156 and / or payload bay 116 / opening 117 can be guided.

[0032] Instead of or in addition to cameras and / or other sensors 119 on UAV 110, cameras and / or other sensors 136 may be mounted on hub station 130, regardless of whether hub station processing unit 132 is used as UAV controller 120. For example, hub station 130 may observe a large area of ​​local geography from camera 119 located in a high vantage position. Further envisioning that hub station 130, rather than UAV controller(s) 110, may obtain the location of UAV controller(s) 110, determine ground properties(s), derive payload ratios, and / or cause payload bay 116 on UAV(s) 110 to release payload 20. Similarly, some or all of the functions of UAV controller 120 may be provided by another UAV 110. Therefore, UAV(s) 110 may receive relevant data and / or commands from hub station 130 and / or from another UAV 110 via hub station communication interface 134 and / or UAV communication interface 158. For example, a combination of one or more drones 110 and / or hub stations 130 may first map / scan / analyze farmland 10 or other terrain, and then may dispatch one or more other drones 110 to perform payload delivery.

[0033] Regarding the use of the drone swarm 110, such a swarm can coordinate to act as a network (e.g., a mesh network). An example of a coordinated flight plan for such a UAV network can be found in U.S. Patent No. 8,862,285, entitled "Aerial Display System with Floating Pixels," the entire contents of which are incorporated herein by reference. Further examples of coordinated drone / hub activities can be found in U.S. Patent Nos. 10,434,451 and 11,219,852, entitled "Apparatus and Method of Harvesting Airborne Moisture," the entire contents of which are incorporated herein by reference. The swarm of drones 110 can work in coordination with each other to cover an area more quickly with payload 20, with each drone operating independently and covering its own designated area. Alternatively, multiple drones 110 can work together, with one drone 110 dropping a type of payload 20-1 and a second drone 110 dropping a second type of payload 20-1, wherein the payload ratio has been derived as described above and transmitted to the individual drones 110 and / or between the drones. In other cases, a drone ensemble 110 can operate as a “reconnaissance aircraft,” potentially using a sensor platform to map an area while identifying various ground properties, while another drone ensemble 110 performs the delivery of payload 20. In some cases, system 100 can be arranged as a network including one or more fixed hub stations 130 and / or one or more drones 110. Hub station 130 can act as a control / command center as described above, and can also serve as a drone battery charging or replacement station, a payload loading / unloading location, and / or a location for human / drone interfaces for observation, manual control and / or programming, firmware updates, etc., of the drones 110. As a concrete example, a swarm of drones 110 can be programmed to drop payload 20 at specific times each day and then return to hub 130 for exchanging payload bays 117 and for charging or battery replacement. Alternatively, one swarm of drones 110 can operate while another swarm of drones 110 is charging and / or refreshing payload 20, or vice versa. If backup power is available (e.g., multiple redundant batteries or backup solar power), battery deployment and deployment can be implemented in flight. Daily flight paths can be mapped using GPS, Simultaneous Localization and Mapping (SLAM), Visual Simultaneous Localization and Mapping (vSLAM), etc., and daily flight paths can be recorded for, for example, error reporting. By using geofencing, flight path reporting and human / drone interactions, including updates and new instructions, can be configured to occur when drones 110 enter the vicinity of hub 130, without requiring physical docking.

[0034] As another example, a swarm of multiple drones 110 can be transported to farmland 10 or other payload delivery targets on vehicles (or multiple vehicles), such as trucks, boats, small airships, or other transport vehicles capable of carrying multiple UAVs or other drones. The vehicles can act as hub stations 130. Thus, payload delivery activities can be directed to distant locations, and drones 110 can be deployed close to the intended target without consuming fuel or battery power to reach that location. This can be particularly useful for non-agricultural payload delivery that may be far from developed areas, such as when using system 100 to deliver payload 20 to stop the spread of wildfires, for erosion control, to clean up sewage or oil spills (e.g., by dropping biological agents, cleaning agents, bacteria, etc.), or to stop the spread of invasive plants and other species in the field (e.g., by dropping herbicides, biological agents, etc.). Drones 110 communicating with each other and / or with the vehicles can be deployed or detached from the vehicles to perform payload delivery in nearby areas as described herein, and return to the vehicles to replace or refill payload bay 116. Furthermore, the vehicles may have docking stations that allow the drones 110 to be charged during transport, or the drones 110 may return to the vehicles during payload delivery operations to be recharged, possibly via solar photovoltaic cells, and then redeployed as needed. After completing a payload delivery mission at one location, one or more vehicles may then move to other locations. In this way, a fleet of drones 110 can provide on-demand services for those that need or request payload delivery. Using vehicles can also reduce the necessary range of the drones 110 and / or allow the drones 110 to access areas that might otherwise be difficult to access.

[0035] Figure 6 Example operational flows according to one or more embodiments of this disclosure are shown. (This can be understood from...) Figures 1 to 5 The system 100 shown and described executes an operational flow, and for example, the operational flow may represent processing steps performed by the drone controller 120 of the system 100. As mentioned above, the drone controller 120 itself may be implemented on one or more drones 110 or in a processor / memory located in a fixed or mobile hub 130. In this regard, it is conceivable that, in some cases, the system 100 may be partitioned among different entities. Figure 6The steps are shown below. The operation may begin by obtaining the location of at least one drone 110 while it is flying or otherwise deployed (step 610) and determining the ground attribute values ​​of the surface associated with the location (step 620). For example, the location may include geographic location, postal code, geofenced area, Schneider 2 (S2) cell, grid location, fixed location, relative location, landmark, simultaneous localization and mapping (SLAM) location, visual simultaneous localization and mapping (vSLAM) location, wireless triangulation point and / or location relative to one or more beacons. In some embodiments, the area may be divided into multiple sub-areas, each of which may be labeled with its own specific ground attribute. Note that the location may include the location of an individual drone 110 or the location of a group of drones 110, such as average location, centroid or most relevant area, grid cell, etc. The drone controller 120 (whether or not on the drone 110 in question) may determine one or more ground attributes based on the location and a combination of sensor data collected as described above (e.g., using a camera or other sensor 119, 136). Location can be used as an index to look up one or more ground attributes in addition to those determined by real-time sensor analysis (e.g., sensor measurements from the previous day), and / or to look up relevant weather conditions, air traffic conditions, mission instructions, warnings, or other location-related data that can inform one or more UAVs 110 how to move. In this regard, it should be recognized that the surface associated with the location need not have completely unknown attributes and can include, for example, at least a portion of a previously characterized area. Thus, ground attribute values ​​can be determined at least in part by referencing previously characterized attributes of the surface associated with the location.

[0036] Figure 6The operational flow can continue: derive the payload ratio based on (one or more) ground attribute values ​​(step 630), and cause (one or more) payload bays 116 to release the corresponding amount of payload 20 according to the payload ratio (step 640). For example, the UAV controller 120, whether locally or remotely implemented (e.g., on another UAV 110 or hub station 130), can input data features including (one or more) ground attribute values ​​into lookup tables, functions, or machine learning models, which can themselves be stored locally or remotely (e.g., on a server or cloud-based infrastructure). Based on the output, the UAV controller 120 can issue commands to (one or more) payload bays 116 or their openings 117 and to (one or more) corresponding flight controllers 156 to release the payload 20 according to the payload ratio as described herein and any other release parameters. In this respect, system 100 can be considered to provide a location-based service that uses agricultural or other soil information to determine the appropriate payload ratio at a fine level of detail.

[0037] In some embodiments, instructions to payload bays 115(1) , openings 117(1) , flight controllers 156(1) , etc., may include the execution of path management routines (e.g., by UAV controller 120) that seek to maximize or otherwise optimize the use of a given mixture of payloads 20 before moving to different mixtures of payloads 20. For example, a path (e.g., along the ground) may be characterized by regions having one or more common ground properties. One or more UAVs 110(1) may traverse a given path while dropping payloads 20 at a constant payload ratio. Assuming the path is continuous, this would allow the UAV to maintain a constant drop rate instead of having to change openings 117(1) on payload bays 115(1). Traversing discontinuous paths(1) with the same ground properties (i.e., including intervention areas with one or more different ground properties) may also be beneficial, as openings 117 can be simply temporarily closed during intervention areas without requiring new payload ratio calculations. Path management routines can optimize path definitions so that one or more drones 110 drop a first quantity per unit time, then a second quantity, and so on, possibly starting with smaller quantities and increasing until completion. In addition to effectively utilizing time, battery life, and processing resources, such routines can help ensure that priorities are met even when payload delivery is incomplete, such as covering the largest area first, followed by smaller areas with different payload ratios.

[0038] Figure 6The operational process may additionally include determining the dispersion of one or more payloads 20 on the ground surface (step 650). For example, based on input to one or more cameras or other sensors 119, 136, the UAV controller 120 may determine the dispersion after the complete release of one or more payloads 20, during the release of one or more payloads 20, or after / during a test drop of one or more payloads 20. If the release of one or more payloads 20 is not yet complete, the UAV controller 120 may adjust the release of one or more payloads 20 based on this dispersion (step 660), for example, to change the relative amount of the released payloads 20 and / or other release parameters (e.g., to correct for wind or ground profile). The UAV controller 120 may implement these adjustments by issuing new commands to one or more payload bays 116 or their openings 117 and / or one or more flight controllers 156 during the release of one or more payloads 20 or between a test release and a complete release of one or more payloads 20. This adjustment may be repeated cyclically. Figure 6 The operation process includes one or more steps, in which, in some cases, one or more drones 110 continue to drop payloads 20 until the requirements of a specific location are met (e.g., as can be known from the ground property values ​​that can be re-determined in step 620).

[0039] In the example above, an aerial drone 110, such as a UAV, is referred to as one possible drone 110 of system 100. However, system 100 is not necessarily limited to this aspect, and other types of drones 110 may also be used. For example, one or more drones 110 may include ground-based drones 110 (e.g., tracking drones, walkers, wheeled robots, etc.), and / or in some cases, may include terrestrial drones (in which case the surface to be targeted may be an underwater surface such as the seabed). More generally, the surface may be a solid ground (e.g., soil including sand, clay, silt, chalk, peat, loam, etc., or mixtures thereof), such as Figure 1 The farmland 10 (plowned or unplowned) may also be forest, grassland, lawn, hillside, or ocean surface or other water surface (e.g., observable by aerial drone 110). One or more drones 110 may be autonomous to varying degrees, for example, capable of autonomously navigating and moving to a location without collision, autonomously collecting sensor data from the ground surface, autonomously deploying payload 20, etc. Alternatively or additionally, one or more drones 110 may allow or require manual control of some or all of these functions.

[0040] In computer program products, information about... can be fully or partially implemented. Figures 1 to 5 System 100 and Figure 6 The computer program product describes various functions and processes in its operation flow and, in some cases, one or more machine learning models used by system 100. This computer program product may reside within or otherwise communicate with one or more drones 110, one or more drone controllers 120, and / or one or more hub stations 130 of system 100. The computer program product may include one or more non-transitory program storage media (e.g., hard disk drives, FPGAs, PLAs, solid-state drives, RAM, flash memory, ROM, etc.) storing computer programs or other instructions that may be executed by one or more processors (e.g., CPUs or GPUs) or programmable circuitry to perform operations according to various embodiments of this disclosure. In some cases, one or more non-transitory program storage media may reside outside of one or more drones 110, drone controllers 120, and / or hubs 130 of system 100, such as in cloud infrastructure (e.g., Amazon Web Services, Microsoft Azure, Google Cloud, etc.) and / or server systems accessible via networks such as the Internet, where computer programs or other instructions are provided to one or more drones 110, drone controllers 120, and / or hubs 130 via the network. In addition to processor-executable code, examples of program instructions stored on computer-readable media may include state information for execution by programmable circuit systems such as field-programmable gate arrays (FPGAs) or programmable logic arrays (PLAs).

[0041] As an example, Figure 7This is a high-level block diagram of an exemplary device 700 that can be used to implement the systems and methods described herein. Device 700 may include a processor 710 operatively coupled to persistent storage device 720 and main memory device 730. Processor 710 can control the overall operation of device 700 by executing computer program instructions that define such operations. The computer program instructions may be stored in persistent storage device 720 or other computer-readable medium and loaded into main memory device 730 when execution is desired. For example, unmanned aerial vehicle (UAV) processing unit 152 and other elements of UAV 110 and / or hub station 130 (e.g., UAV communication interface 158) may include one or more components of device 700. Similarly, hub station processing unit 132 and other elements of hub station 130 (e.g., hub station communication interface 134) may include one or more components of device 700. Therefore, regarding Figure 6 The operations described and throughout this disclosure can be defined, at least in part, by computer program instructions stored in main memory device 730 and / or persistent storage device 720, and controlled by processor 710 that executes the computer program instructions. For example, the computer program instructions can be implemented as computer-executable code programmed by those skilled in the art to perform the algorithms defined by the operations described herein. Thus, by executing the computer program instructions, processor 710 can execute the algorithms defined by the described operations. Device 720 may also include one or more network interfaces 750 for communicating with other devices via a network, such as via UAV communication interface 158 or hub station communication interface 134. Device 700 may also include one or more input / output devices 740 (e.g., display, keyboard, mouse, speaker, buttons, etc.) that enable a user to interact with device 700.

[0042] Processor 710 may include general-purpose microprocessors and special-purpose microprocessors, and may be the sole processor of device 700 or one of multiple processors. For example, processor 710 may include one or more central processing units (CPUs). Processor 710, persistent storage device 720 and / or main memory device 730 may include one or more application-specific integrated circuits (ASICs), and / or one or more field-programmable gate arrays (FPGAs), or be supplemented by or incorporated therein.

[0043] Both persistent storage device 720 and main memory device 730 include tangible, non-transitory, computer-readable storage media. Both persistent storage device 720 and main memory device 730 may include high-speed random access memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), double data rate synchronous dynamic random access memory (DDR RAM), or other random access solid-state memory devices, and may include non-volatile memory, such as one or more disk storage devices, such as internal hard disks and removable disks, magneto-optical disk storage devices, optical disk storage devices, flash memory devices, semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), optical disc read-only memory (CD-ROM), digital versatile disc read-only memory (DVD-ROM), or other non-volatile solid-state storage devices.

[0044] Input / output device 740 may include peripheral devices such as printers, scanners, displays, etc. For example, input / output device 740 may include display devices (such as cathode ray tube (CRT), plasma, or liquid crystal display (LCD) monitors), keyboards, and pointing devices (such as mice or trackballs) for displaying information (e.g., image recognition search results) to a user, through which the user can provide input to device 700.

[0045] Those skilled in the art will recognize that the implementation of an actual computer or computer system may have other structures and may include other components, and Figure 7 This is a high-level representation of certain components of such a computer for illustrative purposes.

[0046] It should be noted that any computer described herein may include any suitable combination of computing devices, including servers, interfaces, systems, databases, agents, peers, engines, controllers, modules, or other types of computing devices operating individually or in combination. It should be understood that any such computing device may include a processor configured to execute software instructions stored on tangible, non-transient, computer-readable storage media such as those described above, and the software instructions may configure the computing device to provide the roles, responsibilities, or other functions discussed above with respect to the disclosed subject matter. A system controller may include at least computer-readable, non-transient memory, a processor, and computer code with instructions stored in the memory that perform functions when executed by the processor. Any suitable computer-readable, non-transient memory that allows the storage of software instructions or allows firmware to be flashed may be used, such as hard disks, solid-state drives, ROM, programmable EEPROM chips. In some embodiments, various servers, systems, databases, or interfaces may exchange data using standardized protocols or algorithms, possibly based on HTTP, HTTPS, AES, public-key exchange, web service APIs, known financial transaction protocols, or other electronic information exchange methods. Data exchange can be performed through packet-switched networks, the Internet, LANs, WANs, VPNs, or other types of packet-switched networks, circuit-switched networks, cell-switched networks, or other types of networks. As used herein, when a system, engine, server, device, module, or other computing element is described as being configured to perform or execute functions on data in memory, "configured to" or "programmed to" can mean that one or more processors or cores of the computing element are programmed by a set of software instructions stored in the memory of the computing element to perform a set of functions on target data or data objects stored in memory.

[0047] As used herein, and unless the context otherwise indicates, the term “coupled to” is intended to include both direct coupling (where two elements coupled to each other are in contact with each other or communicate directly with each other) and indirect coupling (where at least one additional element is located between the two elements). Therefore, the terms “coupled to” and “coupled with” are used synonymously. In the context of this document, “coupled with” and “coupled to” are also considered to mean “communicatively coupled to” via a network, possibly through one or more intermediate devices.

[0048] The subject matter described herein is considered to include all possible combinations of the disclosed elements. Therefore, if a disclosed example includes elements A, B, and C, and a second example includes elements B and D, the subject matter described herein is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed. As used in the description and appended claims herein, the terms "a" and "the" include plural references unless the context clearly specifies otherwise. All methods, processes, and procedures described herein may be performed in any suitable order unless otherwise stated herein or clearly contradicted by the context. Unless otherwise required, the use of any and all examples or exemplary language (e.g., "such as") provided with respect to certain embodiments herein is intended only to better illustrate the subject matter described herein and does not impose a limitation on the scope of the subject matter described herein. The language in the specification should not be construed as indicating any unclaimed element necessary for the practice of the subject matter described herein. Grouping of alternative elements or embodiments of the subject matter described herein should not be construed as limiting. Each member of the group may be mentioned and claimed individually or in any combination with other members of the group or other elements found herein. For convenience and / or patentability reasons, one or more members of a group may be included in or removed from the group. When any such inclusion or removal occurs, the specification herein is deemed to contain the group as modified, thereby satisfying the written description of all Markush groups as used in the appended claims.

[0049] It will be apparent to those skilled in the art that further modifications are possible beyond those already described without departing from the concepts set forth herein. Therefore, the disclosed subject matter is not limited in any way except within the scope of the appended claims. Furthermore, in interpreting the specification and claims, all terms should be interpreted in the widest possible manner consistent with the context. In particular, the term “comprise” (comprises, comprising, include, including) should be interpreted as referring to an element, component, or step in a non-exclusive manner, indicating that the mentioned element, component, or step may be present, used, or combined with other elements, components, or steps not expressly mentioned. Where a claim in the specification refers to at least one thing selected from the group consisting of A, B, C… and N, the text should be interpreted as requiring only one element from that group, rather than A plus N, or B plus N, etc.

[0050] The above description is given by way of example and not limitation. Given the above disclosure, those skilled in the art can devise variations within the scope and spirit of the subject matter disclosed herein. Furthermore, the various features of the embodiments disclosed herein may be used individually or in different combinations thereof, and are not intended to be limited to the specific combinations described herein. Therefore, the scope of the claims is not limited to the embodiments shown.

Claims

1. A payload management system based on unmanned aerial vehicles (UAVs), comprising: At least one unmanned aerial vehicle (UAV), the at least one UAV having a first payload bay and a second payload bay, wherein the first payload bay is configured to store a first payload, and the second payload bay is configured to store a second payload; and An unmanned aerial vehicle (UAV) controller, coupled to a first payload bay and a second payload bay, includes at least one processor and at least one computer-readable storage device, the at least one computer-readable storage device storing software instructions executable by the at least one processor to perform operations including: When deploying the at least one drone, obtain the location of the at least one drone; Determine the surface attribute values ​​of the land surface associated with the location; Based on the ground attribute values, derive the payload ratio of the first amount of the first payload to the second amount of the second payload; and The first payload compartment and the second payload compartment release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

2. The system according to claim 1, wherein, The ground attribute values ​​conform to the ground attribute namespace or ontology.

3. The system according to claim 1, wherein, The ground attribute values ​​are quantified from one or more attributes in the following group: chemical attributes, altitude attributes, slope attributes, physical attributes, optical attributes, and geographic attributes.

4. The system according to claim 1, wherein, The at least one drone includes at least one unmanned aerial vehicle (UAV).

5. The system according to claim 1, wherein, At least one of the first amount and the second amount includes an amount released per unit time or per unit area.

6. The system according to claim 1, wherein, The ground attribute values ​​are derived at least partially from the image descriptor.

7. The system according to claim 1, wherein, The payload ratio is derived from the ground attribute values ​​by means of one or more selected from the group consisting of: lookup tables, functions, and machine learning models.

8. The system according to claim 1, wherein, One or both of the first payload compartment and the second payload compartment include a controllable payload opening coupled to the UAV controller.

9. The system according to claim 1, wherein, The location includes one or more selected from the group consisting of: geographic location, postal code, geofence area, Schneider 2 (S2) cell, grid location, fixed location, relative location, landmark, simultaneous localization and mapping (SLAM) location, visual simultaneous localization and mapping (vSLAM) location, wireless triangulation point and / or location relative to one or more beacons.

10. The system according to claim 1, wherein, The acquisition includes: acquiring the position of the at least one drone while the at least one drone is in flight.

11. The system according to claim 1, wherein, The first and second quantities are measured by weight.

12. The system according to claim 1, wherein, The first and second quantities are measured by volume.

13. The system according to claim 1, wherein, The effective payload ratio is in the range of 1:100 to 1:

1.

14. The system according to claim 1, wherein, One or both of the first payload and the second payload include a seed.

15. The system according to claim 1, wherein, One or both of the first payload and the second payload include spores.

16. The system according to claim 1, wherein, One or both of the first payload and the second payload include one or more payloads selected from the group consisting of: fertilizers, pesticides, liquids, powders, slurries, regulators, worms, biological products, and mycorrhizal fungi.

17. The system according to claim 1, wherein, The second payload includes calcium carbonate.

18. The system according to claim 17, wherein, The second payload includes oolitic aragonite.

19. The system of claim 1, further comprising one or more sensors, wherein, The ground attribute value is determined based on the output of at least one of the one or more sensors.

20. The system according to claim 19, wherein, The one or more sensors include one or more types of sensors selected from the group consisting of: GPS sensors, accelerometers, LiDAR sensors, RADAR sensors, cameras, thermometers, magnetometers, gyroscopes, inertial measurement units (IMUs), and spectrometers.

21. The system according to claim 19, wherein, The one or more sensors are installed in the at least one drone.

22. The system according to claim 1, wherein, The ground attribute values ​​are determined in real time based on the digital representation of the ground surface.

23. The system according to claim 1, wherein, The operation further includes: determining the dispersion of one or both of the first payload and the second payload on the ground surface.

24. The system according to claim 23, wherein, The operation further includes: performing a test release of one or both of the first payload compartment and the second payload compartment before releasing the first quantity and the second quantity, the dispersion being determined based on the test release.

25. The system according to claim 23, wherein, Determining the dispersion includes measuring the time from release to the arrival of one or both of the first payload and the second payload at the ground.

26. The system according to claim 23, wherein, The operation further includes adjusting the release of one or both of the first payload and the second payload based on the dispersion.

27. The system according to claim 1, wherein, The at least one UAV also has a third payload bay.

28. The system according to claim 1, wherein, The at least one drone includes a swarm of two or more drones.

29. The system according to claim 1, wherein, The same drone in the at least one drone includes the first payload compartment and the second payload compartment.

30. The system according to claim 1, wherein, The at least one drone includes at least one autonomous drone.

31. The system according to claim 1, wherein, The ground attribute value is determined at least in part by referring to previously characterized attributes of the ground surface associated with the location.

32. A payload management method based on unmanned aerial vehicles (UAVs), comprising: When deploying at least one drone, the location of the at least one drone is obtained, the at least one drone having a first payload compartment and a second payload compartment, wherein the first payload compartment is configured to store a first payload and the second payload compartment is configured to store a second payload; Determine the surface attribute values ​​of the land surface associated with the location; Based on the ground attribute values, derive the payload ratio of the first amount of the first payload to the second amount of the second payload; and The first payload compartment and the second payload compartment release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

33. A computer program product comprising one or more non-transitory program storage media, wherein instructions are stored on the one or more non-transitory program storage media, the instructions being executable by one or more processors or programmable circuits to perform operations for payload management based on an unmanned aerial vehicle (UAV), the operations including: When deploying at least one drone, the location of the at least one drone is obtained, the at least one drone having a first payload compartment and a second payload compartment, wherein the first payload compartment is configured to store a first payload and the second payload compartment is configured to store a second payload; Determine the surface attribute values ​​of the land surface associated with the location; Based on the ground attribute values, derive the payload ratio of the first amount of the first payload to the second amount of the second payload; and The first payload compartment and the second payload compartment release the first amount of the first payload and the second amount of the second payload, respectively, according to the payload ratio.

Images