Logistics distribution method and device based on unmanned aerial vehicle cluster, equipment and medium

Abstract

The embodiment of the invention discloses a logistics distribution method and device based on an unmanned aerial vehicle cluster, equipment and a medium. The method comprises the steps of obtaining to-be-processed order information and state information of the unmanned aerial vehicle cluster; determining a to-be-delivered task based on the order information, and determining a target unmanned aerial vehicle from an unmanned aerial vehicle cluster based on the delivery information and the state information; determining a flight strategy of the target unmanned aerial vehicle based on a preset relay link, and controlling the unmanned aerial vehicle to execute a distribution task according to the flight strategy; and monitoring real-time state information of the target unmanned aerial vehicle, and determining a real-time control strategy of the target unmanned aerial vehicle based on the real-time state information so as to adjust a flight strategy of the target unmanned aerial vehicle based on the real-time control strategy. According to the embodiment of the invention, an efficient, flexible and safe unmanned aerial vehicle distribution system is constructed, and a solid technical support is provided for large-scale commercial application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of low-altitude economy, and in particular to a logistics distribution method and device based on a UAV cluster, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] With the rapid development of e-commerce, instant retail and other industries, the demand for logistics distribution is growing explosively, and the traditional distribution mode relying on manual and ground vehicles is facing the bottleneck of low efficiency, high cost, poor environmental adaptability, etc. In particular, in the scenarios of urban "last mile" distribution, remote area coverage, and emergency material transportation, ground traffic congestion, complex terrain, time efficiency requirements, and other problems further exacerbate the limitations of traditional logistics.

[0003] The UAV technology has become an important innovation direction in the logistics field due to its flexibility, efficiency, and non-restriction by ground traffic, so how to use UAVs for logistics distribution is a problem to be solved at present. SUMMARY

[0004] To solve the above technical problems, the embodiments of the present application provide a logistics distribution method and device based on a UAV cluster, an electronic device, a computer readable storage medium, and a computer program product.

[0005] According to an aspect of an embodiment of the present application, a logistics distribution method based on a UAV cluster is provided, including: obtaining order information to be processed and state information of a UAV cluster; determining a distribution task to be distributed based on the order information, and determining a target UAV from the UAV cluster based on the distribution information and the state information; determining a flight strategy of the target UAV based on a preset relay link, and controlling the UAV to perform the distribution task according to the flight strategy; monitoring real-time state information of the target UAV, and determining a real-time control strategy of the target UAV based on the real-time state information, to adjust the flight strategy of the target UAV based on the real-time control strategy.

[0006] According to an aspect of an embodiment of the present application, the method further includes: obtaining real-time weather data, airspace control information, and historical order distribution; dynamically dividing a plurality of low-altitude distribution grids according to the real-time weather data, the airspace control information, and the historical order distribution; determining a UAV corresponding to the plurality of low-altitude distribution networks, and determining a target UAV based on location information corresponding to the distribution task to be distributed.

[0007] According to an aspect of an embodiment of the present application, the determination of the flight strategy of the target UAV based on the preset relay link includes: determine a low-altitude delivery grid corresponding to the target UAV, and determine an edge computing node corresponding to the low-altitude delivery grid in the preset relay link; determine a flight strategy of the UAV based on the edge computing node.

[0008] According to an aspect of an embodiment of the present application, the flight strategy includes a flight path, and the method further includes: generating a globally optimal path corresponding to the target UAV by a distributed reinforcement learning algorithm, and taking the globally optimal path as the flight path in the flight strategy; monitoring real-time sensing data of the target UAV, and determining front path information corresponding to the target UAV based on the sensing data; if the front path information indicates that there is an obstacle in front, re-planning a flight path of the target UAV based on the edge computing node, and updating a target UAV trajectory in the air control information based on the updated flight path.

[0009] According to an aspect of an embodiment of the present application, the determining of the real-time control strategy of the target UAV based on the real-time state information includes: if the real-time state information indicates that a remaining power value of the target UAV is lower than a preset power value threshold, determining a target battery supply station based on real-time location information of the target UAV; determining a target power value required for the target UAV to reach the battery supply station, and if the remaining power value is greater than the target power value, controlling the target UAV to charge at the target battery supply station.

[0010] According to an aspect of an embodiment of the present application, the method further includes: if the remaining power value is not greater than the target power value, re-determining a relay target UAV from the UAV cluster based on the preset relay link; determining a target handover area based on real-time location information of the target UAV, and controlling the target UAV and the relay target UAV to perform task handover in the target handover area.

[0011] According to an aspect of an embodiment of the present application, the method further includes: if it is detected that the target UAV reaches a target delivery area, controlling to turn on a visual guidance device of the target UAV; determining a target receiving device in the target delivery area through the visual guidance device, and establishing a connection with the target receiving device to trigger a mechanical arm to load and unload goods.

[0012] According to an aspect of some embodiments of the present application, there is provided a logistics distribution method based on a UAV cluster, the method comprising: obtaining order information to be processed and state information of a UAV cluster; determining a delivery task to be delivered based on the order information, and determining a target UAV from the UAV cluster based on the delivery information and the state information; determining a flight strategy of the target UAV based on a preset relay link, and controlling the UAV to perform the delivery task according to the flight strategy; and monitoring real-time state information of the target UAV, determining a real-time control strategy of the target UAV based on the real-time state information, and adjusting the flight strategy of the target UAV based on the real-time control strategy.

[0013] According to an aspect of some embodiments of the present application, there is provided an electronic device, comprising: one or more processors; and a storage device storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the logistics distribution method based on a UAV cluster as described above.

[0014] According to an aspect of some embodiments of the present application, there is provided a computer-readable storage medium having computer-readable instructions stored thereon, which when executed by a processor of a computer, cause the computer to perform the logistics distribution method based on a UAV cluster as described above.

[0015] According to an aspect of some embodiments of the present application, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the logistics distribution method based on a UAV cluster as described above.

[0016] In the technical solutions provided in the embodiments of the present application, by constructing a multi-link cooperative intelligent decision system, the efficiency and reliability of the unmanned aerial vehicle distribution system are significantly improved. First, the order and unmanned aerial vehicle cluster state information are synchronously acquired, providing a comprehensive and real-time data basis for the system, ensuring that task allocation and resource scheduling can accurately match demand and avoid resource waste; then, through intelligent correlation analysis of order information and unmanned aerial vehicle state data, the system can dynamically filter out the optimal target unmanned aerial vehicle, ensuring the efficiency and adaptability of task execution, such as preferentially selecting unmanned aerial vehicles with sufficient power and close locations to reduce task response time; subsequently, based on the preset relay link, the flight strategy is planned, not only ensuring the stability of communication, but also optimizing path selection to improve flight efficiency and safety, such as avoiding high-risk areas or selecting faster routes; finally, the real-time monitoring and dynamic adjustment mechanism forms a closed-loop control, enabling the system to quickly respond to environmental changes or abnormal unmanned aerial vehicle states, such as immediately adjusting the flight height or speed when encountering sudden weather to ensure the safe completion of tasks. From information acquisition, intelligent decision-making to real-time feedback, the whole process optimization builds an efficient, flexible and safe unmanned aerial vehicle distribution system, providing solid technical support for large-scale commercial applications.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings incorporated into the specification and forming part of the specification, show embodiments consistent with the present application, and together with the specification, serve to explain the principles of the present application. It is obvious that the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings from these drawings without creative labor. In the drawings: Figure 1 is a schematic diagram of an implementation environment for unmanned aerial vehicle cluster-based logistics distribution in logistics distribution according to an exemplary embodiment of the present application; Figure 2 is a flowchart of a logistics distribution method based on an unmanned aerial vehicle cluster according to an exemplary embodiment of the present application; Figure 3 is a flowchart of a logistics distribution method based on an unmanned aerial vehicle cluster according to another exemplary embodiment of the present application; Figure 4 is a flowchart of a logistics distribution method based on an unmanned aerial vehicle cluster according to another exemplary embodiment of the present application; Figure 5 is a flowchart of a logistics distribution method based on an unmanned aerial vehicle cluster according to another exemplary embodiment of the present application; Figure 6This is a flowchart illustrating another exemplary embodiment of a logistics delivery method based on a drone swarm, as shown in this application; Figure 7 This is a flowchart illustrating another exemplary embodiment of a logistics delivery method based on a drone swarm, as shown in this application; Figure 8 This is a flowchart illustrating another exemplary embodiment of a logistics delivery method based on a drone swarm, as shown in this application; Figure 9 This is a block diagram illustrating a drone swarm-based logistics delivery device, as shown in an exemplary embodiment of this application. Figure 10 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0020] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0021] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0022] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0023] First, it's important to note that drone technology has developed rapidly in recent years. In terms of flight performance, drone endurance has continuously improved. The application of new battery technologies and lightweight materials allows drones to fly longer distances and carry heavier loads. Simultaneously, flight stability has been significantly improved. Advanced flight control systems and sensor technologies ensure safe and accurate flight in complex weather conditions and geographical environments. Regarding navigation and positioning technology, high-precision satellite navigation systems such as GPS and BeiDou, combined with technologies like visual recognition and lidar, enable drones to accurately locate targets, plan optimal flight routes, and achieve precise delivery.

[0024] Compared to traditional logistics and delivery methods, drone delivery offers numerous advantages. First, drones are not limited by ground transportation, allowing them to fly directly from origin to destination, significantly shortening delivery time and improving efficiency. Especially in scenarios such as emergency supplies delivery and medical supply transport, drones can respond quickly, providing strong support for saving lives and ensuring livelihoods. Second, drone delivery costs are relatively low. Although the initial research and development and purchase costs of drones are high, these costs will gradually decrease as the technology becomes more widespread and production scales up. Furthermore, drones do not require human pilots, reducing labor costs, and are unaffected by traffic congestion, lowering fuel consumption and vehicle maintenance costs. In addition, drone delivery is highly flexible, adapting to various complex terrains and environments, easily reaching areas that traditional logistics cannot cover, effectively expanding the coverage of logistics and delivery.

[0025] Unmanned aerial vehicle (UAV) swarm technology refers to the integration of multiple UAVs into a collaborative system. Through centralized control or distributed autonomous decision-making, information sharing, task allocation, and coordinated flight among the UAVs are achieved. This technology originates from the imitation of the collective behavior of insects and birds in nature. By establishing a swarm intelligence model, UAVs can spontaneously organize themselves like biological groups to complete complex tasks. In recent years, with the continuous advancement of artificial intelligence, communication technology, and control technology, UAV swarm technology has developed rapidly. Researchers have achieved significant results in collaborative control algorithms, communication protocols, and task planning for UAV swarms, laying a solid foundation for their application in real-world scenarios.

[0026] Figure 1 This is a schematic diagram illustrating an exemplary embodiment of the present application, showing the implementation environment of a drone swarm-based logistics delivery process. For example... Figure 1As shown, server 120 acquires order information to be processed and status information corresponding to the drone cluster 110. Then, server 120 determines the delivery task based on the order information and identifies the target drone from the drone cluster based on the delivery information and status information. Server 120 can then determine the target drone's flight strategy based on a preset relay link and control the drone to execute the delivery task according to the flight strategy. Subsequently, the real-time status information of the target drone can be monitored through the preset relay link or edge nodes. Server 120 then determines the real-time control strategy of the target drone based on the real-time status information and adjusts the target drone's flight strategy accordingly. This achieves the management and planning of logistics delivery based on a drone cluster.

[0027] Figure 1 The server 120 shown can be, for example, a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. No restrictions are imposed here. The drone 110 can communicate with the server 120 via wireless networks such as 3G (third-generation mobile information technology), 4G (fourth-generation mobile information technology), and 5G (fifth-generation mobile information technology), which is also not restricted here.

[0028] With the rapid development of the logistics industry and the increasing volume of delivery orders, higher demands are being placed on the efficiency, quality, and flexibility of logistics delivery. Single drones, when performing large-scale delivery tasks, suffer from limited endurance, insufficient payload, and restricted delivery range, making it difficult to meet actual needs. Drone swarm technology, however, can fully leverage the collaborative advantages of multiple drones, achieving efficient and large-scale logistics delivery through the rational allocation of tasks. For example, during large e-commerce promotional events, order volumes surge; using drone swarms allows for the simultaneous processing of multiple orders, quickly delivering goods to customers and significantly improving delivery efficiency. Furthermore, drone swarms can dynamically adjust flight routes and task allocation based on different delivery needs and environmental conditions, enhancing delivery flexibility and adaptability. In complex terrain or adverse weather conditions, drone swarms can cooperate to complete delivery tasks, ensuring the safe delivery of goods.

[0029] To address these issues, embodiments of this application propose a logistics delivery method based on drone swarms, a logistics delivery device based on drone swarms, an electronic device, a computer-readable storage medium, and a computer program product, which will be described in detail below.

[0030] Please see Figure 2 , Figure 2 This is a flowchart illustrating an exemplary embodiment of a drone swarm-based logistics delivery method according to this application. This method can be applied to... Figure 1 The implementation environment shown is specifically executed by server 120 within that implementation environment. It should be understood that this method can also be applied to other exemplary implementation environments and executed by devices in other implementation environments; this embodiment does not limit the implementation environment to which the method is applicable.

[0031] like Figure 2 As shown, in an exemplary embodiment, the logistics delivery method based on drone swarms includes at least steps S210 to S240, which are described in detail below: Step S210: Obtain the information on orders to be processed and the status information of the drone cluster.

[0032] For example, it's necessary to interface with different order source channels, which may include online e-commerce platforms (such as Taobao and JD.com), the company's own sales system, and mobile applications. Standardized interfaces (such as APIs) are developed to enable data interaction with these channels. For instance, after a customer places an order, the e-commerce platform pushes the order information to the logistics and delivery system in real time via the API, according to the agreed format and protocol. Upon receiving the order information, the logistics and delivery system first parses it. The parsing process mainly involves splitting and extracting the raw data according to a predefined format, identifying the specific content of each field. For example, customer address information is extracted from the order data and broken down into more detailed geographical information such as province, city, district, and street, for subsequent delivery route planning. Each drone is equipped with multiple sensors for real-time monitoring of its hardware status. For example, accelerometers can monitor changes in the drone's acceleration to determine whether it is in a stable flight state or experiencing severe vibrations; gyroscopes are used to measure the drone's attitude angles (such as pitch, roll, and yaw) to ensure it maintains the correct flight attitude; temperature sensors monitor the temperature of various drone components (such as motors and batteries) to prevent damage from overheating; and voltage sensors monitor the battery voltage in real time to keep track of remaining battery power. Furthermore, the drone continuously provides feedback on its mission status during delivery. For instance, when the drone arrives at the pickup point, it sends a "Arrived at pickup point" message to the system; after loading the goods, it reports "Goods loaded"; and when the drone arrives at the delivery point and completes delivery, it sends a "Goods delivered" message.

[0033] Step S220: Determine the delivery task based on the order information, and determine the target drone from the drone cluster based on the delivery information and status information.

[0034] For example, the delivery information of the task to be delivered (such as delivery address, delivery distance, estimated delivery time, etc.) is deeply integrated and analyzed with the status information of each drone in the drone swarm. The drone status information includes its current location, remaining battery power, flight speed, payload capacity, and historical task execution status (such as whether there are frequent failures, task completion efficiency, etc.). By comprehensively considering this information, the feasibility of each drone performing the current delivery task can be fully assessed. According to the requirements of the task to be delivered, the drone swarm is first initially screened. Regarding payload capacity, if the total weight of the goods to be delivered exceeds the maximum payload of a certain drone, that drone is excluded; regarding remaining battery power, the battery power required for the drone to complete the task is calculated based on the delivery distance and estimated flight time, and if the remaining battery power is insufficient to ensure a safe return, it is also not considered; based on the delivery address and the drone's current location, drones that are close enough to arrive within the specified time are selected to narrow down the candidate range. On the basis of the initial screening, multiple factors are further comprehensively considered to determine the final target drone. On the one hand, considering the historical mission performance of the drones, priority is given to drones with high mission completion efficiency and low failure rate to improve the reliability and timeliness of delivery. On the other hand, the flight performance of the drones, such as flight speed and stability, is analyzed. For missions with long delivery distances or high time requirements, drones with faster flight speeds and better stability are selected. Simultaneously, the overall load balancing of the drone swarm is monitored to avoid situations where some drones are overloaded while others are idle. Tasks are allocated using reasonable algorithms to optimize the overall operational efficiency of the drone swarm. After this series of comprehensive evaluations and comparisons, the most suitable target drone for performing the current delivery task is determined from the candidate drones. This target drone can be one or more drones, and the task is assigned to it.

[0035] Step S230: Determine the flight strategy of the target drone based on the preset relay link, and control the drone to perform the delivery task according to the flight strategy.

[0036] For example, during the delivery area planning phase, comprehensive geographical information about the delivery area is collected, including topography (such as mountains, rivers, and the distribution of high-rise buildings), meteorological conditions (such as annual wind direction, wind speed, and rainfall frequency), and the distribution of communication infrastructure. Simultaneously, the specific communication requirements of drone delivery tasks are clarified, such as bandwidth requirements for real-time data transmission and signal stability requirements. For instance, complex mountainous terrain may cause signal obstruction, necessitating careful consideration of relay node placement; for delivery tasks with high real-time requirements, such as fresh food cold chain delivery, stable communication signals are crucial to ensure timely transmission of data such as temperature monitoring during the delivery process. Based on the analysis of the geographical environment and communication needs, professional site selection algorithms and models are used to rationally determine the locations of relay nodes within the delivery area. Relay nodes can include fixed ground base stations, mobile communication vehicles, and other drones with communication relay capabilities. During site selection, factors such as signal coverage, construction costs, and ease of maintenance are comprehensively considered. For example, in densely populated urban areas with high-rise buildings, the density of fixed ground base stations should be appropriately increased to ensure signal strength; in remote mountainous areas, mobile communication vehicles can be used as temporary relay nodes, with flexible adjustments to their locations to ensure communication coverage. The communication quality of each node in the relay link should be monitored in real time, including indicators such as signal strength, bandwidth utilization, and packet loss rate. Based on the communication quality assessment results, flight paths should be planned for the target UAV. Areas with good communication quality should be prioritized for flight paths, avoiding prolonged flights in areas with weak signals. For example, if a signal blind spot is found on a flight path, the path will be replanned to bypass the area, or a relay node will be placed nearby to enhance signal coverage.

[0037] Furthermore, when a target drone needs to switch from the coverage area of ​​one relay node to that of another during flight, a detailed relay node handover strategy is developed. This includes the timing of the handover, signal preservation measures during the handover process, and contingency plans for handover failure. For example, before the handover, communication negotiations are conducted with the target relay node to ensure a smooth handover process; during the handover, seamless handover technology is employed to avoid signal interruption; if the handover fails, a backup communication link is immediately activated, or the drone is controlled to return to the vicinity of the previous relay node to retry the handover.

[0038] Step S240: Monitor the real-time status information of the target UAV and determine the real-time control strategy of the target UAV based on the real-time status information, so as to adjust the flight strategy of the target UAV based on the real-time control strategy.

[0039] For example, the target drone is equipped with multiple types of sensors to comprehensively acquire its operational status information. Attitude sensors monitor the drone's pitch, roll, and yaw angles in real time, accurately determining its flight attitude; accelerometers measure changes in acceleration in various directions, helping to determine flight stability and the presence of abnormal vibrations; velocity sensors accurately measure the drone's flight speed, providing fundamental data for subsequent flight strategy adjustments; position sensors (such as GPS) determine the drone's latitude, longitude, altitude, and other location information in real time, ensuring accurate tracking of its flight trajectory; battery sensors continuously monitor battery voltage, current, and remaining power to prevent drone crashes or mission interruptions due to insufficient power; after collecting real-time status data, the drone's sensors transmit the data to a ground control station or cloud server via built-in communication modules (such as 4G / 5G, Wi-Fi, or satellite communication modules). During transmission, efficient data compression and encryption algorithms are used to ensure the timeliness and security of data transmission. Upon receiving data from multiple target drones, the ground control station or cloud server aggregates and integrates it to form a complete real-time drone status information database, providing data support for subsequent control strategy formulation. The system performs in-depth evaluation and analysis of the received real-time status information of the target drone. By comparing this information with preset normal status thresholds, it determines whether the drone is experiencing any abnormalities. For example, if the attitude sensor data shows that the drone's pitch or roll angle exceeds the normal range, it is determined that the drone is in an unstable flight state; if the battery sensor shows that the remaining battery power is below a set safety threshold, a low battery warning is issued. Simultaneously, it analyzes the changing trends of the status data, predicts potential problems, and generates corresponding real-time control strategies based on the status analysis results. Then, based on these strategies, it replans the target drone's flight path. If the drone needs to proceed to a charging point due to low battery, it plans an optimal flight path based on the charging point's location and the drone's current status, ensuring the drone arrives safely before its battery runs out. Furthermore, the path planning also considers avoiding areas with severe weather, air traffic control zones, and other factors that may affect flight safety. For example, if weather monitoring detects strong winds or heavy rain ahead of the drone's flight path, the path is adjusted promptly to bypass these areas.

[0040] In some embodiments of this application, by comprehensively acquiring order and drone cluster information, precise matching of tasks and drones is achieved. Scientific flight strategies are formulated using preset relay links, and the drone status is monitored in real time during the delivery process to dynamically adjust the strategy. This significantly improves the intelligence level of drone logistics delivery, ensures efficient, safe, and flexible execution of delivery tasks, reduces operating costs, and improves customer satisfaction.

[0041] Furthermore, based on the above embodiments, please refer to... Figure 3 In one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned logistics delivery method based on drone swarm may further include steps S310 and S320, which are described in detail below: Step S310: Obtain real-time meteorological data, airspace control information, and historical order distribution; dynamically divide multiple low-altitude delivery grids based on real-time meteorological data, airspace control information, and historical order distribution; Step S320: Identify the drones corresponding to multiple low-altitude delivery networks, and determine the target drone based on the location information corresponding to the delivery task.

[0042] For example, key information is first obtained through multiple channels: on the one hand, data is interfaced with meteorological departments to collect real-time meteorological data such as temperature, humidity, wind speed, wind direction, and precipitation probability within the delivery area; simultaneously, information from the airspace management system is accessed to understand airspace control time, area, and altitude restrictions; on the other hand, historical order data is extracted from the order database to analyze the distribution patterns of orders at different times and geographical locations. Next, this information is used to dynamically divide the delivery area into grids. Based on real-time meteorological data, adjacent areas with similar meteorological conditions (e.g., similar wind speeds, similar precipitation probabilities) are grouped into the same grid to reduce the impact of meteorological factors on drone delivery. Combined with airspace control information, areas within the same airspace control period and area are grouped into a single grid to ensure that drone flights within that grid comply with airspace control requirements. Then, referring to historical order distribution, areas with similar order density are merged into grids to facilitate the subsequent rational allocation of drone resources. After grid division, available drones are determined for each low-altitude delivery grid, based on drone performance parameters (e.g., payload capacity, range, flight speed), current location, and maintenance status. Finally, when a new delivery task is available, the system determines the low-altitude delivery grid where the task is located based on the location information of the task. Then, from the available drones in the grid, the system comprehensively considers the task requirements (such as cargo weight, delivery distance, urgency, etc.) and the real-time status of the drones (such as remaining battery power, current task load, etc.) to select one or more suitable target drones to perform the delivery task, thereby achieving efficient planning and resource allocation for drone logistics delivery.

[0043] In some embodiments of this application, low-altitude delivery grids are dynamically divided by comprehensively considering real-time meteorological data, airspace control information, and historical order distribution. This can accurately adapt to complex and ever-changing flight environments and order demands, making the division of delivery areas more scientific and reasonable. Based on this, the drones corresponding to each delivery grid are determined, and the target drones are quickly locked according to the location information of the task to be delivered. This can significantly improve the planning efficiency and resource utilization of drone logistics delivery, reduce flight conflicts and invalid flights, and thus improve the overall delivery efficiency and service quality.

[0044] Furthermore, based on the above embodiments, please refer to... Figure 4 In one exemplary embodiment provided in this application, the specific implementation process of determining the flight strategy of the target UAV based on a preset relay link may further include steps S410 and S420, which are described in detail below: Step S410: Determine the low-altitude delivery grid corresponding to the target UAV, and determine the edge computing node corresponding to the low-altitude delivery grid in the preset relay link; Step S420: Determine the flight strategy of the UAV based on the edge computing nodes.

[0045] For example, firstly, based on the target drone's location information and the previously dynamically divided low-altitude delivery grid range (these grids are divided based on a combination of factors such as real-time weather, airspace control, and historical order distribution), the current low-altitude delivery grid to which the target drone belongs is accurately determined. Then, using relevant information from a pre-set relay link, including the location, coverage area, and communication connection relationships of relay nodes (including edge computing nodes), a spatial matching algorithm is used to identify edge computing nodes that have communication coverage or optimal communication connections with the target drone's low-altitude delivery grid. Finally, based on the capabilities of this edge computing node (such as computing resources, storage capacity, and data processing speed) and its connections with the target drone, other relay nodes, and ground control... The system considers the communication status between control stations (such as signal strength, bandwidth, and latency), as well as the delivery task requirements of the target drone (such as cargo type, delivery destination, and time constraints). It also utilizes intelligent algorithms (such as reinforcement learning algorithms and path planning algorithms) to generate the drone's flight strategy. This strategy includes flight path planning (selecting the optimal route to avoid obstacles and areas with severe weather, while ensuring good communication with edge computing nodes), flight speed adjustment (adjusting the speed according to the urgency of the task and battery status), and relay node switching timing (switching between appropriate edge computing nodes or relay nodes during flight based on signal quality and task requirements). This ensures that the drone can complete the delivery task efficiently and safely.

[0046] In some embodiments of this application, by clearly defining the low-altitude delivery grid corresponding to the target UAV and its edge computing nodes in the preset relay link, the precise matching of delivery tasks and computing resources is achieved. By utilizing the powerful real-time data processing capabilities of edge computing nodes, more realistic, efficient and reasonable flight strategies can be quickly formulated based on grid environment characteristics, airspace conditions, etc., which effectively improves the response speed, flight safety and scientific nature of UAV logistics delivery, and reduces delivery risks and costs caused by information processing delays or unreasonable strategies.

[0047] Furthermore, based on the above embodiments, please refer to... Figure 5 In one exemplary embodiment provided in this application, the flight strategy includes a flight path, and the specific implementation process of the above-mentioned logistics delivery method based on drone swarms may further include steps S510 to S530, which are described in detail below: Step S510: Generate the global optimal path corresponding to the target UAV through a distributed reinforcement learning algorithm, and use the global optimal path as the flight path in the flight strategy; Step S520: Monitor the real-time sensor data of the target drone and determine the forward path information of the drone based on the sensor data; Step S530: If the forward path information indicates that there is an obstacle ahead, the flight path of the target UAV is replanned based on the edge settlement node, and the trajectory of the target UAV in the air traffic control information is updated based on the updated flight path.

[0048] For example, in the path planning and dynamic adjustment scheme for drone logistics delivery, a distributed reinforcement learning framework is first constructed, using multiple edge computing nodes within the delivery area as distributed computing units, with each node responsible for path optimization in its local area. The target drone uploads its own state information (such as position, speed, and battery level), task information (such as start point, destination, and time constraints), and environmental information (such as meteorological data and airspace control information) to its respective edge computing node. Each edge computing node, through collaborative interaction with other nodes, uses a distributed reinforcement learning algorithm (such as distributed Q-learning or distributed Actor-Critic algorithm) to perform global path search and optimization, comprehensively considering factors such as flight distance, time cost, power consumption, and airspace control constraints, ultimately generating the globally optimal path for the target drone, which becomes a core component of the flight strategy. During the drone's flight mission, various onboard sensors (such as cameras, lidar, and millimeter-wave radar) collect real-time sensor data of the environment ahead, including the position, shape, and motion status of obstacles. The system processes and analyzes this sensor data in real time to determine whether there are obstacles on the path ahead. If an obstacle is detected, the system immediately uploads the obstacle information (such as location, size, and hazard level) to the edge computing node. The edge computing node combines the latest obstacle information, the drone's real-time status, and current airspace control information to quickly replan the drone's flight path, avoiding the obstacle area while ensuring the new path complies with airspace control requirements (such as flight altitude restrictions and no-fly zones). Once the planning is complete, the system synchronizes the updated flight path information to the airspace control system, updates the drone's trajectory record in the airspace control information, and issues new flight commands to the drone, enabling it to continue its delivery mission according to the updated path, thereby ensuring the safety of the drone's flight and the efficiency of the delivery mission.

[0049] In some embodiments of this application, a globally optimal path for the target drone is generated through a distributed reinforcement learning algorithm, providing an efficient and scientific initial flight strategy for the delivery task and helping to improve overall delivery efficiency. Real-time monitoring of drone sensor data and determination of the path information ahead can promptly detect potential obstacles. When an obstacle is detected ahead, the flight path is quickly replanned with the help of edge computing nodes, and the target drone trajectory in the air traffic control information is updated. This dynamic adjustment mechanism significantly enhances the adaptability and flight safety of the drone in complex environments, effectively avoids risks such as collisions, and ensures the smooth progress of logistics delivery tasks.

[0050] Furthermore, based on the above embodiments, please refer to... Figure 6In one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned drone swarm logistics delivery method may further include steps S610 and S620, which are described in detail below: Step S610: If the real-time status information indicates that the remaining power value of the target drone is lower than the preset power value threshold, then the target battery replenishment station is determined based on the real-time location information of the target drone. Step S620: Determine the target power value required for the target drone to reach the battery replenishment station. If the remaining power value is greater than the target power value, control the target drone to replenish power at the target battery replenishment station.

[0051] For example, the system continuously monitors the real-time status information of the target drone, especially its remaining battery power. When the system detects that the target drone's remaining battery power is lower than a preset battery power threshold (this threshold is determined based on factors such as the drone's model, payload, and flight environment to ensure the drone has sufficient power to safely reach the refueling station), it immediately triggers the battery refueling process. Based on the target drone's real-time location information (obtained via GPS or other positioning technologies) and a pre-built battery refueling station distribution map (which includes the location, charging power, and number of available charging stations for each station), the system uses a shortest path algorithm or a nearest neighbor algorithm to determine the nearest available target battery refueling station to the target drone's current location. Subsequently, the system calculates the amount of power required for the target drone to fly from its current location to the target battery refueling station (considering the impact of environmental factors such as flight distance, flight speed, and wind speed on power consumption). If the drone's remaining battery power is greater than the calculated target battery power (ensuring the drone can safely reach the refueling station), the system generates navigation instructions to control the target drone to fly to the target battery refueling station. Upon arrival, it initiates an automatic charging process (such as wireless charging or docking with a charging station), while simultaneously updating the drone's mission status and scheduling subsequent delivery tasks to ensure the continuity and efficiency of the entire logistics and delivery process.

[0052] In some embodiments of this application, by monitoring the remaining battery level of the target drone in real time and comparing it with a preset battery level threshold, insufficient battery power can be detected in a timely manner. Based on the real-time location information of the target drone, the target battery refueling station is accurately determined, and the target battery level required to reach the refueling station is further calculated. Under the premise that the remaining battery level is greater than the target battery level to ensure safe arrival, the target drone is controlled to go to the refueling station for refueling. This series of operations effectively avoids the risk of mission interruption or crash due to the drone running out of power, ensures the continuity and stability of drone logistics delivery missions, improves resource utilization efficiency, and reduces unnecessary energy waste.

[0053] Furthermore, based on the above embodiments, please refer to... Figure 7In one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned drone swarm logistics delivery method may further include steps S710 and S720, which are described in detail below: Step S710: If the remaining power value is not greater than the target power value, then the target drone to be connected is re-determined from the drone cluster based on the preset relay link. Step S720: Determine the target handover area based on the real-time location information of the target UAV, and control the target UAV and the successor target UAV to perform task handover in the target handover area.

[0054] For example, in an emergency mission succession plan for drone logistics delivery, when the system detects that the remaining battery power of the target drone is not greater than the target battery power required to reach the target battery refueling station (i.e., the battery power is insufficient to support its safe arrival at the refueling station), the system immediately initiates the mission succession process. First, based on preset relay link information (including real-time data such as the position, status, and mission load of each drone in the drone cluster), the system filters out suitable succession target drones from the drone cluster. The filtering criteria include: the succession drone has a light current mission load, sufficient remaining battery power, a close proximity to the target drone, and a high degree of matching between its flight path and the original mission path. After determining the succession drone, the system uses the real-time location information of the target drone (obtained via GPS or other positioning technologies) and the succession drone's location information, combined with Geographic Information System (GIS) data, to determine a suitable target handover area. This area must meet conditions such as open airspace, no obstacles, and good communication signals. Subsequently, the system sends control commands to both the target drone and the succession drone, adjusting their flight paths and guiding them to the target handover area. In the handover area, the system uses a high-precision positioning system and communication module on the drones to ensure precise docking between the two drones, and employs automated cargo handover devices (such as robotic arms and hooks) to complete the transfer of cargo or tasks. After the handover is completed, the system updates the task allocation information, and the successor drone continues to perform the remaining delivery tasks. Meanwhile, the target drone chooses to land safely or fly to the nearest emergency landing point based on its remaining battery power, thereby ensuring uninterrupted execution of logistics and delivery tasks and overall efficiency.

[0055] Furthermore, in the emergency support plan for drone logistics delivery, besides situations involving insufficient battery power, when a target drone malfunctions during a delivery mission (e.g., abnormal flight attitude, abnormal power system parameters, or communication signal interruption detected by sensors on the drone, confirmed by system analysis), the system will quickly activate an emergency mission succession mechanism. Based on pre-set relay link information, which aggregates real-time data on the location, status (including remaining battery power, current mission load, and health status) and flight trajectory of each drone in the drone cluster, and combining this with the location of the malfunctioning target drone, the type of malfunction, and the requirements of the original delivery mission (such as cargo type, urgency, and destination), intelligent algorithms (such as multi-objective optimization algorithms that comprehensively consider factors such as distance, time, and payload capacity) are used to re-select suitable successor drones from the drone cluster. The selected successor drones must meet conditions such as sufficient remaining battery power, a relatively light current mission load, and the capabilities required to complete the remaining delivery mission (such as load matching, flight altitude and speed adaptation). After identifying the successor drone, the system uses a path planning algorithm to determine a suitable target handover area based on the real-time location information of both the faulty target drone and the successor drone, while also referencing geographical environmental data (such as terrain, weather conditions, and airspace control areas). This area should have open airspace, good communication signals, and be free of obstacles to ensure a safe and smooth handover process. Subsequently, the system sends precise control commands to both the faulty target drone and the successor drone, adjusting their flight paths and guiding them to the target handover area. During flight, the system continuously monitors the flight status of both drones to ensure they follow the predetermined paths. Once the two drones reach the target handover area, the system uses the drones' high-precision positioning system (such as Real-Time Kinematic RTK) and communication modules (such as 5G communication) to achieve precise docking. After docking, an automated cargo handover device (such as a handover platform with electromagnetic adsorption function or a retractable robotic arm) completes the rapid and safe transfer of cargo or tasks. After the handover is completed, the system immediately updates the task allocation information, and the successor drone continues to perform the remaining delivery tasks, ensuring that the goods can be delivered to their destination on time and accurately. At the same time, the malfunctioning drone is handled according to the severity of the malfunction and its own condition, following the preset emergency procedures (such as automatically returning to the maintenance base or making an emergency landing in a safe area), so as to facilitate subsequent troubleshooting and repair, thereby minimizing the impact of drone malfunctions on logistics and delivery tasks and ensuring the stability and reliability of the entire logistics and delivery system.

[0056] In some embodiments of this application, when the remaining battery power of the target drone is insufficient to safely reach the battery resupply station, a new target drone can be quickly selected from the drone cluster based on a preset relay link to ensure the continuity of mission execution. At the same time, the target handover area is accurately determined based on the real-time location of the target drone, and the two drones are controlled to complete an efficient and safe mission handover in this area. This minimizes the risk of delivery delays or failures caused by battery issues, significantly improves the flexibility and reliability of the drone logistics delivery system in the face of emergencies, and ensures that logistics delivery tasks can be carried out continuously and stably.

[0057] Furthermore, based on the above embodiments, please refer to... Figure 8 In one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned drone swarm logistics delivery method may further include steps S810 and S820, which are described in detail below: Step S810: If the target drone is detected to have reached the target delivery area, the visual guidance device of the target drone is activated. In step S820, the target receiving device within the target delivery area is determined by the visual guidance device, and a connection is established with the target receiving device to trigger the robotic arm to load and unload the goods.

[0058] For example, in a precise loading and unloading solution for drone logistics delivery, when the drone's positioning system (such as GPS, BeiDou, or other high-precision positioning modules) compares in real time with the geofence information of the delivery area, and detects that the target drone has entered the preset target delivery area, the system immediately sends a control command to the drone to activate its onboard visual guidance device. This visual guidance device typically includes a high-definition camera, an image processing chip, and related algorithm software. Once activated, it quickly performs a comprehensive image scan and identification of the target delivery area. Using advanced computer vision technologies (such as target detection algorithms and feature matching algorithms), the visual guidance device analyzes and processes the scanned images, accurately identifying the target receiving device (such as a smart parcel locker with a specific identifier, a customized cargo receiving platform, etc.; these target receiving devices may have unique shapes, colors, QR codes, or RFID tags) from among numerous objects in the delivery area. After identifying the target receiving device, the drone establishes a communication connection with it through its built-in communication module (such as Wi-Fi, Bluetooth, 4G / 5G, etc.), and the two parties exchange necessary information (such as cargo information, receiving instructions, loading and unloading parameters, etc.). After the connection is established and confirmed to be correct, the drone starts its onboard robotic arm (which has multi-degree-of-freedom motion capabilities and precise grasping control functions). Based on the target receiving device position and cargo placement requirements fed back by the visual guidance device, the robotic arm precisely adjusts its posture and movement trajectory to accurately and safely place the cargo it carries into the designated position of the target receiving device, thereby completing the entire cargo loading and unloading process and achieving efficient and accurate delivery of drone logistics.

[0059] In some embodiments of this application, when the target drone arrives at the target delivery area, the visual guidance device is precisely activated. Utilizing its powerful image recognition and positioning capabilities, the target receiving device is quickly and accurately identified from the delivery area and a connection is established with it. This triggers the robotic arm to complete the automated loading and unloading of goods. This series of processes significantly improves the accuracy and efficiency of drone logistics delivery, reduces human intervention, lowers the operational error rate, and provides strong support for the intelligent and automated development of drone logistics delivery.

[0060] Figure 9 This is a block diagram illustrating a drone swarm-based logistics delivery device as an exemplary embodiment of this application. This device can be applied to... Figure 1 The implementation environment shown is specifically configured in server 120. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0061] like Figure 9As shown, this exemplary drone swarm-based logistics delivery device includes: an acquisition module 910, used to acquire pending order information and drone swarm status information; a determination module 920, used to determine the delivery task based on the order information, and to determine the target drone from the drone swarm based on the delivery information and status information; a control module 930, used to determine the flight strategy of the target drone based on a preset relay link, and control the drone to perform the delivery task according to the flight strategy; and an adjustment module 940, used to monitor the real-time status information of the target drone, and to determine the real-time control strategy of the target drone based on the real-time status information, so as to adjust the flight strategy of the target drone based on the real-time control strategy.

[0062] According to one aspect of the embodiments of this application, the determination module 920 is further configured to: acquire real-time meteorological data, airspace control information and historical order distribution; dynamically divide multiple low-altitude delivery grids according to the real-time meteorological data, airspace control information and historical order distribution; determine the drones corresponding to the multiple low-altitude delivery networks, and determine the target drone based on the location information corresponding to the delivery task.

[0063] According to one aspect of the embodiments of this application, the determining module 920 is further configured to determine the low-altitude delivery grid corresponding to the target UAV, and determine the edge computing node corresponding to the low-altitude delivery grid in the preset relay link, and determine the flight strategy of the UAV based on the edge computing node.

[0064] According to one aspect of the embodiments of this application, the determination module 920 is further configured to: generate a globally optimal path corresponding to the target UAV through a distributed reinforcement learning algorithm, and use the globally optimal path as the flight path in the flight strategy; monitor the real-time sensing data of the target UAV, and determine the forward path information corresponding to the UAV based on the sensing data; if the forward path information indicates that there is an obstacle ahead, then replan the flight path of the target UAV based on the edge settlement node, and update the trajectory of the target UAV in the air traffic control information based on the updated flight path.

[0065] According to one aspect of the embodiments of this application, the adjustment module 940 is further configured to: if the real-time status information indicates that the remaining power value of the target drone is lower than a preset power value threshold, then determine the target battery replenishment station based on the real-time location information of the target drone; determine the target power value required for the target drone to reach the battery replenishment station; and if the remaining power value is greater than the target power value, control the target drone to replenish power at the target battery replenishment station.

[0066] According to one aspect of the embodiments of this application, the adjustment module 940 is further configured to: if the remaining power value is not greater than the target power value, re-determine the successor target drone from the drone cluster based on a preset relay link; determine the target handover area based on the real-time location information of the target drone, and control the target drone and the successor target drone to perform task handover in the target handover area.

[0067] According to one aspect of the embodiments of this application, the control module 930 is further configured to, if the target drone is detected to have reached the target delivery area, control the activation of the visual guidance device of the target drone; determine the target receiving device within the target delivery area through the visual guidance device, and establish a connection with the target receiving device to trigger the robotic arm to load and unload the goods.

[0068] It should be noted that the drone swarm-based logistics delivery device and the drone swarm-based logistics delivery method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the drone swarm-based logistics delivery device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0069] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, enable the electronic device to implement the drone swarm-based logistics delivery method provided in the above embodiments.

[0070] Figure 10 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 10 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0071] like Figure 10As shown, the computer system 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from storage portion 1008 into Random Access Memory (RAM) 1003, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1003. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. An Input / Output (I / O) interface 1005 is also connected to bus 1004.

[0072] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0073] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs various functions defined in the system of this application.

[0074] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0075] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0076] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0077] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned drone swarm-based logistics delivery method. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0078] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the drone swarm-based logistics delivery method provided in the various embodiments described above.

[0079] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

Claims

1. A logistics delivery method based on unmanned aerial vehicle (UAV) swarms, characterized in that, include: Obtain information on pending orders and the status information of the drone cluster; The task to be delivered is determined based on the order information, and the target drone is determined from the drone cluster based on the delivery information and the status information; The flight strategy of the target drone is determined based on a preset relay link, and the drone is controlled to perform the delivery task according to the flight strategy. The system monitors the real-time status information of the target UAV and determines the real-time control strategy of the target UAV based on the real-time status information, so as to adjust the flight strategy of the target UAV based on the real-time control strategy.

2. The method as described in claim 1, characterized in that, The method further includes: Acquire real-time meteorological data, airspace control information, and historical order distribution; dynamically divide multiple low-altitude delivery grids based on the real-time meteorological data, airspace control information, and historical order distribution; The drones corresponding to the multiple low-altitude delivery networks are identified, and the target drone is determined based on the location information corresponding to the delivery task.

3. The method as described in claim 2, characterized in that, The process of determining the flight strategy of the target UAV based on a preset relay link includes: Determine the low-altitude delivery grid corresponding to the target UAV, and determine the edge computing node corresponding to the low-altitude delivery grid in the preset relay link; The flight strategy of the UAV is determined based on the edge computing node.

4. The method as described in claim 3, characterized in that, The flight strategy includes a flight path, and the method further includes: A globally optimal path for the target UAV is generated using a distributed reinforcement learning algorithm, and the globally optimal path is used as the flight path in the flight strategy. Monitor the real-time sensor data of the target drone and determine the forward path information of the drone based on the sensor data; If the forward path information indicates that there is an obstacle ahead, the flight path of the target UAV is replanned based on the edge settlement node, and the trajectory of the target UAV in the air traffic control information is updated based on the updated flight path.

5. The method as described in claim 1, characterized in that, The method further includes: If the real-time status information indicates that the remaining power value of the target drone is lower than a preset power value threshold, then a target battery replenishment station is determined based on the real-time location information of the target drone. The target power level required for the target drone to reach the battery recharge station is determined. If the remaining power level is greater than the target power level, the target drone is controlled to recharge at the target battery recharge station.

6. The method as described in claim 5, characterized in that, The method further includes: If the remaining battery power value is not greater than the target battery power value, then the target drone to be connected is re-determined from the drone cluster based on the preset relay link; Based on the real-time location information of the target UAV, the target handover area is determined, and the target UAV and the successor target UAV are controlled to perform task handover in the target handover area.

7. The method as described in claim 1, characterized in that, The method further includes: If the target drone is detected to have reached the target delivery area, the visual guidance device of the target drone is activated. The visual guidance device identifies the target receiving device within the target delivery area and establishes a connection with the target receiving device to trigger the robotic arm to load and unload the goods.

8. A logistics delivery device based on a drone swarm, characterized in that, The device includes: The acquisition module is used to acquire information on pending orders and the status information of the drone cluster. The determination module is used to determine the delivery task based on the order information, and to determine the target drone from the drone cluster based on the delivery information and the status information; The control module is used to determine the flight strategy of the target drone based on a preset relay link, and control the drone to perform the delivery task according to the flight strategy; An adjustment module is used to monitor the real-time status information of the target UAV and determine the real-time control strategy of the target UAV based on the real-time status information, so as to adjust the flight strategy of the target UAV based on the real-time control strategy.

9. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the logistics delivery method based on a drone swarm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer-readable instructions, which, when executed by the computer's processor, cause the computer to perform the logistics delivery method based on a drone swarm as described in any one of claims 1 to 7.

Images