A method and system for unmanned aerial vehicle charging decision in a multi-charging base station environment

Abstract

This invention discloses a method and system for UAV charging decision-making in a multi-charging-base station environment. The method includes: constructing and dynamically updating a UAV mission execution environment model; determining whether the mission execution energy safety constraints are met; if met, continuing the mission; otherwise, selecting reachable base stations from the multiple charging base stations based on the charging reachable energy safety constraints; calculating the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and selecting the reachable base station with the smallest comprehensive evaluation value as the target charging base station. This invention enables dynamic charging decisions for UAVs during mission execution, thereby improving mission execution efficiency and ensuring flight safety.

Description

Technical Field

[0001] This invention belongs to the field of drone scheduling technology and relates to a drone charging decision-making method and system in a multi-charging base station environment. Background Technology

[0002] With the rapid development of drone technology, it has been widely used in environmental monitoring, power line inspection, emergency rescue, logistics delivery, and data collection. Typically, drones need to visit multiple task points along a pre-set path to acquire data or execute tasks. However, due to limitations in battery capacity, drones have limited endurance, often requiring multiple refuelings when performing long-distance or multi-tasking missions, significantly impacting mission efficiency.

[0003] In existing technologies, the following methods are commonly used to address the energy management problem of drones: First, a return-to-home strategy based on a fixed threshold, where the drone returns to its starting point or a designated charging location when its remaining battery power falls below a preset threshold. Second, a path planning method based on a single charging base station, which introduces a unique charging point as a replenishment node during path planning. Third, separating path planning from energy management, first generating a visit path, and then making charging decisions based on path execution. While these methods are applicable to simple scenarios, they suffer from significant shortcomings in path planning efficiency, energy utilization, and system stability in complex task environments due to the lack of a comprehensive optimization mechanism.

[0004] With increasing application demands, multiple charging base stations are typically deployed within the mission area to enhance the coverage and flexibility of drone operations. However, in multi-base station environments, existing methods generally lack an effective selection mechanism for multiple base stations, often making decisions solely based on distance or fixed rules, failing to comprehensively consider flight energy consumption, mission progress, and the state differences between different base stations. This can easily lead to unreasonable path planning and low energy utilization efficiency. Furthermore, existing technologies often separate path planning from charging decisions, lacking a unified optimization framework, making it difficult for drones to dynamically adjust based on real-time conditions during execution. In addition, in multi-base station scenarios, different charging base stations may experience load differences or resource contention, but existing methods typically do not model base station load or availability, further impacting overall system efficiency. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for making charging decisions for unmanned aerial vehicles (UAVs) in a multi-charging-base station environment. In such an environment, the method comprehensively considers factors such as flight distance, energy consumption, mission delay, and base station status to make dynamic charging decisions for UAVs during mission execution, thereby improving mission efficiency and ensuring flight safety.

[0006] The present invention adopts the following technical solution.

[0007] A method for drone charging decision-making in a multi-charging-base station environment includes: Step 1: Construct and dynamically update the drone mission execution environment model, which includes the drone's location, remaining battery power, mission completion status, and information on multiple charging base stations. Step 2: Based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission, determine whether the mission execution energy safety constraints are met. If they are met, continue the mission; otherwise, proceed to Step 3. Step 3: Select reachable base stations from the plurality of charging base stations based on the charging reachability energy safety constraints; Step 4: Calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

[0008] Preferably, the state space of the UAV mission execution environment model includes the UAV's location, remaining battery power, mission completion status, and information on each charging base station, with the state vector being:

[0009] in, Indicates the location of the drone; Indicates the remaining battery power of the drone; Indicates the first j Task completion status at each task point j Take 1- m , m The number of task points; Indicates the first i Information on individual charging base stations For the first i The location of a charging base station Characterizing the first i Load status of each charging base station i Take 1- n , n This refers to the number of charging base stations.

[0010] Preferably, the energy safety constraint for task execution in step 2 is that there exists at least one charging base station location that satisfies the following formula:

[0011] in, The remaining battery power of the drone. As a safety threshold, The estimated energy consumption for the drone to continue performing its mission. For drones from drone location Flying to the i Location of charging base stations Energy consumed.

[0012] Preferably, continuing to execute the task includes: continuing to execute the remaining part of the current task when the current task is not completed, or executing the next task when the current task has been completed.

[0013] Preferably, the charging reachable energy safety constraint condition in step 3 is:

[0014] in, The remaining battery power of the drone. As a safety threshold, For drones from drone location Flying to the i Location of charging base stations Energy consumed.

[0015] Preferably, the safety threshold Specifically:

[0016] in, Based on the basic security threshold, For safety reasons, This is the maximum battery capacity for the drone.

[0017] Preferably, in step 3, if no charging base station meets the charging reachable energy safety constraint, then there is no reachable base station, and the safety threshold is lowered to the preset minimum safety value, and reachable base stations are re-screened; if there is still no reachable base station after lowering, then the charging base station with the shortest flight distance is selected as the target charging base station; if the target charging base station cannot be reached due to insufficient energy, then the forced landing mode can be triggered.

[0018] Preferably, the formula for calculating the comprehensive evaluation value in step 4 is:

[0019]

[0020]

[0021] in, For drones to the first i The distance between charging base stations; For drones from drone location Flying to the i Location of charging base stations Energy consumed; For the drone to fly to the i The cost of delay in charging at each charging base station; For the first i Load status of each charging base station; As weight; For the drone's flight speed, For charging time, Queuing time for base stations This is the task delay penalty coefficient. The number of uncompleted tasks. Indicates the first j Task completion status at each task point m This represents the number of task points.

[0022] Preferably, the weights are: ; ; in, For the g-th weight, g takes values ​​from 1 to 4; , These are the g-th and k-th weight values ​​before normalization; , , , To preset the initial weights, This represents the percentage of remaining battery power.

[0023] A drone charging decision system in a multi-charging-base station environment, the system comprising: The environment model construction and update module is used to construct and dynamically update the UAV mission execution environment model. The model includes the UAV location, the UAV's remaining battery power, the mission completion status, and the location and status information of multiple charging base stations. The scheduling decision module is used to determine whether the energy safety constraints for mission execution are met based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission. If the constraints are met, the mission continues; otherwise, the module enters the reachable base station filtering module. The reachable base station screening module is used to screen reachable base stations from the plurality of charging base stations based on the charging reachable energy safety constraints; The comprehensive decision-making module is used to calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

[0024] A terminal includes a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method.

[0025] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method.

[0026] Compared with the prior art, the beneficial effects of the present invention include at least the following: This invention constructs and dynamically updates a drone mission execution environment model that includes information on the drone's location, remaining battery power, mission completion status, and multiple charging base stations. Based on this model, it makes drone charging decisions, dynamically selecting whether to continue the mission or proceed to charging based on the drone's real-time status (remaining battery power), charging base station information, and the estimated energy consumption for continuing the mission. This overcomes the problem of separating path planning and charging strategy in existing technologies. Furthermore, this invention improves the accuracy, security, and robustness of drone charging decisions in multi-charging-base station environments by using dynamic safety thresholds to determine whether to continue the mission and whether candidate charging base stations are reachable.

[0027] This invention employs a comprehensive evaluation-based charging base station selection mechanism. It not only considers the spatial distance between the UAV and each base station, but also incorporates multiple factors such as flight energy consumption, mission delay costs, and base station load status for joint evaluation. This enables quantitative assessment of candidate base stations and selects the optimal charging base station under the condition of meeting the energy safety constraints of charging availability. This avoids the path redundancy and inefficiency problems caused by relying solely on distance or fixed rules in traditional methods. It can reduce the total flight distance of the UAV, improve path planning efficiency, reduce overall energy consumption, and improve energy utilization efficiency.

[0028] This invention determines the available charging energy safety constraints of the drone based on its remaining battery power and flight consumption when making charging decisions. This ensures that the drone has the ability to safely reach the target charging base station at any decision time, thereby effectively avoiding mission interruption or flight risks due to insufficient energy, shortening mission completion time, and improving mission execution efficiency.

[0029] This invention also supports an adaptive decision-making mechanism based on dynamic strategies. By incorporating the current battery status of the UAV into the decision weight adjustment process, the UAV prioritizes reducing flight risks and energy consumption when the battery is low, and prioritizes reducing mission delay when the battery is sufficient. This improves the adaptability of the overall scheduling strategy. Furthermore, the urgency of the mission (based on the number of uncompleted missions) is incorporated into the calculation of mission delay costs, achieving comprehensive optimization of charging decisions. This allows the various influencing factors in the evaluation function to be dynamically adjusted according to the actual operating status, enabling the UAV to have differentiated decision-making capabilities at different stages. For example, it prioritizes reducing energy consumption when the battery is low and prioritizes reducing mission delay when the mission is urgent, further enhancing the flexibility and adaptability of the overall scheduling strategy. Attached Figure Description

[0030] Figure 1 This is a flowchart of the drone charging decision method in a multi-charging base station environment according to the present invention.

[0031] Figure 2 This is a simulation scenario of UAV mission execution in a multi-charging base station environment, as described in this embodiment of the invention.

[0032] Figure 3 This is a comparison of simulation results between the UAV charging decision method in a multi-charging base station environment in this invention embodiment and the traditional nearest base station strategy and fixed strategy. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0034] Embodiment 1 of the present invention provides a method for drone charging decision-making in a multi-charging-base station environment, involving a drone and multiple charging base stations. The drone is used to perform data collection or inspection tasks at multiple task points, and the charging base stations are used to provide energy replenishment for the drone. Figure 1 As shown, the drone charging decision-making method in a multi-charging base station environment mainly includes the following steps: Step 1: Construct and dynamically update the drone mission execution environment model. The model includes the drone's location, remaining battery power, mission completion status, and the location and status information of multiple charging base stations. (1) Environmental modeling: Construct a drone mission execution environment model, including the drone's current location, remaining battery power, mission completion status, and the location and status information of multiple charging base stations.

[0035] (2) State space construction: Define the state vector as follows: (1) in, Indicates the location of the drone; Indicates the remaining battery power of the drone; Indicates the first j Task completion status j Take 1- m , m The number of task points; Indicates the first i Information on each charging base station includes its location and status information. , For the first i Location of charging base stations Characterizing the first i Load status of each charging base station i Take 1- n , n This refers to the number of charging base stations.

[0036] (3) Definition of action space: The defined action set includes: ① going to the target task point; ② going to any charging base station to charge.

[0037] Step 2: Based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission, determine whether the mission execution energy safety constraints are met. If they are met, continue the mission; otherwise, proceed to Step 3. Specifically, the drone charging decision is made based on the drone mission execution environment model. The decision is made according to the drone's current remaining battery power and its energy state after mission execution. If, assuming the drone continues to execute the mission (the remaining part of the current mission or the next mission), there is still at least one charging base station that meets the energy safety constraint (mission execution energy safety constraint), then the mission continues. If, assuming the drone continues to execute the mission, there is no charging base station that meets the energy safety constraint, then the system enters a charging scheduling mode. The energy safety constraints for task execution are as follows: (2) in, The remaining battery power of the drone. As a safety threshold, The estimated energy consumption for the drone to continue performing its mission. For drones from drone location Flying to thei Location of charging base stations Energy consumed.

[0038] It is understood that continuing to execute subsequent tasks can mean that the UAV continues to execute the remaining part of the current task, or that the UAV begins and executes the next task to be executed in the task sequence. Accordingly, the energy expected to be consumed by continuing to execute the task corresponds to the energy required to complete the remaining part of the current task, or the energy required to execute the next complete task. Step 3: Select reachable base stations from the plurality of charging base stations based on the charging reachability energy safety constraints; Specifically, in the charging scheduling mode, the set of reachable base stations is selected based on factors such as the energy consumed by the drone flying to each charging base station and energy safety constraints (charging reachable energy safety constraints); the charging reachable energy safety constraints are: (3) in, The remaining battery power of the drone. As a safety threshold, For drones from drone location Flying to the i Location of charging base stations Energy consumed.

[0039] Preferably, the safety threshold in this invention Dynamic representation (4) in, Based on the basic security threshold, For safety reasons, Maximum battery capacity for the drone; basic safety threshold. and safety factor The value can be determined based on factors such as the drone's battery capacity, flight speed, mission area size, and safety requirements; unrestricted, It can be set to 10% of the drone's maximum battery level. It can be set to 0.6.

[0040] Charging base stations that meet the above-mentioned charging reachability energy safety constraints constitute a set of reachable base stations.

[0041] Compared to traditional fixed threshold judgment methods, this invention uses dynamic safety thresholds to determine whether to continue the task and whether candidate charging base stations are reachable, thereby improving the accuracy, safety, and robustness of drone charging decisions in multi-charging base station environments.

[0042] Understandably, in practice, if the set of reachable base stations calculated in step 3 is empty, it means that the current battery level is insufficient to guarantee the drone's safe arrival at any charging base station. In this case, the system can enter emergency mode: lowering the energy safety threshold... The speed is lowered to the preset minimum safety value (e.g., half of the basic safety threshold); if there is still no reachable base station after lowering the speed, the charging base station with the shortest flight distance is directly selected as the target; if the base station with the shortest flight distance is still unable to be reached due to insufficient energy, the emergency landing mode can be triggered, that is, the drone lands safely near the current location and sends out a distress signal.

[0043] Step 4: Calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

[0044] Specifically, only charging base stations that meet the above constraints constitute the candidate base station set. A comprehensive evaluation function for charging base stations is constructed here. Based on the distance from the UAV to the base station, the energy consumed by the UAV flying to the base station, the mission delay cost, and the base station load, a comprehensive evaluation value is calculated for each reachable base station. The reachable base station with the smallest comprehensive evaluation value is selected as the target charging base station. The comprehensive evaluation function is: (5) in, , , , These are drones to the first i The distance to each charging base station, the energy consumption for flying to that base station, the mission delay cost, and the base station load. For weights.

[0045] In practical implementation, the above formula , , , All samples were uniformly mapped to the [0,1] interval using the min-max normalization method to eliminate dimensional differences. For example, its normalized value is , These represent the maximum and minimum distances from the drone to each reachable base station, respectively. When the two are equal, the normalized value is 0. , , Similarly, normalization is performed.

[0046] The cost of task delay is represented as: (6) Where V is the flight speed of the drone. For charging time, Queuing time for base stations This is the task delay penalty coefficient. The number of incomplete tasks, determined based on the task completion status, can be more specifically represented as follows: (7) in, Indicates the first j The task completion status.

[0047] Charging time It can be a fixed value or inversely proportional to the remaining battery power of the drone; that is, the lower the remaining battery power, the longer the charging time. Base station queuing time It can be estimated based on the number of drones currently queuing at the charging base station and the average charging time, or it can be fed back to the drones in real time by the charging base station. The task delay penalty coefficient represents the additional delay time caused by each unfinished task. It can be adjusted according to the urgency of the task, taking a larger value when the task is urgent and a smaller value when the task is lenient. Non-restricted, its value range can be 0.1 to 10 seconds, preferably 1 second.

[0048] In the formula for calculating the comprehensive evaluation value, the weights of each evaluation factor in the comprehensive evaluation function are adjusted according to the proportion of remaining electricity.

[0049] When the remaining battery percentage decreases, increase the weight of the distance factor and energy consumption factor; when the remaining battery percentage increases, increase the weight of the task delay cost factor. (8) (9) in, For the g-th weight, g takes values ​​from 1 to 4; , These are the g-th and k-th weight values ​​before normalization; , , , These are the preset initial weights, This represents the percentage of remaining battery power, i.e., the remaining battery power of the drone. Maximum battery capacity of the drone The ratio; , , , The settings can be adjusted according to the actual task requirements. For example, when the task has high real-time requirements, the settings can be appropriately increased. Unrestricted , , , The values ​​can be set to 0.4, 0.3, 0.2, and 0.1 respectively.

[0050] In practical implementation, if under extremely low power conditions, (1 ξ)(1 The value of ξ) is close to 1. To avoid the above weight adjustment potentially causing excessive weighting of distance and energy consumption factors, thus ignoring task delay and base station load, a weight cap η can be set to balance the factors, for example, η=0.8; or, when (1 When ξ) > η, the weight will no longer increase to prevent decision imbalance. This upper limit can be adaptively adjusted according to task requirements.

[0051] In this invention, the minimum value that ultimately satisfies the task execution energy safety constraint is selected. The target charging base station is then used. Through the aforementioned dynamic weighting adjustment mechanism, the drone prioritizes reducing flight risks and energy consumption when its battery is low, and prioritizes reducing mission delays when its battery is sufficient, thus improving the adaptability of the overall scheduling strategy. Execution and Update: Based on the decision, the drone executes flight or charging operations and updates its status information in real time, repeating the above steps until the mission is completed.

[0052] In summary, this invention proposes a unified decision-making method for multi-charging-base station environments. By constructing a multi-dimensional state model that includes the UAV's location, remaining battery power, mission execution status, and information about each charging base station, it integrates mission execution and charging decisions into a unified model. This allows the UAV to dynamically choose between executing a mission or heading to a charging station based on its real-time status, thus overcoming the problem of separating path planning and charging strategies in existing technologies. Based on this, a charging base station selection mechanism based on a comprehensive evaluation function is proposed. This mechanism not only considers the spatial distance between the UAV and each base station but also incorporates multiple factors such as flight energy consumption, mission delay costs, and base station load status for joint modeling. By constructing a multi-objective weighted evaluation model, it achieves quantitative evaluation of candidate base stations and selects the optimal charging base station under the condition of satisfying energy reachability constraints. This avoids the path redundancy and inefficiency problems caused by relying solely on distance or fixed rules in traditional methods. This invention also introduces an energy safety constraint mechanism, constraining the UAV's remaining battery power and flight consumption during charging decisions. This ensures that the UAV has the ability to safely reach the target charging base station at any decision time, effectively avoiding mission interruption or flight risks due to insufficient energy. Furthermore, this invention also supports an adaptive decision-making mechanism based on dynamic strategies, enabling the various influencing factors in the evaluation function to be dynamically adjusted according to the actual operating state. This allows the UAV to have differentiated decision-making capabilities at different stages, such as prioritizing energy consumption reduction when the battery is low and prioritizing task delay reduction when the task is urgent, thereby further improving the flexibility and adaptability of the overall scheduling strategy.

[0053] Based on the above steps, this invention constructs a simulation scenario for UAV mission execution in a multi-charging-base station environment. Taking three charging base stations as an example, ... Figure 2 As shown, three charging base stations are used as a reference. The simulation area is set as a two-dimensional plane area of ​​1000m×1000m, with 20 task points randomly distributed in this area, and 3 charging base stations set up at different locations in the area.

[0054] The drone's initial position is in the center of the area, with an initial battery of 100 units. It consumes 1 unit of energy per unit of flight distance.

[0055] The method of this invention adopts a charging decision strategy based on a comprehensive evaluation function, which dynamically decides whether to go to charging and select a target base station during the task execution process.

[0056] The evaluation function comprehensively considers factors such as flight distance, energy consumption, mission delay, and base station load, and selects the optimal base station under the condition of satisfying energy security constraints.

[0057] During the simulation, the total flight distance, total energy consumption, and mission completion time of the three methods were statistically analyzed to complete all tasks.

[0058] Simulation results are as follows Figure 3 As shown. Compared to the nearest base station strategy and the fixed strategy, the method of the present invention performs better in all indicators. Specifically, the total flight distance of the method of the present invention is approximately 95 units, which is about 20.8% lower than the nearest base station strategy of 120 units and about 29.6% lower than the fixed strategy of 135 units; In terms of energy consumption, the method of the present invention consumes approximately 82 units, which is about 18% lower than the nearest base station strategy and about 25% lower than the fixed strategy. In terms of task completion time, the method of the present invention is approximately 78 units, which is about 13.3% shorter than the nearest base station strategy and about 25.7% shorter than the fixed strategy.

[0059] Furthermore, when the UAV charging decision method in the multi-charging base station environment of this invention is used in the simulation, the UAV can dynamically select different charging base stations according to the remaining power and task distribution at different stages, avoiding the situation of repeatedly going back and forth to the same base station. At the same time, due to the introduction of energy safety constraints, the UAV did not experience task interruption due to insufficient power during the entire execution process.

[0060] In summary, the method of the present invention can effectively reduce flight distance and energy consumption, shorten mission completion time, and improve the safety and stability of system operation in a multi-charging base station environment.

[0061] This invention reduces the total flight distance of drones and improves path planning efficiency. By constructing a unified path planning and charging decision model, it comprehensively considers task distribution and flight costs when selecting charging base stations, avoiding the path detour problem caused by local optima in traditional nearest-base-station strategies. In this invention, the total flight distance is reduced from 120 units in the nearest-base-station strategy to 95 units, a reduction of approximately 20%.

[0062] This invention reduces overall energy consumption and improves energy utilization efficiency by incorporating energy consumption factors into the decision-making process and selecting a better charging base station, thereby effectively reducing unnecessary flight distances. In this embodiment, total energy consumption is reduced from 100 units to 82 units, a reduction of approximately 18%.

[0063] This invention reduces the number of times a drone travels between different areas through an integrated scheduling strategy, making the task execution path more continuous, thereby shortening the overall task completion time and improving task execution efficiency. In this embodiment, the task completion time is reduced from 90 units to 78 units, a reduction of approximately 13%.

[0064] This invention unifies task execution and charging decision-making into a single model, enabling UAVs to dynamically select the optimal strategy during execution, overcoming the efficiency problems caused by the separation of path planning and energy management in existing technologies. Furthermore, by introducing base station load factors, this invention rationally allocates multiple charging base stations, avoiding frequent selection of the same base station by the UAV, resulting in more balanced utilization of charging resources. This invention also sets energy safety constraints and introduces a dynamic weighting mechanism to ensure that the UAV has the ability to safely reach the charging base station at any decision point and improves the adaptability of the scheduling strategy.

[0065] This invention has significant technical effects in reducing flight distance, reducing energy consumption, shortening mission time, and improving system safety and resource utilization. It can effectively solve problems in existing technologies such as limited effective selection mechanisms in multi-base station scenarios, disconnect between path planning and energy management, and insufficient energy security, and realize the efficient and safe operation of UAVs in complex mission environments.

[0066] Embodiment 2 of the present invention provides a drone charging decision system in a multi-charging base station environment, comprising: The environment model construction and update module is used to construct and dynamically update the UAV mission execution environment model. The model includes the UAV location, the UAV's remaining battery power, the mission completion status, and the location and status information of multiple charging base stations. The scheduling decision module is used to determine whether the energy safety constraints for mission execution are met based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission. If the constraints are met, the mission continues; otherwise, the module enters the reachable base station filtering module. The reachable base station screening module is used to screen reachable base stations from the plurality of charging base stations based on the charging reachable energy safety constraints; The comprehensive decision-making module is used to calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

[0067] Embodiment 3 of the present invention provides a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method.

[0068] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method.

[0069] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0070] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0071] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0072] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for drone charging decision-making in a multi-charging-base station environment, characterized in that, include: Step 1: Construct and dynamically update the drone mission execution environment model, which includes the drone's location, remaining battery power, mission completion status, and information on multiple charging base stations. Step 2: Based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission, determine whether the mission execution energy safety constraints are met. If they are met, continue the mission; otherwise, proceed to Step 3. Step 3: Select reachable base stations from the plurality of charging base stations based on the charging reachability energy safety constraints; Step 4: Calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

2. The UAV charging decision method in a multi-charging base station environment according to claim 1, characterized in that: The state space of the UAV mission execution environment model includes the UAV's location, remaining battery power, mission completion status, and information on each charging base station. The state vector is: in, Indicates the location of the drone; Indicates the remaining battery power of the drone; Indicates the first j Task completion status at each task point j Take 1- m , m The number of task points; Indicates the first i Information on individual charging base stations For the first i The location of a charging base station Characterizing the first i Load status of each charging base station i Take 1- n , n This refers to the number of charging base stations.

3. The UAV charging decision method in a multi-charging base station environment according to claim 1, characterized in that: Step 2 states that the energy safety constraint for task execution is that there exists at least one charging base station location that satisfies the following formula: in, The remaining battery power of the drone. As a safety threshold, The estimated energy consumption for the drone to continue performing its mission. For drones from drone location Flying to the i Location of charging base stations Energy consumed.

4. The UAV charging decision method in a multi-charging base station environment according to claim 1, characterized in that: The continued execution of the task includes: continuing to execute the remaining part of the current task when the current task is not completed, or executing the next task when the current task has been completed.

5. The UAV charging decision method in a multi-charging base station environment according to claim 1, characterized in that: The charging energy safety constraint condition mentioned in step 3 is as follows: in, The remaining battery power of the drone. As a safety threshold, For drones from drone location Flying to the i Location of charging base stations Energy consumed.

6. A method for UAV charging decision-making in a multi-charging base station environment according to claim 3 or 5, characterized in that: Safety threshold Specifically: in, Based on the basic security threshold, For safety reasons, This is the maximum battery capacity for the drone.

7. The UAV charging decision method in a multi-charging base station environment according to claim 5, characterized in that: If no charging base station meets the charging reachability energy safety constraint in step 3, then there is no reachable base station. The safety threshold is lowered to the preset minimum safety value, and reachable base stations are re-screened. If no base station can be reached after adjusting the distance, the charging base station with the shortest flight distance will be selected as the target charging base station. If the target charging station cannot be reached due to insufficient energy, a forced landing mode can be triggered.

8. The UAV charging decision method in a multi-charging base station environment according to claim 1, characterized in that: The formula for calculating the comprehensive evaluation value in step 4 is: in, For drones to the first i The distance between charging base stations; For drones from drone location Flying to the i Location of charging base stations Energy consumed; For the drone to fly to the i The cost of delay in charging at each charging base station; For the first i Load status of each charging base station; As weight; For the drone's flight speed, For charging time, Queuing time for base stations This is the task delay penalty coefficient. The number of uncompleted tasks. Indicates the first j Task completion status at each task point m This represents the number of task points.

9. The UAV charging decision method in a multi-charging base station environment according to claim 8, characterized in that: The weights are: ； ； in, For the g-th weight, g takes values ​​from 1 to 4; , These are the g-th and k-th weight values ​​before normalization; , , , To preset the initial weights, This represents the percentage of remaining battery power.

10. A drone charging decision system in a multi-charging base station environment, comprising the method described in any one of claims 1-9, characterized in that, The system includes: The environment model construction and update module is used to construct and dynamically update the UAV mission execution environment model. The model includes the UAV location, the UAV's remaining battery power, the mission completion status, and the location and status information of multiple charging base stations. The scheduling decision module is used to determine whether the energy safety constraints for mission execution are met based on the drone's location, remaining battery power, information on multiple charging base stations, and the estimated energy consumption for continuing the mission. If the constraints are met, the mission continues; otherwise, the module enters the reachable base station filtering module. The reachable base station screening module is used to screen reachable base stations from the plurality of charging base stations based on the charging reachable energy safety constraints; The comprehensive decision-making module is used to calculate the comprehensive evaluation value of each reachable base station based on the UAV mission execution environment model, and select the reachable base station with the smallest comprehensive evaluation value as the target charging base station.

11. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-9.

Images