Generation method and device of unmanned aerial vehicle path planning and adjustment scheme under hybrid demand, computer equipment and storage medium

Abstract

The embodiment of the invention relates to the field of unmanned aerial vehicles, and provides an unmanned aerial vehicle path planning and adjusting scheme generation method and device under hybrid requirements, computer equipment and a storage medium, and the method comprises the steps: obtaining initial model parameters; under the condition that the random demand is not realized, an unmanned aerial vehicle path planning optimization model is constructed; the unmanned aerial vehicle path planning optimization model is solved based on an improved large-scale neighborhood search algorithm, and an unmanned aerial vehicle optimal path planning scheme is generated; under the condition that the optimal path planning scheme of the unmanned aerial vehicle is given and the random demand is realized, an unmanned aerial vehicle path planning adjustment model is constructed; and based on an improved large-scale neighborhood search algorithm, solving the unmanned aerial vehicle path planning adjustment model, and generating an unmanned aerial vehicle optimal path adjustment scheme. By adopting the method, the accuracy and rationality of unmanned aerial vehicle path planning can be improved.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method, apparatus, computer equipment, and storage medium for generating UAV path planning and adjustment schemes under mixed requirements. Background Technology

[0002] In the field of drone technology, the use of drones is rapidly growing in many civilian applications, including real-time monitoring, providing wireless coverage, remote sensing, search and rescue, cargo transportation, security and surveillance, precision agriculture, and civilian infrastructure inspection. Intelligent drones represent the next major revolution in drone technology and are expected to offer new opportunities in various application areas, particularly in the civilian infrastructure sector, where risk and cost reduction are crucial.

[0003] Despite their advantages such as high maneuverability, low cost, and ease of deployment, drones' limited flight time due to energy consumption restricts their application over large geographical areas. To overcome these drawbacks, smart airports are needed to provide charging / battery swapping services for drones. A smart drone airport is a ground-based facility comprised of modules for drone storage, intelligent observation, automatic charging or battery replacement, wireless communication, automatic battery maintenance, UPS power outage protection, fault self-diagnosis, and takeoff condition detection.

[0004] However, traditional UAV path planning technology does not take into account the diversity of planning needs, resulting in low accuracy and rationality of UAV path planning. Summary of the Invention

[0005] This application provides a method, apparatus, computer equipment, and computer storage medium for generating UAV path planning and adjustment schemes under mixed requirements, which can improve the accuracy and rationality of UAV path planning.

[0006] In a first aspect, embodiments of this application provide a method for generating UAV path planning and adjustment schemes under mixed requirements, including:

[0007] Obtain the initial model parameters required for the representation process of the target task scenario;

[0008] In the absence of stochastic demand, the first objective function is to maximize the total service revenue of deterministic demand, and an optimization model for UAV path planning is constructed based on the initial model parameters.

[0009] The improved large-scale neighborhood search algorithm is used to solve the UAV path planning optimization model to generate the optimal UAV path planning scheme.

[0010] Given the optimal path planning scheme for the UAV and the fulfillment of stochastic requirements, the UAV path planning adjustment model is constructed based on the initial model parameters with the second objective function being to maximize the total service revenue of all requirements.

[0011] Based on the improved large-scale neighborhood search algorithm, the UAV path planning adjustment model is solved to generate the optimal UAV path adjustment scheme.

[0012] Secondly, embodiments of this application provide an apparatus for generating UAV path planning and adjustment schemes under mixed demands, which has the function of implementing the method for generating UAV path planning and adjustment schemes under mixed demands provided in the first aspect above. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, and the modules can be software and / or hardware.

[0013] In one possible design, the device includes:

[0014] The parameter acquisition module is used to acquire the initial model parameters required for the representation process of the target task scenario;

[0015] The first model construction module is used to construct an UAV path planning optimization model based on the initial model parameters, with the first objective function being to maximize the total service revenue of the deterministic demand, when the stochastic demand is not met.

[0016] The first model solving module is used to solve the UAV path planning optimization model based on the improved large-scale neighborhood search algorithm to generate the optimal path planning scheme for the UAV.

[0017] The second model construction module is used to construct an UAV path planning adjustment model based on the initial model parameters, given the optimal path planning scheme for the UAV and the fulfillment of stochastic requirements, with the maximization of the total service revenue of all requirements as the second objective function.

[0018] The second model solving module is used to solve the UAV path planning adjustment model based on the improved large-scale neighborhood search algorithm, and generate the optimal UAV path adjustment scheme.

[0019] In another aspect, this application provides a computer device including at least one connected processor and a memory, wherein the memory is used to store program code, and the processor is used to invoke the program code in the memory to execute the methods described in the above aspects.

[0020] In another aspect, this application provides a computer storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0021] In another aspect, this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the above aspects.

[0022] Compared to traditional drone path planning methods in conventional technologies, the technical solution of this application optimizes the path planning and adjustment schemes in scenarios with mixed demands, thereby improving the service performance of smart airports and drone systems. It can provide further guidance for the application of drones in fields such as surveillance, search, and the Internet of Things, thereby enhancing the accuracy and rationality of drone path planning. Attached Figure Description

[0023] Figure 1 This is an application environment diagram from one embodiment;

[0024] Figure 2 This is a flowchart illustrating a method for generating UAV path planning and adjustment schemes under mixed requirements in one embodiment.

[0025] Figure 3 This is a schematic diagram of a task scenario in one embodiment;

[0026] Figure 4 This is a schematic diagram of the optimal path planning scheme for a drone in one embodiment.

[0027] Figure 5 This is a schematic diagram of the optimal path adjustment scheme for a drone in one embodiment;

[0028] Figure 6 This is a schematic diagram of the implementation process of the technical solution in one embodiment;

[0029] Figure 7 This is a structural block diagram of a device for generating UAV path planning and adjustment schemes under mixed requirements in one embodiment;

[0030] Figure 8 This is an internal structural diagram of a computer device in one embodiment;

[0031] Figure 9 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0032] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. The division of modules in the embodiments of this application is merely a logical division; in actual applications, there may be other division methods. For example, multiple modules may be combined into or integrated into another system, or some features may be ignored or not performed. Additionally, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interface, and the indirect coupling or communication connection between modules may be electrical or other similar forms, none of which are limited in the embodiments of this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed among multiple circuit modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of this application.

[0033] Figure 1 As shown in the application environment diagram of one embodiment, this application provides a method for generating UAV path planning and adjustment schemes under mixed requirements, which can be applied to, for example... Figure 1 In the application scenario shown, terminal 102 communicates with server 104 via a network.

[0034] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0035] It should be noted that the terminal 102 involved in the embodiments of this application can be a wired terminal or a wireless terminal, and can be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a wireless access network, and the wireless terminal can be a mobile terminal, such as a mobile phone or a computer with a mobile terminal.

[0036] Figure 2This is a flowchart illustrating a method for generating UAV path planning and adjustment schemes under mixed requirements in one embodiment. Figure 2 As shown in the embodiments of this application, the method for generating UAV path planning and adjustment schemes under mixed requirements includes:

[0037] S201, Obtain the initial model parameters required for the representation process of the target task scenario.

[0038] Among them, the target mission scenario refers to the scenario of using drones and smart airports to provide services to mission points.

[0039] The initial model parameters include, but are not limited to, the task point number set, the location of the task point, the service time of the task point, the number of deterministic demands of the task point, the service revenue of the deterministic demands of the task point, the random variable of the number of stochastic demands of the task point, the service revenue of the stochastic demands of the task point, the smart airport number, the location of the smart airport, the charging / battery swapping time of the smart airport, the flight speed of the UAV, the upper and lower limits of the UAV's energy, the hovering energy consumption and flight energy consumption of the UAV per unit time, and the duration of the planning period.

[0040] S202, in the case that the stochastic demand is not met, the total service revenue of the deterministic demand is maximized as the first objective function, and an optimization model for UAV path planning is constructed based on the initial model parameters.

[0041] Among them, deterministic demand refers to the demand that exists constantly and has a clear quantity of task points throughout the entire planning scope, and its service benefits are directly related to the number of demand met; random demand refers to the sudden demand that is only realized at the beginning of each planning period and whose quantity follows a random distribution, and can obtain corresponding benefits after service. The two together constitute the mixed demand scenario of drone services.

[0042] The first objective function is the objective function corresponding to the UAV path planning optimization model, which is constructed by maximizing the total service revenue for deterministic demand.

[0043] S203, based on an improved large-scale neighborhood search algorithm, solves the UAV path planning optimization model and generates the optimal UAV path planning scheme.

[0044] Among them, the large-scale neighborhood search algorithm is a heuristic optimization algorithm for complex combinatorial optimization problems. It first randomly or strategically destroys the current solution, and then uses optimization strategies to repair and generate new solutions, continuously exploring the large-scale solution space to approach the optimal solution.

[0045] For example, after solving the UAV path planning optimization model and obtaining the relevant parameters, the path planning scheme represented by the values ​​of the relevant parameters is the optimal path planning scheme for the UAV.

[0046] S204. Given the optimal path planning scheme for the UAV and the fulfillment of stochastic requirements, the UAV path planning adjustment model is constructed based on the initial model parameters with the maximization of the total service revenue of all requirements as the second objective function.

[0047] The second objective function is the objective function corresponding to the UAV path planning adjustment model, which is constructed to maximize the total service revenue of all demands.

[0048] S205, based on an improved large-scale neighborhood search algorithm, solves the UAV path planning adjustment model and generates the optimal UAV path adjustment scheme.

[0049] For example, after solving the UAV path planning adjustment model and obtaining the relevant parameters, the path adjustment scheme represented by the values ​​of the relevant parameters is the optimal path adjustment scheme for the UAV.

[0050] Compared to traditional UAV path planning methods, this embodiment first obtains initial model parameters. Then, when the randomness requirement is not met, an optimized UAV path planning model is constructed and solved using an improved large-scale neighborhood search algorithm. Subsequently, given the optimal UAV path planning scheme and the randomness requirement has been met, an adjusted UAV path planning model is constructed and solved using the improved large-scale neighborhood search algorithm to generate the optimal UAV path adjustment scheme. The technical solution of this embodiment improves the service performance of smart airports and UAV systems by optimizing the path planning and adjustment schemes in scenarios with mixed requirements. It provides further guidance for the application of UAVs in fields such as surveillance, search, and the Internet of Things, thereby enhancing the accuracy and rationality of UAV path planning.

[0051] Optionally, in some embodiments of this application, the target task scenario is: a scenario in which drones and smart airports are used to provide services to task points; wherein, the smart airport is used to provide charging or battery swapping services to drones, and the task points have constant deterministic demand throughout the entire planning scope and random demand realized at the beginning of each planning period.

[0052] Figure 3 This is a schematic diagram of a task scenario in one embodiment, such as... Figure 3 As shown, the task scenario representation process relies on a task scenario representation method, including: for scenarios where drones and smart airports provide services to task points. Specifically, the smart airport can charge / swap batteries for drones, and the task points have deterministic demands that remain constant throughout the planning scope and stochastic demands that are realized at the beginning of each planning period. The specific process includes the following:

[0053] S301. After numbering the task points, a task point number set is formed: (1);

[0054] In equation (1), This represents a set consisting of the numbers of m task points. In this embodiment, Task points Figure 3 The square in the diagram represents the task point number, and the square contains the task point number.

[0055] S302, The location of task point i is: In this embodiment, Figure 3 The position of the square in the middle represents the two-dimensional projection position of the corresponding task point, and the height coordinates of all task points are 0;

[0056] S303, the service time for task point i is: In this embodiment, each All values ​​were randomly generated within 2 to 10 minutes.

[0057] S304, The number of deterministic requirements for task point i is: In this embodiment, each All values ​​are randomly generated between 0 and 2;

[0058] S305, The service benefit of the deterministic requirement for task point i is: .in, This represents the number of deterministic requirements satisfied for task point i. In this embodiment, each All values ​​are randomly generated from 1 to 3;

[0059] S306. The random variable representing the randomness requirement of task point i is: In this embodiment, each All follow a uniform distribution between 0 and 1;

[0060] S307, The service benefit of the randomness requirement of task point i is: .in, This represents the number of times the randomness requirement of task point i is satisfied. In this embodiment, each All values ​​are randomly generated within the range of 2 to 3;

[0061] S308, the intelligent airport is numbered 0. Intelligent airports and task points are collectively referred to as waypoints. In this embodiment, the intelligent airport is... Figure 3The circle in the diagram represents the smart airport, and the number of the smart airport is marked inside the circle.

[0062] The locations of S309 and the smart airport are: In this embodiment, Figure 3 The position of the middle circle represents the two-dimensional projection position of the smart airport, and the height coordinates of the smart airport are all 0;

[0063] The charging / swapping time for S310 and smart airports is... In this embodiment, ;

[0064] S311, The drone's flight speed is v. In this embodiment, ;

[0065] The upper and lower energy limits of the S312 and the drone are respectively and In this embodiment, , ;

[0066] S313, the hovering energy consumption and flight energy consumption of the UAV per unit time are respectively and In this embodiment, , ;

[0067] S314, The duration of the planned time period is T. In this embodiment, .

[0068] Optionally, in some embodiments of this application, when the randomness requirement is not met, a UAV path planning optimization model is constructed based on the initial model parameters with the goal of maximizing the total service revenue of the deterministic requirement as the first objective function. This includes: calculating the service revenue of the deterministic requirement at any task point and the number of deterministic requirements satisfied at any task point; and constructing the first objective function with the goal of maximizing the total service revenue of the deterministic requirement based on the service revenue of the deterministic requirement at any task point and the number of deterministic requirements satisfied at any task point.

[0069] Here, the service revenue of the deterministic demand at any task point refers to the service revenue of the deterministic demand at task point i, which can be denoted as: .

[0070] Here, the number of deterministic requirements satisfied at any task point refers to the number of deterministic requirements satisfied at task point i, which can be denoted as: .

[0071] The first objective function can be denoted as: .

[0072] Optionally, in some embodiments of this application, a UAV path planning optimization model is constructed based on initial model parameters, including: using the range constraints of the number of task points passed through in the UAV path planning scheme, the range constraints of the number decision variable of any task point passed through by the UAV, the duration constraint of the planning period, and the constraint that the number of deterministic requirements satisfied by the task point does not exceed the number of its deterministic requirements as first constraints; and constructing a UAV path planning optimization model based on the first constraints and the first objective function.

[0073] The constraint on the range of the number of task points traversed in the UAV's path planning scheme can be denoted as: .

[0074] The constraint on the range of values ​​for the decision variable for the number of any task point the UAV passes through refers to the constraint on the range of values ​​for the decision variable for the number of the k-th task point the UAV passes through, which can be denoted as: .

[0075] Among them, the duration constraint of the planning period can be denoted as: .

[0076] Where the number of deterministic requirements satisfied at a task point does not exceed its deterministic requirement number constraint, it can be denoted as: .

[0077] For example, the construction process of the UAV path planning optimization model includes: when stochastic demands are not met, maximizing the total service revenue of deterministic demands as the objective, with constraints such as the planning period duration, and solving for the optimal UAV path planning scheme. Specifically, this includes the following processes:

[0078] S401, the distance between path point i1 and path point i2 is:

[0079] (2);

[0080] In equation (2), This represents the distance between path point i1 and path point i2.

[0081] S402. The number of task points that the UAV passes through in the path planning scheme is n;

[0082] S403, the number of the kth transit point in the UAV path planning scheme is: ;

[0083] S404, the remaining energy of the drone upon arrival and departure at the kth mission point are respectively... and ;

[0084] S405, the arrival and departure times of the UAV at the kth transit point are respectively... and ;

[0085] S406, the residual energy transfer equation for the UAV is:

[0086] (3);

[0087] (4);

[0088] In equations (3) and (4), ;

[0089] S407. The transfer equations for the arrival and departure times of the UAV are:

[0090] (5);

[0091] (6);

[0092] In equations (5) and (6), ;

[0093] S408. Constraints on the range of values ​​for the number of task points traversed in the UAV's path planning scheme:

[0094] (7);

[0095] In equation (7), Represents the set of all natural numbers;

[0096] S409. Constraints on the range of values ​​for the decision variable indicating the kth mission point the UAV passes through:

[0097] (8);

[0098] S410, Planning Period Duration Constraints: (9);

[0099] S411. In the path planning scheme, calculate the number of deterministic requirements satisfied for task point i:

[0100] (10);

[0101] In equation (10), This indicates the operation of counting the elements in a set;

[0102] S412. The number of deterministic requirements satisfied at a task point does not exceed the constraint of the number of deterministic requirements:

[0103] (11);

[0104] S413. Set the objective function to maximize the total service revenue for deterministic demand:

[0105] (12);

[0106] In equation (12), Represents the total service revenue from deterministic demand;

[0107] S414. Summarize equations (2) to (12) to obtain the UAV path planning optimization model.

[0108] Optionally, in some embodiments of this application, the UAV path planning optimization model is solved based on an improved large-scale neighborhood search algorithm to generate the optimal UAV path planning scheme, including: copying each task point to a preset number of copies, calculating the revenue of each copied task point, and calculating the unit time rate of return of each copied task point; while ensuring energy consumption constraints, arranging the flight order of UAVs in descending order of unit time rate of return until the planned time period constraint is reached; taking the path generated in the UAV flight order as the current solution, and calculating the objective function value under the current solution; using a random removal operator with a removal count as a destruction operator to remove the copied task points in the current solution; using the best repair operator for repair; calculating the objective function value under the best repair operator with different repair counts, and taking the largest one as the new solution; calculating the difference between the objective function value under the new solution and the current solution; if the difference meets a preset condition, accepting the new solution as the current solution; and outputting the current solution as the optimal UAV path planning scheme when the number of iterations reaches a preset number.

[0109] The phrase "copying each task point a preset number of times" refers to making a certain number of copies of each task point; this preset number can be adjusted adaptively. The phrase "each task point as a copy after copying" refers to the number of copies of each task point after it has been copied.

[0110] Here, taking the path generated in the flight sequence of the UAV as the current solution means taking the path generated in step S504 as the current solution.

[0111] Among them, the difference meeting the preset condition means that... The number of iterations reaching the preset number of iterations refers to the time when the number of iterations reaches G.

[0112] For example, this application employs an improved large-scale neighborhood search algorithm for solving the aforementioned UAV path planning optimization model. The specific steps of the algorithm are as follows:

[0113] S501. Copy each task point several times. Among them, the task point numbered i is copied... share;

[0114] S502. Calculate the revenue of each task point after replication. Wherein, the revenue of task point i is... The revenue from replication is ;

[0115] S503. Calculate the unit-time rate of return for each task point after replication. ;

[0116] S504. While ensuring energy consumption constraints, arrange the flight sequence of UAVs in descending order of rate of return per unit time until the planned time period constraint is reached.

[0117] S505. Use the path generated in step S504 as the current solution;

[0118] S506. Calculate the objective function value under the current solution;

[0119] S507, Using the number of removals is The random removal operator is used as a destruction operator to remove elements from the current solution. The copied task points are removed. In this embodiment, ;

[0120] S508, Number of repairs used They are respectively , and The optimal repair operator is used for repair;

[0121] S509. Calculate the objective function value under the three optimal repair operators with different repair numbers, and take the largest one as the new solution;

[0122] S510. Calculate the difference between the objective function value under the new solution and the current solution. ;

[0123] S511, if If the solution is correct, accept the new solution as the current solution; otherwise, return to S507.

[0124] Steps S512, S507 to S511 constitute one iteration. When the number of iterations reaches G, the current solution is output as the optimal path planning scheme for the UAV, and the entire algorithm ends.

[0125] In this embodiment, In the optimal path planning scheme for a UAV, the number of times the UAV passes through the task point numbered i is denoted as . .

[0126] Figure 4 This is a schematic diagram of the optimal path planning scheme for a drone in one embodiment, such as... Figure 4 As shown, in this embodiment, the maximum total service revenue for deterministic demands can be calculated to be 20.53, and the following can be calculated: Figure 4 The diagram shows the optimal path planning scheme for the drone. The solid arrows indicate the drone's flight direction. If the path between two consecutive charging / battery swapping sessions is considered a single flight, then the optimal path planning scheme in this example contains three single flights. The numbers on the solid arrows indicate the order of these single flights.

[0127] Optionally, in some embodiments of this application, given the optimal path planning scheme for the UAV and the fulfillment of stochastic requirements, a UAV path planning adjustment model is constructed based on initial model parameters with the goal of maximizing the total service revenue of all requirements. This includes: calculating the service revenue of deterministic requirements at any task point, the service revenue of stochastic requirements at any task point, and the number of deterministic requirements satisfied at any task point; determining the service revenue of any task point based on the service revenue of deterministic requirements at any task point, the service revenue of stochastic requirements at any task point, and the number of deterministic requirements satisfied at any task point; and constructing a second objective function with the goal of maximizing the total service revenue of all requirements based on the service revenue of any task point.

[0128] Here, the service revenue of the deterministic demand at any task point refers to the service revenue of the deterministic demand at task point i, which can be denoted as: .

[0129] Here, the service revenue from the randomness requirement of any task point refers to the service revenue from the randomness requirement of task point i, which can be denoted as: .

[0130] Here, the number of deterministic requirements satisfied at any task point refers to the number of deterministic requirements satisfied at task point i, which can be denoted as: .

[0131] Here, the service revenue of any task point refers to the service revenue of task point i, which can be denoted as: .

[0132] The second objective function refers to setting the objective function to maximize the total service revenue of all demands, which can be denoted as: .

[0133] Optionally, in some embodiments of this application, a UAV path planning adjustment model is constructed based on initial model parameters, including: using the constraints on the range of values ​​for the number of task points passed through in the UAV path adjustment scheme, the range of values ​​for the decision variable of the number of any passed task point, the duration of the planning period, and the constraint that the number of task point requirements satisfied does not exceed the sum of the number of requirements satisfied by the path planning scheme and the number of random requirements as second constraints; and constructing the UAV path planning adjustment model according to the second constraints and the second objective function.

[0134] The constraint on the range of the number of task points traversed in the UAV's path adjustment scheme can be denoted as: .

[0135] Here, the constraint on the range of values ​​for the decision variable for the number of any mission point along the route refers to the constraint on the range of values ​​for the decision variable for the number of the kth mission point along the route of the UAV, which can be denoted as: .

[0136] Among them, the duration constraint of the planning period can be denoted as: .

[0137] The constraint that the number of requirements satisfied at a task point does not exceed the sum of the number of requirements satisfied by its path planning scheme and the number of random requirements can be denoted as: .

[0138] For example, the construction process of the UAV path planning adjustment model includes: given the UAV path planning scheme and the fulfillment of stochastic requirements, maximizing the total service revenue of all requirements as the objective, and using constraints such as the inheritance of path planning schemes and task consistency as constraints, and solving for the optimal UAV path adjustment scheme. Specifically, this includes the following processes:

[0139] S601, the number of mission points passed through in the UAV's path adjustment plan is: ;

[0140] S602, the number of the kth transit point in the UAV path adjustment scheme is: ;

[0141] S603, the remaining energy for arrival and departure from the kth transit point in the UAV path adjustment scheme are respectively... and ;

[0142] S604, the arrival and departure times of the kth transit point in the UAV path adjustment scheme are respectively... and ;

[0143] The residual energy transfer equation for the S605 UAV is as follows:

[0144] (13);

[0145] (14);

[0146] In equations (13) and (14), ;

[0147] S606, The transfer equations for the arrival and departure times of the UAV are:

[0148] (15);

[0149] (16);

[0150] In equations (15) and (16), ;

[0151] S607. Constraints on the range of values ​​for the number of mission points traversed in the UAV path adjustment scheme:

[0152] (17);

[0153] S608. Constraints on the range of values ​​for the decision variable indicating the kth transit point in the UAV path adjustment scheme: (18);

[0154] S609, Duration Constraints for Planning Periods: (19);

[0155] S610. In the calculation path adjustment scheme, the number of deterministic requirements satisfied for task point i is:

[0156] (20);

[0157] S611. Inheritance constraint of path planning schemes: In a path adjustment scheme, the number of requirements satisfied by task points does not exceed the number of requirements satisfied by its path planning scheme. With randomness demand number Sum-of-Sum Constraints:

[0158] (twenty one);

[0159] S612. In the path adjustment scheme, the service benefit of task point i is calculated as follows:

[0160] (twenty two);

[0161] In equation (22), This represents the service benefit of task point i in the path adjustment scheme;

[0162] S613. Set the objective function to maximize the total service revenue of all demands:

[0163] (twenty three);

[0164] In equation (23), This represents the total service revenue from all demands;

[0165] S614. Summarize equations (13) to (23) to obtain the UAV path planning optimization model.

[0166] In another embodiment, this application employs an improved large-scale neighborhood search algorithm similar to that described above to solve the UAV path planning optimization model. The specific steps of the algorithm are as follows:

[0167] S701. Copy each task point several times. Among them, the task point numbered i is copied... share;

[0168] S702. Calculate the revenue of each task point after replication. Specifically, for task point i... The first copy The revenue from replication is , and after The first copy The revenue from replication is ;

[0169] S703. Calculate the unit-time yield of each task point after replication. ;

[0170] S704. While ensuring energy consumption constraints, arrange the flight sequence of UAVs in descending order of rate of return per unit time until the planned time period constraint is reached.

[0171] S705. Use the path generated in step S704 as the current solution;

[0172] S706. Calculate the objective function value under the current solution;

[0173] S707, using the number of removals is The random removal operator is used as a destruction operator to remove elements from the current solution. The copied task points are removed. In this embodiment, ;

[0174] S708, Number of repairs used They are respectively , and The optimal repair operator is used for repair;

[0175] S709. Calculate the objective function value under the three optimal repair operators with different repair numbers, and take the smallest one as the new solution.

[0176] S710. Calculate the difference between the minimum value of the objective function under the new solution and the current solution. ;

[0177] S711, if If the solution is correct, accept the new solution as the current solution; otherwise, return to step S707.

[0178] Steps S712, S707, and S711 constitute one iteration. When the iteration number reaches G, the current solution is output as the optimal path adjustment scheme for the UAV, and the entire algorithm ends. In this embodiment, .

[0179] Figure 5 This is a schematic diagram of the optimal path adjustment scheme for a drone in one embodiment, such as... Figure 5 As shown, in this embodiment, the maximum total service revenue for all demands can be calculated to be 22.37, and the following can be calculated: Figure 5 The diagram shows the optimal path adjustment scheme for the drone. The solid arrows indicate the drone's flight direction. If the path between two consecutive charging / battery swapping sessions is considered a single flight, then the optimal path scheme in this example contains three single flights. The numbers on the solid arrows indicate the order of these single flights.

[0180] Figure 6 This is a schematic diagram of the implementation process of the technical solution in one embodiment. See below for reference. Figure 6 The technical research process and other technical details of this application are described with reference to a specific embodiment.

[0181] In practical applications of drones, mission requirements often include both constant deterministic requirements and sudden, stochastic requirements. Drone flight control systems typically need to develop daily path planning schemes based on deterministic requirements, while adjusting these schemes to meet unexpected demands. Therefore, optimization studies are needed for the path planning and adjustment schemes in the aforementioned scenarios.

[0182] Based on this, this application provides a method for generating UAV path planning and adjustment schemes under mixed requirements, also known as a method for UAV path planning and adjustment under mixed requirements, as detailed below.

[0183] This application addresses scenarios where drones and smart airports are used to provide services to mission sites. The smart airport can charge / swap batteries for the drones, and the mission sites have both constant deterministic requirements throughout the planning period and stochastic requirements that are fulfilled at the beginning of each planning period.

[0184] When the randomness requirement is not met, this application proposes an optimization model for UAV path planning with the objective of maximizing the total service revenue of the deterministic requirement and constraints such as the planning period duration, and solves for the optimal UAV path planning scheme.

[0185] When the UAV path planning scheme is given and the randomness requirement has been met, this application also proposes a UAV path adjustment optimization model with the goal of maximizing the total service revenue of all requirements and constraints such as the inheritance of path planning scheme and task consistency, and solves the optimal UAV path adjustment scheme.

[0186] This application improves the service performance of smart airports and drone systems by optimizing path planning and path adjustment schemes in scenarios with mixed demands, and provides further guidance for the application of drones in fields such as surveillance, search, and the Internet of Things.

[0187] Figures 1 to 6 Any technical feature in the embodiments corresponding to any of the above items is also applicable to the embodiments of this application. Figures 7 to 9 The corresponding implementation examples will not be repeated hereafter.

[0188] The above describes a method for generating a UAV path planning and adjustment scheme under mixed requirements in the embodiments of this application. The following describes the apparatus or device for performing the above method.

[0189] Figure 7 This is a structural block diagram of a device for generating UAV path planning and adjustment schemes under mixed requirements in one embodiment, referring to... Figure 7 The device includes:

[0190] The parameter acquisition module 701 is used to acquire the initial model parameters required for the representation process of the target task scenario;

[0191] The first model construction module 702 is used to construct an UAV path planning optimization model based on the initial model parameters, with the goal of maximizing the total service revenue of the deterministic demand as the first objective function, when the stochastic demand is not met.

[0192] The first model solving module 703 is used to solve the UAV path planning optimization model based on the improved large-scale neighborhood search algorithm and generate the optimal path planning scheme for the UAV.

[0193] The second model construction module 704 is used to construct an UAV path planning adjustment model based on the initial model parameters, with the second objective function being to maximize the total service revenue of all requirements, given the optimal path planning scheme for the UAV and the fulfillment of stochastic requirements.

[0194] The second model solving module 705 is used to solve the UAV path planning adjustment model based on the improved large-scale neighborhood search algorithm and generate the optimal UAV path adjustment scheme.

[0195] In this embodiment of the application, based on, as follows Figure 7 The connections between the modules shown in the diagram demonstrate how the cooperation between these modules can improve the accuracy and rationality of UAV path planning.

[0196] In another embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, it includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the various methods described in the above embodiments.

[0197] In yet another embodiment, a computer device is provided, such as a terminal, whose internal structure diagram may be as follows: Figure 9As shown, it includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements the various methods described in the above embodiments.

[0198] Those skilled in the art will understand that Figure 8 and Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. It may also include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, in order to achieve functions such as a terminal or server.

[0199] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0200] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the systems, devices, equipment, modules or units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0201] In the embodiments provided in this application, it should be understood that the disclosed systems, devices, equipment, or methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or modules may be electrical, mechanical, or other forms.

[0202] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0204] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0205] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0206] The technical solutions provided in the embodiments of this application have been described in detail above. Specific examples have been used in the embodiments of this application to illustrate the principles and implementation methods of the embodiments of this application. The description of the above embodiments is only for the purpose of helping to understand the methods and core ideas of the embodiments of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments of this application. Therefore, the content of this specification should not be construed as a limitation on the embodiments of this application.

Claims

1. A method for generating a UAV path planning and adjustment scheme under mixed demand, characterized in that, The method comprises: acquiring initial model parameters required by a representation process of a target task scene; in a case where a randomness requirement is not implemented, taking maximization of total service benefits of deterministic requirements as a first objective function, and constructing a UAV path planning optimization model based on the initial model parameters; solving the UAV path planning optimization model based on an improved large-scale neighborhood search algorithm, and generating a UAV optimal path planning scheme; in a case where the UAV optimal path planning scheme is given and the randomness requirement is implemented, taking maximization of total service benefits of all requirements as a second objective function, and constructing a UAV path planning adjustment model based on the initial model parameters; solving the UAV path planning adjustment model based on the improved large-scale neighborhood search algorithm, and generating a UAV optimal path adjustment scheme.

2. The method of claim 1, wherein, The method comprises: calculating service benefits of deterministic requirements of any task point and satisfaction numbers of deterministic requirements of any task point; constructing the first objective function by taking maximization of total service benefits of deterministic requirements as a target according to the service benefits of deterministic requirements of any task point and the satisfaction numbers of deterministic requirements of any task point.

3. The method of claim 1, wherein, The method comprises: taking a value range constraint of a number of task points in a path planning scheme of a UAV, a value range constraint of a number decision variable of any task point of the UAV, a planning time period length constraint, and a constraint that a satisfaction number of deterministic requirements of a task point is not more than a deterministic requirement number of the task point as a first constraint condition; constructing the UAV path planning optimization model according to the first constraint condition and the first objective function.

4. The method of claim 1, wherein, The method comprises: copying each task point by a preset number of copies, calculating benefits of each copied task point, and calculating a unit time benefit rate of each copied task point; arranging a flight order of the UAV in a descending order of the unit time benefit rate while ensuring an energy consumption constraint, and until a planning time period constraint is reached; taking a corresponding generated path in the flight order of the UAV as a current solution, and calculating a target function value under the current solution; using a random removal operator with a removal number of n as a destruction operator to remove n copied task points in the current solution, and using a best repair operator to repair; calculating the target function value under the best repair operator with different repair numbers, taking a maximum of the target function values as a new solution, and calculating a difference between the target function values of the new solution and the current solution; in a case where the difference meets a preset condition, accepting the new solution as the current solution; and in a case where an iteration number reaches a preset number of times, outputting the current solution at this time as the UAV optimal path planning scheme.

5. The method of claim 1, wherein, The unmanned aerial vehicle path planning adjustment model is constructed based on the initial model parameters, including: The service revenue of the deterministic demand of any task point, the service revenue of the random demand of any task point, and the satisfaction number of the deterministic demand of any task point are calculated. The service revenue of any task point is determined according to the service revenue of the deterministic demand of any task point, the service revenue of the random demand of any task point, and the satisfaction number of the deterministic demand of any task point. The second objective function is constructed to maximize the total service revenue of all demands according to the service revenue of any task point.

6. The method of claim 1, wherein, The unmanned aerial vehicle path planning adjustment model is constructed based on the initial model parameters, including: The value range constraint of the number of task points in the path adjustment scheme of the unmanned aerial vehicle, the value range constraint of the number decision variable of any task point, the planning time period length constraint, and the constraint that the satisfaction number of the demand of a task point does not exceed the sum of the demand satisfaction number and the random demand number of the path planning scheme of the task point are taken as the second constraint condition. The unmanned aerial vehicle path planning adjustment model is constructed according to the second constraint condition and the second objective function.

7. The method of claim 1, wherein, The target task scenario is a scenario in which an unmanned aerial vehicle and an intelligent airport serve task points; the intelligent airport is used to provide charging or battery replacement services for the unmanned aerial vehicle, and the task points have constant deterministic demands in the entire planning range and random demands realized at the beginning of each planning time period.

8. A device for generating a UAV path planning and adjustment scheme under mixed requirements, characterized in that, The device includes: A parameter acquisition module is configured to acquire initial model parameters required by a representation process of a target task scenario. A first model construction module is configured to construct an unmanned aerial vehicle path planning optimization model based on the initial model parameters, with the total service revenue of deterministic demands maximized as a first objective function in the case where random demands are not realized. A first model solving module is configured to solve the unmanned aerial vehicle path planning optimization model based on an improved large-scale neighborhood search algorithm to generate an optimal unmanned aerial vehicle path planning scheme. A second model construction module is configured to construct an unmanned aerial vehicle path planning adjustment model based on the initial model parameters, with the total service revenue of all demands maximized as a second objective function in the case where the optimal unmanned aerial vehicle path planning scheme is given and random demands are realized. A second model solving module is configured to solve the unmanned aerial vehicle path planning adjustment model based on the improved large-scale neighborhood search algorithm to generate an optimal unmanned aerial vehicle path adjustment scheme.

9. A computer device, comprising: The computer device includes: At least one processor and a memory; The memory is configured to store program code, and the processor is configured to call the program code stored in the memory to execute the method in any one of claims 1 to 7.

10. A computer storage medium, characterized in that The program product includes instructions that, when executed on a computer, cause the computer to execute the method in any one of claims 1 to 7.

Images