Unmanned aerial vehicle three-dimensional path planning method and system based on multi-strategy improved black wing plinary optimization algorithm

Abstract

The invention discloses an unmanned aerial vehicle three-dimensional path planning method and system based on a multi-strategy improved black-wing optimization algorithm, and the method comprises the steps: generating an initial population through a Latin hypercube sampling method, thereby improving the distribution uniformity and diversity of the population; an adaptive weight factor is introduced to realize dynamic balance of exploration and development capabilities; meanwhile, a dynamic reverse learning strategy is combined, so that the global search capability is effectively enhanced, and premature convergence is avoided; the algorithm performance is further improved by fusing a warning person position updating formula in a sparrow search algorithm. The method is used for solving the problems that a traditional path planning problem is prone to falling into local optimum, the convergence speed is low, and the path is unstable. And a shorter and safer optimal flight path can be efficiently planned.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle path planning, and particularly relates to a three-dimensional path planning method and system for unmanned aerial vehicles based on a multi-strategy improved black kite optimization algorithm. BACKGROUND

[0002] Unmanned aerial vehicles (UAVs) have been widely used in modern society due to their flexible maneuverability, high autonomy, low cost and good scalability. Whether in military fields such as reconnaissance, attack and battlefield management, or in civil fields such as power line inspection, agricultural plant protection and disaster rescue, UAVs play an irreplaceable role. These applications show that UAVs have significantly expanded the scope and boundaries of human activities. In many application scenarios, path planning has always been the core technology of the UAV mission planning system, and its main goal is to generate a feasible flight path from the starting point to the target point while meeting various constraint conditions such as terrain, threat areas and obstacles. The quality of flight path planning directly determines whether the UAV can successfully complete the assigned task. In the actual environment, obstacles divide the flight area into multiple spaces, making path planning a combined optimization problem with nonlinearity and multiple constraints. As the problem size increases, its complexity grows exponentially, making it extremely difficult to find the optimal path.

[0003] Black kite optimization algorithm (BKA) is a new meta-heuristic algorithm inspired by the migratory foraging behavior of black kite. Due to its simple structure, strong performance and strong adaptability, it has been widely used in various fields. However, according to the NFL theory, each algorithm has its applicable scenarios and limitations. When facing the complex combined optimization problem of UAV trajectory planning, the traditional black kite optimization algorithm (BKA) may fall into local optimum, slow convergence, and lack of population diversity. From a theoretical point of view, as a new algorithm, black kite optimization algorithm (BKA) is still in its early stages of development, and its algorithm architecture and parameter optimization mechanism need to be further studied. SUMMARY

[0004] The present application provides a three-dimensional path planning method and system for unmanned aerial vehicles based on a multi-strategy improved black kite optimization algorithm to overcome the defects of the prior art.

[0005] To achieve the above application purposes, the technical solutions adopted by the present application are as follows:

[0006] A three-dimensional path planning method for unmanned aerial vehicles based on a multi-strategy improved black kite optimization algorithm, comprising the following steps:

[0007] S1, constructing a three-dimensional space model of the UAV flight environment: using a real digital elevation model to construct the terrain, and using a cylindrical model to represent the threat obstacles, and setting the starting point and the end point of the UAV;

[0008] S2, construct a target function of the UAV path planning, the target function integrates a flight distance constraint cost F l , a flight height constraint cost F h , a threat constraint cost F t , and a smoothness constraint cost F s , and the expression is:

[0009] F = α1F l + α2F h + α3F t + α4F s

[0010] Wherein, α i is the weight coefficient of each constraint, i = 1, 2, 3, 4;

[0011] S3, solve the path planning problem by multi-strategy improved black-winged kite optimization algorithm, including:

[0012] The Latin hypercube sampling method is used to initialize the population;

[0013] An adaptive weight factor is introduced to dynamically adjust the exploration and exploitation weights;

[0014] A dynamic reverse learning strategy is used to enhance the population diversity;

[0015] The sparrow search algorithm is used to update the population;

[0016] S4, output the optimal path: select the individual that meets all the constraint conditions and has the highest fitness value to construct the optimal flight path.

[0017] Further, in the step S2:

[0018] The calculation formula of the flight distance constraint cost F l is:

[0019]

[0020] Wherein, P i and P i+1 represent the i-th waypoint and the i+1-th waypoint respectively; Xi and Yi are the x-axis and y-axis coordinate values of the i-th waypoint respectively; and N is the total number of waypoints.

[0021] The calculation formula of the flight height constraint cost F h is:

[0022]

[0023] Wherein, h min and h maxRespectively represent the minimum flight altitude and maximum flight altitude of the UAV; h i Indicates that the drone is at two waypoints (P i ,P i+1 ) between the two track points; N is the total number of track points.

[0024] Threat constraint cost F t The calculation formula is:

[0025]

[0026] Where M represents the set of all threatening obstacles, and each threat is limited to a radius of R M In the cylinder, D represents the diameter of the drone; S represents the safety buffer zone; d M Indicates the vertical distance from the drone to the center of the cylinder;

[0027] Stationarity constraint cost F s The calculation formula is:

[0028]

[0029] in, is the steering angle, σ i is the pitch angle, λ1,λ2 are penalty coefficients.

[0030] Furthermore, is the steering angle, σ i The calculation formula for the pitch angle is as follows:

[0031]

[0032] in, Indicates waypoint P i to P i+1 The horizontal projection vector of Indicates waypoint P i+1 to P i+2 The horizontal projection vector, z i+1 -z i Indicates the altitude difference between adjacent waypoints.

[0033] Furthermore, the specific steps of initializing the population using the Latin Hypercube sampling method are as follows:

[0034] Step 1: Determine the population size N;

[0035] Step 2: The domain interval (S lb ,S ub ) is evenly divided into N subintervals;

[0036] Step3: generate a random full permutation matrix A of N rows and D columns, each column in A is a random permutation of {1, 2, …, N};

[0037] Step4: each row in matrix A corresponds to a hypercube. By sampling in each hypercube, N population individuals with significant differences can be generated.

[0038] Further, the expression of the adaptive weight factor Φ is:

[0039] Φ = Φ min +(Φ max -Φ min )×(t / T)

[0040] Wherein, Φ min and Φ max are constants, t is the current iteration number, and T is the maximum iteration number.

[0041] Further, the formula of the dynamic reverse learning strategy to generate the reverse solution is:

[0042]

[0043] Wherein respectively represent the minimum value and the maximum value of the jth dimension of the population at the tth iteration.

[0044] Further, the position updating formula of the sparrow search algorithm alarm is:

[0045]

[0046] Wherein, δ and ω are random numbers; ε is a constant; Represents the fitness value of the ith black-winged kite at the tth iteration; And respectively represent the fitness value of the population optimal individual and the worst individual.

[0047] Further, the construction condition of the optimal path in step S4 is: under the premise of meeting the flight distance constraint, flight height constraint, threat constraint and stability constraint, the path is generated by selecting the individual position sequence with the highest fitness value.

[0048] The application also discloses a UAV three-dimensional path planning system, which can be used to implement the UAV three-dimensional path planning method.

[0049] The environment modeling module is used for constructing a three-dimensional space model of a UAV flight path environment, generating terrain data through a real digital elevation model, adopting a cylinder model to represent a threat obstacle, and setting a UAV flight starting point and ending point coordinate parameter.

[0050] The objective function construction module is configured to generate a comprehensive objective function for UAV path planning.

[0051] The path optimization solving module is used for integrating a multi-strategy improved black-winged kite optimization algorithm engine, including:

[0052] The population initialization unit is used for executing a Latin hypercube sampling method to generate an initial solution set.

[0053] The adaptive balance unit adopts a dynamic weight factor to adjust the exploration and development weight.

[0054] The diversity enhancement unit implements a dynamic reverse learning strategy to update the population.

[0055] The position updating unit applies a peregrine falcon search algorithm sentry formula to drive iterative evolution.

[0056] The path output module is used for screening a highest fitness solution meeting all constraint conditions to generate a three-dimensional space optimal flight path coordinate sequence.

[0057] The application further discloses a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the UAV three-dimensional path planning method when executing the program.

[0058] The application further discloses a computer readable storage medium, which stores a computer program, and the program is executed by the processor to implement the UAV three-dimensional path planning method.

[0059] Compared with the prior art, the application has the following advantages:

[0060] 1. The three-dimensional space model is constructed by using real geographic elevation data, the complex terrain features and obstacle distribution are accurately restored, the problem of insufficient path practicability caused by the simplified model in the traditional simulation environment is effectively solved, the planning result is closer to the actual flight scene demand, and the engineering application value of the path planning is greatly improved.

[0061] 2. Four improved mechanisms are innovatively integrated to form a technical closed loop: the Latin hypercube sampling ensures the global coverage ability of the population, the adaptive weight factor realizes dynamic optimization balance, the dynamic reverse learning maintains the evolution vitality of the population, and the peregrine falcon alert strategy enhances the local optimization efficiency. The four technical linkages significantly improve the defects of the traditional algorithm, such as premature convergence and low optimization efficiency.

[0062] 3. Excellent performance in various complex terrain tests: the total length of the generated flight path is shortened by more than 12% on average, the number of turns is reduced by nearly 40%. The path smoothness index is improved by more than 30%, completely solving the problems of path redundancy and abrupt turning of traditional methods, greatly reducing the energy consumption and time cost of unmanned aerial vehicle flight.

[0063] 4. The improved optimization algorithm has a convergence speed that is 58% higher than the traditional black-winged kite algorithm, and the iteration efficiency is nearly doubled. Under the same computing resource conditions, the optimization accuracy is improved by more than 24%, providing strong technical support for real-time path planning.

[0064] 5. Through multi-dimensional constraint condition modeling and smoothness optimization mechanism, zero violation is realized in key indicators such as threat avoidance and height control. The path safety passing rate is 100% in six types of extreme terrain tests, significantly enhancing the task reliability in complex environments. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 A flowchart of the three-dimensional path planning method for unmanned aerial vehicles based on the multi-strategy improved black-winged kite optimization algorithm of the present application;

[0066] Figure 2 A population space distribution diagram generated by the Latin hypercube sampling method initialization;

[0067] Figure 3 A trend graph showing that the adaptive weight factor dynamically changes with the increase of the number of iterations in the algorithm iteration process;

[0068] Figure 4 A schematic diagram of six different terrain scenarios shown in the embodiment of the present application;

[0069] Figure 5 A front view of the path planning comparison of each algorithm in six different terrain scenarios in the embodiment of the present application;

[0070] Figure 6 A top view of the path planning comparison of each algorithm in six different terrain scenarios in the embodiment of the present application;

[0071] Figure 7 A convergence curve graph of the path planning comparison of each algorithm in six different terrain scenarios in the embodiment of the present application;

[0072] Figure 8 An algorithm parameter configuration graph in the embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the following will be further described in detail according to the drawings and examples.

[0074] The present applicationFigure 1 As shown, the application provides a method for three-dimensional path planning of unmanned aerial vehicles based on a multi-strategy improved black kite optimization algorithm, comprising:

[0075] Step 1: Initialize the basic parameters of the algorithm, the maximum number of iterations T, the search dimension D, and the population size N;

[0076] Step 2: Initialize the population using the Latin hypercube sampling method;

[0077] Step 3: Calculate the fitness value of the population and record the optimal individual as the population leader;

[0078] Step 4: Use the dynamic reverse learning strategy to disturb the population and increase the diversity of solutions;

[0079] Step 5: Initialize the adaptive weight factor to achieve a dynamic balance between exploration and exploitation capabilities;

[0080] Step 6: Update the individual position using the lookout position update strategy of the sparrow search algorithm;

[0081] Step 7: Recalculate the fitness value of the population and update the optimal individual position;

[0082] 1. Principle of black kite optimization algorithm

[0083] (1) Attack behavior

[0084] Black kites inhabit open plains and exhibit two distinct attack behaviors. The first is hovering attack, which the black kite optimization algorithm simulates the behavior of black kites hovering in the air to lock in prey. The second is diving attack, which the black kite optimization algorithm simulates the behavior of black kites diving at high speed to capture prey. Its mathematical model can be defined as follows:

[0085]

[0086] In the formula: represents the position of the i-th black kite at the t-th iteration; Q is a constant with a default value of 0.9; r is a random quantity uniformly distributed in (0, 1); t is the current iteration number; T is the upper limit threshold set by the algorithm for iterations.

[0087] (2) Migration behavior

[0088] The black kite optimization algorithm simulates the migration behavior of the black kite population. In the black kite optimization algorithm, once a better individual appears, that individual becomes the new leader, leading the population to migrate. By constantly updating the leader, the population can more flexibly respond to environmental changes, significantly improving the success rate of population migration. Its mathematical model can be defined as follows:

[0089]

[0090] C(0,1) represents Cauchy mutation; is the leader of the tth iteration; and respectively represent the fitness value of the ith black-winged kite and the fitness value of any black-winged kite during the tth iteration.

[0091] 2. Black-winged kite optimization algorithm based on multi-strategy improvement

[0092] When the traditional black-winged kite optimization algorithm algorithm faces the complex combinatorial optimization problem of unmanned aerial vehicle trajectory planning, problems such as easy to fall into local optimum, slow convergence speed, and insufficient population diversity may occur. From a theoretical point of view, as a new algorithm, the black-winged kite optimization algorithm is still in its early stages of development, and its algorithm architecture and parameter optimization mechanism need to be further studied. Therefore, in order to make the black-winged kite optimization algorithm algorithm better applicable to the field of unmanned aerial vehicle trajectory planning, the present application proposes a three-dimensional path planning method for unmanned aerial vehicles based on a multi-strategy improved black-winged kite optimization algorithm.

[0093] (1) Latin hypercube sampling method

[0094] The Latin hypercube sampling method is used to initialize the population, and the steps are as follows:

[0095] Step 1: Determine the population size N;

[0096] Step 2: Divide the definition domain interval (S lb ,S ub ) corresponding to the solution space into N subintervals on average;

[0097] Step 3: Generate a random full permutation matrix A of N rows and D columns, and each column in A is a random permutation of {1, 2, …, N};

[0098] Step 4: Each row in matrix A corresponds to a hypercube. By sampling in each hypercube, N population individuals with significant differences can be generated;

[0099] Figure 2 The population space distribution diagram generated by the Latin hypercube sampling method is given. As can be seen from the figure, the individuals generated by the Latin hypercube sampling method can be uniformly distributed in the search space. Therefore, using the Latin hypercube sampling method to initialize the population can effectively improve the population diversity and global search ability.

[0100] (2) Adaptive weight factor

[0101] An adaptive weight factor is introduced to control the exploration and exploitation behavior of the black-winged kite population, and the mathematical expression of the adaptive weight factor is as follows:

[0102] Φ = Φ min + (Φ max - Φ min ) x (t / T)

[0103] In the formula: Φ min and Φ max are constants, which are set to 0.4 and 0.9 respectively in the application.

[0104] Figure 3 The adaptive weight factor presents a dynamic adjustment trend with the increase of the number of algorithm iterations.

[0105] (3) Dynamic reverse learning

[0106] The dynamic reverse learning can further enhance the diversity of the solution of the black-winged kite optimization algorithm and avoid premature convergence.

[0107]

[0108] Wherein represents the initial solution of the jth dimension of the ith black-winged kite individual at the tth iteration; is its reverse solution.

[0109] At the same time, the boundary adopts a dynamic boundary, that is:

[0110]

[0111] Wherein a and b represent the minimum value and maximum value of the jth dimension in the black-winged kite population at the tth iteration.

[0112] (4) Using the alarm position updating strategy of sparrow search algorithm to optimize the black-winged kite optimization algorithm

[0113] The application introduces the alarm position updating strategy in the sparrow search algorithm into the black-winged kite optimization algorithm to replace the original migration behavior.

[0114]

[0115] In the formula: δ and ω are both random numbers; ε is a constant; represents the fitness value of the ith black-winged kite at the tth iteration; and respectively represent the fitness values of the population optimal individual and the worst individual.

[0116] 3. Adopting the black-winged kite optimization algorithm based on multi-strategy improvement to carry out three-dimensional path planning of unmanned aerial vehicle

[0117] (1) Establishing objective function

[0118] In the optimization of UAV path, the objective function is the key basis for measuring the pros and cons of the path, and needs to consider multiple aspects such as flight efficiency, safety and task feasibility. Based on this, the objective function constructed by the application integrates multiple cost indicators such as distance, flight height, threat avoidance and smoothness, so as to realize comprehensive evaluation of path performance.

[0119] (2) Scene setting

[0120] The application adopts the actual terrain data of Christmas Island in Australia as the experimental scene, and the data is derived from a publicly available true digital elevation model. In order to simulate the difference in terrain complexity, the application adopts a cylindrical model to represent various types of threat obstacles. On the basis of the UAV path planning objective function established in (1), the application selects six kinds of terrain scenes shown in the drawings to carry out simulation experiments on the black kite optimization algorithm based on multi-strategy improvement. Figure 4

[0121] (3) Simulation experiment

[0122] The application compares the black kite optimization algorithm based on multi-strategy improvement with other eight classical algorithms. These classical algorithms include BKA, COA, RIME, WOA, GWO, SSA, HHO and PSO. Figure 8 The important parameters of these algorithms are given.

[0123] Figure 5 And Figure 6 The three-dimensional simulation graphs and top views of the black kite optimization algorithm based on multi-strategy improvement and the other eight algorithms under the six kinds of terrain scenes are respectively given. It can be seen that all the algorithms can plan a feasible flight path that meets the requirements of obstacle avoidance, flight range limitation and other constraints. However, under various terrain conditions, BKA, SSA, COA, PSO, WOA and HHO all have different degrees of path redundancy phenomenon, and cannot find the optimal flight path, thereby causing additional consumption of flight resources. At the same time, although RIME and GWO can generate relatively optimal feasible paths, the flight routes planned by them have the problems of too many turns and too large turning angles, which are also easy to cause the consumption of additional energy and time resources of the UAV in the flight process. In comparison, the flight path generated by the black kite optimization algorithm based on multi-strategy improvement is not only shorter, but also smoother, which shows that it has better performance in path planning.

[0124] Figure 7 The convergence curves of the black kite optimization algorithm based on multi-strategy improvement intuitively show the advantages of the algorithm compared with other algorithms. In most scenarios, the black kite optimization algorithm based on multi-strategy improvement always finds the optimal solution with faster convergence speed and higher convergence accuracy, which reflects its excellent optimization ability and stability.

[0125] ​In still another embodiment of the present application, a UAV three-dimensional path planning system is provided, which can be used to implement the UAV three-dimensional path planning method described above, and specifically comprises:

[0126] The environment modeling module is configured to construct a three-dimensional space model of the UAV flight path environment, generate terrain data through a real digital elevation model, use a cylinder model to represent threat obstacles, and set the starting point and ending point coordinates of the UAV flight.

[0127] The objective function construction module is configured to generate a comprehensive objective function for UAV path planning.

[0128] The path optimization solving module is configured to integrate a multi-strategy improved black-winged kite optimization algorithm engine, which comprises:

[0129] The population initialization unit is configured to generate an initial solution set by using a Latin hypercube sampling method.

[0130] The adaptive balance unit is configured to adjust the exploration and exploitation weights by using a dynamic weight factor.

[0131] The diversity enhancement unit is configured to update the population by implementing a dynamic reverse learning strategy.

[0132] The position updating unit is configured to drive iterative evolution by using a peregrine falcon search algorithm sentry formula.

[0133] The path output module is configured to filter the highest fitness solution that satisfies all constraint conditions and generate a three-dimensional space optimal flight path coordinate sequence.

[0134] In still another embodiment of the present application, a terminal device is provided, which comprises a processor and a memory, the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function. The processor described in the embodiments of the present application can be used for the operation of the UAV three-dimensional path planning method.

[0135] In another embodiment of the present application, a storage medium, specifically a computer readable storage medium (Memory) is provided, which is a memory device in the terminal equipment, used to store programs and data. It can be understood that the computer readable storage medium herein can include the built-in storage medium in the terminal equipment, and of course can also include the expansion storage medium supported by the terminal equipment. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. Moreover, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, which can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory.

[0136] The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for three-dimensional path planning of the unmanned aerial vehicle in the above embodiments; the one or more instructions in the computer readable storage medium are loaded and executed by the processor.

[0137] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0138] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The means for implementing the functions specified in one or more flows and / or blocks.

[0139] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0141] Those skilled in the art will realize that the embodiments described herein are for illustrative purposes only and that various modifications and changes in light thereof will be apparent to those skilled in the art without departing from the scope and spirit of the application. It is therefore understood that this application can encompass all such modifications and changes as fall within the scope of the appended claims.

Claims

1. A three-dimensional path planning method for unmanned aerial vehicles based on a multi-strategy improved black kite optimization algorithm, characterized in that: The following steps are involved: S1. Construct a 3D spatial model of the drone's trajectory environment: Use a real digital elevation model to construct the terrain, use a cylindrical model to represent threatening obstacles, and set the drone's starting and ending points; S2. Construct an objective function for the UAV path planning, which integrates the flight length constraint cost F l , flight altitude constraint cost F h , threat constraint cost F t and the stationarity constraint cost F s , the expression is: F=α1F l +α2F h +α3F t +α4F s Among them, α i is the weight coefficient of each constraint, i=1,2,3,4; S3. Solve the path planning problem by improving the Black Kite optimization algorithm through multiple strategies, including: The population is initialized using Latin hypercube sampling; Introducing adaptive weight factors to dynamically adjust the exploration and development weights; Adopting dynamic reverse learning strategy to enhance population diversity; Update the population using the sentinel position update formula of the sparrow search algorithm; S4. Output the optimal path: Select the individual that meets all constraints and has the highest fitness value to construct the optimal flight path.

2. The method for three-dimensional path planning of a UAV according to claim 1, characterized in that: In the step S2: Flight length constraint cost F l The calculation formula is: Among them, P i and P i+1 Represent the i-th waypoint and the i+1-th waypoint respectively; are the x-axis, y-axis, and coordinate values ​​of the i-th waypoint respectively; N is the total number of track points; Flight altitude constraint cost F h The calculation formula is: Among them, h min and h max Respectively represent the minimum flight altitude and maximum flight altitude of the UAV; h i Indicates that the drone is at two waypoints (P i ,P i+1 ) is the relative height above the ground between them; N is the total number of track points; Threat constraint cost F t The calculation formula is: Where M represents the set of all threatening obstacles, and each threat is limited to a radius of R M In the cylinder, D represents the diameter of the drone; S represents the safety buffer zone; d M Indicates the vertical distance from the drone to the center of the cylinder; Stationarity constraint cost F s The calculation formula is: in, is the steering angle, σ i is the pitch angle, λ1,λ2 are penalty coefficients.

3. The method for three-dimensional path planning of an unmanned aerial vehicle according to claim 2, wherein: is the steering angle, σ i The calculation formula for the pitch angle is as follows: in, Indicates waypoint P i to P i+1 The horizontal projection vector of Indicates waypoint P i+1 to P i+2 The horizontal projection vector, z i+1 -z i Indicates the altitude difference between adjacent waypoints.

4. The method according to claim 1, wherein The specific steps of initializing the population using the Latin Hypercube sampling method are: Step 1: Determine the population size N; Step 2: The domain interval (S lb ,S ub ) is evenly divided into N subintervals; Step 3: Generate a random full permutation matrix A with N rows and D columns, where each column in A is a random permutation of {1, 2, …, N}; Step 4: Each row in the matrix A corresponds to a hypercube; by sampling in each hypercube, N population individuals with significant differences can be generated.

5. The method according to claim 1, wherein The expression of the adaptive weight factor Φ is: F=F min +(Φ max -F min )×(t / T) Among them, Φ min and Φ max are all constants, t is the current number of iterations, and T is the maximum number of iterations.

6. The method according to claim 1, characterized in that The dynamic reverse learning strategy generates a reverse solution The formula is: in They represent the minimum and maximum values ​​of the j-th dimension of the population at the t-th iteration respectively.

7. The method according to claim 1, characterized in that The sentinel position update formula of the sparrow search algorithm is: Among them, δ and ω are random numbers; ε is a constant; represents the fitness value of the i-th black-winged kite at the t-th iteration; and They represent the fitness values ​​of the best and worst individuals in the population respectively.

8. The method according to claim 1, characterized in that The optimal path construction condition in step S4 is: under the premise of simultaneously satisfying the flight length constraint, the flight altitude constraint, the threat constraint and the stability constraint, the individual position sequence with the highest fitness value is selected to generate the path.

9. A three-dimensional path planning system for an unmanned aerial vehicle, characterized by: The system can be used to implement the three-dimensional path planning method for a UAV according to any one of claims 1 to 8, specifically comprising: The environment modeling module is used to construct a three-dimensional spatial model of the UAV's trajectory environment, generate terrain data through a real digital elevation model, use a cylindrical model to represent threatening obstacles, and set the coordinate parameters of the UAV's flight start and end points; The objective function building module is configured to generate a comprehensive objective function for UAV path planning; The path optimization solution module is used to integrate the multi-strategy improved Black Kite optimization algorithm engine, including: Population initialization unit: executes Latin hypercube sampling method to generate initial solution set; Adaptive balancing unit: uses dynamic weight factors to adjust the exploration and development weights; Diversity enhancement unit: implements dynamic reverse learning strategy to update the population; Position update unit: Apply the sparrow search algorithm and the vigilant formula to drive iterative evolution; The path output module is used to screen the highest fitness solution that meets all constraints and generate the optimal flight path coordinate sequence in three-dimensional space.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, which, when executed by a processor, implements the three-dimensional path planning method for a drone as described in one of claims 1 to 8.

Images