Three-dimensional unmanned aerial vehicle path planning method based on improved grey wolf optimization algorithm

Abstract

The invention relates to a three-dimensional unmanned aerial vehicle path planning method based on an improved grey wolf optimization algorithm, and the method comprises the steps: obtaining a three-dimensional environment model, setting a starting point position and an end point position of an unmanned aerial vehicle according to the three-dimensional environment model, employing the improved grey wolf optimization algorithm, forming a fitness function through a target function, and carrying out the optimization of the fitness function. And synchronously updating the positions of all grey wolf individuals in an iteration process, and outputting an optimal path. According to the method, circle chaotic mapping is introduced into a grey wolf optimization algorithm to increase population diversity; a self-adaptive exploration factor is introduced to increase the balance between global search and local search of the algorithm; by combining global and local development formulas of a dung beetle optimization algorithm, the defect that a traditional grey wolf optimization algorithm is low in convergence speed is overcome; then introducing a sine and cosine strategy to help the algorithm search a potential optimal solution area so as to better explore a global optimal solution; and finally, a pooling mechanism is introduced to randomly recombine and generate a new solution by storing historical poorer solutions, so that the convergence speed of the algorithm is accelerated, and the robustness of the algorithm is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) path planning, and particularly to a three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm. Background Art

[0002] In recent years, UAV technology has been increasingly popular in military, civilian, and commercial fields, covering various scenarios such as disaster relief, agricultural monitoring, and logistics distribution. Path planning is one of the core issues in UAV autonomous navigation. Especially in a complex three-dimensional environment, how to efficiently and safely plan an optimal path has become an extremely challenging task.

[0003] Traditional path planning methods (such as the A* algorithm and Dijkstra algorithm) perform well in two-dimensional scenarios, but have a high computational complexity in three-dimensional environments and are difficult to handle dynamic obstacles and complex terrains, often failing to meet the requirements of real-time performance and accuracy. In addition, traditional algorithms are prone to falling into computational bottlenecks and having low planning efficiency when facing a large-scale search space. To overcome these limitations, path planning methods based on intelligent optimization algorithms (such as genetic algorithms and particle swarm optimization algorithms) have gradually become a research hotspot in recent years. The grey wolf optimization algorithm (GWO) is a new swarm intelligence optimization algorithm that has received extensive attention in recent years due to its advantages such as fast convergence speed and simple parameter settings. However, although the grey wolf optimization algorithm performs well in simple optimization problems, it still has deficiencies in dealing with complex problems, and its convergence accuracy and stability need to be further improved. There are problems of local optimal solutions and insufficient convergence accuracy in dealing with complex three-dimensional path planning problems. Summary of the Invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm to improve the search ability, convergence accuracy, and obstacle avoidance ability of three-dimensional path planning. The present invention plans a fitness function from aspects such as path length, altitude change, and smoothness during the flight of the UAV, and combines the grey wolf optimization algorithm to optimize the path.

[0005] To achieve the above purpose, the present invention provides the following solution:

[0006] A three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm, comprising:

[0007] Obtain a three-dimensional environment model, set the starting position and ending position of the UAV according to the three-dimensional environment model, adopt the improved grey wolf optimization algorithm, form a fitness function with the objective function, synchronously update the positions of all grey wolf individuals during the iteration process, and output the optimal path; the objective function includes: path length, altitude change, smoothness, and a penalty term;

[0008] Outputting the optimal path using the improved grey wolf optimization algorithm includes:

[0009] Step 1: Initialize the population using the circle chaotic mapping to generate an initial path;

[0010] Step 2: Calculate the fitness value of the initial path according to the fitness function;

[0011] Step 3: Replace the contraction coefficient of the grey wolf optimization algorithm with an adaptive exploration factor, update the positions of the grey wolf population. During the process of updating the positions of the grey wolf population, introduce the global and local search mechanism dynamic adjustment mechanism of the dung beetle optimization algorithm to balance global exploration and local exploration, introduce the sine-cosine optimization strategy to jump out of local extrema during the optimization process, introduce a pooling mechanism to store poor solutions, and reuse the above poor solutions in subsequent iterations;

[0012] Step 4: Calculate the fitness value of the current position of the grey wolf population according to the fitness function;

[0013] Step 5: Determine whether the maximum iteration condition is satisfied. If the maximum iteration condition is not satisfied, repeat Steps 1 - 4 until the maximum iteration condition is satisfied. If the maximum iteration condition is satisfied, output the optimal path.

[0014] Optionally, the components of the fitness function include:

[0015] L = (ω 1 ·J path +ω 2 ·J hight +ω 3 ·J smooth ) + Violation·p f

[0016] Where ω 1 、ω 2 and ω 3 are weights, J path is the path length, J hight is the height change, J smooth is the smoothness, p f is the penalty factor, and Violation is the violation term.

[0017] Optionally, initializing the population using the circle chaotic mapping includes:

[0018]

[0019] Where Positions i+1 is the mapped position, Positions iis the original position, i represents the dimension, and both a and b are natural numbers.

[0020] Optionally, the expression of the adaptive exploration factor is:

[0021]

[0022] where l is the number of iterations and Max_iter is the maximum number of iterations.

[0023] Optionally, replacing the contraction coefficient of the Grey Wolf Optimization Algorithm with the adaptive exploration factor includes:

[0024] A = 2a·r 1 -a

[0025] C = 2r 2

[0026] where C and A are coefficient vectors, r 1 and r 2 are random vectors in [0, 1].

[0027] Optionally, updating the positions of the Grey Wolf population includes:

[0028]

[0029] where D α , D β , D δ respectively represent the distances between α, β, and δ and other individuals, l is the current number of iterations, C 1 , C 2 , C 3 are coefficient vectors, Positions α , Positions β , Positions δ are the position vectors of the α, β, and δ wolves in the current population, and Positions(l) is the individual position vector of the Grey Wolf at the l-th iteration;

[0030]

[0031] Positions(l + 1) = (Positions 1 + Positions 2 + Positions 3 ) / 3

[0032] where Position 1 , Position 2 , Position 3 are the position update vectors guided by the α, β, and δ wolves.

[0033] Optionally, introducing the global and local search mechanism dynamic adjustment mechanism of the dung beetle optimization algorithm to balance global exploration and local exploration includes:

[0034]

[0035] Among them, Alpha_pos is the current optimal solution, Worse_pos is the worse solution, Delta_pos is the sub-optimal solution, a is a random coefficient, 0.3 and 0.1 are weight coefficients, θ is a random angle, and tan(θ) is the generated random step size, r 1 is a random factor.

[0036] Optionally, introducing the sine-cosine optimization strategy to jump out of local extrema during the optimization process includes:

[0037]

[0038] Among them, ω is the dynamic inertia weight, r 2 is the random angle factor; r 3 is the random factor, Alpha_pos is the position of the current optimal solution, is the position of the i-th gray wolf at the l-th iteration in the j-th dimension.

[0039] Optionally, introducing the pooling mechanism to store the worse solutions includes:

[0040] P = B × X brnd +(1 - B) × X worst

[0041] Among them, P is the matrix used to store the worse solutions in the pooling mechanism, B is a randomly generated binary matrix, and X brnd is the position randomly generated based on the current optimal solution; X worst is the worse solution in the current iteration.

[0042] The beneficial effects of the present invention are:

[0043] The present invention plans the fitness function in terms of the path length, altitude change, smoothness, etc. during the flight of the drone, and combines the gray wolf optimization algorithm for path optimization. The present invention introduces circle chaotic mapping into the gray wolf optimization algorithm to increase the population diversity; introduces an adaptive exploration factor to increase the balance between the global search and local search of the algorithm; combines the global and local exploitation formulas of the dung beetle optimization algorithm to make up for the deficiency of the slow convergence speed of the traditional gray wolf optimization algorithm and balance the exploration and exploitation of the algorithm; then introduces the sine-cosine strategy to help the algorithm search for potential optimal solution regions to better explore the global optimal solution; finally, introduces the pooling mechanism, which generates new solutions by storing historical worse solutions and randomly recombining them, accelerating the algorithm convergence speed and improving the algorithm robustness. Brief Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 It is a flowchart of a three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm according to an embodiment of the present invention;

[0046] Figure 2 It is a three-dimensional environment simulation diagram according to an embodiment of the present invention;

[0047] Figure 3 It is a contour path diagram of the original grey wolf algorithm and the improved grey wolf algorithm according to an embodiment of the present invention;

[0048] Figure 4 It is a three-dimensional path diagram of the original grey wolf algorithm and the improved grey wolf algorithm according to an embodiment of the present invention;

[0049] Figure 5 It is a fitness function curve of the original grey wolf algorithm and the improved grey wolf algorithm according to an embodiment of the present invention. Detailed Description of the Embodiments

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0051] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0052] This embodiment discloses a three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm, including:

[0053] Obtain a three-dimensional environment model, set the starting position and ending position of the UAV according to the three-dimensional environment model, adopt the improved grey wolf optimization algorithm, form a fitness function with the objective function, synchronously update the positions of all grey wolf individuals during the iteration process, and output the optimal path; the objective function includes: path length, altitude change, smoothness, and penalty term;

[0054] Outputting the optimal path by using the improved grey wolf optimization algorithm includes:

[0055] Step 1: Initialize the population using the circle chaotic map to generate an initial path.

[0056] Step 2: Calculate the fitness value of the initial path according to the fitness function.

[0057] Step 3: Replace the contraction coefficient of the grey wolf optimization algorithm with an adaptive exploration factor to update the positions of the grey wolf population. During the process of updating the positions of the grey wolf population, introduce the global and local search mechanism dynamic adjustment mechanism of the dung beetle optimization algorithm to balance global exploration and local exploration, introduce the sine-cosine optimization strategy to jump out of local extrema during the optimization process, introduce a pooling mechanism to store the worse solutions, and reuse the above-mentioned worse solutions in subsequent iterations.

[0058] Step 4: Calculate the fitness value of the current positions of the grey wolf population according to the fitness function.

[0059] Step 5: Determine whether the maximum iteration condition is satisfied. If the maximum iteration condition is not satisfied, repeat Steps 1 - 4 until the maximum iteration condition is satisfied. If the maximum iteration condition is satisfied, output the optimal path.

[0060] Specifically:

[0061] This embodiment discloses a three-dimensional UAV path planning method based on an improved grey wolf optimization algorithm. As Figure 1 shown, the brief steps of this method are as follows: (1) Establish a three-dimensional environment model. (2) Initialize the grey wolf population using the circle chaotic map to generate the initial path of the UAV. (3) Calculate the fitness value of the initial path according to the fitness function. (4) Update and record the optimal path. (5) Introduce an adaptive exploration factor to update the positions of the grey wolf population. (6) Introduce the global search and local search mechanism of the dung beetle optimization algorithm to update the positions of the grey wolf population. (7) Introduce the sine-cosine strategy to update the positions of the grey wolf population. (8) Use the pooling mechanism to process the worse solutions. (9) Record the current optimal solution. (10) Determine whether the maximum iteration number is reached. If not, return to update and record the optimal solution. (11) If satisfied, output the optimal path.

[0062] Furthermore, it is characterized in that the composition of the fitness function includes:

[0063] L = (ω 1 ·J path + ω 2 ·J hight + ω 3 ·J smooth ) + Violation·p f

[0064] where ω 1 、ω 2 and ω3 is the weight, J path is the path length, J hight is the height change, J smooth is the smoothness, p f is the penalty factor, and Violation is the default item.

[0065] Specifically:

[0066] The three-dimensional environmental model applied in the present invention is a natural mountain scene of 150*100*3 with five obstacles of different sizes and positions. The starting and ending points of the unmanned aerial vehicle are set at the diagonal positions of the coordinate system. The present invention plans the fitness function from aspects such as path length, height change, and smoothness.

[0067] Considering minimizing the path length during flight to reduce energy consumption and time, the specific formula for the path length is:

[0068]

[0069] In the formula, x i , y i , z i respectively represent the abscissa value, ordinate value, and height value of the unmanned aerial vehicle at the i-th step during flight; x i+1 , y i+1 , z i+1 respectively represent the abscissa value, ordinate value, and height value of the unmanned aerial vehicle at the (i + 1)-th step during flight.

[0070] Considering controlling the vertical fluctuation of the path during flight to avoid unnecessary up and down undulations, the specific formula for the height change is:

[0071]

[0072] In the formula, n is the number of data points, and μ is the mean value of the height during the path optimization process of the unmanned aerial vehicle.

[0073] Considering avoiding sharp turns during flight to facilitate the stable movement of the unmanned aerial vehicle, the specific formula for the smoothness is:

[0074]

[0075] In the formula, θ represents the deflection angle of the i-th point.

[0076] Considering ensuring that the path avoids obstacles during flight to ensure safety, the specific formula for the default item is:

[0077]

[0078] In the formula, M is the number of obstacles, d iis the distance from the path point to the center of the i-th obstacle, r i is the influence radius of the i-th obstacle.

[0079] The final fitness function is obtained through the above four evaluation indicators:

[0080] L = (ω 1 ·J path + ω 2 ·J hight + ω 3 ·J smooth ) + Violation·p f

[0081] In the formula, ω 1 , ω 2 , ω 3 are weights, defined as ω 1 = 0.5; ω 2 = 0.3; ω 3 = 0.2, p f is the penalty factor defined as 10 5 .

[0082] Furthermore, initializing the population using the circle chaotic map includes:

[0083]

[0084] where, Positions i+1 is the position after mapping, Positions i is the original position, i represents the dimension, and both a and b are natural numbers.

[0085] Furthermore, the expression of the adaptive exploration factor is:

[0086]

[0087] where, l is the number of iterations, and Max_iter is the maximum number of iterations.

[0088] Furthermore, replacing the contraction coefficient of the Grey Wolf Optimization Algorithm with the adaptive exploration factor includes:

[0089] A = 2a·r 1 - a

[0090] C = 2r 2

[0091] where, C and A are coefficient vectors, r 1 and r 2 are random vectors in [0, 1].

[0092] Furthermore, updating the positions of the gray wolf population includes:

[0093]

[0094] where D α , D β , D δ represent the distances between α, β, and δ and other individuals respectively, l is the current iteration number, C 1 , C 2 , C 3 are coefficient vectors, Positions α , Positions β , Positions δ are the position vectors of the α, β, and δ wolves in the current population, and Positions(l) is the individual position vector of the gray wolves in the l-th iteration;

[0095]

[0096] Positions(l + 1) = (Positions 1 + Positions 2 + Positions 3 ) / 3

[0097] where Position 1 , Position 2 , Position 3 are the position update vectors guided by the α, β, and δ wolves.

[0098] Specifically:

[0099] An improved gray wolf optimization algorithm involved in the present invention introduces circle chaotic mapping initialization to improve the quality of the initialized population; introduces an adaptive exploration factor to balance exploration and exploitation; combines the global and local exploitation formulas of the dung beetle optimization algorithm to enhance the convergence accuracy of the algorithm; introduces a sine-cosine strategy to help the algorithm expand the search range; introduces a pooling mechanism to store poor solutions and accelerate the convergence speed of the algorithm. The specific operation steps are as follows:

[0100] Generate the initial positions of gray wolves using circle chaotic mapping:

[0101]

[0102] In the formula, a = 0.5; b = 0.2, Positions i+1 is the position after mapping, Positions i is the original position, and i represents the dimension.

[0103] Using an adaptive exploration factor to replace the contraction coefficient of the Grey Wolf Optimization algorithm, maintaining a high exploration ability in the early stage; smoothly transitioning with a quadratic exponential decline in the middle stage; promoting local development in the later stage. It balances the global search and local search of the algorithm, improving the convergence accuracy and speed of the algorithm. The specific operations are as follows:

[0104]

[0105] In the formula, l is the iteration number, and Max_iter is the maximum iteration number.

[0106] The position of the grey wolf is updated by the following formula:

[0107] A = 2a·r 1 -a

[0108] C = 2r 2

[0109] In the formula, C and A are coefficient vectors.

[0110]

[0111] In the formula, D α , D β , D δ represent the distances between α, β, and δ and other individuals respectively, and l is the current iteration number.

[0112]

[0113] Positions(l + 1) = (Positions 1 +Positions 2 +Positions 3 ) / 3

[0114] In the formula, Positions α , Positions β , Positions δ represent the current positions of α, β, and δ wolves respectively.

[0115] Furthermore, introducing the global and local search mechanism dynamic adjustment mechanism of the Dung Beetle Optimization algorithm to balance global exploration and local exploration includes:

[0116]

[0117] Among them, Alpha_pos is the current optimal solution, Worse_pos is the worse solution, Delta_pos is the sub-optimal solution, a is a random coefficient, 0.3 and 0.1 are weight coefficients, θ is a random angle, tan(θ) is the generated random step size, r 1is a random factor.

[0118] Furthermore, introducing the sine-cosine optimization strategy to jump out of local extrema during the optimization process includes:

[0119]

[0120] where ω is the dynamic inertia weight, r 2 is a random angle factor; r 3 is a random factor, Alpha_pos is the position of the current optimal solution, is.

[0121] Furthermore, introducing a pooling mechanism to store worse solutions includes:

[0122] P = B × X brnd +(1 - B) × X worst

[0123] where P is the matrix used to store worse solutions in the pooling mechanism, B is a randomly generated binary matrix, X brnd is the position randomly generated based on the current optimal solution; X worst is the worse solution in the current iteration.

[0124] Specifically:

[0125] Introducing the dung beetle optimization algorithm: Since the grey wolf optimization is prone to falling into local optima and the algorithm may have the problem of premature convergence in optimization. Therefore, introducing the search mechanism of the dung beetle optimization algorithm and balancing global exploration and local exploration through a dynamic adjustment mechanism enhances the search ability of the grey wolf optimization algorithm. The specific expression is as follows.

[0126]

[0127] In the formula, Alpha_pos is the current optimal solution (the position of Alpha wolf); Worse_pos is the worse solution (here using the position Beta_pos of Beta wolf as the worse solution); Delta_pos is the sub-optimal solution (the position of Delta wolf); a is a random coefficient, taking values of 1 or -1, used to control the search direction; 0.3 and 0.1 are weight coefficients, used to adjust the search step size; θ is a random angle, with a value range of [0, π]; tan(θ) is used to generate a random step size to enhance the diversity of the search.

[0128] Introducing the sine-cosine optimization strategy to optimize the optimization ability of the grey wolf search algorithm, the specific expression is as follows:

[0129]

[0130] In the formula, ω is the dynamic inertia weight, controlling the search range, which gradually decreases as the number of iterations increases; r1 is a random factor that controls the search step size; r 2 is a random angle factor that controls the search direction; r 3 is a random factor that controls the distance between an individual and the current optimal solution; Alpha_pos is the position of the current optimal solution,

[0131] Introduce a pooling mechanism to store the historical poor solutions in the pool and reuse these solutions in subsequent iterations, effectively improving the convergence performance of the algorithm. The specific operations are as follows:

[0132] P = B × X brnd +(1 - B) × X worst

[0133] In the formula, P is the matrix used to store the poor solutions in the pooling mechanism, B is a randomly generated binary matrix that determines whether to use the randomly generated solution or the poor solution; X brnd is the position randomly generated based on the current optimal solution; X worst is the poor solution in the current iteration.

[0134] By establishing a three-dimensional environment model, an experimental scenario is obtained, as Figure 2 shown.

[0135] By comparing the UAV path optimization based on the Grey Wolf Optimization Algorithm and the improved Grey Wolf Optimization Algorithm in the initial state, as Figures 3-4 shown. A three-dimensional UAV path planning method based on the improved Grey Wolf Optimization Algorithm of the present invention has the best performance.

[0136] By calculating the fitness function and comparing the current fitness values, as Figure 5 shown.

[0137] Among them, Figures 2-4 the three-dimensional environment model is set as a natural mountain range scene of 150*100*3, and five obstacles with different sizes and positions, as well as the starting point and the ending point, are defined.

[0138] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A three-dimensional UAV path planning method based on an improved gray wolf optimization algorithm, characterized in that: include: Obtain a three-dimensional environment model, set the starting position and the end position of the UAV according to the three-dimensional environment model, use the improved gray wolf optimization algorithm, form a fitness function with the objective function, and iterate to synchronously update the positions of all gray wolf individuals and output the optimal path; The objective function includes: path length, height change, smoothness and default term; The optimal path outputted by the improved grey wolf optimization algorithm includes: Step 1: Initialize the population using circle chaotic mapping to generate the initial path; Step 2: Calculate the fitness value of the initial path according to the fitness function; Step 3, using an adaptive exploration factor to replace the shrinkage coefficient of the gray wolf optimization algorithm, updating the position of the gray wolf population, and in the process of updating the position of the gray wolf population, introducing the dynamic adjustment mechanism of the global and local search mechanisms of the dung beetle optimization algorithm to balance the global exploration and local exploration, introducing the sine and cosine optimization strategy to jump out of the local extreme value during the optimization process, introducing the pooling mechanism to store poor solutions, and reusing the poor solutions in subsequent iterations; Step 4: Calculate the fitness value of the current gray wolf population position according to the fitness function; Step 5: determine whether the maximum iteration condition is met. If the maximum iteration condition is not met, repeat steps 1-4 until the maximum iteration condition is met. If the maximum iteration condition is met, output the optimal path.

2. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: The fitness function comprises: L=(ω1·J path +ω2·J hight +ω3·J smooth )+Violation·p f Among them, ω1, ω2 and ω3 are weights, J path is the path length, J hight is the height change, J smooth is the smoothness, p f is the penalty factor, and Violation is the default item.

3. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: Initializing the population using the circle chaotic map includes: Among them, Positions i+1 Positions is the position after mapping. i is the original position, i represents the dimension, and a and b are both natural numbers.

4. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: The adaptive exploration factor expression is: Among them, l is the number of iterations and Max_iter is the maximum number of iterations.

5. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 4 is characterized in that: Using the adaptive exploration factor to replace the shrinkage coefficient of the gray wolf optimization algorithm includes: A=2a·r1-a C＝2r2 Where C and A are coefficient vectors, and r1 and r2 are random vectors in [0,1].

6. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 5 is characterized in that: Updates to the locations of gray wolf populations include: Among them, D α , D β , D δ Represents the distance between α, β and δ and other individuals, l is the current iteration number, C1, C2, C3 are coefficient vectors, Positions α 、Positions β 、Positions δ is the position vector of α, β, and δ wolves in the current population, and Positions(l) is the individual position vector of the gray wolf in the lth iteration; Positions(l+1)=(Positions1+Positions2+Positions3) / 3 Among them, Position1, Position2, and Position3 are position update vectors guided by α, β, and δ wolves.

7. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: The introduction of the global and local search mechanisms of the dung beetle optimization algorithm to dynamically adjust the mechanism to balance global exploration and local exploration includes: Among them, Alpha_pos is the current optimal solution, Worse_pos is the worse solution, Delta_pos is the suboptimal solution, a is the random coefficient, 0.3 and 0.1 are weight coefficients, θ is the random angle, tan(θ) is the generated random step size, and r1 is the random factor.

8. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: Introducing the sine-cosine optimization strategy to jump out of the local extreme value during the optimization process includes: Among them, ω is the dynamic inertia weight, r2 is the random angle factor; r3 is the random factor, Alpha_pos is the position of the current optimal solution, is the position of the i-th gray wolf in the j-th dimension at the l-th iteration.

9. The three-dimensional unmanned aerial vehicle path planning method based on the improved gray wolf optimization algorithm according to claim 1 is characterized in that: The introduction of the pooling mechanism to store poor solutions includes: P=B×X brnd +(1-B)×X worst Among them, P is the matrix used to store poor solutions in the pooling mechanism, B is a randomly generated binary matrix, and X brnd is a randomly generated position based on the current optimal solution; X worst is the worse solution in the current iteration.

Images