Unmanned aerial vehicle path planning method and system based on pol atom optimization algorithm

Abstract

The invention discloses an unmanned aerial vehicle path planning method and system based on a pol atom optimization algorithm, and the method comprises the steps: carrying out the three-dimensional space modeling and path calculation of an unmanned aerial vehicle path planning problem, and constructing a target function; and solving the target function by adopting a pol atom optimization algorithm to obtain an optimal path in the path cruising process of the unmanned aerial vehicle. The method has the remarkable effects that information is abstracted in a real space to construct a three-dimensional space model, a terrain threat area and an obstacle area are considered in the modeling process, the influence of the size of the unmanned aerial vehicle on the space range is considered, turning and climbing states in a path need to be evaluated in the flight process, and the accuracy of the three-dimensional space model is improved. Path optimization, safety and constrainability are combined as a whole; and the current optimal path is searched by applying a pol atom optimization algorithm, so that the unmanned aerial vehicle can efficiently avoid space obstacles, and the cruise working efficiency of the unmanned aerial vehicle can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle path planning, and in particular to a method and system for unmanned aerial vehicle path planning based on Bohr atomic optimization algorithm. Background Art

[0002] As an important achievement of modern military science and technology, drone technology has been rapidly popularized and applied in various military and civilian fields around the world in recent years. In the development of drones, there are urgent problems to be solved in technical optimization. Drone technology requires more agile response, more efficient optimization effect and more sophisticated control system.

[0003] At present, although traditional path optimization methods, such as genetic algorithm, particle swarm optimization algorithm, ant colony algorithm, etc., have achieved certain results in some applications, they still have some limitations when solving the UAV path planning problem, such as:

[0004] 1. Sensitive to parameters, requiring experience to adjust parameters;

[0005] 2. It may fall into the local optimal solution and may not be able to find the global optimal solution for complex problems;

[0006] 3. It requires more iterations to achieve better results, and has defects such as slow convergence speed, low convergence accuracy, and long calculation time.

[0007] Therefore, there is no good solution in the prior art for how to effectively construct a three-dimensional model space and seek the optimal path for drone planning. Summary of the invention

[0008] In view of the low efficiency of solving UAV path planning problems in the prior art, the purpose of the present invention is to provide a UAV path planning method and system based on the Bohr atomic optimization algorithm, which can better apply the optimization mechanism of the Bohr atomic optimization algorithm to the UAV path planning problem, provide the UAV with an optimal path during the cruising process, efficiently avoid obstacles, and effectively improve the cruising efficiency of the UAV.

[0009] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0010] In the first aspect, the present invention proposes a UAV path planning method based on the Bohr atomic optimization algorithm, the key of which is that it includes the following steps:

[0011] Step 1: Perform three-dimensional spatial modeling and path calculation on the UAV path planning problem and construct the objective function;

[0012] Step 2: Use the Bohr atomic optimization algorithm to solve the objective function and obtain the optimal path of the UAV path cruising process;

[0013] The process of solving the objective function by the Bohr atomic optimization algorithm is as follows:

[0014] S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D;

[0015] S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ;

[0016] S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ;

[0017] S4: Update parameters;

[0018] S5: When P>0.5, the quantum transition mechanism is executed to update the position, otherwise the stationary orbital motion mechanism is executed to update the position;

[0019] S6: Update the global optimal individual;

[0020] S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

[0021] Furthermore, in step 1, three-dimensional space modeling and path calculation are performed on the UAV path planning problem, and the specific process of constructing the objective function is as follows:

[0022] Step 1.1: According to the flight path of the UAV, a mathematical model of the path length cost F1 is established;

[0023] Step 1.2: Based on the diameter of the UAV and the threat area and danger area, a mathematical model of the threat cost F2 of the obstacle area at a certain path point is established;

[0024] Step 1.3, according to the height cost corresponding to each path point on the UAV flight path, establish a mathematical model of the height cost F3;

[0025] Step 1.4, according to the turning angle and climbing angle of the UAV during flight, establish a mathematical model of the smoothing cost F4;

[0026] Step 1.5: Construct the objective function F based on the mathematical model of path length cost F1, threat cost F2, height cost F3, and smoothness cost F4.

[0027] Furthermore, the mathematical model of the path length cost F1 is as follows:

[0028]

[0029] Among them, X i is the ith flight path, n is the total number of path points in the flight path, are two path points P in the flight path ij , P i，j+1 The Euclidean distance between them, j∈[1,n];

[0030] The mathematical model of the threat cost F2 is as follows:

[0031]

[0032] Among them, K is the set of threat areas, R k is the radius of the threat area, R is the diameter of the drone, S is the set of dangerous areas, d k is the threat area K and its projection coordinates C k The distance between is the obstacle area path segment, is the current path segment;

[0033] The mathematical model of the height cost F3 is as follows:

[0034]

[0035] Among them, H ij is the flight altitude of the drone;

[0036] The mathematical model of the smoothing cost F4 is as follows:

[0037]

[0038] Where a1 and a2 are the penalty coefficients for turning and climbing angles, respectively, and φ ij is the turning angle of the drone, ψ ij is the climbing angle of the UAV, ψ i，j This is the projection of the climb angle of the UAV.

[0039] Furthermore, the objective function is expressed as:

[0040]

[0041] Among them, b k is the weight coefficient, F1(X i ) to F4(X i ) are path length cost F1, threat cost F2, height cost F3, and smoothing cost F4 respectively.

[0042] Furthermore, the inductive behavior of the individuals in the quantum transition mechanism described in step S5 after being affected by the parameters is controlled by introducing levy flight parameters;

[0043] The calculation formula of the quantum transition mechanism is:

[0044] X(t+1)=X+E·levy(X gb -X),

[0045] Where E = a·cos(θ), a is a constant, θ is a random vector between [0,1], and X gb is the individual at the center of the nucleus, and X is the current individual value.

[0046] Furthermore, in the steady-state orbital motion mechanism described in step S5, when β>1, the quantum steady-state motion mechanism is executed, otherwise, the differentiated random search mechanism is executed.

[0047] Furthermore, the calculation formula of the quantum steady-state motion mechanism is:

[0048]

[0049] Among them, X gb is the nucleus center individual, X lb is the center individual of the electron orbit, λ is the preference weight, X m represents the average individual value in the particle electron group, β is the adjustment factor, α is the coefficient vector, and X r1 , X r2 represents two unequal random individuals in the particle electron group, and l is the probability factor;

[0050] The calculation formula of the differentiated random search mechanism is:

[0051]

[0052] Among them, X is the current individual value.

[0053] In a second aspect, the present invention proposes a UAV path planning system based on the Bohr atomic optimization algorithm, comprising:

[0054] The objective function building module is used to perform three-dimensional spatial modeling and path calculation for the UAV path planning problem and build the objective function;

[0055] The path planning module is used to solve the objective function using the Bohr atomic optimization algorithm and calculate the optimal path for the UAV's path cruising process;

[0056] The path planning module uses the Bohr atomic optimization algorithm to calculate the optimal path for the UAV path cruising process as follows:

[0057] S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D;

[0058] S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ;

[0059] S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ;

[0060] S4: Calculate control parameter r1;

[0061] S5: When P>0.5, the quantum transition mechanism is executed to update the position, otherwise the stationary orbital motion mechanism is executed to update the position;

[0062] S6: Update the global optimal individual;

[0063] S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

[0064] In a third aspect, the present invention proposes a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0065] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0066] The remarkable effects of the present invention are:

[0067] In order to solve the problems of poor optimization effect and low efficiency in the UAV path planning problem, the present invention adopts the unique optimization mechanism of Bohr atomic optimization algorithm to perform optimization, provide the optimal path for the UAV cruising process, effectively avoid space obstacles, and improve the efficiency of UAV cruising. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a flow chart of the method of the present invention;

[0069] Figure 2 is a system block diagram of the present invention;

[0070] Figure 3 It is a block diagram of computer equipment. DETAILED DESCRIPTION

[0071] The specific implementation manner and working principle of the present invention are further described in detail below with reference to the accompanying drawings.

[0072] The embodiment of the present invention abstracts information from real space to construct a three-dimensional space model, and considers terrain threat areas and obstacle areas during the modeling process, taking into account that the range of space is affected by the size of the drone, and that the turning and climbing states in the path need to be evaluated during flight, and the path optimization, safety and constrainability are generally combined; the Bohr atomic optimization algorithm is used to initialize the population, set the population number, number of iterations, random search individuals, local optimal search individuals, global optimal search individuals and other parameters, and avoid obstacles and determine the shortest path during the drone cruise as the optimization goal, and find the current optimal path as the algorithm iterates. The details are as follows:

[0073] like Figure 1 As shown, this embodiment proposes a UAV path planning method based on the Bohr atomic optimization algorithm, and the specific steps are as follows:

[0074] Step 1: Perform three-dimensional spatial modeling and path calculation on the UAV path planning problem and construct the objective function;

[0075] Step 1.1: According to the flight path of the UAV, a mathematical model of the path length cost F1 is established;

[0076] In this example, mathematical modeling of threat area and obstacle area is carried out under the premise of considering threat cost and fuel cost. i is the flight path, represented as a list of n path points. Each path point corresponds to a coordinate P ij =(x ij ,y ij ,z ij ) in the search map. The Euclidean distance between two nodes is recorded as Then the mathematical model of the path length cost F1 related to the path length is as follows:

[0077]

[0078] Among them, X i is the ith flight path, n is the total number of path points in the flight path, are two path points P in the flight path ij , P i,j+1 The Euclidean distance between them, j∈[1,n];

[0079] Step 1.2: Based on the diameter of the UAV and the threat area and danger area, a mathematical model of the threat cost F2 of the obstacle area at a certain path point is established;

[0080] During the operation of the drone, it is necessary to focus on planning the threat area and obstacle area. Here, K is the set of threat areas, and the threat area is defined as a cylinder with a projection coordinate of Ck and a radius of R. k .

[0081] exist In the example, the projection coordinates of the threat area K are C k , the distance is d k When considering the diameter R of the drone, the threat area K, and the danger area S, the obstacle area K is at the path point P. ij The mathematical model of the threat cost F2 is as follows:

[0082]

[0083] Among them, K is the set of threat areas, R k is the radius of the threat area, R is the diameter of the drone, S is the set of dangerous areas, d k is the threat area K and its projection coordinates C k The distance between is the obstacle area path segment, is the current path segment;

[0084] Here, it is considered that the range of diameter R is affected by the size of the drone, but S is affected by other factors. Assume that in real space, the drone is positioned at a lower range when the signal is good, and at a higher range when the signal is poor.

[0085] Step 1.3, according to the height cost corresponding to each path point on the UAV flight path, establish a mathematical model of the height cost F3;

[0086] First, calculate the path point Path according to the following formula ij Relevant height costs:

[0087]

[0088] Among them, H ij is the distance between the ground and the drone, i.e. the flight altitude, H min and H max The minimum and maximum altitudes for safe flight of the drone.

[0089] Then, for all path points between H ij By summing up, we can get the mathematical model of the height cost F3 as follows:

[0090]

[0091] Step 1.4, according to the turning angle and climbing angle of the UAV during flight, establish a mathematical model of the smoothing cost F4;

[0092] Since the UAV needs to evaluate the turning and climbing status during the flight, is a unit vector in the z-axis direction, then the expression of the projection vector is:

[0093]

[0094] Therefore, the calculation formula for the turning angle is:

[0095]

[0096] Climb angle ψ ij Is a path segment Its projection on the horizontal plane The angle between them. The calculation formula is:

[0097]

[0098] Based on the turning angle φ ij and the climb angle ψ ij , the mathematical model of the smoothing cost F4 is as follows:

[0099]

[0100] Where a1 and a2 are the penalty coefficients for turning and climbing angles, respectively, and φ ij is the turning angle of the drone, ψ ij is the climbing angle of the UAV, ψ i，j This is the projection of the climb angle of the UAV.

[0101] Based on these definitions of the setup, the cost function F is completely deterministic and can be used as input to the path planning process. So we proceed to step 1.5:

[0102] Step 1.5: Construct the objective function F based on the mathematical model of path length cost F1, threat cost F2, height cost F3, and smoothness cost F4.

[0103] In the case of global search, it is necessary to consider the construction of the objective function. The objective function is constructed by combining the path optimality, security and constrainability, that is, combining the path length cost F1, threat cost F2, height cost F3, and smoothness cost F4. Its expression is:

[0104]

[0105] Here, b k is the weight coefficient, F1(Xi ) to F4(X i ) are path length cost F1, threat cost F2, height cost F3, and smoothing cost F4 respectively. Among them, n waypoints P ij =(x ij ,y ij , z ij ), P ij ∈O, O is the operating space of the UAV.

[0106] Step 2: Use the Bohr atomic optimization algorithm to solve the objective function and obtain the optimal path of the drone's path cruising process. The specific process is as follows:

[0107] S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D;

[0108] S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ;

[0109] S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ;

[0110] S4: Update parameters α, β, P and L;

[0111] S5: When P>0.5, the quantum transition mechanism described in step S5.1 is executed to update the position, otherwise the stationary orbital motion mechanism described in step S5.2 is executed to update the position;

[0112] Step S5.1, in the quantum transition mechanism, the induction behavior of the individual after being affected by the parameters is controlled by introducing levy flight parameters;

[0113] The calculation formula of the quantum transition mechanism is:

[0114] X(t+1)=X+E·levy(X gb -X),

[0115] Wherein, X(t+1) is the individual value at the next iteration; E=a·cos(θ), a is a constant, which is 2 in this embodiment, and θ is a random vector between [0, 1]; X gb is the nucleus-centered individual, representing the best search agent (nucleus) in the particle electron group (global individual group); X is the individual value in the current iteration process.

[0116] Step S5.2: In the steady-state orbital motion mechanism, when β>1, the quantum steady-state motion mechanism is executed, otherwise, the differentiated random search mechanism is executed, specifically:

[0117] The calculation formula of the quantum steady-state motion mechanism is:

[0118]

[0119] Among them, X lb is the center individual of the electron orbit, that is, the best search agent in the electron orbit (local population); λ is the preference weight, and the calculation formula is λ=(d1+d2)·0.5, d1 and d2 represent the preference weights of the best search agent of the electron orbit and the best search agent of the electron group (nucleus), respectively; X m represents the average individual value in the particle electron group, β is the adjustment factor, which gradually decreases from 2 to 0 with iteration; α is the coefficient vector, ranging from [0,2]; X r1 , X r2 represents two unequal random individuals in a particle electron group; l is a probability factor, a random vector ranging from [0,1].

[0120] The calculation formula of the differentiated random search mechanism is:

[0121]

[0122] Among them, X(t+1) is the individual value in the next iteration, and X is the individual value in the current iteration process.

[0123] S6: Update the global optimal individual;

[0124] S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

[0125] See attached Figure 2 The embodiment of the present invention further proposes a UAV path planning system based on the Bohr atomic optimization algorithm, comprising:

[0126] The objective function building module is used to perform three-dimensional spatial modeling and path calculation for the UAV path planning problem and build the objective function;

[0127] The path planning module is used to solve the objective function using the Bohr atomic optimization algorithm and calculate the optimal path for the UAV's path cruising process;

[0128] The path planning module uses the Bohr atomic optimization algorithm to calculate the optimal path for the UAV path cruising process as follows:

[0129] S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D;

[0130] S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ;

[0131] S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ;

[0132] S4: Update parameters α, β, P and L;

[0133] S5: When P>0.5, the quantum transition mechanism described in step S5.1 is executed to update the position, otherwise the stationary orbital motion mechanism described in step S5.2 is executed to update the position;

[0134] Step S5.1, in the quantum transition mechanism, the induction behavior of the individual after being affected by the parameters is controlled by introducing levy flight parameters;

[0135] The calculation formula of the quantum transition mechanism is:

[0136] X(t+1)=X+E·levy(X gb -X),

[0137] Wherein, X(t+1) is the individual value at the next iteration; E=a·cos(θ), a is a constant, which is 2 in this embodiment, and θ is a random vector between [0, 1]; X gb is the nucleus-centered individual, representing the best search agent (nucleus) in the particle electron group (global individual group); X is the individual value in the current iteration process.

[0138] Step S5.2: In the steady-state orbital motion mechanism, when β>1, the quantum steady-state motion mechanism is executed, otherwise, the differentiated random search mechanism is executed, specifically:

[0139] The calculation formula of the quantum steady-state motion mechanism is:

[0140]

[0141] Among them, X lb is the center individual of the electron orbit, that is, the best search agent in the electron orbit (local population); λ is the preference weight, and the calculation formula is λ=(d1+d2)·0.5, d1 and d2 represent the preference weights of the best search agent of the electron orbit and the best search agent of the electron group (nucleus), respectively; X mrepresents the average individual value in the particle electron group, β is the adjustment factor, which gradually decreases from 2 to 0 with iteration; α is the coefficient vector, ranging from [0, 2]; X r1 , X r2 represents two unequal random individuals in a particle electron group; l is a probability factor, a random vector ranging from [0, 1].

[0142] The calculation formula of the differentiated random search mechanism is:

[0143]

[0144] Among them, X(t+1) is the individual value in the next iteration, and X is the individual value in the current iteration process.

[0145] S6: Update the global optimal individual;

[0146] S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

[0147] The embodiment of the present invention also provides a computer device, see Figure 3 , is a principle block diagram of a computer device provided in an embodiment of the present invention, the computer device includes a processor, a user interface, a network interface and a memory connected by a communication bus. Among them, the processor of the computer device is used to provide computing and control capabilities, call logical instructions in the memory, and optionally, the processor can adopt a central processing unit (CPU), a digital signal processing (DSP), etc. The user interface of the computer device is used to provide an input interface for the user and obtain its input data. The network interface of the computer device is used to connect the computer device to an external terminal through a network. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a user interface module, a network interface module and a computer application; the memory provides an operating environment for the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the steps of the above-mentioned drone path planning method based on the Bohr atomic optimization algorithm are implemented.

[0148] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and the computer program is used by a processor to execute the steps of the above-mentioned UAV path planning method based on the Bohr atomic optimization algorithm. Figure 3 In the computer device shown, a person of ordinary skill in the art can use a processor to call several computer application instructions of a method for evaluating the performance of rural industrial land stored in a memory to implement all or part of the steps of the methods of various embodiments of the present invention, and the aforementioned readable storage medium includes ROM / RAM, U disk, mobile hard disk, etc.

[0149] In summary, in order to solve the problems of poor optimization effect and low efficiency in the path planning of unmanned aerial vehicles, the embodiments of the present invention abstract information from the real space to construct a three-dimensional space model, and consider the terrain threat area and the obstacle area in the modeling process, taking into account that the range of the space is affected by the size of the unmanned aerial vehicle, and the turning and climbing states in the path need to be evaluated during the flight, and the path optimality, safety and constrainability are generally combined; the Bohr atomic optimization algorithm is applied to initialize the population, set the population number, the number of iterations, the random search individual, the local optimal search individual, the global optimal search individual and other parameters, and take avoiding obstacles and determining the shortest path during the cruising process of the unmanned aerial vehicle as the optimization goal, and find the current optimal path as the algorithm iterates, so that the unmanned aerial vehicle can not only efficiently avoid spatial obstacles, but also improve its cruising work efficiency.

[0150] The technical solution provided by the present invention is described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A UAV path planning method based on Bohr atomic optimization algorithm, characterized in that: The steps include: Step 1: Perform three-dimensional spatial modeling and path calculation on the UAV path planning problem and construct the objective function; Step 2: Use the Bohr atomic optimization algorithm to solve the objective function and obtain the optimal path of the UAV path cruising process; The process of solving the objective function by the Bohr atomic optimization algorithm is as follows: S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D; S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ; S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ; S4: Update parameters; S5: When P>0.5, the quantum transition mechanism is executed to update the position, otherwise the stationary orbital motion mechanism is executed to update the position; S6: Update the global optimal individual; S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

2. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 1 is characterized in that: In step 1, three-dimensional space modeling and path calculation are performed on the UAV path planning problem. The specific process of constructing the objective function is as follows: Step 1.1: According to the flight path of the UAV, a mathematical model of the path length cost F1 is established; Step 1.2: Based on the diameter of the UAV and the threat area and danger area, a mathematical model of the threat cost F2 of the obstacle area at a certain path point is established; Step 1.3, according to the height cost corresponding to each path point on the UAV flight path, establish a mathematical model of the height cost F3; Step 1.4, according to the turning angle and climbing angle of the UAV during flight, establish a mathematical model of the smoothing cost F4; Step 1.5: Construct the objective function F based on the mathematical model of path length cost F1, threat cost F2, height cost F3, and smoothness cost F4.

3. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 2 is characterized in that: The mathematical model of the path length cost F1 is as follows: Among them, X i is the ith flight path, n is the total number of path points in the flight path, are two path points P in the flight path ij , P i,j+1 The Euclidean distance between them, j∈[1,n]; The mathematical model of the threat cost F2 is as follows: Among them, K is the set of threat areas, R k is the radius of the threat area, R is the diameter of the drone, S is the set of dangerous areas, d k is the threat area K and its projection coordinates C k The distance between is the obstacle area path segment, is the current path segment; The mathematical model of the height cost F3 is as follows: Among them, H ij is the flight altitude of the drone; The mathematical model of the smoothing cost F4 is as follows: Where a1 and a2 are the penalty coefficients for turning and climbing angles, respectively, and φ ij is the turning angle of the UAV, ψ ij is the climbing angle of the UAV, ψ i,j This is the projection of the climb angle of the UAV.

4. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 2 or 3 is characterized in that: The expression of the objective function is: Among them, b k is the weight coefficient, F1(X i ) to F4(X i ) are path length cost F1, threat cost F2, height cost F3, and smoothing cost F4 respectively.

5. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 1, characterized in that: The induction behavior of the individuals in the quantum transition mechanism described in step S5 after being affected by the parameters is controlled by introducing levy flight parameters; The calculation formula of the quantum transition mechanism is: X(t+1)=X+E·levy(X gb -X), Where E = a·cos(θ), a is a constant, θ is a random vector between [0,1], and X gb is the individual at the center of the nucleus, and X is the current individual value.

6. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 5 is characterized in that: In the steady-state orbital motion mechanism described in step S5, when β>1, the quantum steady-state motion mechanism is executed, otherwise, the differentiated random search mechanism is executed.

7. The UAV path planning method based on Bohr atomic optimization algorithm according to claim 1, characterized in that: The calculation formula of the quantum steady-state motion mechanism is: Among them, X gb is the nucleus center individual, X lb is the center individual of the electron orbit, λ is the preference weight, X m represents the average individual value in the particle electron group, β is the adjustment factor, α is the coefficient vector, and X r1 , X r2 represents two unequal random individuals in the particle electron group, and l is the probability factor; The calculation formula of the differentiated random search mechanism is: Among them, X is the current individual value.

8. A UAV path planning system based on Bohr atomic optimization algorithm, characterized in that: include: The objective function building module is used to perform three-dimensional spatial modeling and path calculation for the UAV path planning problem and build the objective function; The path planning module is used to solve the objective function using the Bohr atomic optimization algorithm and calculate the optimal path for the UAV's path cruising process; The path planning module uses the Bohr atomic optimization algorithm to calculate the optimal path for the UAV path cruising process as follows: S1. Randomly initialize the population, set the population size to N, set the current number of iterations to t, the maximum number of algorithm iterations to T, and the spatial dimension to D; S2: Calculate the fitness of each individual and find the global optimal individual, which is defined as the nucleus center individual X gb ; S3: Set the number of neighbors m and find the local optimal individual, which is defined as the individual X at the center of the electron orbit. lb ; S4: Update parameters; S5: When P>0.5, the quantum transition mechanism is executed to update the position, otherwise the stationary orbital motion mechanism is executed to update the position; S6: Update the global optimal individual; S7: Determine whether t is greater than T. If so, stop the iteration and output the global optimal solution to obtain the optimal path of the UAV cruising process. Otherwise, turn to S4.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images