Three-dimensional path planning method and device for improving seagull optimization algorithm

Abstract

The invention relates to a three-dimensional path planning method and device for improving a seagull optimization algorithm, and belongs to the technical field of swarm intelligence algorithms, and the method comprises the steps: constructing a target function of path planning of a moving target on a moving region map; initializing an individual initial position of the population by adopting chaotic mapping, and calculating an optimal fitness value and an optimal seagull individual position according to a target function based on a reverse learning strategy; a Levy flight strategy and a sine and cosine operator are introduced to update the positions of the seagull individuals, and the updated optimal fitness value and the updated optimal positions of the seagull individuals are determined; and determining an optimal path planning result according to the updated optimal seagull individual position. According to the method, the chaotic mapping and reverse learning strategies are adopted on the basis of the sea gull optimization algorithm, the convergence efficiency of the algorithm is improved, the Levy flight strategy and the sine and cosine operator are introduced, dependence on parameter setting is reduced, the algorithm is more robust, and therefore the efficiency of path planning in the three-dimensional space is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of swarm intelligence algorithms, and in particular to a three-dimensional path planning method and device for improving a seagull optimization algorithm. Background Art

[0002] Swarm Intelligence Optimization Algorithms are an optimization method that simulates group behavior in nature. These algorithms simulate the foraging and nesting behaviors of insects, animal flocks, bird flocks, and fish schools, and use individuals in the group to find the optimal solution through information sharing and collaboration. Swarm intelligence algorithms have the characteristics of self-organization, self-learning, and self-adaptation, and can solve complex optimization problems.

[0003] Swarm intelligence optimization algorithms include a variety of specific algorithms, such as particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony optimization (ABC), differential evolution (DE), gravitational search algorithm (GSA), firefly algorithm (FA), bat algorithm (BA), cuckoo optimization algorithm (COA), grey wolf optimization algorithm (GWO), whale optimization algorithm (WOA), etc. The Seagull Optimization Algorithm (SOA) is a population-based optimization algorithm that simulates the migration and predation behavior of seagulls. The algorithm was proposed by Indian scholar Gaurav Dhiman in 2018, and was mainly inspired by the migration and attack behavior of seagulls in nature.

[0004] In the field of path planning, especially three-dimensional map path planning, the problems of existing technologies are: 1) In three-dimensional space, the search for the global optimal solution is more difficult, and existing algorithms may not be able to fully explore the solution space and are prone to fall into local optimality; 2) Existing algorithms may require more iterations to converge, which is a limitation for real-time path planning applications; 3) Algorithm performance is highly dependent on parameter settings, and it is challenging to find a suitable parameter combination in three-dimensional path planning.

[0005] In summary, the prior art lacks an improved Seagull optimization algorithm to improve the efficiency of path planning in three-dimensional space. Summary of the invention

[0006] In view of this, it is necessary to provide a three-dimensional path planning method and device with an improved Seagull optimization algorithm to solve the problem of low efficiency of three-dimensional space path planning in the prior art.

[0007] In order to solve the above problems, the present invention provides a three-dimensional path planning method of improving the seagull optimization algorithm, comprising: Obtain a moving area map of the moving target and construct an objective function for path planning of the moving target on the moving area map; The initial positions of individuals in the population are initialized using chaotic mapping, and the optimal fitness value and the optimal individual position of seagulls are calculated according to the objective function based on the reverse learning strategy; Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull, and the updated optimal fitness value and the updated optimal individual position of the seagull are determined; According to the updated optimal individual seagull position, the optimal path planning result is determined.

[0008] In a possible implementation, obtaining a map of a robot movement area includes: The environment of the moving target is modeled, a moving area map is obtained and the map is gridded.

[0009] In a possible implementation, the initializing individual initial positions of the population using a chaotic map includes: The initial positions of individuals in the population are initialized using the LogisticsTent chaotic map.

[0010] In one possible implementation, variable values ​​are generated based on the LogisticsTent chaotic map; Determine the size of the seagull population and the upper and lower boundaries of the optimal population; The initial positions of the individuals in the population are determined based on the values ​​of the variables, the size of the seagull population, and the upper and lower boundaries.

[0011] In a possible implementation, the method of calculating the optimal fitness value and the optimal individual seagull position according to the objective function based on the reverse learning strategy includes: The individual initial positions of the population are calculated based on the reverse learning strategy to obtain the mirrored individual initial positions of the population; The individual initial positions of the population and the mirrored individual initial positions of the population are combined to obtain the individual positions of the population; The individual positions of the population are screened based on the upper and lower boundaries to obtain the elite individual positions of the seagulls; The elite individual positions of the seagulls are calculated according to the objective function to obtain the optimal fitness value and the optimal individual position of the seagulls.

[0012] In a possible implementation, the method of introducing the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual seagull position to update the individual seagull position includes: Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy is introduced into the seagull position update formula of the seagull optimization algorithm to obtain the updated first position update formula; Introducing sine and cosine operators into the first position update formula to obtain a second position update formula; The updated individual position of the seagull is obtained based on the second position updating formula.

[0013] In a possible implementation, the formula of the Levy flight strategy is:

[0014] In the formula, represents the value of Levy's flight strategy; ~N(0, ), ~N(0,1), is a hyperparameter, is the gamma function.

[0015] In a possible implementation, the expression of the second position update formula is:

[0016] in, Indicates the current position of the seagull; Indicates that the seagull has moved to a new location; x , y , z Indicates the coordinate value of the moving target in three-dimensional space; represents the value of Levy flight strategy; In the interval [0,2 ] Random value; is a uniform random number in [0,1]; Indicates the adaptive search range; represents a hyperparameter; Indicates the number of iterations; Indicates the maximum number of iterations.

[0017] On the other hand, the present invention also provides a three-dimensional path planning device for improving the seagull optimization algorithm, comprising: An objective function building module is used to obtain a moving area map of a moving target and build an objective function for path planning of the moving target on the moving area map; The optimal individual acquisition module is used to initialize the initial position of the individuals in the population using chaotic mapping, and calculate the optimal fitness value and the optimal seagull individual position according to the objective function based on the reverse learning strategy; A position update module is used to introduce the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual seagull position to update the individual seagull position, and determine the updated optimal fitness value and the updated optimal individual seagull position; The optimal path planning module is used to determine the optimal path planning result according to the updated optimal individual seagull position.

[0018] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in a three-dimensional path planning method of an improved seagull optimization algorithm described in any one of the above implementations.

[0019] The beneficial effects of the present invention are as follows: the present invention provides a three-dimensional path planning method based on an improved seagull optimization algorithm, firstly obtains a moving area map of a moving target, and constructs an objective function for path planning of the moving target on the moving area map, uses a chaotic map to initialize the individual initial positions of the population, thereby improving the convergence speed of the algorithm, and based on the reverse learning strategy, calculates the optimal fitness value and the optimal individual position of the seagull according to the objective function, thereby further improving the convergence speed of the algorithm, introduces the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual position of the seagull to update the individual position of the seagull, introduces the Levy flight strategy and the sine-cosine operator to reduce the dependence on parameter settings, improves the adaptability of the algorithm, determines the updated optimal fitness value and the updated optimal individual position of the seagull, and determines the optimal path planning result according to the updated optimal individual position of the seagull. The present invention adopts a chaotic map and a reverse learning strategy on the basis of the seagull optimization algorithm to significantly reduce the number of iterations required for the algorithm to reach the optimal solution, improves the convergence efficiency of the algorithm, introduces the Levy flight strategy and the sine-cosine operator to reduce the dependence on parameter settings, makes the algorithm more robust, thereby improving the efficiency of path planning in three-dimensional space. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of an embodiment of a three-dimensional path planning method of an improved seagull optimization algorithm provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of S102; Figure 3 An embodiment of a three-dimensional path planning method of an improved seagull optimization algorithm provided by the present invention is a start and end point peak map set by a MATLAB tool; Figure 4 A path trajectory diagram of an embodiment of a three-dimensional path planning method of an improved seagull optimization algorithm provided by the present invention; Figure 5 A fitness iteration diagram of an embodiment of a three-dimensional path planning method of an improved seagull optimization algorithm provided by the present invention; Figure 6 A schematic flow chart of an embodiment of a three-dimensional path planning device for improving the Seagull optimization algorithm provided by the present invention; Figure 7 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0022] The present invention provides a three-dimensional path planning method and device for improving the Seagull optimization algorithm, which are described below respectively.

[0023] Embodiment 1: Figure 1 A schematic flow chart of an embodiment of a three-dimensional path planning method of an improved seagull optimization algorithm provided by the present invention is as follows: Figure 1 As shown, the three-dimensional path planning method of the improved Seagull optimization algorithm includes: S101, obtaining a moving area map of a moving target, and constructing an objective function for path planning of the moving target on the moving area map; S102, using chaotic mapping to initialize the initial positions of individuals in the population, and calculating the optimal fitness value and the optimal individual position of the seagull according to the objective function based on the reverse learning strategy; S103, based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull, and the updated optimal fitness value and the updated optimal individual position of the seagull are determined; S104. Determine the optimal path planning result according to the updated optimal individual seagull position.

[0024] Compared with the prior art, the present embodiment provides a three-dimensional path planning method based on an improved seagull optimization algorithm. First, a moving area map of a moving target is obtained, and an objective function of path planning of the moving target on the moving area map is constructed. The individual initial positions of the population are initialized by using a chaotic map, thereby improving the convergence speed of the algorithm. The optimal fitness value and the optimal individual position of the seagull are calculated according to the objective function based on a reverse learning strategy, thereby further improving the convergence speed of the algorithm. Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull. The Levy flight strategy and the sine-cosine operator are introduced to reduce the dependence on parameter settings, thereby improving the adaptability of the algorithm. The updated optimal fitness value and the updated optimal individual position of the seagull are determined, and the optimal path planning result is determined according to the updated optimal individual position of the seagull. The present invention adopts a chaotic map and a reverse learning strategy on the basis of the seagull optimization algorithm to significantly reduce the number of iterations required for the algorithm to reach the optimal solution, thereby improving the convergence efficiency of the algorithm. The Levy flight strategy and the sine-cosine operator are introduced to reduce the dependence on parameter settings, thereby making the algorithm more robust, thereby improving the efficiency of path planning in three-dimensional space.

[0025] It should be noted that the present invention is applicable to the scenario of path planning in three-dimensional space. It is understandable that the present invention is also applicable to all scenarios requiring path planning, and it is only necessary to replace the objective function according to the specific scenario.

[0026] It should be noted that the present invention is an improvement on the Seagull optimization algorithm, with the following main improvements: Improvement 1: Use the LogisticsTent chaotic map to initialize the initial position of the seagull individuals. The specific formula is:

[0027] Where n is the nth moment, is the position value at the nth moment, ranging from (0, 1], is a hyperparameter. The chaotic distribution of values ​​is also different. It means remainder with respect to 1.

[0028] Improvement point 2: After the seagull individuals generate the initial position using the reverse learning strategy (OBL), the number of seagull individuals is doubled according to the upper and lower bound generation formulas, and then the fitness value is sorted according to the function to be tested to select the first half of the best seagull individual positions. Specifically, the specific formula for generating the new seagull position (reverse solution) is:

[0029] UB is the upper bound and LB is the lower bound. The fitness of the reverse solution and the original solution X is calculated, and the individual positions of the seagulls with the best fitness in the first half are selected to finally obtain the initial elite individual positions of the seagulls.

[0030] Improvement point three: Introduce the Levy flight strategy on the basic seagull individual position update formula, so that the seagull individual performs random step updates when moving to avoid falling into the local optimal solution. Specifically, introduce the Levy flight strategy, the specific formula is:

[0031] in ~N(0, ), ~N(0,1), The specific calculation formula is:

[0032] is a hyperparameter, Gamma function. Combining the final iterative position update with Levy flight yields the following improved formula:

[0033] Improvement point 4: Introduce sine and cosine operators based on the basic seagull individual position update formula, so that the seagull uses different formulas to update the position at different flight stages, and iterate at a better and more optimal speed. Specifically, introduce sine and cosine operators into the seagull position update formula, the specific formula is:

[0034]

[0035] in, Indicates the current position of the seagull; Indicates that the seagull has moved to a new location; x , y , z Indicates the coordinate value of the moving target in three-dimensional space; represents the value of Levy flight strategy; In the interval [0,2 ] Random value; is a uniform random number in [0,1]; Indicates the adaptive search range; represents a hyperparameter; Indicates the number of iterations; Indicates the maximum number of iterations.

[0036] In some embodiments of the present invention, the step of obtaining a map of a robot movement area includes: The environment of the moving target is modeled, a moving area map is obtained and the map is gridded.

[0037] In some embodiments of the present invention, the initialization of the individual initial positions of the population using chaotic mapping includes: The initial positions of individuals in the population are initialized using the LogisticsTent chaotic map.

[0038] In some embodiments of the present invention, variable values ​​are generated based on the LogisticsTent chaotic map; Determine the size of the seagull population and the upper and lower boundaries of the optimal population; The initial positions of the individuals in the population are determined based on the values ​​of the variables, the size of the seagull population, and the upper and lower boundaries.

[0039] In some embodiments of the present invention, in step S102, as Figure 2 As shown, the optimal fitness value and the optimal individual position of the seagull are calculated according to the objective function based on the reverse learning strategy, including: S201, calculating the initial positions of individuals in the population based on the reverse learning strategy to obtain the initial positions of individuals in the mirrored population; S202, merging the individual initial positions of the population and the individual initial positions of the mirrored population to obtain the individual positions of the population; S203, filtering the individual positions of the population based on the upper and lower boundaries to obtain the individual positions of seagull elites; S204, calculating the elite individual positions of the seagulls according to the objective function, and obtaining the optimal fitness value and the optimal individual position of the seagulls.

[0040] In a specific embodiment of the present invention, the direction of the optimal position is calculated , the calculation formula is:

[0041]

[0042] in, is the current best position, is a random number within (0,1].

[0043] Move to the new position according to this direction , the calculation formula is:

[0044] Seagull performing spiral motion in the air while attacking its prey, abstracted into three-dimensional space The calculation formula is:

[0045] in is a random angle value within (0, 2π].

[0046] In some embodiments of the present invention, the method of introducing the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual seagull position to update the individual seagull position includes: Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy is introduced into the seagull position update formula of the seagull optimization algorithm to obtain the updated first position update formula; Introducing sine and cosine operators into the first position update formula to obtain a second position update formula; The updated individual position of the seagull is obtained based on the second position updating formula.

[0047] In some embodiments of the present invention, the formula of the Levy flight strategy is:

[0048] In the formula, represents the value of Levy flight strategy; ~N(0, ), ~N(0,1), is a hyperparameter, is the gamma function.

[0049] In some embodiments of the present invention, the expression of the second position update formula is:

[0050] in, Indicates the current position of the seagull; Indicates that the seagull has moved to a new location; x , y , z Indicates the coordinate value of the moving target in three-dimensional space; represents the value of Levy flight strategy; In the interval [0,2 ] Random value; is a uniform random number in [0,1]; represents a hyperparameter; Indicates the number of iterations; Indicates the maximum number of iterations.

[0051] Embodiment 2: This embodiment applies the improved Seagull optimization algorithm to the 3D simulation map and performs simulated path planning. The specific steps are as follows: Step 1: Set the parameters of the improved seagull optimization algorithm and set the population size , the maximum number of iterations of the algorithm , the number of runs of the improved Seagull optimization algorithm , in the improved Seagull optimization algorithm , , Both are 1, in step 2 , in step 3 , in step 4 ; Step 2: LogisticTent chaotic mapping generates the initial positions of seagull individuals

[0052] Step 3: Based on the initial position of the seagull Generate inverse solution ,Will And reverse solution The fitness is calculated by specifying the test function, and the top half of the elite seagulls are finally selected according to the fitness ranking. .

[0053] Step 4: Calculate the individual positions of the seagulls according to the second position update formula Numeric values, and: , the second position update formula is as follows:

[0054] Step 5: Calculate the fitness value applied to the 3D simulation map. This includes: The built-in spline function in the simulation software MATLAB is used to calculate the cubic spline interpolation of the x, y, and z values ​​to fit the flight scattered point positions of individual seagulls; Determine whether the height z corresponding to x,y in the individual position of the seagull is within the obstacle (such as the volume of the artificially generated mountain). If it is within the obstacle, set the corresponding fitness value to infinity; if it is outside the obstacle, use the mean square sum function to calculate the corresponding fitness value according to the individual scattered point position x,y,z of the seagull Step 6: Return to step 3 until the maximum number of iterations is reached to obtain the optimal route planning.

[0055] In addition, this embodiment also conducts comparative analysis on 12 classic functions and 3 swarm intelligence optimization algorithms in the CEC standard function. The test functions are shown in Table 1 below, where , , , It is a unimodal function, which is used to evaluate the optimization accuracy and convergence speed of the algorithm. , , , It is a multi-peak function, which has a better test capability for the global exploration ability of the algorithm.

[0056] Table 1: Test function formula

[0057] The MI-SOA algorithm (improved Seagull Optimization Algorithm) proposed in this embodiment is compared with the standard SOA, PSO, and BOA algorithms to verify the algorithm performance of the proposed MI-SOA. The experimental results are the best value, worst value, average fitness value, and standard deviation of the results of 10 runs. The specific experimental results are shown in Table 2 below: Table 2: Experimental results

[0058] It can be seen from Table 2 that the MI-SOA algorithm improved in this paper has a significant advantage in the eight test functions, and in the result of F8, the optimal value is only slightly worse than the SOA algorithm. From the above results, it can be seen that the MI-SOA algorithm improved in this paper has a higher optimization ability, and the optimization results are better than other algorithms. Therefore, for solving the maximum value problem, MI-SOA has better performance.

[0059] In addition, in order to verify that the algorithm of this embodiment can improve the efficiency of 3D simulation map route planning, this embodiment uses MATLAB tool to simulate 3D map for route planning. 100-size 3D grid map, and compared with genetic algorithm (GA) and ant colony algorithm (ACA). Specifically, first, a 3D terrain map is constructed through the 3D surface grid generation function of MATLAB, and the number of peaks is set by the artificial parameter N, and N peaks of random height, range, and area are generated at random positions in the 3D terrain map. By setting the peaks, some real altitude conditions in the real 3D map can be simulated to create artificial obstacles for MI-SOA in route planning. Finally, the starting point (0,0,0) and the end point (100,100,50) are artificially set in the 3D map, and finally a start and end point peak map is formed, as shown in the figure. Figure 3 shown.

[0060] This example compares the MI-SOA algorithm with the GA and ACA algorithms, where the parameter setting dimension is 5, the population size is 50, and the maximum number of iterations is 100. Other parameters are the same as above. The final MI-SOA path trajectory diagram is shown in Figure 4 As shown in the fitness iteration diagram Figure 5 shown.

[0061] from Figure 5It can be observed that the MI-SOA algorithm has shown significant advantages in improving fitness. During the iteration process, the fitness of the MI-SOA algorithm improves significantly faster than that of the GA and ACA algorithms. After about 7 iterations, the fitness of the MI-SOA algorithm reaches the optimal value, close to 160. After about 5 iterations, the fitness of the genetic algorithm is about 190. Although it is slightly faster than MI-SOA in terms of the number of iterations, its fitness is slightly inferior to that of the MI-SOA algorithm. The fitness of the ant colony algorithm is about 200 after about 18 iterations, which is slightly lower than that of the I-SOA and GA algorithms.

[0062] In addition, the performance of MI-SOA in practical applications also verifies its effectiveness. Figure 5 As shown, MI-SOA can effectively plan the optimal path to avoid obstacles, and can quickly adjust the path when encountering dynamic obstacles to ensure smooth arrival at the destination.

[0063] In order to better implement a three-dimensional path planning method of an improved seagull optimization algorithm in an embodiment of the present invention, based on a three-dimensional path planning method of an improved seagull optimization algorithm, correspondingly, Figure 6 As shown, an embodiment of the present invention further provides a three-dimensional path planning device for improving the seagull optimization algorithm. A three-dimensional path planning device 600 for improving the seagull optimization algorithm includes: The objective function construction module 601 is used to obtain a moving area map of the moving target and construct an objective function for path planning of the moving target on the moving area map; The optimal individual acquisition module 602 is used to initialize the initial position of the individuals of the population using chaotic mapping, and calculate the optimal fitness value and the optimal seagull individual position according to the objective function based on the reverse learning strategy; A position updating module 603 is used to introduce the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual seagull position to update the individual seagull position, and determine the updated optimal fitness value and the updated optimal individual seagull position; The optimal path planning module 604 is used to determine the optimal path planning result according to the updated optimal individual seagull position.

[0064] The three-dimensional path planning device 600 of the improved seagull optimization algorithm provided in the above embodiment can implement the technical solution described in the above embodiment of the three-dimensional path planning method of the improved seagull optimization algorithm. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the three-dimensional path planning method of the improved seagull optimization algorithm, which will not be repeated here.

[0065] like Figure 7As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702 and a display 703. Figure 7 Only some components of the electronic device 700 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0066] In some embodiments, the processor 701 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 702, such as a three-dimensional path planning method of an improved seagull optimization algorithm in the present invention.

[0067] In some embodiments, processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 301 may be local or remote. In some embodiments, processor 701 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0068] In some embodiments, the memory 702 may be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. In other embodiments, the memory 702 may also be an external storage device of the electronic device 700, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 700.

[0069] Furthermore, the memory 702 may include both an internal storage unit of the electronic device 700 and an external storage device. The memory 702 is used to store application software installed in the electronic device 700 and various data.

[0070] In some embodiments, the display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 703 is used to display information on the electronic device 700 and to display a visual user interface. The components 701-703 of the electronic device 700 communicate with each other via a system bus.

[0071] In one embodiment, when the processor 701 executes a three-dimensional path planning program of an improved seagull optimization algorithm in the memory 702, the following steps may be implemented: Obtain a moving area map of the moving target and construct an objective function for path planning of the moving target on the moving area map; The initial positions of individuals in the population are initialized using chaotic mapping, and the optimal fitness value and the optimal individual position of seagulls are calculated according to the objective function based on the reverse learning strategy; Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull, and the updated optimal fitness value and the updated optimal individual position of the seagull are determined; According to the updated optimal individual seagull position, the optimal path planning result is determined.

[0072] It should be understood that: when the processor 701 executes a three-dimensional path planning program of an improved seagull optimization algorithm in the memory 702, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0073] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 300 mentioned, and the electronic device 700 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 700 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0074] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0075] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A three-dimensional path planning method based on an improved seagull optimization algorithm, characterized in that: include: Obtain a moving area map of the moving target and construct an objective function for path planning of the moving target on the moving area map; The initial positions of individuals in the population are initialized using chaotic mapping, and the optimal fitness value and the optimal individual position of seagulls are calculated according to the objective function based on the reverse learning strategy; Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull, and the updated optimal fitness value and the updated optimal individual position of the seagull are determined; According to the updated optimal individual seagull position, the optimal path planning result is determined.

2. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 1 is characterized in that: The obtaining of the robot movement area map comprises: The environment of the moving target is modeled, a moving area map is obtained and the map is gridded.

3. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 1 is characterized in that: The initial positions of individuals in the population are initialized using chaotic mapping, including: The initial positions of individuals in the population are initialized using the LogisticsTent chaotic map.

4. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 3 is characterized in that: The initial positions of individuals in the population are initialized by using the LogisticsTent chaotic map, including: Generate variable values ​​based on LogisticsTent chaotic mapping; Determine the size of the seagull population and the upper and lower boundaries of the optimal population; The initial positions of the individuals in the population are determined based on the values ​​of the variables, the size of the seagull population, and the upper and lower boundaries.

5. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 4 is characterized in that: The method calculates the optimal fitness value and the optimal individual position of the seagull according to the objective function based on the reverse learning strategy, including: The individual initial positions of the population are calculated based on the reverse learning strategy to obtain the mirrored individual initial positions of the population; The individual initial positions of the population and the mirrored individual initial positions of the population are combined to obtain the individual positions of the population; The individual positions of the population are screened based on the upper and lower boundaries to obtain the elite individual positions of the seagulls; The elite individual positions of the seagulls are calculated according to the objective function to obtain the optimal fitness value and the optimal individual position of the seagulls.

6. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 1 is characterized in that: The method of introducing the Levy flight strategy and the sine-cosine operator based on the optimal fitness value and the optimal individual seagull position to update the individual seagull position includes: Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy is introduced into the seagull position update formula of the seagull optimization algorithm to obtain the updated first position update formula; Introducing sine and cosine operators into the first position update formula to obtain a second position update formula; The updated individual position of the seagull is obtained based on the second position updating formula.

7. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 6 is characterized in that: The formula of the Levy flight strategy is: In the formula, represents the value of Levy's flight strategy; ~N(0, ), ~N(0,1), is a hyperparameter, is the gamma function.

8. The three-dimensional path planning method based on the improved seagull optimization algorithm according to claim 7 is characterized in that: The expression of the second position update formula is: in, Indicates the current position of the seagull; Indicates that the seagull has moved to a new location; x , y , z Indicates the coordinate value of the moving target in three-dimensional space; represents the value of Levy's flight strategy; In the interval [0,2 ] Random value; is a uniform random number in [0,1]; Indicates the adaptive search range; represents a hyperparameter; Indicates the number of iterations; Indicates the maximum number of iterations.

9. A three-dimensional path planning device with improved seagull optimization algorithm, characterized in that: include: Take the moving area map of the moving target and construct the objective function of the path planning of the moving target on the moving area map; The initial positions of individuals in the population are initialized using chaotic mapping, and the optimal fitness value and the optimal individual position of seagulls are calculated according to the objective function based on the reverse learning strategy; Based on the optimal fitness value and the optimal individual position of the seagull, the Levy flight strategy and the sine-cosine operator are introduced to update the individual position of the seagull, and the updated optimal fitness value and the updated optimal individual position of the seagull are determined; According to the updated optimal individual seagull position, the optimal path planning result is determined.

10. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the three-dimensional path planning method of the improved Seagull optimization algorithm as described in any one of claims 1 to 8.

Images