Unmanned ship path planning method, device and system, and storage medium

Abstract

The invention discloses an unmanned ship path planning method, device and system, and a storage medium. The method comprises the following steps: constructing an offshore obstacle grid map, and integrating an adaptability function technology of a shortest path, obstacle punishment and smoothness; the method comprises the following steps: generating an initial population through Tent-Logistic-Cosine chaotic mapping, and calculating an initial fitness value; a mixed evolutionary strategy is fused, the diversity of the population is kept in each mutation, and premature convergence is avoided; meanwhile, an accurate hunting strategy is adopted to enhance the global search capability of the algorithm; and in combination with a speed optimization strategy, the exploration efficiency of the bending sprint stage is improved. By adopting the technical scheme of the invention, efficient path planning can be realized in a complex ocean simulation environment, and the problem of poor performance of a Red-tail eagle optimization algorithm in path planning is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of path planning, and in particular relates to a method and device, a system, and a storage medium for unmanned ship path planning. Background Art

[0002] The path planning algorithm for unmanned ships refers to a technology that combines conditions such as avoiding running aground, shortest path, and optimal smoothness to plan the most suitable path. An effective path planning algorithm can not only ensure the safety and efficiency of unmanned ships when performing tasks, but also significantly improve their adaptability to complex and changing environments in the ocean. At present, path planning algorithms can be divided into the following two categories. One is traditional algorithms such as A* algorithm, fast search random tree or ant colony algorithm. However, traditional unmanned ship path planning technology has certain limitations when facing complex environments, and it is difficult to meet the requirements of efficient, safe and flexible path planning. The other is the swarm intelligence algorithm that has received widespread attention recently, such as artificial fish swarm algorithm, slime mold algorithm, dung beetle algorithm, etc. This type of algorithm shows stronger adaptability and flexibility when dealing with complex environments, and provides a new solution for unmanned ship path planning. However, there are also problems such as slow convergence and difficulty in jumping out of local optimal solutions.

[0003] The Red-tailed Hawk Algorithm (RTH) is a swarm intelligence algorithm that simulates the hunting of red-tailed hawks. Compared with other swarm intelligence algorithms, it has the advantages of high local search accuracy and fast convergence speed. However, the algorithm currently has problems such as poor global development ability and easy to fall into local optimal solutions. When applied to the path planning of unmanned ships at sea, it is difficult to find a better navigation path for unmanned ships. For example, when the population is initialized, the position of the red-tailed hawk population is determined by random numbers, which leads to a decrease in population diversity in the later stage of the algorithm. When the population diversity decreases, individuals tend to converge to a certain position in the same solution space and are prone to fall into local solutions; when the Red-tailed Hawk algorithm is in the low-altitude hovering stage, it uses a spiral approach to move to the global optimal solution, which may cause the algorithm to focus on a certain area too early and ignore other positions in the solution space, and the global development ability is poor. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an unmanned ship path planning method and device, system, and storage medium to solve the problem that the red-tailed hawk optimization algorithm has poor performance in path planning.

[0005] To achieve the above object, the present invention adopts the following technical solution:

[0006] A method for unmanned ship path planning, comprising:

[0007] Step S1, obtaining a marine obstacle grid map based on the unmanned ship and obstacles;

[0008] Step S2, designing a path fitness function according to the shortest path, obstacle penalty and smoothness of the marine obstacle grid map;

[0009] Step S3, using the Tent-Logistic-Cosine chaotic mapping strategy to generate the initial population of the red-tailed hawk algorithm, and calculating the initial optimal individual and optimal fitness value through the fitness function;

[0010] Step S4, using the high-altitude soaring, low-altitude circling and leaning sprint stages to preliminarily update the population position;

[0011] Step S5: using a hybrid evolution strategy to update the existing population position, and determining the updated optimal solution through boundary condition constraints;

[0012] Step S6, updating the population through the precision hunting phase, and comparing the optimal solution and the optimal position before and after the update to adjust the red-tailed hawk population;

[0013] Step S7, using a speed optimization strategy to adjust the exploration speed of each candidate solution to update the population position;

[0014] Step S8: After each strategy or stage is executed, boundary condition restriction and candidate solution update judgment are performed once; after reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

[0015] Preferably, in step S2, the shortest path between two points is:

[0016]

[0017] Where N is the population size, t is the current number of iterations,

[0018] Use the penalty formula to calculate the obstacle-free path.

[0019] f2 ( t)=E width ·E height ·n B

[0020] Combining the above two formulas, we get the adaptability function used in path planning:

[0021]

[0022] Among them, n B is the obstacle that collides on the path, E width is the width of the map and E height is the height of the map,

[0023] Use the path smoothing function to eliminate unnecessary turning points and twists in the path.

[0024]

[0025] Among them, f i ′(s) represents the first-order derivative of the path, which represents the slope of a point on the path, f i ″(s) ​​represents the second-order derivative of the path, which indicates the curvature of the path. ω1 and ω2 are weight coefficients used to adjust the weights of the slope and curvature in the path function. M represents the total number of line segments the path is divided into, and i represents different line segments in the path.

[0026] Preferably, in step S6, the population updating process is as follows:

[0027]

[0028] RD=randn(1,dim)

[0029] X newpost =X best +HuntingForce·RD

[0030] Among them, t max is the maximum number of iterations set, t is the current number of iterations, RD represents the random exploration and hunting direction generated for each candidate solution, X new is the candidate solution after the strategy is updated, HuntingForce is the hunting force;

[0031] During the update process, the hunting intensity is adjusted according to the current number of iterations.

[0032]

[0033] Among them, mod is a function used to calculate the remainder of the division of two numbers; ifmod(t,10)=0 means that the remainder of dividing the current number of iterations t by 10 is 0. When the remainder is equal to 0, the hunting intensity is adjusted once, that is, the hunting intensity is adjusted once every 10 iterations. In other cases, the hunting intensity remains unchanged.

[0034] Preferably, in step S7, the candidate solution exploration speed calculation formula is:

[0035] V=ω·V+C1·r1·(X best -X)+C2·r2·(X best -X)

[0036] Where V is the exploration speed, ω is the inertia weight, C1 is the individual speed update factor, C2 is the group speed update factor, and r1 and r2 are random numbers between [0,1].

[0037] Position update formula:

[0038] X new =X pos +V

[0039] Among them, X new is the updated candidate solution, X pos is the current candidate solution.

[0040] Preferably, in step S8, the boundary conditions are limited as follows:

[0041]

[0042] If the value of X is greater than the upper bound ub, then X new Take the upper bound ub,

[0043] If the value of X is between the upper bound ub and the lower bound lb, then X new Keep the value of X unchanged,

[0044] If the value of X is less than the lower bound lb, then X new Remove the lower bound lb,

[0045] Update judgment of candidate solution:

[0046] X newcost =fitness(X newpost )

[0047]

[0048] Among them, X cost is the fitness value of the current candidate solution, X newcost is the fitness value of the new candidate solution obtained by strategy update. post is the current candidate solution, X newpost is a new candidate solution obtained by strategy update.

[0049] The present invention also provides an unmanned ship path planning device, comprising:

[0050] The first processing module is used to obtain a marine obstacle grid map according to the unmanned ship and the obstacles;

[0051] The second processing module is used to design a path fitness function according to the shortest path, obstacle penalty and smoothness of the marine obstacle grid map;

[0052] The third processing module is used to generate the initial population of the red-tailed hawk algorithm by using the Tent-Logistic-Cosine chaotic mapping strategy, and calculate the initial optimal individual and the optimal fitness value by using the fitness function;

[0053] The fourth processing module is used to preliminarily update the position of the population by using the high-altitude soaring, low-altitude hovering phase and the diving sprint phase;

[0054] The fifth processing module is used to update the existing population position by adopting a hybrid evolution strategy and determine the updated optimal solution by limiting the boundary conditions;

[0055] The sixth processing module is used to update the population through the precision hunting stage, and compare the optimal solution and the optimal position before and after the update to adjust the red-tailed hawk population;

[0056] A seventh processing module is used to adjust the exploration speed of each candidate solution by adopting a speed optimization strategy to update the population position;

[0057] The eighth processing module is used to perform boundary condition restriction and candidate solution update judgment after each strategy or stage is executed; after reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

[0058] An embodiment of the present invention further provides an unmanned ship path planning system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the unmanned ship path planning method when executed by the processor.

[0059] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program executes the unmanned ship path planning method when running.

[0060] The present invention adopts multiple strategies to improve the unmanned ship path planning of the Red Tailed Hawk optimization algorithm, which can significantly improve the performance of the Red Tailed Hawk algorithm in unmanned ship path planning and effectively reduce the twists and turns in the path, thereby realizing accurate planning of the unmanned ship's navigation path. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0062] Figure 1 This is a flow chart of a method for unmanned ship path planning according to an embodiment of the present invention;

[0063] Figure 2 It is a comparison chart of optimization iteration curves of the improved Red Tailed Hawk algorithm (IRTH) of the embodiment of the present invention and other algorithms in 15 benchmark functions;

[0064] Figure 3 For the embodiment of the present invention Figure 1 Path planning effect in ;

[0065] Figure 4 For the embodiment of the present invention Figure 1 Schematic diagram of the fitness value of the path planning function in;

[0066] Figure 5 For the embodiment of the present invention Figure 2 Path planning effect in ;

[0067] Figure 6 For the embodiment of the present invention Figure 2 Schematic diagram of the fitness value of the path planning function in . DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0070] Embodiment 1:

[0071] like Figure 1 As shown, an embodiment of the present invention provides an unmanned ship path planning method, comprising the following steps:

[0072] S1. Obtain data related to the unmanned ship and obstacles, and construct a two-dimensional grid map based on these data. The map designs whirlpools and reefs on the sea as inaccessible black squares, and passable areas are represented by white squares.

[0073] S2. Initialize each strategy parameter, set the maximum number of iterations and the population size. Design the objective function by combining the shortest path, path smoothness, obstacles and environmental boundaries. Path smoothness: The generated navigation path should reduce invalid twists and turns and be as smooth as possible. Environmental boundaries and obstacles and other constraints: The generated mobile path strictly follows the boundary grid area set by the map, and each node on the path must not cross any grid marked as an obstacle. Shortest path condition: While satisfying the above constraints, when selecting a path, the shortest part of the path between two points should be selected.

[0074] The path fitness functions used include:

[0075] The shortest path between two points uses Euclid's theorem:

[0076]

[0077] Among them, N is the population size and t is the current iteration number.

[0078] In order to allow the unmanned ship to avoid obstacles, a penalty formula is used to calculate an obstacle-free path.

[0079] f2(t)=E width ·E height ·n B

[0080] Combining the above two formulas, we can get the fitness function used in path planning.

[0081]

[0082] Among them, n B is the obstacle that collides on the path, E width is the width of the map and E height is the height of the map.

[0083] After the preliminary path planning is completed, the path smoothness function is used to eliminate unnecessary turning points and twists in the path.

[0084]

[0085] Among them, f i (s) represents the position of a point on the path and is used to describe the geometric shape of the path. i ′(s) represents the first-order derivative of the path, which represents the slope of a point on the path, f i ″(s) ​​represents the second-order derivative of the path, indicating the curvature of the path. ω1 and ω2 are weight coefficients used to adjust the weights of the slope and curvature in the path function. M represents the total number of line segments the path is divided into, and i represents the different line segments in the path.

[0086] S3. Use the Tent-Logistic-Cosine chaotic mapping strategy to improve the initial population generation stage of the Red-tailed Hawk algorithm. The characteristic of this chaotic mapping is that it can show complex and unpredictable behaviors under different parameters and initial conditions, and can make the generated chaotic sequence have good randomness and uniformity. Applying this chaotic mapping to the initialization of the Red-tailed Hawk algorithm can effectively improve the diversity of the algorithm population, so as to improve the shortcomings of the original algorithm's lack of population diversity in the later stage. The formula of the chaotic mapping is as follows:

[0087]

[0088] X(t)=lb+(ub-lb)·Tent-Logistic-Cosine

[0089] Among them, r is a random number, X is the initial population of the Red-tailed Hawk algorithm, and lb and ub represent the lower and upper boundaries of the solution space.

[0090] S4, high altitude flying stage

[0091] The red-tailed hawk will fly high in the sky to find the place with the most food. This algorithm simulates this behavior to design the exploration phase of the algorithm, taking the place with the most food as the optimal solution and the high altitude as the entire solution space, and combines the Levy flight function to simulate the flight of the red-tailed hawk algorithm. The specific position update formula is as follows.

[0092] X(t)=X best +(X mean -X(t-1))·Levy·TF(t)

[0093]

[0094] Among them, X best represents the best position of the current iteration, X mean is the average value of each position, Levy is the flight function of the red-tailed hawk, and TF(t) is the transition factor function. t is the current iteration number, t max is the maximum number of iterations set, which is set to 1000 in the present invention. μ and ν are random numbers between [0,1]. Γ is the standard gamma function, The value range is usually The present invention takes s is a constant of 0.01, and β is a constant of 1.5.

[0095] S5, low altitude hovering stage:

[0096] When a red-tailed hawk locates a prey, it will lower its altitude and hover over the prey, observing and gradually approaching the prey. The red-tailed hawk algorithm simulates this behavior and approaches the optimal solution through spiral approximation in the solution space. The specific steps are as follows:

[0097] X(t)=X best +(x(t)+y(t))·StepSize(t)

[0098] StepSize(t)=X(t)-X mean

[0099]

[0100] Where x and y represent the direction coordinates; R0∈[0.5,3] is the initial circling radius; A∈[5,15] is the amplitude factor used to control the angle scaling. r∈[1,2] is the final circling radius, and rand is a random number between [0,1]. R(t) is the radius of each circling, and θ(t) is the angle of each circling.

[0101] After the position is updated, the direction coordinates are normalized to ensure that they are in the range of [-1, 1].

[0102]

[0103] S6, leaning sprint phase:

[0104] In this phase, the red-tailed hawk will sprint towards the target. The algorithm is inspired by the action of the red-tailed hawk leaning forward and sprinting, and quickly approximates the optimal position updated during the low-altitude soaring phase. The specific steps are as follows:

[0105] X(t)=α(t)·X best +x(t)·StepSize1(t)+y(t)·StepSize2(t)

[0106] StepSizel(t)=X(t)-TF(t)·X mean

[0107] StepSize2(t)=G(t)·X(t)-TF(t)·X best

[0108]

[0109] Among them, StepSizel1 and StepSizel2 are step size factors; a(t) is the acceleration factor, which increases with the increase of t; G(t) is the gravity factor. When it is close to the optimal solution, the gravity effect decreases and the optimal range is converged. mean is the average of the candidate solutions.

[0110] S7. Hybrid Evolutionary Strategy

[0111] A hybrid evolutionary strategy is used to enhance the global search capability of the Red-tailed Hawk algorithm. The hybrid evolutionary strategy is specifically divided into two stages: mutation and crossover.

[0112] In the mutation phase, the mutation vector is first calculated.

[0113] mutant = X a +F·X b -X c

[0114] Among them, a, b, and c are three random numbers, which are integers between (1, N), and N is the size of the population. These three random numbers are used to randomly select three different individuals from the population to determine the mutant individuals involved in generating candidate solutions. a , X b , X c It represents the candidate solutions selected from the corresponding positions of a, b, and c. F is the mutation weight, which controls the strength of the mutation. The present invention sets F=0.5.

[0115] Crossover phase:

[0116]

[0117] Wherein, trial is the candidate solution after the crossover phase update, CR is the crossover probability of the hybrid evolution strategy crossover phase, and the judgment condition for executing the crossover is that when the probability obtained randomly is less than the crossover probability, the crossover is executed. The present invention sets CR=0.9.

[0118] S8, Precision Hunting Stage

[0119] The present invention adds a precise hunting stage to the red-tailed hawk algorithm, which is used to enhance the local search capability near the global optimal solution in the later stage of the algorithm.

[0120] The strategy updates the population as follows:

[0121]

[0122] RD=randn(1,dim)

[0123] X newpost =X best +HuntingForce·RD

[0124] Among them, t max is the maximum number of iterations set, t is the current number of iterations, RD represents the random exploration and hunting direction generated for each candidate solution, X new is the candidate solution after the strategy is updated. HuntingForce is the hunting force.

[0125] The precise hunting strategy will also adjust the hunting intensity according to the current number of iterations during the update process.

[0126]

[0127] Where mod is a function used to calculate the remainder of the division of two numbers. ifmod(t,10)=0 means that the remainder of the current iteration number t divided by 10 is 0. When the remainder is equal to 0, the hunting intensity is adjusted once, that is, the hunting intensity is adjusted once every 10 iterations. In other cases, the hunting intensity remains unchanged.

[0128] S9. Speed ​​Optimization Strategy

[0129] The position update effect is achieved by changing the exploration speed of each candidate solution. The specific steps are as follows:

[0130] Candidate solution exploration speed calculation formula:

[0131] V=ω·V+C1·r1·(X best -X)+C2·r2·(X best -X)

[0132] Wherein, V is the exploration speed, ω is the inertia weight, which is set to 0.5 in the present invention. C1 is the individual speed update factor, which is set to 1.5. C2 is the group speed update factor, which is set to 1.5. r1 and r2 are random numbers between [0,1].

[0133] Position update formula:

[0134] X new =X pos +V

[0135] Among them, X new is the updated candidate solution, X pos is the current candidate solution.

[0136] S10. Boundary conditions and candidate solution update conditions

[0137] After each strategy or stage is executed, a boundary condition restriction and candidate solution update judgment must be performed. The boundary condition restriction can control the updated candidate solution not to exceed the solution space. The candidate solution update judgment can ensure the effectiveness of the update strategy and avoid blind updates.

[0138] The boundary conditions are as follows:

[0139]

[0140] If the value of X is greater than the upper bound ub, then X new Take the upper bound ub,

[0141] If the value of X is between the upper bound ub and the lower bound lb, then X new Keep the value of X unchanged,

[0142] If the value of X is less than the lower bound lb, then X newRemove the lower bound lb,

[0143] Update judgment of candidate solution:

[0144] X newcost =fitness(X newpost )

[0145]

[0146] Among them, X cost is the fitness value of the current candidate solution, X newcost is the fitness value of the new candidate solution obtained by strategy update. post is the current candidate solution, X newpost is a new candidate solution obtained by strategy update.

[0147] S11. After reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

[0148] In order to verify the effectiveness of the improved algorithm, the present invention conducted benchmark function tests and path planning tests. In the benchmark function test, the present invention compared the improved algorithm with the original red-tailed hawk algorithm, beluga optimization algorithm, genetic algorithm, gray wolf optimization algorithm, and nutcracker optimization algorithm in 15 benchmark functions. The formulas or names of the 15 benchmark functions are shown in Table 1. In the 15 benchmark function tests, the running results of each algorithm are shown in Table 1. Figure 2 In the path planning test, the present invention combines the improved algorithm with the other algorithms mentioned above to find the optimal path in two maps with different obstacle distributions. The specific path is as follows Figure 3 , Figure 5 As shown in the figure, the fitness values ​​of the path planning functions of each algorithm are as follows: Figure 4 , Figure 6 shown.

[0149] Table 1

[0150]

[0151]

[0152] In the algorithm performance test, the population size of each algorithm is set to 30, the maximum number of iterations is 1000, and each test function is tested 30 times. The final test data of each function are shown in Table 2. In the tests under different environments, the maximum number of iterations is set to 200, and the shortest path values ​​of each algorithm are shown in Table 3.

[0153] Table 2

[0154]

[0155]

[0156]

[0157] Table 3

[0158]

[0159] The beneficial effects of the embodiments of the present invention are as follows:

[0160] 1. The Tent-Logistic-Cosine chaotic mapping strategy is used to improve the initial population generation stage of the Red-tailed Hawk algorithm. This chaotic mapping is known for its complex and unpredictable behavior under diverse parameters and initial conditions, and can produce chaotic sequences with strong randomness and uniform distribution characteristics. Applying this chaotic mapping technology to the initialization process of the Red-tailed Hawk algorithm not only enriches the diversity of the population, but also effectively optimizes the problem of insufficient population diversity that may occur in the late iteration of the original algorithm, thereby significantly improving the global search capability and convergence performance of the algorithm.

[0161] 2. Combined with the hybrid evolution strategy, the randomness and diversity brought by the mutation crossover stage effectively improve the exploration ability of the population and reduce the risk of the algorithm falling into the local optimum. It allows the algorithm to continue to expand new search areas while maintaining in-depth development of the known solution area. Therefore, when facing complex optimization problems, it can more quickly approach the global optimal solution or find a solution close to the optimal solution, which improves the convergence speed and global search ability of the Red-tailed Hawk algorithm.

[0162] 3. A precise hunting phase is added to the Red-tailed Hawk algorithm. This strategy enhances the algorithm's adaptability to the search space by introducing random directions, helps to escape from the local optimal solution, and increases the robustness of the algorithm. The gradually reduced hunting force enables the algorithm to search the area near the global optimal solution more finely in the later stage, increasing the probability of finding a precise solution. The introduction of a precise hunting strategy helps to improve the global development search capability of the Red-tailed Hawk algorithm and enhance its local space optimization capability.

[0163] 4. The speed optimization strategy changes the exploration speed of each candidate solution to achieve the effect of position update. The interaction of inertia weight, individual speed update factor and group speed update factor is used to guide the candidate solution to move towards a better solution. The inertia weight helps the candidate solution maintain the current search direction, while the individual and group speed update factors push the candidate solution closer to its historical best position and the global best position respectively. The introduction of random numbers adds necessary randomness to the search process to prevent the algorithm from falling into the local optimum too early. In this way, the algorithm can continue to explore other unfamiliar areas while maintaining in-depth exploration of the known solution space. The introduction of this strategy enhances the exploration ability and adaptability of the algorithm, and improves the search efficiency and the quality of the solution.

[0164] Embodiment 2:

[0165] The embodiment of the present invention further provides an unmanned ship path planning device, comprising:

[0166] The first processing module is used to obtain a marine obstacle grid map according to the unmanned ship and the obstacles;

[0167] The second processing module is used to design a path fitness function according to the shortest path, obstacle penalty and smoothness of the marine obstacle grid map;

[0168] The third processing module is used to generate the initial population of the red-tailed hawk algorithm by using the Tent-Logistic-Cosine chaotic mapping strategy, and calculate the initial optimal individual and the optimal fitness value by using the fitness function;

[0169] The fourth processing module is used to preliminarily update the position of the population by using the high-altitude soaring, low-altitude hovering phase and the diving sprint phase;

[0170] The fifth processing module is used to update the existing population position by adopting a hybrid evolution strategy and determine the updated optimal solution by limiting the boundary conditions;

[0171] The sixth processing module is used to update the population through the precision hunting stage, and compare the optimal solution and the optimal position before and after the update to adjust the red-tailed hawk population;

[0172] A seventh processing module is used to adjust the exploration speed of each candidate solution by adopting a speed optimization strategy to update the population position;

[0173] The eighth processing module is used to perform boundary condition restriction and candidate solution update judgment after each strategy or stage is executed; after reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

[0174] Embodiment 3:

[0175] An embodiment of the present invention further provides an unmanned ship path planning system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the unmanned ship path planning method when executed by the processor.

[0176] Embodiment 4:

[0177] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program executes the unmanned ship path planning method when running.

[0178] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for unmanned ship path planning, characterized in that: include: Step S1, obtaining a marine obstacle grid map based on the unmanned ship and obstacles; Step S2, designing a path fitness function according to the shortest path, obstacle penalty and smoothness of the marine obstacle grid map; Step S3, using the Tent-Logistic-Cosine chaotic mapping strategy to generate the initial population of the red-tailed hawk algorithm, and calculating the initial optimal individual and optimal fitness value through the fitness function; Step S4, using the high-altitude soaring, low-altitude circling and leaning sprint stages to preliminarily update the population position; Step S5: using a hybrid evolution strategy to update the existing population position, and determining the updated optimal solution through boundary condition constraints; Step S6, updating the population through the precision hunting phase, and comparing the optimal solution and the optimal position before and after the update to adjust the red-tailed hawk population; Step S7, using a speed optimization strategy to adjust the exploration speed of each candidate solution to update the population position; Step S8: After each strategy or stage is executed, boundary condition restriction and candidate solution update judgment are performed once; after reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

2. The unmanned ship path planning method according to claim 1, characterized in that: In step S2, the shortest path between two points is: Where N is the population size, t is the current number of iterations, Use the penalty formula to calculate the obstacle-free path. f2(t)=E width ·E height ·n B Combining the above two formulas, we get the adaptability function used in path planning: Among them, n B is the obstacle that collides on the path, E width is the width of the map and E height is the height of the map, Use the path smoothing function to eliminate unnecessary turning points and twists in the path. Among them, f i ′(s) represents the first-order derivative of the path, which represents the slope of a point on the path, f i ″(s) ​​represents the second-order derivative of the path, which indicates the curvature of the path. ω1 and ω2 are weight coefficients used to adjust the weights of the slope and curvature in the path function. M represents the total number of segments the path is divided into, and i represents different segments in the path.

3. The unmanned ship path planning method according to claim 2, characterized in that: In step S6, the population update process is as follows: RD=randn(1,dim) X newpost =X best +HuntingForce·RD Among them, t max is the maximum number of iterations set, t is the current number of iterations, RD represents the random exploration and hunting direction generated for each candidate solution, X new is the candidate solution after the strategy is updated, HuntingForce is the hunting force; During the update process, the hunting intensity is adjusted according to the current number of iterations. Among them, mod is a function used to calculate the remainder of the division of two numbers; ifmod(t,10)=0 means that the remainder of dividing the current number of iterations t by 10 is 0. When the remainder is equal to 0, the hunting intensity is adjusted once, that is, the hunting intensity is adjusted once every 10 iterations. In other cases, the hunting intensity remains unchanged.

4. The unmanned ship path planning method according to claim 3, characterized in that: In step S7, the candidate solution exploration speed calculation formula is: V=ω·V+C1·r1·(X best -X)+C2·r2·(X best -X) Where V is the exploration speed, ω is the inertia weight, C1 is the individual speed update factor, C2 is the group speed update factor, and r1 and r2 are random numbers between [0,1]. Position update formula: X new =X pos +V Among them, X new is the updated candidate solution, X pos is the current candidate solution.

5. The unmanned ship path planning method according to claim 4, characterized in that: In step S8, the boundary conditions are limited as follows: If the value of X is greater than the upper bound ub, then X new Take the upper bound ub, If the value of X is between the upper bound ub and the lower bound lb, then X new Keep the value of X unchanged, If the value of X is less than the lower bound lb, then X new Remove the lower bound lb, Update judgment of candidate solution: X newcost =fitness(X newpost ) Among them, X cost is the fitness value of the current candidate solution, X newcost is the fitness value of the new candidate solution obtained by strategy update. post is the current candidate solution, X newpost is a new candidate solution obtained by strategy update.

6. An unmanned ship path planning device, characterized in that: include: The first processing module is used to obtain a marine obstacle grid map according to the unmanned ship and the obstacles; The second processing module is used to design a path fitness function according to the shortest path, obstacle penalty and smoothness of the marine obstacle grid map; The third processing module is used to generate the initial population of the red-tailed hawk algorithm by using the Tent-Logistic-Cosine chaotic mapping strategy, and calculate the initial optimal individual and the optimal fitness value by using the fitness function; The fourth processing module is used to preliminarily update the position of the population by using the high-altitude soaring, low-altitude hovering phase and the diving sprint phase; The fifth processing module is used to update the existing population position by adopting a hybrid evolution strategy and determine the updated optimal solution by limiting the boundary conditions; The sixth processing module is used to update the population through the precision hunting stage, and compare the optimal solution and the optimal position before and after the update to adjust the red-tailed hawk population; A seventh processing module is used to adjust the exploration speed of each candidate solution by adopting a speed optimization strategy to update the population position; The eighth processing module is used to perform boundary condition restriction and candidate solution update judgment after each strategy or stage is executed; after reaching the maximum number of iterations, the optimal individual and the optimal fitness value are extracted to obtain the shortest path.

7. An unmanned ship path planning system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the unmanned ship path planning method according to any one of claims 1 to 3 is executed.

8. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the unmanned ship path planning method according to any one of claims 1 to 3.

Images