A path planning method based on artificial gorilla troop optimization algorithm

Abstract

The application discloses a path planning method based on an artificial gorilla troop optimization algorithm, which comprises the following steps: constructing a global grid environment map model, initializing related parameters of the artificial gorilla troop optimization algorithm, wherein the related parameters comprise a population size, a current iteration number and a maximum iteration number; initializing a current position of an i-th gorilla individual in a gorilla population in the global grid environment map model, evaluating an adaptive value of a gorilla adaptive function; judging whether the current iteration number is less than or equal to the maximum iteration number, and if not, outputting an optimal gorilla position, i.e. a global optimal path; and planning a path for a mobile robot according to the global optimal path. The application solves the problems of weak local search capability and easy falling into a local optimal solution in a traditional robot path planning algorithm.

Description

Technical Field

[0001] This invention relates to the field of mobile robot path planning technology, and in particular to a path planning method based on an optimization algorithm for artificial gorilla troops. Background Technology

[0002] Robot path planning is an important component of intelligent navigation. Specifically, it refers to finding a collision-free optimal or near-optimal path from the starting point to the target point in a space containing certain obstacles. Enabling mobile robots to avoid obstacles and quickly reach the target point mainly relies on improving and optimizing relevant algorithms or developing a new path planning algorithm based on previous algorithms.

[0003] With the development of technology, robot path planning technologies have become increasingly mature. In recent years, biomimetic swarm intelligence algorithms have emerged as a powerful force, achieving significant results in robot path planning. Examples include genetic algorithms, ant colony optimization, particle swarm optimization, and whale optimization. Genetic algorithms, the earliest proposed biomimetic swarm intelligence algorithms, have shown good performance in robot path planning, but their local search capabilities are weak, often yielding suboptimal solutions rather than optimal ones, and they consume significant internal storage space during computation. Ant colony optimization exhibits strong robustness in path planning, but its complex parameter settings make it prone to premature convergence and stagnation. Particle swarm optimization also performs well in path planning, but its search is also prone to premature convergence and getting trapped in local optima. Summary of the Invention

[0004] To address the aforementioned shortcomings, this invention proposes a path planning method based on an artificial gorilla force optimization algorithm. The aim is to solve the problems of weak local search capabilities and easy getting trapped in local optima in traditional robot path planning algorithms.

[0005] To achieve this objective, the present invention adopts the following technical solution:

[0006] A path planning method based on an artificial gorilla troop optimization algorithm includes the following steps:

[0007] Step S1: Construct a global grid environment map model and initialize the relevant parameters of the artificial gorilla army optimization algorithm. The relevant parameters include the population size N, the current iteration number t, and the maximum iteration number Itermax.

[0008] Step S2: In the global grid environment map model, initialize the current position X of the i-th gorilla individual in the gorilla population. i (i = 1, 2, ..., N), evaluate the fitness value of the gorilla fitness function;

[0009] Step S3: Determine whether the current iteration number t is less than or equal to the maximum iteration number Itermax. If not, output the optimal gorilla position, i.e., the globally optimal path.

[0010] If so, update the optimization ability factor C and the leadership ability factor L of the silverback gorilla. The gorilla enters the exploration phase. Determine whether the number of gorillas in the exploration phase is less than or equal to the population size N. If so, update the current position of the gorilla according to the update formula for the exploration phase. If not, calculate the fitness value of the gorilla at the updated position in the exploration phase and compare it with the fitness value of the gorilla at the original position. The position of the gorilla with the larger fitness value is taken as the first optimal position.

[0011] When an individual gorilla enters the development phase, it is determined whether the number of gorillas in the development phase is less than or equal to the population size N. If so, the position is updated based on two mechanisms: following silverback gorillas and competing for adult females. If not, the fitness value of the gorilla at the updated position in the development phase is calculated and compared with the fitness value of the gorilla at the first optimal position. The position of the gorilla with the larger fitness value is taken as the second optimal position, i.e., the global optimal path.

[0012] Step S4: Perform path planning for the mobile robot based on the globally optimal path.

[0013] Preferably, in step S3, the specific calculation formula for the optimization capability factor C is as follows:

[0014]

[0015] Where C is the optimization capability factor; F is the correlation coefficient of optimization capability, calculated by F=cos(2×r4)+1, r4 is the random number updated in each iteration, ranging from 0 to 1; t is the current iteration number, and Itermax is the maximum iteration number;

[0016] The specific formula for calculating the leadership factor L in silverback gorillas is as follows:

[0017] L=C×l

[0018] Where L is the leadership ability factor of silverback gorillas; C is the optimization ability factor; and l is a random value ranging from -1 to 1.

[0019] Preferably, in step S3, the gorilla's current position is updated according to the exploration phase update formula, wherein the exploration phase update formula is as follows:

[0020]

[0021] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X(t) is the current position vector of the gorilla individual; r1, r2, r3, and rand are random values ​​from 0 to 1 updated in each iteration; p is a random value from 0 to 1 that determines the probability of migrating to an unknown location during the exploration phase; UB and LB are the upper and lower bounds of the variable, respectively; X r (t) represents a member of a group of gorillas randomly selected from the original population when rand≥0.5, following the mechanism of moving to other gorillas; GX r (t) represents a member of a group of gorillas randomly selected from the original population when rand < 0.5, following the mechanism of migrating to a known location.

[0022] H = Z × X(t), where Z is a random value of the problem dimension, which is taken within the range of the optimization capability factor C, and the range is [-C to C]. H is the position vector of the current generation in the random dimension.

[0023] Preferably, in step S3, the position is updated based on the judgment of two mechanisms: following silverback gorillas and competing for adult females. Specifically, this includes the following sub-steps:

[0024] Determine whether the optimization ability factor C is greater than or equal to the random scale factor W of the selection mechanism. If so, update the gorilla's position using the position update formula of the silverback gorilla following mechanism; otherwise, update the gorilla's position using the position update formula of the adult female competition mechanism.

[0025] The position update formula for the silverback gorilla following mechanism is as follows:

[0026] GX(t+1)=L×M×(X(t)-X sliverback )+X(t)

[0027] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X(t) is the current position vector of the gorilla individual; X sliverback Let L be the position vector of the silverback gorilla; L is the leadership ability factor of the silverback gorilla.

[0028] M is the following coefficient of the average candidate position vector of the population at the t-th iteration, and the specific calculation formula is as follows:

[0029]

[0030] Among them, GX i (t) represents the candidate position vector for each gorilla individual at the t-th iteration; g is a constant, derived from the equation g = 2. L It was found that L represents the leadership ability factor of silverback gorillas; N represents the population size.

[0031] The position update formula for the mechanism of striving for adult females is as follows:

[0032] GX(t+1)=X sliverback -(X sliverback ×QX(t)×Q)×A

[0033] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X sliverback Let X(t) be the position vector of the silverback gorilla; X(t) be the gorilla's current position vector; Q be the violence conflict factor, Q = 2 × r⁵ - 1, where r⁵ is a random value in the interval [0 ~ 1]; A be the coefficient vector of the degree of violence in the conflict, where A = β × E, β is a parameter value given before the optimization operation, representing the proportional relationship between the coefficient vector A of the degree of violence and the influence coefficient E of violence on the problem-solving dimension; E is the influence coefficient of violence on the problem-solving dimension, where... When rand ≥ 0.5, the value of E is N1, where N1 is equal to the random value in the normal distribution and the dimension of the problem; when rand < 0.5, the value of E is N2, where N2 is equal to the random value in the normal distribution, and rand is a random value between 0 and 1.

[0034] Preferably, step S4 specifically includes the following sub-steps:

[0035] The system determines whether obstacles exist in the globally optimal path. If no obstacles exist, the robot continues to move along the globally optimal path. If obstacles exist, the robot uses an obstacle repulsion field function for obstacle avoidance. The obstacle repulsion field function is as follows:

[0036]

[0037] Among them, U rep (q) represents the repulsive force field function of the obstacle; η represents the repulsive force scale factor; d(q, q) obs ) represents the distance between the mobile robot and the obstacle; q represents the position of the mobile robot; q obs d0 represents the position of the obstacle; d0 represents the radius of the repulsive field of the obstacle.

[0038] Preferably, after using the obstacle repulsion field function to perform obstacle avoidance processing for the mobile robot, a local planned path is obtained. The calculation formula for the local planned path is as follows:

[0039] f(x) = min(d(q, O)) i )+d(O i q goal ))

[0040] Where d(q, O)i d(Q) represents the distance from the mobile robot to the point of tangency between the light ray and the obstacle; i q goal ) represents the distance from the point of tangency between the ray and the obstacle to the target point of the locally planned path; f(x) represents the locally planned path; O i q represents the point of tangency between the i-th ray and the obstacle; q represents the position of the mobile robot; q goal This represents the target point of the local planning path.

[0041] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0042] This scheme utilizes the Artificial Gorilla Squad Optimization Algorithm to obtain the globally optimal path, thereby achieving path planning for the mobile robot. Compared to other algorithms, such as ant colony optimization, particle swarm optimization, and genetic algorithms, the Artificial Gorilla Squad Optimization Algorithm has stronger local search capabilities, higher solution efficiency, and better stability. Furthermore, this algorithm exhibits rapid convergence in the early stages, allowing it to focus more on promising areas during the optimization phase. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating the steps of a path planning method based on an artificial gorilla force optimization algorithm. Detailed Implementation

[0044] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0045] A path planning method based on an artificial gorilla troop optimization algorithm includes the following steps:

[0046] Step S1: Construct a global grid environment map model and initialize the relevant parameters of the artificial gorilla army optimization algorithm. The relevant parameters include the population size N, the current iteration number t, and the maximum iteration number Itermax.

[0047] Step S2: In the global grid environment map model, initialize the current position X of the i-th gorilla individual in the gorilla population. i (i = 1, 2, ..., N), evaluate the fitness value of the gorilla fitness function;

[0048] Step S3: Determine whether the current iteration number t is less than or equal to the maximum iteration number Itermax. If not, output the optimal gorilla position, i.e., the globally optimal path.

[0049] If so, update the optimization ability factor C and the leadership ability factor L of the silverback gorilla. The gorilla enters the exploration phase. Determine whether the number of gorillas in the exploration phase is less than or equal to the population size N. If so, update the current position of the gorilla according to the update formula for the exploration phase. If not, calculate the fitness value of the gorilla at the updated position in the exploration phase and compare it with the fitness value of the gorilla at the original position. The position of the gorilla with the larger fitness value is taken as the first optimal position.

[0050] When an individual gorilla enters the development phase, it is determined whether the number of gorillas in the development phase is less than or equal to the population size N. If so, the position is updated based on two mechanisms: following silverback gorillas and competing for adult females. If not, the fitness value of the gorilla at the updated position in the development phase is calculated and compared with the fitness value of the gorilla at the first optimal position. The position of the gorilla with the larger fitness value is taken as the second optimal position, i.e., the global optimal path.

[0051] Step S4: Perform path planning for the mobile robot based on the globally optimal path.

[0052] This scheme proposes a path planning method based on an artificial gorilla force optimization algorithm, such as... Figure 1 As shown, the first step is to construct a global grid environment map model and initialize the relevant parameters of the artificial gorilla army optimization algorithm. These parameters include the population size N, the current iteration count t, and the maximum iteration count Itermax. Specifically, constructing the global grid environment map model facilitates path planning for the mobile robot, and setting the relevant parameters of the artificial gorilla army optimization algorithm is beneficial for subsequent evaluation of the gorillas' fitness values. The second step is to initialize the current position X of the i-th gorilla individual in the gorilla population within the global grid environment map model. i(i = 1, 2, ..., N), evaluate the fitness value of the gorilla using the fitness function. Specifically, the fitness function, also called the evaluation function, is used to determine the superiority or inferiority of individuals in a population. The fitness value of the gorilla is calculated using the fitness function; a higher fitness value indicates a stronger individual advantage within the population. Further, by comparing the fitness values ​​of all gorillas in the population, the position of the gorilla with the highest fitness value is taken as the global optimal position. In the third step, if the current iteration count reaches the maximum iteration count, the optimal gorilla position is directly output as the global optimal position; if the current iteration count has not reached the maximum iteration count, the iteration loop continues. During the iterative cycle, individual gorillas undergo two phases for position updates: the exploration phase and the development phase. In the exploration phase, it's determined whether the number of gorillas has reached the population size. If not, the current position of the gorilla is updated using the exploration phase update formula. If it has, the fitness value of the gorilla at the updated position is calculated and compared with the fitness value of the gorilla at the original position. If the comparison shows the updated position is better than the original position, it replaces the original position as the first optimal position. In the development phase, it's again determined whether the number of gorillas has reached the population size. If not, due to the two behavioral mechanisms of following silverback gorillas and competing for adult females, the gorilla's position is updated by selecting two different behavioral mechanisms. If it has, the fitness value of the gorilla at the updated position is calculated and compared with the fitness value of the gorilla at the first optimal position. If the comparison shows the updated position is better than the original position, it replaces the first optimal position as the second optimal position, thus obtaining the globally optimal position. In the fifth step, the globally optimal path is calculated and the mobile robot moves along this path. Furthermore, while moving along this optimal path, the mobile robot can detect the surrounding local environment in real time, checking for obstacles. If no obstacles are found, it continues moving along the globally optimal path.

[0053] This scheme utilizes the Artificial Gorilla Squad Optimization Algorithm to obtain the globally optimal path, thereby achieving path planning for the mobile robot. Compared to other algorithms, such as ant colony optimization, particle swarm optimization, and genetic algorithms, the Artificial Gorilla Squad Optimization Algorithm has stronger local search capabilities, higher solution efficiency, and better stability. Furthermore, this algorithm exhibits rapid convergence in the early stages, allowing it to focus more on promising areas during the optimization phase.

[0054] Preferably, in step S3, the specific calculation formula for the optimization capability factor C is as follows:

[0055]

[0056] Where C is the optimization capability factor; F is the correlation coefficient of optimization capability, calculated by F=cos(2×r4)+1, r4 is the random number updated in each iteration, ranging from 0 to 1; t is the current iteration number, and Itermax is the maximum iteration number;

[0057] The specific formula for calculating the leadership factor L in silverback gorillas is as follows:

[0058] L=C×l

[0059] Where L is the leadership ability factor of silverback gorillas; C is the optimization ability factor; and l is a random value ranging from -1 to 1.

[0060] In this embodiment, by calculating the optimization ability factor and the leadership ability factor of the silverback gorilla, it is beneficial to improve the algorithm's ability to search for the optimal solution and further improve the efficiency of mobile robot path planning.

[0061] Preferably, in step S3, the gorilla's current position is updated according to the exploration phase update formula, wherein the exploration phase update formula is as follows:

[0062]

[0063] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X(t) is the current position vector of the gorilla individual; r1, r2, r3, and rand are random values ​​from 0 to 1 updated in each iteration; p is a random value from 0 to 1 that determines the probability of migrating to an unknown location during the exploration phase; UB and LB are the upper and lower bounds of the variable, respectively; X r (t) represents a member of a group of gorillas randomly selected from the original population when rand≥0.5, following the mechanism of moving to other gorillas; GX r (t) represents a member of a group of gorillas randomly selected from the original population when rand < 0.5, following the mechanism of migrating to a known location.

[0064] H = Z × X(t), where Z is a random value of the problem dimension, which is taken within the range of the optimization capability factor C, and the range is [-C to C]. H is the position vector of the current generation in the random dimension.

[0065] In this embodiment, the gorilla's current position is updated using an update formula during the exploration phase. This helps to find the gorilla's optimal position and further realize the path planning of the mobile robot.

[0066] Preferably, in step S3, the position is updated based on the judgment of two mechanisms: following silverback gorillas and competing for adult females. Specifically, this includes the following sub-steps:

[0067] Determine whether the optimization ability factor C is greater than or equal to the random scale factor W of the selection mechanism. If so, update the gorilla's position using the position update formula of the silverback gorilla following mechanism; otherwise, update the gorilla's position using the position update formula of the adult female competition mechanism.

[0068] The position update formula for the silverback gorilla following mechanism is as follows:

[0069] GX(t+1)=L×M×(X(t)-X sliverback )+X(t)

[0070] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X(t) is the current position vector of the gorilla individual; X sliverback Let L be the position vector of the silverback gorilla; L is the leadership ability factor of the silverback gorilla.

[0071] M is the following coefficient of the average candidate position vector of the population at the t-th iteration, and the specific calculation formula is as follows:

[0072]

[0073] Among them, GX i (t) represents the candidate position vector for each gorilla individual at the t-th iteration; g is a constant, derived from the equation g = 2. L It was found that L represents the leadership ability factor of silverback gorillas; N represents the population size.

[0074] The position update formula for the mechanism of striving for adult females is as follows:

[0075] GX(t+1)=X sliverback -(X sliverback ×QX(t)×Q)×A

[0076] Where GX(t+1) is the candidate position vector of the gorilla individual in the next iteration; X sliverback Let X(t) be the position vector of the silverback gorilla; X(t) be the gorilla's current position vector; Q be the violence conflict factor, Q = 2 × r⁵ - 1, where r⁵ is a random value in the interval [0 ~ 1]; A be the coefficient vector of the degree of violence in the conflict, where A = β × E, β is a parameter value given before the optimization operation, representing the proportional relationship between the coefficient vector A of the degree of violence and the influence coefficient E of violence on the problem-solving dimension; E is the influence coefficient of violence on the problem-solving dimension, where... When rand ≥ 0.5, the value of E is N1, where N1 is equal to the random value in the normal distribution and the dimension of the problem; when rand < 0.5, the value of E is N2, where N2 is equal to the random value in the normal distribution, and rand is a random value between 0 and 1.

[0077] In this embodiment, two behavioral mechanisms exist during the development phase: following the silverback gorilla and competing for adult females. When the optimization ability factor C is greater than or equal to the random scale factor W of the selection mechanism, the mechanism of following the silverback gorilla is selected, and the gorilla's position is updated. When the optimization ability factor C is less than the random scale factor W of the selection mechanism, the mechanism of competing for adult females is selected, and the gorilla's position is updated. By updating the gorilla's position, it is beneficial to find the gorilla's optimal position, further realizing the path planning of the mobile robot.

[0078] Preferably, step S4 specifically includes the following sub-steps:

[0079] The system determines whether obstacles exist in the globally optimal path. If no obstacles exist, the robot continues to move along the globally optimal path. If obstacles exist, the robot uses an obstacle repulsion field function for obstacle avoidance. The obstacle repulsion field function is as follows:

[0080]

[0081] Among them, U rep (q) represents the repulsive force field function of the obstacle; η represents the repulsive force scale factor; d(q, q) obs ) represents the distance between the mobile robot and the obstacle; q represents the position of the mobile robot; q obs d0 represents the position of the obstacle; d0 represents the radius of the repulsive field of the obstacle.

[0082] In this embodiment, as the mobile robot moves along the globally optimal path, an infrared distance sensor installed on the robot can scan the surrounding environment in real time and detect whether there are obstacles in the globally optimal path. If no obstacles are detected, the mobile robot will continue to move along the globally optimal path. If an obstacle is detected, a repulsive field is applied to the obstacle, i.e., the obstacle is expanded. This ensures the safe distance for obstacle avoidance of the mobile robot. Specifically, the distance between the mobile robot and the obstacle is measured by the infrared distance sensor, and it is determined whether the distance between the two is less than the radius of the obstacle's repulsive field. If so, a stopping strategy is adopted, the path to the target point is replanned, and the robot continues to move forward. If not, the obstacle has no repulsive effect on the mobile robot.

[0083] Preferably, after using the obstacle repulsion field function to perform obstacle avoidance processing for the mobile robot, a local planned path is obtained. The calculation formula for the local planned path is as follows:

[0084] f(x) = min(d(q, O)) i )+d(O i q goal ))

[0085] Where d(q, O) i ) represents the distance from the mobile robot to the point where the light ray is tangent to the obstacle; d(O i q goal ) represents the distance from the point of tangency between the ray and the obstacle to the target point of the locally planned path; f(x) represents the locally planned path; O i q represents the point of tangency between the i-th ray and the obstacle; q represents the position of the mobile robot; q goal This represents the target point of the local planning path.

[0086] In this embodiment, the calculation of the local planning path involves the BUG2 algorithm. This solution uses the BUG2 algorithm for local path planning. First, based on the detection radius of the infrared distance sensor, the path detours along the boundary of the obstacle repulsion field region, thus ensuring a safe distance while avoiding obstacles. Then, it continues to move towards the target point along the initial global planning path. Due to the arbitrariness of the location map and obstacles, and its simple calculation characteristics, the BUG2 algorithm is highly effective in obstacle avoidance. By incorporating the obstacle repulsion field, the obstacle avoidance path becomes safer and smoother.

[0087] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0088] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A path planning method based on artificial gorilla troop optimization algorithm, characterized in that: The method comprises the following steps: Step S1: constructing a global grid environment map model, initializing related parameters of the artificial gorilla troop optimization algorithm, the related parameters including a population size N, a current iteration number t and a maximum iteration number Itermax; Step S2: In the global grid environment map model, the current position X of the i-th gorilla individual in the gorilla population is initialized i (i = 1, 2, …, N), the fitness value of the gorilla fitness function is evaluated; Step S3: determining whether the current iteration number t is less than or equal to the maximum iteration number Itermax, if not, outputting an optimal gorilla position, that is, a global optimal path; if yes, updating an optimization ability factor C and a leadership ability factor L of a silver-backed gorilla, and the gorilla individual entering an exploration stage, and determining whether the number of gorilla individuals in the exploration stage is less than or equal to the population size N, if yes, updating the current position of the gorilla according to an exploration stage updating formula; if not, calculating an adaptive value of the gorilla at the updated position in the exploration stage, and comparing the adaptive value with an adaptive value of the gorilla at the original position, and taking the position of the gorilla with the greater adaptive value as a first optimal position; the gorilla individual entering a development stage, and determining whether the number of gorilla individuals in the development stage is less than or equal to the population size N, if yes, updating the position of the gorilla through the judgment of the two mechanisms of following the silver-backed gorilla and competing for adult females; if not, calculating an adaptive value of the gorilla at the updated position in the development stage, and comparing the adaptive value with an adaptive value of the gorilla at the first optimal position, and taking the position of the gorilla with the greater adaptive value as a second optimal position, that is, a global optimal path; Step S4: planning a path for the mobile robot according to the global optimal path.

2. The path planning method based on the artificial gorilla troop optimization algorithm according to claim 1, characterized in that: In step S3, the specific calculation formula of the optimization ability factor C is as follows: wherein C is the optimization ability factor; F is a related coefficient of the optimization ability, which is calculated by F = cos(2 x r4) + 1, r4 is a random number updated each time, ranging from 0 to 1; t is the current iteration number, and Itermax is the maximum iteration number; The specific calculation formula of the leadership ability factor L of the silver-backed gorilla is as follows: L = C x l wherein L is the leadership ability factor of the silver-backed gorilla; C is the optimization ability factor; and l is a random number value, ranging from -1 to 1.

3. The path planning method based on the artificial gorilla troop optimization algorithm according to claim 1, characterized in that: In step S3, the current position of the gorilla is updated according to an exploration stage updating formula, wherein the exploration stage updating formula is as follows: where GX(t+1) is the candidate position vector of the gorilla individual at the next iteration; X(t) is the current position vector of the gorilla individual; r1, r2, r3, and rand are random values from 0 to 1 updated at each iteration; p is a random value from 0 to 1 that determines the probability of the exploration phase migrating to an unknown position; UB and LB are the upper and lower bounds of the variable, respectively; X r (t) is the update formula that, when rand≥ 0.5, follows a mechanism of moving to other gorillas, randomly selecting a member from a group of gorillas in the original entire population; GX r (t) is the update formula that, when rand< 0.5, follows a mechanism of migrating to known positions, randomly selecting a member from a group of gorillas in the original entire population; H = Z x X(t), Z is a random value of the problem dimension, taking a random value within the range of the optimization ability factor C, ranging from -C to C, and H is a position vector of the current generation in the random dimension.

4. The path planning method based on the artificial gorilla troop optimization algorithm according to claim 1, characterized in that: In step S3, the position of the gorilla is updated through the judgment of the two mechanisms of following the silver-backed gorilla and competing for adult females, specifically including the following sub-steps: determining whether the optimization ability factor C is greater than or equal to a random scale factor W of the selection mechanism, if yes, updating the position of the gorilla by using a position updating formula of the mechanism of following the silver-backed gorilla; if not, updating the position of the gorilla by using a position updating formula of the mechanism of competing for adult females; wherein the position updating formula of the mechanism of following the silver-backed gorilla is as follows: GX(t+1) = L x M x (X(t) - X sliverback ) + X(t) wherein GX(t+1) is the candidate position vector of the gorilla individual at the next iteration; X(t) is the current position vector of the gorilla individual; X sliverback is the position vector of the silverback gorilla; L is the leadership factor of the silverback gorilla; M is a following coefficient of the average candidate position vector of the population at the tth iteration, and the specific calculation formula is as follows: wherein, GX i (t) is the candidate position vector of each gorilla individual at the tth iteration; g is a constant, derived from the formula g = 2 L L is derived as the silverback gorilla leadership factor; N is the population size; the position updating formula of the mechanism of competing for adult females is as follows: GX(t+1) = X sliverback - (X sliverback × Q - X(t) × Q) × A wherein GX(t+1) is the candidate position vector of gorilla individual at next iteration; X sliverback is the position vector of silverback gorilla; X(t) is the current position vector of gorilla; Q is the violence conflict factor, Q = 2xr5-1, r5 is a random value in the interval of [0-1]; A is the coefficient vector of violence degree in conflict, wherein A = βxE, β is the given parameter value before optimization operation, indicating the proportional relationship between the coefficient vector A of violence degree and the influence coefficient E of violence on problem dimension; E is the influence coefficient of violence on problem dimension, wherein, When rand≥0.5, the value of E is N1, N1 is equal to a random value in normal distribution and problem dimension; when rand<0.5, the value of E is N2, N2 is equal to a random value in normal distribution, rand is a random value between 0 and 1.

5. The path planning method based on the artificial gorilla troop optimization algorithm according to claim 1, characterized in that: In step S4, specifically including the following sub-steps: Judge whether there is an obstacle in the global optimal path, if there is no obstacle, the mobile robot continues to move along the global optimal path; if there is an obstacle, the obstacle repulsive field function is used for obstacle avoidance processing of the mobile robot, and the obstacle repulsive field function is as follows: where U rep (q) represents an obstacle repulsive force field function; η represents a repulsive force scale factor; d(q, q obs ) represents a distance between the mobile robot and the obstacle; q represents a position of the mobile robot; q obs represents a position of the obstacle; do represents a repulsive force field radius of the obstacle.

6. The path planning method based on the artificial gorilla troop optimization algorithm according to claim 5, characterized in that: After the obstacle avoidance processing of the mobile robot is performed by using the obstacle repulsive field function, a local planning path is obtained, and a calculation formula of the local planning path is as follows: f(x) = min(d(q, O i )+d(O i , q goal )) where d(q, O i ) denotes the distance from the mobile robot to the ray-obstacle intersection; d(O i , q goal ) denotes the distance from the ray-obstacle intersection to the goal point of the local planning path; f(x) denotes the local planning path; O i denotes the i-th ray-obstacle intersection; q denotes the position of the mobile robot; q goal denotes the goal point of the local planning path.

Images