Robot path planning method and system based on improved litsea rotundifolia optimization algorithm
By improving the Golden Jackal optimization algorithm and combining the position update mechanisms of the Cordyceps optimization and Krill swarm algorithms, the shortcomings of the Golden Jackal optimization algorithm in path planning under complex scenarios are solved, and faster and better path planning results are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-15
- Publication Date
- 2026-03-13
AI Technical Summary
Existing Golden Jackal optimization algorithms struggle to fully traverse the solution space in complex scenarios during path planning, leading to the omission of globally optimal paths. Furthermore, they exhibit slow convergence when employing conservative local search strategies, resulting in poor adaptability.
The location update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm is introduced to improve the exploration and development stage of the golden jackal optimization algorithm. By comprehensively considering factors such as the optimal position of the golden jackal, the search coefficient of Cordyceps, the search step size and the effective coefficient of individual krill, the position of the golden jackal is updated, thereby enhancing the global search capability and convergence speed.
It enables full traversal and exploration of path solutions in complex scenarios, avoids local optima, improves the robustness and adaptability of path planning, and obtains better path planning results.
Smart Images
Figure CN121655558A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of robot path planning technology, specifically to a robot path planning method and system based on an improved Golden Jackal optimization algorithm. Background Technology
[0002] Path planning is a key technology in mobile robotics. Path planning technology enables mobile robots to automatically find a collision-free trajectory from a starting point to a destination based on information about their surrounding environment. The path planning algorithm is the core of mobile robot path planning. Path planning refers to a mobile robot's ability to autonomously plan an optimal movement path from its starting point to its destination after perceiving its surrounding environment. This optimal path can satisfy requirements such as minimizing the distance traveled, minimizing travel time, or minimizing energy consumption.
[0003] Path planning can actually be viewed as a complex optimization problem with constraints. Therefore, some intelligent optimization algorithms have played a positive role in improving the effectiveness of path planning, and many scholars have carried out a lot of research. The Golden Jackal Optimization Algorithm (GJOA) is a new metaheuristic algorithm proposed in 2022. This algorithm is a new type of intelligent optimization algorithm that imitates the cooperative hunting behavior of golden jackals and can also be applied to robot path planning problems. For example, the mobile robot path planning based on the hybrid golden jackal optimization algorithm with improved particle swarm optimization proposed by Chang Xinzhong et al. (Chang Xinzhong, Yue Zhepeng, Gao Haichao, et al. Mobile robot path planning based on the hybrid golden jackal optimization algorithm with improved particle swarm optimization [J]. Journal of Zhongyuan University of Technology, 2023, 34(4):24-29.). However, existing Golden Jackal optimization algorithms still have some shortcomings when applied to path planning: In path planning tasks that require the shortest path, the least time, or the lowest energy consumption, due to the wide range of solution spaces and the diversity of solutions in complex scenarios, existing Golden Jackal optimization algorithms often cannot fully traverse and explore all possible path solutions. This increases the possibility of missing globally optimal paths and often fails to achieve the ideal path planning effect. Summary of the Invention
[0004] This invention provides a robot path planning method based on an improved golden jackal optimization algorithm, which can quickly obtain the optimal path planning results.
[0005] Specifically, the following steps are included: The environment of the mobile robot is modeled to obtain a map of the mobile area, and the map of the mobile area is rasterized to obtain a raster map. Based on the grid map, establish an objective function for robot path planning with constraints of the shortest movement path, the shortest time, or the least energy consumption; determine the constraints and the number of key nodes. A population of golden jackals is randomly generated. Each individual in the population corresponds to a path in a raster map from the starting point to the ending point that meets the requirement of the number of critical nodes. Based on the objective function and constraints, the optimal position is updated using an improved golden jackal optimization algorithm to determine the optimal golden jackal individual, and its corresponding path is the optimal path planning result. The improved golden jackal optimization algorithm involves introducing the position update mechanisms of the Cordyceps optimization algorithm and the krill swarm algorithm into the exploration and development phases of the original golden jackal optimization algorithm to improve the golden jackal position update method. This is achieved by considering the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator phase, and the effective coefficient of the krill individual, as well as the mechanism of gradually decreasing the search step size of the Cordyceps as the number of iterations increases.
[0006] Preferably, the step of updating the optimal position and determining the optimal golden jackal individual by using an improved golden jackal optimization algorithm based on the objective function and constraints, with the corresponding path being the optimal path planning result, includes the following steps: Determine the objective function and constraints for robot path planning that are constrained by the shortest movement path, the shortest time, or the least energy consumption. A population of golden jackals with a preset number of individuals is randomly generated. Each individual in the golden jackal population corresponds to a path from the starting point to the ending point in a grid map that meets the key node count requirement. The maximum number of iterations is determined, and the upper and lower boundaries for optimization are found. The fitness value of the prey is calculated based on the objective function. The prey with the best fitness value is designated as the male golden jackal, and the prey with the second best fitness value is designated as the female golden jackal. Solve for the escape energy of the current prey. If the prey escapes, energy| E If |≥ 1, proceed to the exploration phase, calculate the location of the prey, re-identify the male and female golden jackals, and update the location of the golden jackals; otherwise, proceed to the development phase to calculate the location of the prey. Determine whether the stopping condition is met, i.e., convergence or reaching the maximum number of iterations, output the optimal prey, and determine the optimal planning path result.
[0007] Preferably, the constraints include boundary constraints, obstacle constraints, and walking mode constraints; the walking mode constraints include inter-grid walking modes and the maximum walking grid.
[0008] Preferably, if the prey escapes with energy |E| ≥ 1, the exploration phase begins, calculating the prey's location, re-identifying the male and female golden jackals, and updating the jackal's location, including the following steps: The improved formula for updating the positions of male and female golden jackals is as follows: ; ; In the formula: t This represents the current iteration number; For the first t The location of the prey in the next iteration; , The first t The positions of the male and female golden jackals in the next iteration; , These represent the updated positions of the male and female golden jackals corresponding to the prey in the t-th iteration; This represents a random number based on the Lévy distribution; Let be the position of the golden jackal in the t-th iteration; ; ; ; ; In the formula: A random number within the range [0,1]; The search coefficient describes the random search step size when a Cordyceps individual moves to a better position; A random number uniformly distributed within the interval [0,1]. It is a random integer that takes the value 1 or 2. This represents the search step size of Cordyceps in the spiral ascent operator stage; A random number uniformly distributed within the interval [0,1]. This indicates that Cordyceps has a larger search step size in the early stages of iteration, while the search step size gradually decreases in the later stages of iteration. It is the effective coefficient of individual krill; A random number between [0, 1]; The formula for updating the position of the golden jackal has been improved as follows: ; In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
[0009] Preferably, the step of calculating the location of the prey during the development phase includes the following steps: The improved formula for updating the positions of male and female golden jackals is as follows: ; ; In the formula: tThis represents the current iteration number; Let be the position of the prey in the t-th iteration, and be the current optimal solution; , These represent the positions of the male and female golden jackals in the t-th iteration, respectively. , The first t The updated positions of the male and female golden jackals corresponding to the prey in the next iteration; The formula for updating the golden jackal's position is as follows: ; In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
[0010] This invention also proposes a robot path planning system based on an improved golden jackal optimization algorithm, the system comprising: The grid map generation module is used to model the environment of the mobile robot, obtain a map of the mobile area, and perform gridding processing on the map of the mobile area to obtain a grid map. The path planning module is used to establish an objective function for robot path planning based on a grid map, with constraints of minimizing the shortest movement path, the shortest time, or the least energy consumption; determine the constraints and the number of key nodes; randomly generate a golden jackal population, with each individual in the population corresponding to a path from the starting point to the ending point on the grid map that meets the key node requirement; and update the optimal position using an improved golden jackal optimization algorithm based on the objective function and constraints to determine the optimal golden jackal individual, whose corresponding path is the optimal path planning result. The improved golden jackal optimization algorithm is as follows: in the exploration and development phases of the original golden jackal optimization algorithm, the position update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm is introduced to improve the golden jackal position update method. The update is based on factors such as the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator stage, and the effective coefficient of the krill individual, as well as the mechanism of gradually decreasing the search step size of the Cordyceps as the number of iterations increases.
[0011] The present invention also proposes a computer-readable storage medium storing a data processing program, which, when executed by a processor, implements the steps of the robot path planning method based on the improved golden jackal optimization algorithm.
[0012] The beneficial effects of this invention are: This invention proposes a robot path planning method based on an improved golden jackal optimization algorithm. This method uses an improved golden jackal optimization algorithm to optimize the path planning scheme and introduces the position update mechanism of the cordyceps optimization algorithm and the krill swarm algorithm to enhance the optimization performance of the algorithm and obtain better path planning results.
[0013] In the GJOA exploration phase, to more effectively improve the algorithm's global search capability, a position update mechanism combining the Cordyceps optimization algorithm and the krill swarm algorithm was introduced. This improved the golden jackal position update method, comprehensively considering factors such as the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator stage, the gradual decrease in the search step size of the Cordyceps as the number of iterations increases, and the effective coefficient of individual krill to update the golden jackal position. This avoids local optima in each iteration, and thus fully traverses and explores all possible path schemes to find a globally optimal path.
[0014] During the development phase of GJOA, in order to more effectively improve the convergence speed of the algorithm, the position update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm was introduced to improve the golden jackal position update method. The golden jackal position was updated by comprehensively considering factors such as the optimal position of the golden jackal in this iteration, the search coefficient of Cordyceps, the search step size of Cordyceps in the spiral ascent operator stage, the gradual decrease of the search step size of Cordyceps as the number of iterations increases, and the effective coefficient of individual krill. This avoids the loss of population diversity during the solution search process and makes the search process in the global solution space of each path planning scheme less likely to converge prematurely. It can plan feasible paths with strong robustness and better adaptability in obstacle-dense or dynamic scenarios. Attached Figure Description
[0015] Figure 1 This is a flowchart of the robot path planning method according to an embodiment of the present invention; Figure 2 This is a flowchart of the improved golden jackal optimization algorithm according to an embodiment of the present invention; Figure 3 This is a path planning result diagram of an embodiment of the present invention; Figure 4 This is the iterative process curve of an embodiment of the present invention. Detailed Implementation
[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.
[0017] Example 1 This invention proposes a robot path planning method based on an improved golden jackal optimization algorithm, the flowchart of which is shown below. Figure 1 As shown, the specific steps are as follows: S1: Model the environment of the mobile robot to obtain a map of the mobile area, and then rasterize the map of the mobile area to obtain a raster map.
[0018] S2: Based on the grid map, establish an objective function for robot path planning with constraints of the shortest movement path, the shortest time, or the least energy consumption; determine the constraints and the number of key nodes.
[0019] S3: Randomly generate a population of golden jackals. Each individual in the golden jackal population corresponds to a path in the raster map from the starting point to the ending point that meets the requirement of the number of critical nodes.
[0020] S4: Based on the objective function and constraints, the optimal position is updated using an improved golden jackal optimization algorithm to determine the optimal golden jackal individual, and its corresponding path is the optimal path planning result. The improved golden jackal optimization algorithm is as follows: In the exploration and development stages of the original golden jackal optimization algorithm, the position update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm is introduced to improve the golden jackal position update method. The optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator stage, and the effective coefficient of the krill individual, as well as the mechanism of the Cordyceps gradually decreasing the search step size as the number of iterations increases, are used to update the golden jackal position.
[0021] Specifically, the Golden Jackal Optimization Algorithm (GJOA) is a novel metaheuristic algorithm proposed in 2022. This algorithm is a new type of intelligent optimization algorithm that imitates the cooperative hunting behavior of golden jackals and can also be applied to robot path planning problems. However, the existing Golden Jackal Optimization Algorithm still has some defects: (1) During the exploration phase, the Golden Jackal Optimization Algorithm cannot effectively cover the entire problem search space, which may lead to the algorithm getting stuck in local optima. (2) During the development phase, the Golden Jackal Optimization Algorithm converges slowly due to its overly conservative local search strategy. For example, it relies too much on the optimal solution, and the population diversity may be lost rapidly, causing the algorithm to converge to a local optimum too early, resulting in poor adaptability to solving complex problems.
[0022] Therefore, such as Figure 2 As shown, this invention proposes an improved golden jackal optimization algorithm, the optimization of which includes the following steps: S2.1: Determine the objective function and constraints for robot path planning, which are constrained to minimize the movement path, the time taken, or the energy consumed.
[0023] S2.2: Set the parameters, mainly including: population size (i.e., the number of golden jackals) N; maximum number of iterations (i.e., the condition for stopping the iteration). T ; Problem optimization lower boundary ; Problem optimization upper boundary .
[0024] S2.3: The mathematical description of the initialization of the golden jackal population is as follows: (1); In the formula: This indicates the location of the initial golden jackal population. It is a random number in the range [0,1]. and These are the upper and lower boundaries of the problem to be solved.
[0025] In the GJOA algorithm, the prey matrix is represented as: (2); In the formula: For the prey matrix; For the first i The first prey j Dimensional position; The winners of the first and second place rankings (the one with the best and second-best fitness values) are paired together as the Golden Jackal Pair; n The number of prey; d The dimensions for solving the problem.
[0026] S2.4: According to the objective function The fitness value of the prey is calculated, and the one with the best fitness value is designated as the male golden jackal, while the one with the second best fitness value is designated as the female golden jackal.
[0027] During the optimization process, the fitness value of each prey is estimated using a fitness (objective) function, and the fitness value matrix of all prey is represented as follows: (3); In the formula: This is the fitness value matrix of the prey; The fitness function or objective function is used; the jackal with the best fitness value is designated as the male, and the jackal with the second best fitness value is designated as the female. The location of the prey obtained by each jackal is determined.
[0028] S2.5: Calculate the prey's escape energy : (4); This indicates the process of the prey's energy decreasing. This indicates the initial energy state of the prey.
[0029] (5); In the formula: r is a random number in the range [0,1].
[0030] (6); In the formula: T This represents the maximum number of iterations. It is a constant with a value of 1.5; tThis represents the current iteration number. Throughout the entire iteration process, It decreases linearly from 1.5 to 0.
[0031] S2.6: Energy if prey escapes | E If |≥1, proceed to the exploration stage and calculate the location of the prey; otherwise, proceed to the development stage and calculate the location of the prey.
[0032] Specifically, the exploration and development phases include the following steps: (1) Exploration stage: In the GJOA exploration phase, to more effectively improve the algorithm's global search capability, a position update mechanism combining the Cordyceps optimization algorithm and the krill swarm algorithm was introduced. This improved the golden jackal position update method, comprehensively considering factors such as the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascent operator stage, the gradual decrease in the search step size of the Cordyceps as the number of iterations increases, and the effective coefficient of individual krill to update the golden jackal position. This avoids local optima in each iteration, thereby improving the algorithm's global search capability and effectively covering the entire problem search space.
[0033] The Cordyceps Optimization Algorithm (COA) is an intelligent optimization algorithm inspired by the growth mechanism of Cordyceps. Its position update mechanism revolves around the "Cordyceps search coefficient," which dynamically balances global exploration and local development. In the spiral ascent operator stage, the search step size is jointly regulated by the search coefficient and a random factor, guiding individuals to explore along a spiral path and enhancing global optimization capabilities. As the number of iterations increases, the search coefficient decreases according to a preset rule (e.g., linear or nonlinear), thus gradually reducing the search step size. This design allows the algorithm to favor large-scale exploration in the early stages and shift towards refined development in the later stages, effectively improving convergence accuracy and stability. The adaptive step size reduction mechanism is a key feature of COA in avoiding premature convergence and achieving efficient optimization. Therefore, this invention introduces the Cordyceps search coefficient, the search step size of Cordyceps in the spiral ascent operator stage, and an update mechanism where the search step size gradually decreases as the number of iterations increases into the position update mechanism, focusing on improving the convergence accuracy and stability of the algorithm.
[0034] The krill swarm algorithm's position update mechanism uses the "effective coefficient of individual krill" as its core regulator, driving each individual to move through a combination of three components: induced movement (group social interaction), foraging movement (approaching the optimum), and random diffusion (exploration perturbation). The effective coefficient specifically refers to the weight of the directional movements induced and foraging, which decreases linearly with iteration. In the early stages of the search, a larger effective coefficient grants dominance to directional movements, enabling the population to quickly aggregate under strong guidance and perform efficient global exploration. As iterations deepen, the effective coefficient gradually decreases, the directional guidance effect weakens, and the relative influence of random diffusion increases, naturally transitioning the algorithm to a refined development phase near the optimal region. This coefficient cleverly achieves a dynamic balance and smooth transition from "exploration" to "utilization," a key design element ensuring its global optimization capability and final convergence accuracy. Therefore, this invention incorporates the effective coefficient of individual krill into the algorithm for adjustment, enhancing its global search capability.
[0035] During the exploration phase of GJOA, the Cordyceps optimization algorithm and the krill swarm algorithm were introduced. The improved position update formulas for male and female golden jackals are as follows: (7); (8); In the formula: t This represents the current iteration number; For the first t The location of the prey in the next iteration; , The first t The positions of the male and female golden jackals in the next iteration; , These represent the updated positions of the male and female golden jackals corresponding to the prey in the t-th iteration; This represents a random number based on the Lévy distribution; For the first t The position of the golden jackal in the next iteration; (9); (10); (11); (12); In the formula: A random number within the range [0,1]; The search coefficient describes the random search step size when a Cordyceps individual moves to a better position; A random number uniformly distributed within the interval [0,1]. It is a random integer that takes the value 1 or 2. This represents the search step size of Cordyceps in the spiral ascent operator stage; A random number uniformly distributed within the interval [0,1]. This indicates that Cordyceps has a larger search step size in the early stages of iteration, while the search step size gradually decreases in the later stages of iteration. It is the effective coefficient of individual krill; A random number between [0, 1]; The formula for updating the position of the golden jackal has been improved as follows: (13); In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
[0036] Furthermore, A random number based on the Lévy distribution can be calculated using the following formula: (14); This is the Lévy flight function, and its calculation method is as follows: (15); In the formula: and A random number within the range (0,1); This is a default constant with a value of 1.5.
[0037] (2) Development stage: During the development phase of GJOA, in order to more effectively improve the convergence speed of the algorithm, the position update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm was introduced to improve the golden jackal position update method. The golden jackal position was updated by comprehensively considering factors such as the optimal position of the golden jackal in this iteration, the search coefficient of Cordyceps, the search step size of Cordyceps in the spiral ascent operator stage, the gradual decrease of the search step size of Cordyceps as the number of iterations increases, and the effective coefficient of individual krill. This avoids the possibility of rapid loss of population diversity, which could cause the algorithm to converge to a local optimum too early, thereby improving the convergence speed of the algorithm.
[0038] During the development phase of GJOA, the Cordyceps optimization algorithm and the krill swarm algorithm were introduced. The improved position update formulas for male and female golden jackals are as follows: The improved formula for updating the positions of male and female golden jackals is as follows: (16); (17); In the formula: t This represents the current iteration number; Let be the position of the prey in the t-th iteration, and be the current optimal solution; , These represent the positions of the male and female golden jackals in the t-th iteration, respectively. , The first t The updated positions of the male and female golden jackals corresponding to the prey in the next iteration; The formula for updating the golden jackal's position is as follows: (18); In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
[0039] S2.7: Determine if the stopping condition is met, i.e., the fitness value converges or the maximum number of iterations is reached. If not, repeat S2.4-S2.6; otherwise, output the optimal golden jackal individual, i.e. the optimal planning path result.
[0040] In this embodiment: Using MATLAB as the simulation platform, a 20×20 grid map of the mobile robot was established. The GJOA and IGJOA methods were analyzed with the goal of minimizing the travel distance. The parameters for the GJOA algorithm were: Popsize=50, Maxiter=200, LB = 1, UB=20; the parameters for the IGJOA algorithm were: Popsize=50, Maxiter=200, LB = 1, UB=20. The simulation environment and the travel paths obtained by the two methods are shown below. Figure 3 As shown, Figure 4 The curve represents the iterative process. Table 1 compares the data results of the two algorithms.
[0041] Table 1. Comparison of algorithm path results; from Figure 3 It can be intuitively observed that the movement path obtained by GJOA is longer and more circuitous than that obtained by IGJOA, while the path obtained by ISOA is more reasonable. Further analysis... Figure 3 and Figure 4 The results show that the GJOA algorithm converges more slowly, while the IGJOA algorithm converges faster and finds a better path more quickly. It can be seen that the IGJOA algorithm designed in this paper has a faster convergence speed and higher convergence accuracy, while GJOA tends to get trapped in local optima. Simulation results demonstrate that under various identical environments, the IGJOA algorithm has stronger search capabilities and obtains a better movement path, verifying the effectiveness of the algorithm.
[0042] The above is one embodiment of the robot path planning method based on the improved Golden Jackal optimization algorithm. Based on the same idea, this embodiment also provides a corresponding robot path planning system based on the improved Golden Jackal optimization algorithm. Specific limitations of the robot path planning system based on the improved Golden Jackal optimization algorithm can be found in the limitations of the robot path planning method based on the improved Golden Jackal optimization algorithm described above, and will not be repeated here. Each module in the above-described robot path planning system based on the improved Golden Jackal optimization algorithm can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0043] This embodiment also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 A robot path planning method based on an improved golden jackal optimization algorithm is provided.
[0044] Those skilled in the art will understand that implementing all or part of the processes in the methods of the above embodiments can be accomplished by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0045] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A robot path planning method based on an improved golden jackal optimization algorithm, characterized in that, Includes the following steps: The environment of the mobile robot is modeled to obtain a map of the mobile area, and the map of the mobile area is rasterized to obtain a raster map. Based on the grid map, establish an objective function for robot path planning with constraints of the shortest movement path, the shortest time, or the least energy consumption; determine the constraints and the number of key nodes. A population of golden jackals is randomly generated. Each individual in the population corresponds to a path in a raster map from the starting point to the ending point that meets the requirement of the number of critical nodes. Based on the objective function and constraints, the optimal position is updated using an improved golden jackal optimization algorithm to determine the optimal golden jackal individual, and its corresponding path is the optimal path planning result. The improved golden jackal optimization algorithm involves introducing the position update mechanisms of the Cordyceps optimization algorithm and the krill swarm algorithm into the exploration and development phases of the original golden jackal optimization algorithm to improve the golden jackal position update method. This is achieved by considering the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator phase, and the effective coefficient of the krill individual, as well as the mechanism of gradually decreasing the search step size of the Cordyceps as the number of iterations increases.
2. The robot path planning method based on the improved golden jackal optimization algorithm according to claim 1, characterized in that, The process of updating the optimal position of a golden jackal based on the objective function and constraints, determining the optimal golden jackal individual, and identifying its corresponding path as the optimal path planning result, includes the following steps: Determine the objective function and constraints for robot path planning that are constrained by the shortest movement path, the shortest time, or the least energy consumption. A population of golden jackals with a preset number of individuals is randomly generated. Each individual in the golden jackal population corresponds to a path from the starting point to the ending point in a grid map that meets the key node count requirement. The maximum number of iterations is determined, and the upper and lower boundaries for optimization are found. The fitness value of the prey is calculated based on the objective function. The prey with the best fitness value is designated as the male golden jackal, and the prey with the second best fitness value is designated as the female golden jackal. Solve for the escape energy of the current prey. If the prey escapes, energy| E If |≥ 1, proceed to the exploration phase, calculate the location of the prey, re-identify the male and female golden jackals, and update the location of the golden jackals; otherwise, proceed to the development phase to calculate the location of the prey. Determine whether the stopping condition is met, i.e., convergence or reaching the maximum number of iterations, output the optimal prey, and determine the optimal planning path result.
3. The robot path planning method based on the improved golden jackal optimization algorithm according to claim 2, characterized in that, The constraints include boundary constraints, obstacle constraints, and walking pattern constraints; the walking pattern constraints include inter-grid walking patterns and the maximum walking grid.
4. The robot path planning method based on the improved golden jackal optimization algorithm according to claim 2, characterized in that, If the prey escapes with energy |E|≥ 1, the exploration phase begins. The prey's location is calculated, the male and female golden jackals are re-identified, and their locations are updated. This includes the following steps: The improved formula for updating the positions of male and female golden jackals is as follows: ； ； In the formula: t This represents the current iteration number; For the first t The location of the prey in the next iteration; , The first t The positions of the male and female golden jackals in the next iteration; , These are the updated positions of the male and female golden jackals corresponding to the prey in the t-th iteration, respectively. This represents a random number based on the Lévy distribution; Let be the position of the golden jackal in the t-th iteration; ； ； ； ； In the formula: A random number within the range [0,1]; The search coefficient describes the random search step size when a Cordyceps individual moves to a better position; A random number uniformly distributed within the interval [0,1]. It is a random integer that takes the value 1 or 2. This represents the search step size of Cordyceps in the spiral ascent operator stage; A random number uniformly distributed within the interval [0,1]. This indicates that Cordyceps has a larger search step size in the early stages of iteration, while the search step size gradually decreases in the later stages of iteration. It is the effective coefficient of individual krill; A random number between [0, 1]; The formula for updating the position of the golden jackal has been improved as follows: ； In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
5. The robot path planning method based on the improved golden jackal optimization algorithm according to claim 4, characterized in that, The process of calculating the location of prey during the development phase includes the following steps: The improved formula for updating the positions of male and female golden jackals is as follows: ； ； In the formula: t This represents the current iteration number; Let be the position of the prey in the t-th iteration, and be the current optimal solution; , These represent the positions of the male and female golden jackals in the t-th iteration, respectively. , The first t The updated positions of the male and female golden jackals corresponding to the prey in the next iteration; The formula for updating the golden jackal's position is as follows: ； In the formula: This represents the position of the golden jackal after the (t+1)th iteration.
6. A robot path planning system based on an improved golden jackal optimization algorithm, characterized in that, The system includes: The grid map generation module is used to model the environment of the mobile robot, obtain a map of the mobile area, and perform gridding processing on the map of the mobile area to obtain a grid map. The path planning module is used to establish an objective function for robot path planning based on a grid map, with constraints of minimizing the shortest movement path, the shortest time, or the least energy consumption; determine the constraints and the number of key nodes; randomly generate a golden jackal population, with each individual in the population corresponding to a path from the starting point to the ending point on the grid map that meets the key node requirement; and update the optimal position using an improved golden jackal optimization algorithm based on the objective function and constraints to determine the optimal golden jackal individual, whose corresponding path is the optimal path planning result. The improved golden jackal optimization algorithm is as follows: in the exploration and development phases of the original golden jackal optimization algorithm, the position update mechanism of the Cordyceps optimization algorithm and the krill swarm algorithm is introduced to improve the golden jackal position update method. The update is based on factors such as the optimal position of the golden jackal in this iteration, the Cordyceps search coefficient, the search step size of the Cordyceps in the spiral ascending operator stage, and the effective coefficient of the krill individual, as well as the mechanism of gradually decreasing the search step size of the Cordyceps as the number of iterations increases.
7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a data processing program, which, when executed by a processor, implements the steps of the robot path planning method based on the improved golden jackal optimization algorithm as described in any one of claims 1 to 5.