Path planning method and system based on improved adaptive ant colony algorithm

Abstract

The invention discloses a path planning method and system based on an improved self-adaptive ant colony algorithm, and the method comprises the following steps: initializing, loading traveling salesman problem instance data of a plurality of places based on basic parameters and dynamic parameters of the improved self-adaptive ant colony algorithm, constructing a distance matrix between the places based on Euclidean distance, and performing path planning on the distance matrix. Initializing a symmetric pheromone matrix; iterative optimization is carried out, each ant starts from a randomly selected initial site, a complete path is constructed step by step through an improved state transition probability rule, the path length of each ant is calculated, and the current iterative optimal path and the length thereof are recorded; iteration is terminated, and when the number of iterations reaches the preset value, the algorithm stops running; according to the method, statistics is carried out on results of multiple rounds of operation, the average optimal distance of the multiple rounds of operation and the minimum distance in the multiple rounds of operation are obtained, namely, the optimal planning path is obtained, a self-adaptive volatilization mechanism is introduced, the pheromone volatilization rate is dynamically adjusted according to the number of iterations, and the local optimum problem is solved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent optimization and path planning technology, specifically relating to a path planning method and system based on an improved adaptive ant colony algorithm. Background Technology

[0002] Path planning has extremely wide applications in mobile robotics, autonomous driving, logistics delivery, and drone trajectory planning. A typical path planning problem can generally be abstracted as a variant of the Traveling Salesman Problem (TSP). However, this problem is NP-hard in combinatorial optimization; the solution space grows factorially with increasing problem size, making it difficult for traditional exact algorithms to find a solution. To address this problem, ant colony optimization can be used to find the shortest path that meets practical requirements.

[0003] Ant Colony Optimization (ACO) is a swarm intelligence algorithm inspired by the foraging behavior of ants in nature. The basic principle is that ants release pheromones (chemical substances) while searching for food, using these pheromones to mark their path. After multiple calculations, the shortest path is finally found. While theoretically quite universal, traditional ant colony algorithms also have some shortcomings, performing poorly in path planning.

[0004] Ant colony optimization (ACO) suffers from pheromone positive feedback, which can easily lead to local optima and prevent the algorithm from finding the globally optimal path. Furthermore, ACO's performance is affected by multiple parameters such as α, β, and ρ, all of which require manual setting and lack autonomy. Therefore, during ACO's operation, the ants' search efficiency and result quality directly depend on the values ​​of these parameters. These limitations restrict ACO's application to complex path planning problems, necessitating algorithm improvements to enhance its performance and broaden its applicability.

[0005] In the prior art, patent CN120198035A provides a method for intelligent drone food delivery. The method involves acquiring order information to be delivered and drone parameter information, determining a target delivery strategy based on the order information and drone parameter information, delivering food according to the target delivery strategy, and acquiring real-time environmental information images of the drone during the delivery process. The real-time environmental information images are compared with initial environmental information images to obtain incremental image information, and the target delivery strategy is adjusted or the drone is controlled to perform intelligent obstacle avoidance based on the incremental image information. The method of this invention combines global delivery path planning and local intelligent obstacle avoidance, eliminating the need for frequent manual intervention and adjustments. This enhances the autonomy and efficiency of drone delivery and places greater emphasis on real-time response to environmental changes, enabling dynamic path adjustments based on actual conditions. Patent CN120252762A provides a mobile robot 3D path planning method based on an adaptive ant colony algorithm. This method rasterizes the mobile robot's 3D search space, with each grid representing a 3D location point and its neighborhood. It improves upon existing ant colony algorithms by introducing a decay factor negatively correlated with the number of iterations. This decay factor adjusts the heuristic information between nodes, making the heuristic information more effective in the early stages of the algorithm, accelerating the exploration of target nodes and improving search efficiency in the initial iterations. As the number of iterations increases, the decay factor gradually decreases, reducing the effectiveness of the heuristic information in the later stages of the algorithm. This increases the guiding effect of pheromone concentration differences between paths, making it more suitable for handling complex path planning problems in 3D space and better handling changes in turning and altitude. Summary of the Invention

[0006] To address the problems existing in the prior art, this invention provides a path planning method based on an improved adaptive ant colony algorithm. The adaptive evaporation mechanism adjusts the evaporation rate according to the number of iterations, dynamically adjusts α and β based on the search state, and the elitist strategy enhances the algorithm's ability to utilize information more effectively. Compared with other algorithms, the improved adaptive ant colony algorithm demonstrates superior performance in path planning.

[0007] To achieve the above objectives, in a first aspect, the present invention provides a path planning method based on an improved adaptive ant colony algorithm, comprising the following steps: Initialization: Based on the basic and dynamic parameters of the improved adaptive ant colony algorithm, load the travel salesman problem instance data from multiple locations, construct the distance matrix between locations based on Euclidean distance, and initialize the symmetric pheromone matrix; Iterative optimization: Each ant starts from a randomly selected initial location and gradually constructs a complete path through an improved state transition probability rule. The path length of each ant is calculated, and the optimal path and its length for the current iteration are recorded. During the iteration, the evaporation coefficient is dynamically adjusted to optimize the algorithm. An evaluation is performed after a set number of iterations. If the search is detected to be stuck, the parameters are adjusted, reducing the weight factor of pheromone importance and increasing the weight factor of heuristic information importance. At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set, increasing the pheromone increment of the elite ants. For each optimal solution in previous generations, only the corresponding unidirectional path pheromone is updated. Iteration Termination: When the number of iterations reaches the preset value, the algorithm stops running; the results of multiple rounds of running are statistically analyzed to obtain the average optimal distance and the minimum distance in multiple rounds of running, which is the optimal planned path.

[0008] Furthermore, when each ant starts from a randomly selected initial location and gradually constructs a complete path through the improved state transition probability rule, the basic parameters of the improved adaptive ant colony algorithm include ant colony size, maximum number of iterations, and pheromone constant. The dynamic parameters include the initial pheromone heuristic factor α and the expected heuristic factor β, and the dynamic adjustment range of the pheromone evaporation coefficient ρ is set, with the parameter adaptive adjustment interval.

[0009] Furthermore, when the ant is at its current location i, the probability of choosing the next location j is determined by the following formula:

[0010] in, The pheromone concentration is represented from location i to location j, and α is a weighting factor for the importance of pheromones. Heuristic information is typically inversely proportional to the distance between two locations, and β is a weighting factor for the importance of the heuristic information. `allowed` represents the set of locations that ant `k` can choose to visit next, ensuring that the ant does not revisit locations it has already visited.

[0011] Furthermore, as the number of iterations increases, the pheromone evaporation rate is increased, and the evaporation coefficient ρ is dynamically adjusted as follows:

[0012] in, ρ is the maximum number of iterations, and t is the current number of iterations; the dynamic adjustment range of ρ is [0.05, 0.3], and ρ increases linearly to 0.3.

[0013] Furthermore, when the search remains stagnant: reduce α to 0.95 times its own to enhance exploration, and increase β to 1.05 times its own to enhance heuristic guidance. During normal search: restore α to 1.05 times its own and restore β to 0.95 times its own.

[0014] Furthermore, at the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set. Then, when this group of elite ants is given a larger pheromone increment, a symmetrical update is performed, simultaneously updating the pheromone levels from i to j and j to i, while maintaining the symmetry of the matrix, as shown in the following equation: Optimal path Where Q is the pheromone constant, The globally optimal path. To enhance strength.

[0015] Furthermore, when increasing the pheromone increment in elite ants, the pheromone update rule is as follows:

[0016] Where ρ represents the pheromone volatility coefficient, which is the rate of pheromone evaporation simulated using the chemical reaction constant method, describing the natural evaporation state of pheromones over time. This refers to the pheromone increment left by the ant along the path from location i to location j in this iteration. Secondly, this invention provides a path planning system based on an improved adaptive ant colony algorithm, including an initialization module, an iterative optimization module, and a termination module. Initialization module: Based on the basic and dynamic parameters of the improved adaptive ant colony algorithm, load the travel salesman problem instance data from multiple locations, construct the distance matrix between locations based on Euclidean distance, and initialize the symmetric pheromone matrix; Iterative optimization module: Each ant starts from a randomly selected initial location and gradually constructs a complete path through an improved state transition probability rule. The path length of each ant is calculated, and the current iteration's optimal path and its length are recorded. During the iteration, the algorithm is optimized by dynamically adjusting the volatile coefficient. After a set number of iterations, an evaluation is performed. If the search is detected to be stuck, parameters are adjusted, reducing the weight factor of pheromone importance and increasing the weight factor of heuristic information importance. At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set, increasing the pheromone increment of the elite ants. For each set of optimal solutions in previous generations, only the corresponding unidirectional path pheromone is updated. Termination module: When the number of iterations reaches the preset value, the algorithm stops running; the results of multiple rounds of running are statistically analyzed to obtain the average optimal distance and the minimum distance in multiple rounds of running, which is the optimal planned path.

[0017] Thirdly, the present invention also provides a computer device, including a processor and a memory, wherein the memory is used to store a computer executable program, the processor reads part or all of the computer executable program from the memory and executes it, and the processor can implement the above-mentioned path planning method based on the improved adaptive ant colony algorithm when executing part or all of the computer executable program.

[0018] Alternatively, a computer-readable storage medium may be provided, in which a computer program is stored, which, when executed by a processor, can implement the above-described path planning method based on the improved adaptive ant colony algorithm.

[0019] Compared with existing technologies, the present invention has at least the following beneficial effects: The method of the present invention innovatively introduces an adaptive evaporation mechanism, which dynamically adjusts the pheromone evaporation rate according to the number of iterations to solve the local optimum problem; it realizes the dynamic intelligent adjustment of key parameters α, β, and ρ, and automatically optimizes parameters based on the search state, thereby improving the autonomy and adaptability of the algorithm; it introduces an elite strategy enhancement mechanism to directionally enhance the pheromone of the best historical path, and accelerates the convergence of the algorithm through symmetric updates. Experiments show that the improved algorithm of the present invention is significantly better than the traditional algorithm in terms of path planning convergence speed and path quality. Attached Figure Description

[0020] Figure 1 This is the overall flowchart of the method of the present invention.

[0021] Figure 2 This is the optimal path graph for the Ant Colony Algorithm (ACO).

[0022] Figure 3 This is a convergence curve of the Ant Colony Algorithm (ACO).

[0023] Figure 4 This is the optimal path graph for the Genetic Algorithm (GA).

[0024] Figure 5 This is a convergence curve of the genetic algorithm (GA).

[0025] Figure 6 This is the optimal path diagram of the improved adaptive ant colony algorithm path planning method (IAACO) of this invention.

[0026] Figure 7 This is a convergence curve of the path planning method based on the improved adaptive ant colony algorithm (IAACO) of this invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] To address the shortcomings of existing methods, this invention proposes an improved adaptive ant colony optimization (IAACO) path planning method to solve the path planning problem. The process of the improved adaptive ant colony optimization path planning method is as follows: Figure 1 As shown.

[0029] Initialization phase: First, set the basic parameters including ant colony size (n_ants=50), maximum number of iterations (max_iter=200), and pheromone constant (Q=1000); for dynamic parameters, initialize the pheromone heuristic factor α=1 and the expected heuristic factor β=2, and set the dynamic adjustment range of the pheromone evaporation coefficient ρ to [0.05,0.3], with the parameter adaptive adjustment interval being 30 iterations.

[0030] In the environmental modeling phase, we obtained instance data of the Traveling Salesman Problem (TSP) from 31 cities, constructed a distance matrix between cities based on Euclidean distance, and initialized a symmetric pheromone matrix tau. The initial value of all elements of the pheromone matrix was set to 0.1 to ensure uniform exploration of each path in the initial stage of the algorithm. This parameter configuration scheme effectively balances global exploration and local development capabilities through a dynamic adjustment mechanism while ensuring the convergence of the algorithm.

[0031] Main loop iterative optimization During the path construction phase, each ant starts from a randomly selected initial city and gradually constructs a complete path using an improved state transition probability rule. Specifically, when an ant is in the current city i, the probability of choosing the next city j is determined by the following formula:

[0032] in, The pheromone concentration is represented from city i to city j, and α is a weighting factor for the importance of pheromones. Heuristic information is typically inversely proportional to the distance between two cities, and β is a weighting factor for the importance of heuristic information. `allowed` represents the set of cities that ant `k` can choose to visit next, ensuring that the ant does not revisit cities it has already visited. This formula combines pheromone concentration, heuristic information, and a degree of randomness, allowing the ant to consider both historical information and the current environment when choosing its next path, thus gradually approaching the optimal path.

[0033] Then, calculate the path length (path_dists) for each ant, and record the optimal path (curr_best_path) and its length (curr_best_dist) for the current iteration.

[0034] Adaptive parameter adjustment An adaptive evaporation rate mechanism is proposed to adaptively adjust the pheromone evaporation rate. The algorithm performance is optimized by dynamically adjusting the evaporation coefficient ρ. The design principle of this mechanism is as follows:

[0035] in, t is the maximum number of iterations, and t is the current number of iterations.

[0036] In the initial iteration, to encourage the ants to explore different possible routes, the pheromone evaporation rate is set relatively low (ρ=ρ min This allows more pheromones to be retained. As the number of iterations increases, the evaporation rate is gradually increased to a larger value (ρ=ρ_evaporation) in order to help the ant colony find a better path as quickly as possible. max ρ increases linearly from 0.05 to 0.3, with a smaller evaporation rate ρ (rho) in the initial stage (when the number of iterations is small). min The higher pheromone retention rate enhances the positive feedback effect and facilitates faster convergence; the evaporation rate ρ(rho) is gradually increased near the end of the iteration. max This accelerates the evaporation of old pheromones to prevent getting stuck in a local optimum.

[0037] Dynamic adjustment of α and β: Based on the principle of artificial trapping, α is used to adjust the importance of pheromones, and β is used to adjust the importance of heuristic factors. In the adaptive ant colony algorithm, α and β also change continuously according to factors such as the number of iterations and the quality of the solution. In the process of selecting the values ​​of α and β, on the one hand, the constraint of these values ​​on the algorithm's exploration and development capabilities is considered, and on the other hand, a balance is made in combination with the current solution situation, so that the algorithm has good global search capabilities and a fast convergence speed.

[0038] To address this, this invention introduces a dynamic parameter adjustment mechanism based on search state to adaptively adjust key parameters. The core of this dynamic parameter adjustment mechanism is a precise stagnation detection system: when continuous iterations fail to improve the global optimum, a stagnation counter is incremented; once a better solution is found, the counter is immediately reset. A stagnation evaluation is performed every 30 iterations of the adaptive parameter adjustment interval (adapt_interval). If the algorithm is detected to be stuck in a stagnation state (i.e., no better solution has been found), the parameter adjustment protocol is automatically triggered. Its mathematical expression is:

[0039] The underlying principle is that lowering α (pheromone factor) reduces ants' dependence on pheromones, promoting new path exploration, while increasing it enhances positive feedback and accelerates the formation of high-quality paths. Increasing β (heuristic factor) increases the inverse distance ratio, prioritizing closer cities, while lowering it balances distance factors to avoid excessive greed. During periods of stagnation: lowering α (by 0.95 times) enhances exploration, while increasing β (by 1.05 times) enhances heuristic guidance. During normal search: α is restored to 1.05 times, and β is restored to the standard value of 0.95 times.

[0040] Elite strategy enhances pheromone update: Pheromones update describes the change in pheromone state along the path after each iteration. It is crucial for the ant colony algorithm to get closer and closer to the optimal solution. Simultaneous evaporation and update allow the algorithm to maintain a balance between exploration and utilization, enabling ants to find better paths. The update formula is:

[0041] Wherein, ρ represents the pheromone volatility coefficient, which is to simulate the pheromone evaporation rate using the chemical reaction constant method, describing the state of pheromone evaporation over time. This represents the pheromone increment left by the ant along the path from city i to city j in this iteration.

[0042] To improve algorithm performance, an elite strategy is introduced. At the end of each generation of evolution, the current optimal solution (shortest distance) and the corresponding ant are stored in the elite ant set. Then, this group of elite ants is given a larger pheromone increment. The larger pheromone amount increases the pheromone concentration on the relevant paths of this group of ants, making the ants in the next round more inclined to spread to this group's path. For each optimal solution in previous generations, only the pheromone of the corresponding path in one direction is updated, and the original symmetric pheromone update method is retained to complete the guidance of the entire path.

[0043] Core mechanism of optimal path: (1) Targeted enhancement: Increase pheromone value along the edges of the historical best path.

[0044] (2) Enhance strength: =Q / L, which is directly related to the quality of the path; the shorter the path, the stronger the enhancement.

[0045] (3) Symmetric update: Simultaneously update the pheromones from i to j and from j to i, while maintaining the symmetry of the matrix.

[0046]

[0047] Where Q is the pheromone constant, This mechanism ensures that the algorithm locks onto a good path in each iteration, preventing deviations due to random factors. Furthermore, it enhances bidirectional reachability through symmetric updates, ensuring that the pheromone intensity received by ants is the same regardless of which direction they approach the target city. Therefore, this approach accelerates the algorithm's convergence towards the global optimum, effectively addressing the poor convergence performance issue of traditional ant colony optimization path planning.

[0048] Termination and Output: During the operation, the maximum number of iterations is set as the termination condition. When the number of iterations reaches this preset value, the algorithm stops running. Finally, the results of multiple rounds of operation are statistically processed, and the average optimal distance and the minimum distance in multiple rounds of operation are output, which is the optimal planned path.

[0049] Example 2: The present invention can also provide a path planning system based on an improved adaptive ant colony algorithm, including an initialization module, an iterative optimization module, and a termination module. Initialization module: Based on the basic and dynamic parameters of the improved adaptive ant colony algorithm, load the travel salesman problem instance data from multiple locations, construct the distance matrix between locations based on Euclidean distance, and initialize the symmetric pheromone matrix; Iterative optimization module: Each ant starts from a randomly selected initial location and gradually constructs a complete path through an improved state transition probability rule. The path length of each ant is calculated, and the current iteration's optimal path and its length are recorded. During the iteration, the algorithm is optimized by dynamically adjusting the volatile coefficient. After a set number of iterations, an evaluation is performed. If the search is detected to be stuck, parameters are adjusted, reducing the weight factor of pheromone importance and increasing the weight factor of heuristic information importance. At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set, increasing the pheromone increment of the elite ants. For each set of optimal solutions in previous generations, only the corresponding unidirectional path pheromone is updated. Termination module: When the number of iterations reaches the preset value, the algorithm stops running; the results of multiple rounds of running are statistically analyzed to obtain the average optimal distance and the minimum distance in multiple rounds of running, which is the optimal planned path.

[0050] On the other hand, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the path planning method based on the improved adaptive ant colony algorithm described in the present invention.

[0051] The present invention can also provide a computer device, including a processor and a memory, wherein the memory is used to store a computer executable program, the processor reads the computer executable program from the memory and executes it, and the processor can implement the path planning method based on the improved adaptive ant colony algorithm described in the present invention when executing the computer executable program.

[0052] The computer device may be a laptop, a desktop computer, or a workstation.

[0053] The processor can be a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or an off-the-shelf programmable gate array (FPGA).

[0054] The memory described in this invention can be an internal storage unit of a laptop, desktop computer, or workstation, such as memory or hard disk; or it can be an external storage unit, such as a portable hard disk or flash memory card.

[0055] Computer-readable storage media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media can include: read-only memory (ROM), random access memory (RAM), solid-state drives (SSDs), or optical discs, etc. Random access memory can include resistive random access memory (ReRAM) and dynamic random access memory (DRAM).

[0056] The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A path planning method based on an improved adaptive ant colony algorithm, characterized in that, Includes the following steps: Initialization: Based on the basic and dynamic parameters of the improved adaptive ant colony algorithm, load the travel salesman problem instance data from multiple locations, construct the distance matrix between locations based on Euclidean distance, and initialize the symmetric pheromone matrix; Iterative optimization: Each ant starts from a randomly selected initial location and gradually constructs a complete path through an improved state transition probability rule. The path length of each ant is calculated, and the optimal path and its length for the current iteration are recorded. During the iteration, the evaporation coefficient is dynamically adjusted to optimize the algorithm. An evaluation is performed after a set number of iterations. If the search is detected to be stuck, the parameters are adjusted, reducing the weight factor of pheromone importance and increasing the weight factor of heuristic information importance. At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set, increasing the pheromone increment of the elite ants. For each optimal solution in previous generations, only the corresponding unidirectional path pheromone is updated. Iteration Termination: When the number of iterations reaches the preset value, the algorithm stops running; the results of multiple rounds of running are statistically analyzed to obtain the average optimal distance and the minimum distance in multiple rounds of running, which is the optimal planned path.

2. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, Each ant starts from a randomly selected initial location and gradually constructs a complete path through improved state transition probability rules. The basic parameters of the improved adaptive ant colony algorithm include ant colony size, maximum number of iterations, and pheromone constant. The dynamic parameters include initial pheromone heuristic factor α and expected heuristic factor β, and the dynamic adjustment range of pheromone evaporation coefficient ρ is set, with parameter adaptive adjustment interval.

3. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, When an ant is at its current location i, the probability of choosing the next location j is determined by the following formula: in, The pheromone concentration is represented from location i to location j, and α is a weighting factor for the importance of pheromones. Heuristic information is usually inversely proportional to the distance between two locations. β is a weighting factor for the importance of heuristic information. Allowed represents the set of locations that ant k can choose to go next, ensuring that the ant does not visit locations that have already been visited.

4. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, As the number of iterations increases, the pheromone evaporation rate is increased, and the evaporation coefficient ρ is dynamically adjusted as follows: in, ρ is the maximum number of iterations, and t is the current number of iterations; the dynamic adjustment range of ρ is [0.05, 0.3], and ρ increases linearly to 0.

3.

5. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, When the search remains stagnant: reduce α to 0.95 times its own to enhance exploration, and increase β to 1.05 times its own to enhance heuristic guidance. During normal search: restore α to 1.05 times its own and restore β to 0.95 times its own.

6. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set. Then, when this group of elite ants is given a larger pheromone increment, a symmetrical update is performed, simultaneously updating the pheromone levels from i to j and j to i, while maintaining the matrix symmetry, as shown in the following equation: Optimal path Where Q is the pheromone constant, The globally optimal path. To enhance strength.

7. The path planning method based on the improved adaptive ant colony algorithm according to claim 1, characterized in that, When increasing the pheromone increment in elite ants, the pheromone update rule is as follows: Where ρ represents the pheromone volatility coefficient, which is the rate of pheromone evaporation simulated using the chemical reaction constant method, describing the natural evaporation state of pheromones over time. This represents the pheromone increment left by the ant along the path from location i to location j in this iteration.

8. A path planning system based on an improved adaptive ant colony algorithm, characterized in that, It includes an initialization module, an iterative optimization module, and a termination module. Initialization module: Based on the basic and dynamic parameters of the improved adaptive ant colony algorithm, load the travel salesman problem instance data from multiple locations, construct the distance matrix between locations based on Euclidean distance, and initialize the symmetric pheromone matrix; Iterative optimization module: Each ant starts from a randomly selected initial location and gradually constructs a complete path through an improved state transition probability rule. The path length of each ant is calculated, and the current iteration's optimal path and its length are recorded. During the iteration, the algorithm is optimized by dynamically adjusting the volatile coefficient. After a set number of iterations, an evaluation is performed. If the search is detected to be stuck, parameters are adjusted, reducing the weight factor of pheromone importance and increasing the weight factor of heuristic information importance. At the end of each generation of evolution, the current optimal solution and the corresponding ant are stored in the elite ant set, increasing the pheromone increment of the elite ants. For each set of optimal solutions in previous generations, only the corresponding unidirectional path pheromone is updated. Termination module: When the number of iterations reaches the preset value, the algorithm stops running; the results of multiple rounds of running are statistically analyzed to obtain the average optimal distance and the minimum distance in multiple rounds of running, which is the optimal planned path.

9. A computer device, characterized in that, It includes a processor and a memory, the memory being used to store a computer-executable program, the processor reading part or all of the computer-executable program from the memory and executing it, and the processor executing part or all of the computer-executable program is able to implement the path planning method based on the improved adaptive ant colony algorithm as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores a computer program that, when executed by a processor, implements the path planning method based on the improved adaptive ant colony algorithm as described in any one of claims 1-7.

Images