Amphibious robot path planning method based on improved sparrow search algorithm

Abstract

The invention discloses an amphibious robot path planning method based on an improved sparrow search algorithm, and relates to the technical field of robot control and path planning, and the method comprises the steps: collecting global environment information, obtaining an image signal of a global environment, inputting the improved sparrow search algorithm, and generating a global path plan. A plurality of amphibious robots share environment information and global path planning, generate cooperative path planning, evaluate the complexity of a cooperative path environment, dynamically adjust key parameters of an improved sparrow search algorithm, adjust the cooperative path planning, obtain a global optimal path, and then perform local search optimization to obtain an optimized shortest path. The algorithm not only can be applied to exploration requirements of a static environment, but also can be adjusted in real time according to complex conditions of a dynamic environment so as to explore a multi-condition comprehensive exploration environment. The system cooperation ability of the amphibious robot is enhanced, the completion efficiency of the whole task is improved, and the ability of the amphibious robot to execute the task in a complex environment is improved.

Description

Technical Field

[0001] The invention relates to the technical field of amphibious robot path planning, in particular to an amphibious robot path planning method based on an improved sparrow search algorithm. Background Art

[0002] With the rapid development of artificial intelligence and robotics, amphibious robots are increasingly used in the fields of ocean exploration, environmental monitoring, and disaster relief. Traditional path planning methods can only solve path planning problems in static and semi-static environments. Faced with complex and changing environments, these algorithms often show certain limitations. When it comes to crossing different media, traditional algorithms are difficult to effectively handle the challenges brought by complex terrain changes and environmental uncertainties. Therefore, researchers began to explore how to use intelligent behavior patterns in nature to improve the path planning capabilities of robots. Among them, the sparrow search algorithm has received widespread attention for simulating the foraging behavior of sparrows.

[0003] Although the sparrow search algorithm has certain adaptive and global search capabilities, its original version still has some limitations. When dealing with high-dimensional optimization problems, the algorithm converges slowly, resulting in a waste of computing resources. Secondly, when faced with nonlinear environmental characteristics, the sparrow search algorithm will fall into a local optimal solution, affecting the quality of the final path planning. Although some studies have attempted to apply the sparrow search algorithm to robot path planning and have achieved certain results, most of these methods have failed to fully consider the complexity and uncertainty of the actual operating environment. Moreover, current methods generally lack real-time path adjustment for data collected by sensor networks. In addition, the existing sparrow search algorithm path planning method does not take into account the needs of multi-robot collaborative work, especially in amphibious environments. Due to insufficient information exchange between each amphibious robot, the collaborative efficiency is low, and the advantages of swarm intelligence cannot be fully utilized for path optimization. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an amphibious robot path planning method based on an improved sparrow search algorithm to solve the problems of unclear application effect of the sparrow search algorithm in complex environments, inability of amphibious robots to work collaboratively and low collaboration efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides an amphibious robot path planning method based on an improved sparrow search algorithm, which includes: collecting global environmental information and obtaining image signals of the global operating environment; inputting the image signals of the global operating environment into the improved sparrow search algorithm to generate global path planning; multiple amphibious robots share environmental information and global path planning through a wireless communication network, and use swarm intelligence theory to generate collaborative path planning; perform environmental complexity evaluation on the collaborative path planning, and dynamically adjust key parameters of the improved sparrow search algorithm; adjust the collaborative path planning based on the adjusted key parameters to obtain the global optimal path; perform local search optimization on the global optimal path to obtain the optimized shortest path.

[0007] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, wherein: collecting global environmental information and obtaining image signals of the global working environment include the following steps: Evenly distribute multiple sensor nodes in the operation area; Acquire image signals of the operating environment of the node where the sensor is located; The collected image signals of the node working environment are spliced ​​using the spatial registration of the iterative closest point algorithm to obtain the image signal of the global working environment.

[0008] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, the image signal of the global working environment is input into the improved sparrow search algorithm to generate the global path planning, including the following steps: Perform noise filtering on the image signal of the global operating environment; The image signal of the global working environment after noise filtering is subjected to a size-invariant feature transformation algorithm to extract environmental features; According to the extracted environmental features, the fitness function is designed by comprehensively considering the path length and obstacle distance; The local search mechanism is introduced into the sparrow search algorithm. After each iteration, the surrounding area of ​​the current path is further searched to obtain the improved sparrow search algorithm. Based on the improved sparrow search algorithm, the position of the sparrow is randomly initialized; Combined with the fitness function and the improved sparrow search algorithm, the sparrow position is iteratively updated, and after continuous iterative optimization, the global path planning is output.

[0009] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm described in the present invention, wherein: multiple amphibious robots share environmental information and global path planning through a wireless communication network, and use swarm intelligence theory to generate collaborative path planning, including the following steps: Choose ZigBee protocol as the communication basis and set up a wireless communication network for all amphibious robots to be stably connected; Setting a timer to synchronize data via a wireless communication network; Comprehensively consider the current position and surrounding environment information of each amphibious robot and design a collaborative strategy function; Based on the collaborative strategy function, each amphibious robot begins to adjust its global path planning after receiving the synchronized data. Each amphibious robot minimizes its own path length while maintaining a safe distance. When the path planning of all amphibious robots no longer changes, the collaborative path planning solution is output.

[0010] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, wherein: the environmental complexity evaluation is performed on the collaborative path planning, and the key parameters of the improved sparrow search algorithm are dynamically adjusted, including the following steps: Extracting data on obstacle locations and sizes from the environmental information shared by each amphibian robot; The environmental complexity assessment result is obtained by counting the number of obstacles per unit area and calculating the standard deviation of terrain height changes; According to the results of the environmental complexity assessment, the step length parameters of the amphibious robot in the improved sparrow search algorithm are adjusted.

[0011] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, wherein: based on the adjusted key parameters, the collaborative path planning is adjusted to obtain the global optimal path, including the following steps: Based on the adjusted step size parameter of the sparrow search algorithm, the length of the collaborative planning path of the amphibious robot is calculated, the avoidance probability is evaluated according to the distance between the obstacle and the collaborative planning path, and the collaborative efficiency is evaluated according to the concentration of the collaborative paths planned by the amphibious robot; The obtained path length, obstacle avoidance probability and cooperation efficiency are integrated into the fitness function by weighted summation. Re-run the improved sparrow search algorithm with adjusted parameters to regenerate the global optimal path.

[0012] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, wherein: performing local search optimization on the global optimal path to obtain the optimized shortest path includes the following steps: Initialize the local search radius, adjustment coefficient and local fitness threshold; Based on the initialization of local search radius, adjustment coefficient and local fitness threshold, the simulated annealing algorithm is used to perform local search optimization on the global optimal path; After each local search optimization, the global optimal path information is updated and the total length of the global path is recalculated; Evaluate environmental fitness based on the total global path length and obstacle avoidance probability; When the total length of the global path is the shortest and the environmental fitness is optimal, the final optimized path is output.

[0013] As a preferred solution of the amphibious robot path planning method based on the improved sparrow search algorithm of the present invention, wherein: performing local search optimization on the global optimal path includes the following steps: Set the spatial scope of each local search according to task requirements and environmental complexity; During the iteration process, the spatial scope of the local search is reduced; When a new local path is searched, the environmental fitness of the new local path is evaluated. When the environmental fitness of the new local path is better than that of the current optimal path and exceeds the local path environmental fitness threshold, the new local path planning is replaced with the current optimal path.

[0014] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the amphibious robot path planning method based on the improved sparrow search algorithm as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the amphibious robot path planning method based on the improved sparrow search algorithm as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: the image signal of global environmental information is used to fully perceive the working environment, thereby ensuring the accuracy and real-time performance of path planning and improving the reliability of path planning; the image signal is input into the improved sparrow search algorithm to generate global path planning, thereby improving the efficiency of path planning and effectively avoiding the problem of local optimal solution; multiple amphibious robots share information and generate collaborative path planning through wireless communication, thereby enhancing the collaborative ability of the system, reducing path conflicts and improving the overall task completion efficiency; the environmental complexity of the collaborative path planning is evaluated and key parameters are dynamically adjusted, so that the amphibious robot can adapt to changes in the complex environment and improve the flexibility of path planning; the path is further optimized based on the adjusted parameters so that the path length is shortest and the avoidance ability is optimal, thereby achieving an efficient and safe path planning effect and improving the ability of the amphibious robot to perform tasks in a complex environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the amphibious robot path planning method based on the improved sparrow search algorithm in Example 1.

[0019] Figure 2 The schematic diagram of Example 1 is that multiple amphibious robots share environmental information and global path planning through a wireless communication network and generate collaborative path planning using swarm intelligence theory. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides an amphibious robot path planning method based on an improved sparrow search algorithm, comprising the following steps: Collect global environmental information and obtain image signals of the global working environment, including: it is necessary to select multiple sensor nodes to be evenly distributed in the working area, and use a regular hexagonal layout to arrange the sensor nodes, because the regular hexagon can provide the largest coverage area in a given area and minimize the overlap between adjacent nodes; after obtaining the image signal of the working environment of the node where the sensor is located, use the iterative closest point (ICP) algorithm for spatial registration, and splice these local image signals into the image signal of the global working environment. In order to improve the splicing accuracy, a formula for optimizing the ICP algorithm is designed, the formula is as follows: ; is the overall error function, which is used to evaluate the difference between the changed image and the target image. Represents the transformed matrix The adjusted image position, is the location of the target image, Represents the entire spatial domain where the image is located, represents a three-dimensional coordinate point in the image domain, is a regularization parameter used to control smoothness and avoid overfitting. It means that the gradient operator is used to measure the smoothness of image changes. The range of this formula is theoretically a non-negative real number. The smaller the value, the higher the degree of match between the two images.

[0024] The image signal of the global working environment is input into the improved sparrow search algorithm to generate a global path planning, including: using a Gaussian filter to better retain the image edge information while removing noise; using the scale-invariant feature transform algorithm (SIFT) to extract environmental features from the global working environment image after filtering out noise. The SIFT algorithm can identify key points in the image and generate descriptors that are invariant to scale and rotation changes; based on the extracted environmental features, the path length and obstacle distance are comprehensively considered, and the fitness function is designed as follows: ; In this function, Indicates the path The fitness value of is the total length of the path, From the path To The distance of obstacles, represents the number of obstacles, Represents the number of each obstacle, It is the weight used to balance the path length and the importance of obstacle avoidance. The value range of this formula is a positive real number. The larger the value, the better the path is. At the same time, it avoids the risk of getting too close to obstacles. In order to improve the sparrow search algorithm, after each iteration, the simulated annealing algorithm is used to implement the local search mechanism. The core formula is: ; in, represents the probability of accepting a worse solution, is the energy difference between the new solution and the current solution, is the temperature parameter, which gradually decreases with the increase of iteration times. This step enhances the ability of the sparrow search algorithm to jump out of the local optimal solution by introducing the simulated annealing algorithm. The initial position of each sparrow is randomly assigned in the search space. Combined with the fitness function and the improved sparrow search algorithm, the position of the sparrow is iteratively updated. By continuously adjusting the position and evaluating the fitness, the global path planning is finally output.

[0025] Multiple amphibious robots share environmental information and global path planning through wireless communication networks, and use swarm intelligence theory to generate collaborative path planning, including: selecting ZigBee protocol as the wireless communication basis of amphibious robots, because ZigBee's low power consumption, low cost and self-organizing network characteristics are very suitable for data exchange in multi-robot systems; to ensure that all amphibious robots can update their environmental information and path planning in real time, a timer is set to synchronize data through wireless communication at fixed time intervals; considering the current position and surrounding environment information of each amphibious robot, a collaborative strategy function is designed to optimize the path planning of each amphibious robot while maintaining a safe distance. The function is expressed as: ; in, Indicates The collaborative strategy value of the amphibious robots, It is The path length of an amphibious robot, It is Amphibious robots to The distance between the amphibious robots, Representative The distance between an amphibious robot and the nearest obstacle, and Represents the number of each amphibious robot, and It is a weight coefficient used to balance the importance of path length, safe distance between amphibious robots and obstacle avoidance. The value range of this formula is a positive real number. The larger the value, the better the path, while ensuring the safe operating distance between amphibious robots. Based on the collaborative strategy function, each amphibious robot optimizes its path planning according to the current environmental information and the position information of other robots received, so as to minimize its own path length while maintaining a safe distance from other amphibious robots. When the path planning of all amphibious robots no longer changes, the collaborative path planning scheme is output.

[0026] The environmental complexity of collaborative path planning is evaluated, and the key parameters of the improved sparrow search algorithm are dynamically adjusted, including: applying computer vision technology to identify the environmental information shared by each amphibious robot and mark the location and size of obstacles; obtaining the environmental complexity evaluation result by counting the number of obstacles per unit area and calculating the standard deviation of terrain height changes. The environmental complexity can be quantified by the following formula: ; in, Indicates the complexity of the environment, is the number of obstacles per unit area, is the total area of ​​the assessment region, is the weight coefficient used to balance the influence of obstacle density and terrain complexity. is the standard deviation of terrain height change, which is used to measure the undulation of terrain. The value range of this formula is a positive real number. The larger the value, the more complex the environment is and the higher the requirement for path planning is. According to the evaluation results of environmental complexity, the step length parameters of the amphibious robot in the improved sparrow search algorithm are adjusted. The specific method is to adjust the step length parameters by designing an adaptive step length adjustment function. The function formula is: ; in, Indicates The step length of an amphibious robot, is the maximum allowed step size, is the complexity of the current environment, is the reference complexity threshold, which is used to standardize the effect of environmental complexity on step length. The range of this formula is , the smaller the value, the smaller the step size is used in complex environments to improve accuracy and safety.

[0027] Based on the adjusted key parameters, the collaborative path planning is adjusted to obtain the global optimal path, including the adjusted step size parameters. and the total number of steps the amphibious robot moves , calculate the path length ; For each planned path, the avoidance probability is evaluated using the following formula : ; in, is the distance between the path and the nearest obstacle, is the set safety distance threshold, is the sensitivity coefficient used to adjust the obstacle avoidance probability The sensitivity to distance changes, the range of this formula is , the larger the value, the safer the path; according to the concentration of collaborative paths planned by the amphibious robot, the collaborative efficiency is calculated using the following formula : ; in, Indicates The path length of an amphibious robot, Represents the number of each amphibious robot, is the total number of robots participating in the collaboration. The closer the collaborative efficiency value is, It means that the more balanced the path distribution between the robots, the higher the cooperation efficiency. The obtained path length, obstacle avoidance probability and cooperation efficiency are integrated into the fitness function by weighted summation, that is: ; in, Indicates the path The larger the fitness value, the better the path. , , They are the weight coefficients of path length, obstacle avoidance probability and collaboration efficiency, which are used to balance the importance of various factors. The improved sparrow search algorithm with adjusted parameters is re-run to regenerate the global optimal path.

[0028] The global optimal path is locally searched and optimized to obtain the optimized shortest path, including: setting the local search radius to 10% of the total path length to allow preliminary optimization in a larger range, the adjustment coefficient is 0.95 to gradually reduce the search radius to ensure that the search range gradually shrinks after each iteration, and the local fitness threshold is the fitness value of the global optimal path; based on the local search radius, the adjustment coefficient and the local fitness function threshold, the simulated annealing algorithm is used to perform local search optimization on the global optimal path. When the fitness value of each candidate path is greater than the threshold and the difference between the candidate path and the optimal path is less than the search radius, the optimal path is updated. Otherwise, whether to update the optimal path is determined according to the probability function of simulated annealing; after each local search optimization, the global path length is recalculated and the obstacle avoidance probability is evaluated; based on the path length and the obstacle avoidance probability, the environmental fitness is recalculated; when the global path length is the shortest and the fitness is the best, the final optimized path is output.

[0029] This embodiment also provides a computer device, which is suitable for the case of an amphibious robot path planning method based on an improved sparrow search algorithm, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the amphibious robot path planning method based on the improved sparrow search algorithm as proposed in the above embodiment.

[0030] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0031] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the amphibious robot path planning method based on the improved sparrow search algorithm as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0032] In summary, the present invention achieves the following by: collecting global environmental information to obtain image signals of the global operating environment; inputting the image signals of the global operating environment into the improved sparrow search algorithm to generate a global path plan; multiple amphibious robots share environmental information and global path planning through a wireless communication network, and generate collaborative path planning using swarm intelligence theory; conducting environmental complexity assessment on the collaborative path planning, and dynamically adjusting the key parameters of the improved sparrow search algorithm; adjusting the collaborative path planning based on the adjusted key parameters to obtain a global optimal path; and performing local search optimization on the global optimal path to obtain an optimized shortest path. The algorithm is not only applied to the exploration needs of static environments, but can also be adjusted in real time according to dynamic environments to explore multi-situation comprehensive environments. It enhances the system collaboration capability of amphibious robots, improves the overall task completion efficiency, and improves the ability of amphibious robots to perform tasks in complex environments.

[0033] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A path planning method for an amphibious robot based on an improved sparrow search algorithm, characterized in that: include: Collect global environmental information and obtain image signals of the global operating environment; The image signal of the global working environment is input into the improved sparrow search algorithm to generate the global path planning; Multiple amphibious robots share environmental information and global path planning through wireless communication networks, and use swarm intelligence theory to generate collaborative path planning; Evaluate the environmental complexity of collaborative path planning and dynamically adjust the key parameters of the improved sparrow search algorithm; Based on the adjusted key parameters, the collaborative path planning is adjusted to obtain the global optimal path; Perform local search optimization on the global optimal path to obtain the optimized shortest path.

2. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 1, characterized in that: Collecting global environment information and obtaining image signals of the global operating environment includes the following steps: Evenly distribute multiple sensor nodes in the operation area; Acquire image signals of the operating environment of the node where the sensor is located; The collected image signals of the node working environment are spliced ​​using the spatial registration of the iterative closest point algorithm to obtain the image signal of the global working environment.

3. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 1, characterized in that: The image signal of the global operating environment is input into the improved sparrow search algorithm to generate a global path planning, including the following steps: Perform noise filtering on the image signal of the global operating environment; The image signal of the global working environment after noise filtering is subjected to a size-invariant feature transformation algorithm to extract environmental features; According to the extracted environmental features, the fitness function is designed by comprehensively considering the path length and obstacle distance; The local search mechanism is introduced into the sparrow search algorithm. After each iteration, the surrounding area of ​​the current path is further searched to obtain the improved sparrow search algorithm. Based on the improved sparrow search algorithm, the position of the sparrow is randomly initialized; Combined with the fitness function and the improved sparrow search algorithm, the sparrow position is iteratively updated, and after continuous iterative optimization, the global path planning is output.

4. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 3, characterized in that: Multiple amphibious robots share environmental information and global path planning through wireless communication networks, and use swarm intelligence theory to generate collaborative path planning, including the following steps: Choose ZigBee protocol as the communication basis and set up a wireless communication network for all amphibious robots to be stably connected; Setting a timer to synchronize data via a wireless communication network; Considering the current position and surrounding environment information of each amphibious robot, a collaborative strategy function is designed; Based on the collaborative strategy function, each amphibious robot begins to adjust its global path planning after receiving the synchronized data. Each amphibious robot minimizes its own path length while maintaining a safe distance. When the path planning of all amphibious robots no longer changes, the collaborative path planning solution is output.

5. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 4, characterized in that: The environment complexity evaluation of the collaborative path planning is performed, and the key parameters of the improved sparrow search algorithm are dynamically adjusted, including the following steps: Extracting data on obstacle locations and sizes from the environmental information shared by each amphibian robot; The environmental complexity assessment result is obtained by counting the number of obstacles per unit area and calculating the standard deviation of terrain height changes; According to the results of the environmental complexity assessment, the step length parameters of the amphibious robot in the improved sparrow search algorithm are adjusted.

6. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 5, characterized in that: Based on the adjusted key parameters, the collaborative path planning is adjusted to obtain the global optimal path, including the following steps: Based on the adjusted step size parameter of the sparrow search algorithm, the length of the collaborative planning path of the amphibious robot is calculated, the avoidance probability is evaluated according to the distance between the obstacle and the collaborative planning path, and the collaborative efficiency is evaluated according to the concentration of the collaborative paths planned by the amphibious robot; The obtained path length, obstacle avoidance probability and cooperation efficiency are integrated into the fitness function by weighted summation. Re-run the improved sparrow search algorithm with adjusted parameters to regenerate the global optimal path.

7. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 6, characterized in that: Perform local search optimization on the global optimal path to obtain the optimized shortest path, including the following steps: Initialize the local search radius, adjustment coefficient and local fitness threshold; Based on the initialization of local search radius, adjustment coefficient and local fitness threshold, the simulated annealing algorithm is used to perform local search optimization on the global optimal path; After each local search optimization, the global optimal path information is updated and the total length of the global path is recalculated; Evaluate environmental fitness based on the total global path length and obstacle avoidance probability; When the total length of the global path is the shortest and the environmental fitness is optimal, the final optimized path is output.

8. The amphibious robot path planning method based on the improved sparrow search algorithm as claimed in claim 6, characterized in that: The local search optimization of the global optimal path includes the following steps: Set the spatial scope of each local search according to task requirements and environmental complexity; During the iteration process, the spatial scope of the local search is reduced; When a new local path is searched, the environmental fitness of the new local path is evaluated. When the environmental fitness of the new local path is better than that of the current optimal path and exceeds the local path environmental fitness threshold, the new local path planning is replaced with the current optimal path.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the amphibious robot path planning method based on the improved sparrow search algorithm described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the amphibious robot path planning method based on the improved sparrow search algorithm described in any one of claims 1 to 8 are implemented.

Images