Electric power material storage intelligent path planning method based on improved A-star algorithm

Abstract

The invention discloses an electric power material storage intelligent path planning method based on an improved A-star algorithm, and relates to the technical field of path planning and artificial intelligence, and the method comprises the steps: 1, constructing a two-dimensional map model for robot path planning; 2, randomly putting an intermediate point into the two-dimensional map model, and converting a global path planning problem into a plurality of local path planning problems through the intermediate point; step 3, constructing a crayfish optimization algorithm; 4, designing a fitness function; 5, planning a complete path from the starting point to the end point through the middle point by an improved A-star algorithm, and completing global path planning; the electric power material storage intelligent path planning method based on the improved A-star algorithm provided by the invention solves the problems of large calculation amount, poor path quality and the like in a complex environment in the prior art.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of path planning and artificial intelligence, in particular to an intelligent path planning method for power material storage based on an improved A-star algorithm. BACKGROUND

[0002] With the development of automation technology, mobile robots are increasingly widely used in various industries, especially in the field of power material storage, and the demand for robot autonomous path planning is increasingly urgent. Path planning technology is an important part of robot autonomous navigation, which determines the optimal path selection of the robot from the starting point to the target point. In practical applications, path planning needs to consider obstacles, dynamic environmental changes, and ensure the safety and efficiency of the path. Although existing improved algorithms have made remarkable achievements in many fields, there are still certain challenges in the face of dynamic environments, complex obstacles and limited computing resources. SUMMARY

[0003] The purpose of the application is to provide an intelligent path planning method for power material storage based on an improved A-star algorithm, which solves the problems of large amount of calculation and poor path quality in the prior art in complex environments.

[0004] To achieve the above purpose, the application provides an intelligent path planning method for power material storage based on an improved A-star algorithm, comprising the following steps: Step 1, constructing a two-dimensional map model for robot path planning; Step 2, randomly placing intermediate points in the two-dimensional map model, and converting the global path planning problem into multiple local path planning problems through the intermediate points; Step 3, constructing a crayfish optimization algorithm; the crayfish optimization algorithm is integrated into the path planning, and the algorithm is divided into initialization stage, summering stage, competition stage and foraging stage according to the self-defined temperature function; Step 4, designing a fitness function; Step 5, planning a complete path from the starting point to the end point through the intermediate points by the improved A-star algorithm, and completing the global path planning.

[0005] Preferably, S11, environment modeling; The modeling environment range required for robot path planning is determined, including the starting point, the end point and the obstacle distribution; relevant data of the modeling environment is collected, including map data and channel width, etc.; S12, dividing the grid; The modeling environment is divided into uniform grid meshes, each mesh representing a local area in the modeling environment, and the grid size is determined; S13, mark the grid; According to the distribution of obstacles and passable areas in the modeling environment, mark each grid, mark the passable grid as 0, and mark the obstacle grid as 1; S14, establish a coordinate system; Assign coordinates to each grid through a two-dimensional coordinate system, and the coordinate expression of the grid is: ; In the formula, represents the position coordinates of the first grid; represents the size of the grid; represents the remainder operation; represents the upward rounding operation; and represent the number of grids in the row direction and the column direction, respectively; S15, create a map data structure; Store the grid information in the form of a two-dimensional matrix to obtain a grid map, which is convenient for subsequent path planning algorithms; S16, visualization and verification; Visualize the established grid map to verify the correctness of the marking of obstacles and passable areas.

[0006] Preferably, in step 3: S31, initialization stage: generate an initial population through an initialization function to ensure that the population has good randomness and ergodicity; set the population to have lobsters, and a population consisting of lobsters is Initialize the position of the population individual, and the fitness function corresponding to each individual in the population is Then: ; ; ; In the formula, represents the first to the lobster; represents the position of each lobster in the first dimension to the dimension; represents the position of the first lobster in the first dimension; and represent the upper and lower bounds of the first dimension, respectively; represents a random number between the interval ; represents the matrix transpose; S32. Temperature changes affect crayfish behavior; when the temperature exceeds 30℃, crayfish will choose a cool place to escape the heat; at appropriate temperatures, crayfish will engage in foraging behavior; the amount of food consumed by crayfish is affected by temperature; the optimal feeding range for crayfish is between 15~30℃, with 25℃ being the best; therefore, the amount of food consumed by crayfish can be approximated by a normal distribution, thus the amount of food consumed is affected by temperature; the formulas for temperature and the amount of food consumed by crayfish are defined as follows: ; ; In the formula, The temperature of the crayfish's living environment; For interval Random numbers; The intake of crayfish at different temperatures; Represents the first constant. ; The standard deviation of the normal distribution is used to control the intake of crayfish at different temperatures; It is the mean of a normal distribution; S33, Summer Retreat Phase: The algorithm updates the location of each crayfish individual based on the results of summer retreat, competition, and foraging behaviors; when the temperature is not lower than 30℃, the crayfish enter burrows to retreat from the heat, which is the summer retreat phase; burrow location... The definition of is: ; In the formula, The optimal position is obtained through iteration; This is the optimal position obtained after updating the previous generation of the population; S34, Competition Stage: Crayfish fight for burrows; like This indicates that if there are no crayfish competing for burrows, then the crayfish will directly enter the burrows to escape the heat. The expression for crayfish entering burrows to escape the heat is: ; In the formula, Indicates the number of iterations; This represents the maximum number of iterations. Indicates the first Time of the first Only one crayfish in the first The position of the dimension; Indicates the first Time of the first Only one crayfish in the first The position of the dimension; If the temperature is not less than 30℃, and This indicates that multiple crayfish have chosen the same burrow, signifying a competition phase. The expression for crayfish competing for a burrow is: ; In the formula, Indicates the first At a certain random moment, a crayfish is in its first... The position of the dimension; among which, This represents the second constant. , Indicates the rounding operation; S35, Foraging stage: Crayfish feeding; If the temperature is not higher than 30℃, it is suitable for crayfish to feed and enter the foraging stage. The crayfish search for food. When feeding, the crayfish choose whether to tear the food apart according to its size. If the food is the right size, the crayfish will eat it directly. If the food is too big, the crayfish will use its claws to tear the food apart and then use its second and third legs to alternately pick up the food. Define food location and food size The expressions are as follows: ; ; In the formula, The maximum food factor constant; For the first The fitness value of each crayfish; This represents the fitness value of the location where the food is located. like The expression for crayfish tearing food is: This indicates that the food needs to be shredded. ; After tearing up their food, crayfish use their second and third legs to alternately grasp and ingest the food. To simulate this alternating feeding behavior, a combination of sine and cosine functions is used in the equation to represent the alternating process. Furthermore, the amount of food obtained by the crayfish is also related to the amount of food ingested. The expression for feeding after tearing up food is: ; In the formula, Indicates the first Time of the first Only one crayfish in the first The position of the dimension; Indicates the first Time of the first Only one crayfish in the first The position of the dimension; like The crayfish moves directly towards its food and eats; the expression for direct feeding is: ; S36. To improve the algorithm's global search capability, escape local optima, enhance population diversity, and increase convergence speed, a Tent chaotic perturbation strategy is introduced. The Tent chaotic mapping position expression is: ; In the formula, For interval Random numbers within; The perturbation value is obtained through chaotic mapping; A random number between 0 and 1; Indicates the current time The value; The expression after Bernoulli shift transformation is: ; In the formula, This is a modulo operation.

[0007] Preferably, in step 4: the fitness function is designed using the cost function, with the following expression: ; In the formula, Indicates the first The total fitness cost of the path for each individual lobster; Indicates the first The cost of Euclidean distance between the intermediate points of each individual lobster is generated by the crayfish optimization algorithm. Indicates the first The cost of the distribution of intermediate points for each individual lobster using the crayfish optimization algorithm; Indicates the first The cost of obstacles at intermediate points generated by the crayfish optimization algorithm for each individual crayfish.

[0008] Preferably, in step 4: The intermediate point distance cost can prevent the generated intermediate point positions from diverging and keep them close to the shortest path, satisfying: ; In the formula, and These represent the x-coordinate and y-coordinate of the starting point, respectively. and These represent the x and y coordinates of the intermediate point where an individual is generated in the population, respectively. and These represent the x-coordinate and y-coordinate of the endpoint, respectively. and These represent the x-coordinate and y-coordinate of the first intermediate point, respectively. and They represent the first The x and y coordinates of each intermediate point; and They represent the first The x and y coordinates of each intermediate point.

[0009] Preferably, in step 4: To ensure a uniform distribution of intermediate points during the iteration process, the following condition must be met: ; In the formula, It is an adjustable constant coefficient; This represents the difference between the individual midpoint position generated by the crayfish optimization algorithm and the midpoint position under an ideal uniform distribution. Indicates the number of intermediate points; Indicates the actual coordinates of the intermediate point; This represents the location information of the ideal midpoint; where, satisfy: ; In the formula, and Representing the actual intermediate points coordinates and coordinate; and These represent the positions of the midpoints under an ideal uniform distribution. coordinates and coordinate; and These represent the difference in horizontal distance and the difference in vertical distance between the starting point and the ending point, respectively. satisfy: ; In the formula, Indicates the number of intermediate points; This indicates the current position information of the ideal midpoint.

[0010] Preferably, in step 4, The obstacle cost at each intermediate point, generated using the crayfish optimization algorithm, and the obstacle cost from the last intermediate point to the endpoint are combined, satisfying the following: ; In the formula, Rules for calculating obstacle costs; Indicates the starting point; Indicates the midpoint; Indicates the endpoint; among which, The specific calculation method for obstacle obstruction cost is defined. Obstacle obstruction cost consists of two independent parts: the obstruction cost for determining whether there is an obstacle between the current point and the previous point, and the potential field cost for determining whether the current point is affected by an obstacle, satisfying: ; In the formula, The coefficient is constant. and These represent the horizontal and vertical dimensions of the raster map, respectively. The potential field coefficient of the obstacle; This indicates that the point is between two points; This indicates the distance to the nearest obstacle at the current point; The range of influence of the obstacle's potential field can be adaptively adjusted according to the actual situation; when When this occurs, it indicates that the current node is under the influence of the obstacle potential field, and the obstacle potential field cost should be calculated as one of the obstacle obstruction costs.

[0011] Preferably, in step 5: S51, Algorithm initialization; create , , and These are stored at the starting point of the forward search, the starting point of the reverse search, the extended node of the forward search, and the extended node of the reverse search, respectively; the starting node... and target node Add separately and In this context, it serves as the starting node for both forward and reverse searches; S52, Forward Search; Will As the starting node For the target node, perform a forward search first along straight lines and then along diagonal lines, and then... join in middle; S53, Adding extended nodes for forward search; Add the extended nodes of the forward search Calculate its estimated cost, and take the node with the smallest estimated cost as the starting point for the next forward search; S54, Reverse Search; Will As the starting node For the target node, perform a forward search first along straight lines and then along diagonal lines, and then... join in middle; S55, Adding extended nodes for reverse search; Add the extended nodes of the reverse search Calculate its estimated cost, and take the node with the smallest estimated cost as the starting point for the next reverse search; S56, Judgment and Update; judge and Check if there are duplicate nodes. If duplicate nodes exist, it means the algorithm has found the optimal path. Traverse backwards based on the duplicate nodes to find their respective parent nodes and connect them to form a path. Connect the forward and reverse paths to obtain the algorithm's optimal path. If no duplicate nodes exist, place the expansion nodes with the minimum forward estimated cost and the minimum reverse estimated cost into the corresponding nodes. and In this case, as the starting point for the next round of search, return to S52 to continue running the algorithm.

[0012] The present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described intelligent path planning method for power material storage based on an improved A-star algorithm.

[0013] The present invention also provides a computer storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described intelligent path planning method for power material warehousing based on an improved A-star algorithm.

[0014] Therefore, this invention employs an intelligent path planning method for power material warehousing based on an improved A-star algorithm. This method uses a crayfish optimization algorithm to generate uniformly distributed intermediate points that avoid obstacles, decomposing the global path into local paths. Combined with a bidirectional search improved A-star algorithm, it effectively reduces computational load in complex environments and improves path planning efficiency. Simultaneously, by comprehensively considering distance, distribution, and obstacle costs through a fitness function, it ensures a better and safer path, solving the problems of poor path quality and low computational efficiency in traditional algorithms in complex warehousing environments. This method is suitable for the intelligent navigation needs of power material warehousing robots.

[0015] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0016] Figure 1 This is an overall flowchart of the intelligent path planning method for power material warehousing based on the improved A-star algorithm of the present invention; Figure 2 The flowchart of the improved A-star algorithm according to an embodiment of the present invention is shown below; Figure 3 This is a diagram showing the results of the conventional A-star algorithm in an embodiment of the present invention; Figure 4 The image shows the results of the improved A-star algorithm according to an embodiment of the present invention. Detailed Implementation

[0017] The following detailed description of embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0018] Please see Figures 1-4 A method for intelligent path planning in power material warehousing based on an improved A-star algorithm includes the following steps: Step 1: Construct a two-dimensional map model for robot path planning; S11, Environmental Modeling; Determine the scope of the modeling environment needed for robot path planning, including the start point, end point, and obstacle distribution; collect relevant data of the modeling environment, including map data and channel width, etc. S12, Divide the grid; The modeling environment is divided into a uniform grid, with each grid representing a local area in the modeling environment, and the grid size is determined at the same time; S13, Marker grid; Based on the distribution of obstacles and passable areas in the modeling environment, each grid is marked, with passable grids marked as 0 and obstacle grids marked as 1; S14. Establish a coordinate system; Each grid cell is assigned coordinates using a two-dimensional coordinate system. The coordinate expression for each grid cell is as follows: ; In the formula, Indicates the first The position coordinates of each grid cell; Indicates the size of the grid; This represents the modulo operation; This indicates the rounding up operation; and These represent the number of grid cells in the row and column directions, respectively. S15. Create map data structure; The raster information is stored in the form of a two-dimensional matrix to obtain a raster map, which is convenient for subsequent path planning algorithms. S16. Visualization and Verification; Visualize the created grid map to verify that the markings of obstacles and passable areas are correct.

[0019] Step 2: Randomly place intermediate points in the two-dimensional map model to transform the global path planning problem into multiple local path planning problems.

[0020] Step 3: Construct an optimization algorithm for crayfish; The crayfish optimization algorithm is a heuristic optimization algorithm that simulates the foraging, attack, and defense behaviors of crayfish. Inspired by the survival strategies of crayfish in their natural environment, such as their cooperative foraging, evading predators, and attacking enemies, this algorithm simulates these natural behaviors to achieve global search and local optimization. To address the problems of the crayfish optimization algorithm, such as its tendency to get trapped in local optima in the early stages and its low accuracy in later optimization stages, this invention introduces Tent chaotic mapping for optimization search, avoiding local optima in path planning and thus improving the efficiency and accuracy of path planning.

[0021] The exploration and development of the crayfish optimization algorithm is influenced by temperature, which is a random number. When the temperature is too high, crayfish will choose burrows to escape the heat. If there are no other crayfish competing for burrows, the crayfish will directly enter the burrows; this is the heat-escape phase of the crayfish optimization algorithm. If there are other crayfish competing for burrows, the crayfish will compete with each other; this is the competition phase of the crayfish optimization algorithm. When the temperature is suitable, the crayfish optimization algorithm enters the foraging phase. In the foraging phase, crayfish will choose to eat the food directly or tear it up first, depending on the size of the food. The amount of food consumed by the crayfish is related to the amount of food foraged. S31. Generate an initial population using an initialization function, ensuring the population has good randomness and ergodicity; assume the population has... One lobster, by A population of lobsters is Initialize the positions of individuals in the population. The fitness function for each individual in the population is: ,but: ; ; ; In the formula, Indicates the first to the second One lobster; Representing the first dimension to the second dimension of each lobster The position of the dimension; Indicates the first The lobster in the first The position of the dimension; and They represent the first The upper and lower bounds of a dimension; Representing an interval Random numbers between; Indicates matrix transpose; S32. Temperature changes affect crayfish behavior; when the temperature exceeds 30℃, crayfish will choose a cool place to escape the heat; at appropriate temperatures, crayfish will engage in foraging behavior; the amount of food consumed by crayfish is affected by temperature; the optimal feeding range for crayfish is between 15~30℃, with 25℃ being the best; therefore, the amount of food consumed by crayfish can be approximated by a normal distribution, thus the amount of food consumed is affected by temperature; the formulas for temperature and the amount of food consumed by crayfish are defined as follows: ; ; In the formula, The temperature of the crayfish's living environment; For interval Random numbers; The intake of crayfish at different temperatures; Represents the first constant. ; The standard deviation of the normal distribution is set to 1 here to control the intake of crayfish at different temperatures; The mean of the normal distribution is 25℃, which is the most suitable temperature for crayfish. S33. The algorithm updates the location of each crayfish individual based on the results of its heat-avoidance, competition, and foraging behaviors; when the temperature is not lower than 30℃, the crayfish enter burrows to avoid the heat, which is the heat-avoidance phase; burrow location... The definition of is: ; In the formula, The optimal position is obtained through iteration; This is the optimal position obtained after updating the previous generation of the population; S34, Crayfish fight for their burrows; like This indicates that if there are no crayfish competing for burrows, then the crayfish will directly enter the burrows to escape the heat. The expression for crayfish entering burrows to escape the heat is: ; In the formula, Indicates the number of iterations; This represents the maximum number of iterations. Indicates the first Time of the first Only one crayfish in the first The position of the dimension; Indicates the first Time of the first Only one crayfish in the first The position of the dimension; If the temperature is not less than 30℃, and This indicates that multiple crayfish have chosen the same burrow, signifying a competition phase. The expression for crayfish competing for a burrow is: ; In the formula, Indicates the first At a certain random moment, a crayfish is in its first... The position of the dimension; among which, This represents the second constant. , Indicates the rounding operation; S35, crayfish eating; If the temperature is no higher than 30℃, it is suitable for crayfish to feed and enter the foraging stage. The crayfish search for food and, depending on the size of the food, decide whether to tear it up. If the food is the right size, the crayfish will eat it directly. If the food is too large, the crayfish will use its claws to tear it up and then use its second and third legs to alternately grasp and eat the food. Define food location and food size The expressions are as follows: ; ; In the formula, This is the maximum food factor constant, which is set to 3 here; For the first The fitness value of each crayfish; This represents the fitness value of the location where the food is located. like The expression for crayfish tearing food is: This indicates that the food needs to be shredded. ; After tearing up their food, crayfish use their second and third legs to alternately grasp and ingest the food. To simulate this alternating feeding behavior, a combination of sine and cosine functions is used in the equation to represent the alternating process. Furthermore, the amount of food obtained by the crayfish is also related to the amount of food ingested. The expression for feeding after tearing up food is: ; In the formula, Indicates the first Time of the first Only one crayfish in the first The position of the dimension; Indicates the first Time of the first Only one crayfish in the first The position of the dimension; like The crayfish moves directly towards its food and eats; the expression for direct feeding is: ; S36. To improve the algorithm's global search capability, escape local optima, enhance population diversity, and increase convergence speed, a Tent chaotic perturbation strategy is introduced. The Tent chaotic mapping position expression is: ; In the formula, For interval Random numbers within; The perturbation value is obtained through chaotic mapping; A random number between 0 and 1; Indicates the current time The value; The expression after Bernoulli shift transformation is: ; In the formula, This is a modulo operation.

[0022] Step 4: Design the fitness function; Based on the cost function, the fitness function is designed, with the following expression: ; In the formula, Indicates the first The total fitness cost of the path for each individual lobster; Indicates the first The cost of Euclidean distance between the intermediate points of each individual lobster is generated by the crayfish optimization algorithm. Indicates the first The cost of the distribution of intermediate points for each individual lobster using the crayfish optimization algorithm; Indicates the first The cost of obstacles at intermediate points generated by the crayfish optimization algorithm for each individual crayfish; The intermediate point distance cost can prevent the generated intermediate point positions from diverging and keep them close to the shortest path, satisfying: ; In the formula, and These represent the x-coordinate and y-coordinate of the starting point, respectively. and These represent the x and y coordinates of the intermediate point where an individual is generated in the population, respectively. and These represent the x-coordinate and y-coordinate of the endpoint, respectively. and These represent the x-coordinate and y-coordinate of the first intermediate point, respectively. and They represent the first The x and y coordinates of each intermediate point; and They represent the first The x and y coordinates of each intermediate point.

[0023] To ensure a uniform distribution of intermediate points during the iteration process, the following condition must be met: ; In the formula, It is an adjustable constant coefficient; This represents the difference between the individual midpoint position generated by the crayfish optimization algorithm and the midpoint position under an ideal uniform distribution. Indicates the number of intermediate points; Indicates the actual coordinates of the intermediate point; This represents the location information of the ideal midpoint; where, satisfy: ; In the formula, and Representing the actual intermediate points coordinates and coordinate; and These represent the positions of the midpoints under an ideal uniform distribution. coordinates and coordinate; and These represent the difference in horizontal distance and the difference in vertical distance between the starting point and the ending point, respectively. satisfy: ; In the formula, Indicates the number of intermediate points; This indicates the current position information of the ideal midpoint; The obstacle cost at each intermediate point, generated using the crayfish optimization algorithm, and the obstacle cost from the last intermediate point to the endpoint are combined, satisfying the following: ; In the formula, Rules for calculating obstacle costs; Indicates the starting point; Indicates the midpoint; Indicates the endpoint; among which, The specific calculation method for obstacle obstruction cost is defined. Obstacle obstruction cost consists of two independent parts: the obstruction cost for determining whether there is an obstacle between the current point and the previous point, and the potential field cost for determining whether the current point is affected by an obstacle, satisfying: ; In the formula, This is a constant coefficient, which is defaulted to 1 in this invention; and These represent the horizontal and vertical dimensions of the raster map, respectively. This is the potential field coefficient for the obstacle, with a default value of 20. This indicates that the point is between two points; This indicates the distance to the nearest obstacle at the current point; The range of influence of the obstacle's potential field can be adaptively adjusted according to the actual situation; when When this occurs, it indicates that the current node is under the influence of the obstacle potential field, and the obstacle potential field cost should be calculated as one of the obstacle obstruction costs.

[0024] Step 5: Plan the complete path from the starting point through the intermediate points to the ending point by improving the A-star algorithm, and complete the global path planning; By introducing a bidirectional search mechanism, the number of search nodes is reduced and the algorithm running time is shortened, resulting in an improved A-star algorithm. The bidirectional search mechanism employs an alternating forward and reverse search approach, which effectively prevents path search failures. Specifically: (1) Set the starting point Target point Perform a forward search from the starting point to the target point to obtain the extended nodes. ; (2) with As the starting point, Perform a reverse search on the target point to obtain extended child nodes. ; (3) Repeat (1) and (2) until the same expansion node appears in the forward search and the reverse search, then stop the search and the path obtained is the optimal path; The improved A-star algorithm process is as follows: S51, Algorithm initialization; create , , and These are stored at the starting point of the forward search, the starting point of the reverse search, the extended node of the forward search, and the extended node of the reverse search, respectively; the starting node... and target node Add separately and In this context, it serves as the starting node for both forward and reverse searches; S52, Forward Search; Will As the starting node For the target node, perform a forward search first along straight lines and then along diagonal lines, and then... join in middle; S53, Adding extended nodes for forward search; Add the extended nodes of the forward search Calculate its estimated cost, and take the node with the smallest estimated cost as the starting point for the next forward search; S54, Reverse Search; Will As the starting node For the target node, perform a forward search first along straight lines and then along diagonal lines, and then... join in middle; S55, Adding extended nodes for reverse search; Add the extended nodes of the reverse search Calculate its estimated cost, and take the node with the smallest estimated cost as the starting point for the next reverse search; S56, Judgment and Update; judge and Check if there are duplicate nodes. If duplicate nodes exist, it means the algorithm has found the optimal path. Traverse backwards based on the duplicate nodes to find their respective parent nodes and connect them to form a path. Connect the forward and reverse paths to obtain the algorithm's optimal path. If no duplicate nodes exist, place the expansion nodes with the minimum forward estimated cost and the minimum reverse estimated cost into the corresponding nodes. and In this case, as the starting point for the next round of search, return to S52 to continue running the algorithm.

[0025] Therefore, this invention adopts the above-mentioned intelligent path planning method for power material warehousing based on the improved A-star algorithm. By generating uniformly distributed intermediate points that avoid obstacles through the crayfish optimization algorithm, the global path is decomposed into local paths. Combined with the bidirectional search improved A-star algorithm, the computational load in complex environments can be effectively reduced and the path planning efficiency can be improved. At the same time, by comprehensively considering distance, distribution and obstacle cost through the fitness function, the path is ensured to be better and safer. This solves the problems of poor path quality and low computational efficiency of traditional algorithms in complex warehousing environments, and is suitable for the intelligent navigation needs of power material warehousing robots.

[0026] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent path planning method for power material storage based on an improved A-star algorithm, characterized in that, The method comprises the following steps: Step 1, constructing a two-dimensional map model for robot path planning; Step 2, randomly placing an intermediate point in the two-dimensional map model; Step 3, constructing a crayfish optimization algorithm; Step 4, designing a fitness function; Step 5, planning a complete path from the starting point to the end point through the intermediate point by improving the A-star algorithm to complete global path planning. 2.The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 1, wherein, In step 1: S11, environment modeling; determine the modeling environment range for robot path planning, including the starting point, the end point and the obstacle distribution; collect relevant data of the modeling environment, including map data and channel width; S12, divide the grid; divide the modeling environment into uniform grid, each grid represents a local area in the modeling environment, and determine the grid size at the same time; S13, mark the grid; according to the obstacle distribution and passable area in the modeling environment, mark each grid, mark the passable grid as 0, and mark the obstacle grid as 1; S14, establish coordinate system; assign coordinates to each grid through two-dimensional coordinate system, and the coordinate expression of the grid is: ； In the formula, represents the position coordinates of the th grid; represents the size of the grid; represents the remainder operation; represents the upward rounding operation; and respectively represent the number of grids in the row direction and the column direction; S15, create a map data structure; store the grid information in the form of two-dimensional matrix to obtain the grid map, which is convenient for subsequent path planning algorithm; S16, visualization and verification; visualize the established grid map, and verify the correctness of the obstacle and passable area marking. 3.The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 2, characterized in that, In step 3: S31, generating initial population by initialization function: suppose there are lobsters in the population, the population consisting of lobsters is , initializing the position of population individuals, the fitness function of each individual in the population is , then: ； ； ； wherein represents the 1st to the represents the matrix transpose;​​​​​​​​​​​ S32, define the temperature and crayfish foraging amount formula, the expressions are respectively: ； ； wherein is the temperature of the environment in which the crayfish lives; is a random number from the interval ; is the intake of the crayfish at different temperatures; denotes a first constant, ; is the standard deviation of the normal distribution; is the mean of the normal distribution; S33, when the temperature is not less than 30℃, crayfish into the cave to avoid the summer heat, for the avoidance of the summer heat stage; cave location The definition is: ； wherein is the optimal position obtained by iteration; is the optimal position obtained after updating the previous generation population; S34, crayfish competing for cave; If , it means that there is no crayfish to compete for the cave, and the crayfish will directly enter the cave to avoid the heat. The expression of crayfish entering the cave to avoid the heat is: ； In the formula, Indicates the number of iterations; This represents the maximum number of iterations. Indicates the first Time of the first Only one crayfish in the first The position of the dimension; Indicates the first Time of the first Only one crayfish in the first The position of the dimension; If the temperature is not less than 30℃, and , indicates that multiple crayfish choose the same cave, and the expression for the competition stage, in which crayfish compete for caves, is ； wherein represents the first constant, represents the position of a certain random crayfish at a certain time in its first dimension; wherein, represents the position of a certain random crayfish at a certain time in its second dimension; wherein, represents the second constant, , represents the rounding operation; S35, crayfish feeding; if the temperature is not greater than 30℃, it is suitable for crayfish to feed, which is the foraging stage; when feeding, crayfish selects whether to tear the food according to the size of the food; defining food locations and food sizes , respectively. ； ； wherein is the maximum food factor constant; is the fitness value of the th crayfish; is the fitness value of the location of the food. If The expression of food needs to be torn apart is shown in the following table for crayfish: ； the expression for feeding after tearing the food is: ； wherein represents the time instant at which only the crayfish in the dimension; represents the time instant at which only the crayfish in the dimension; If The crayfish directly moves to the food and eats, and the expression of direct eating is: ； S36, introduce Tent chaos disturbance strategy, the Tent chaos mapping position expression is: ； wherein is a random number in the interval is a random number in the interval is a chaotic mapped perturbation value; is a random number between 0 and 1; denotes the value of the current time ; the expression after Bernoulli shift transformation is: ； In the formulae, is a remainder operation.

4. The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 3, characterized in that, In step 4: design the fitness function through the cost function, the expression is: ； In the formula, Indicates the first The total fitness cost of the path for each individual lobster; Indicates the first The cost of Euclidean distance between the intermediate points of each individual lobster is generated by the crayfish optimization algorithm. Indicates the first The cost of the distribution of intermediate points for each individual lobster using the crayfish optimization algorithm; Indicates the first The cost of obstacles at intermediate points generated by the crayfish optimization algorithm for each individual crayfish.

5. The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 4, characterized in that, In step 4: satisfies: ； wherein and respectively indicate the horizontal and vertical coordinates of the starting point; and respectively indicate the horizontal and vertical coordinates of the intermediate point of the generation of the population individual; and respectively indicate the horizontal and vertical coordinates of the end point; and respectively indicate the horizontal and vertical coordinates of the first intermediate point; and respectively indicate the horizontal and vertical coordinates of the intermediate point; and respectively indicate the horizontal and vertical coordinates of the intermediate point.

6. The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 5, characterized in that, In step 4: satisfies: ； In the formula, is a constant coefficient; represents the difference value between the position of the intermediate point in the individual generated by the crayfish optimization algorithm and the position of the intermediate point under the ideal uniform distribution; represents the number of intermediate points; represents the actual intermediate point coordinates; represents the position information of the ideal intermediate point; wherein, satisfies: ； wherein and respectively represent the coordinates and coordinates of the actual intermediate point; and respectively represent the coordinates and coordinates of the intermediate point position under ideal uniform distribution; and respectively represent the lateral distance difference and the longitudinal distance difference from the start point to the end point; satisfy: ； In the formula, represents the number of intermediate points; represents the position information of the current ideal intermediate point.

7. The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 6, characterized in that, In step 4, satisfies: ； In the formula, represents a calculation rule of an obstacle cost; represents a start point; represents an intermediate point; represents an end point; wherein, satisfies: ； wherein, are constant coefficients; and are the horizontal and vertical sizes of the grid map, respectively; is the obstacle potential field coefficient; indicates that the current node is between two points; indicates the distance size of the nearest obstacle to the current node; is the influence range of the obstacle potential field; when it indicates that the current node is in the influence of the obstacle potential field, and the obstacle potential field cost should be calculated as one of the obstacle obstacle costs.

8. The intelligent path planning method for power material storage based on improved A-star algorithm according to claim 7, characterized in that, In step 5: S51, algorithm initialization; create , , and are stored in the forward search starting point, the reverse search starting point, the forward search expansion node and the reverse search expansion node respectively; the starting node and the target node are added to and respectively as the starting nodes of the forward search and the reverse search; S52, forward search; Will As the starting node, For the target node, the forward search is first straight and then diagonal, and Join In; S53, add the expansion node of forward search; adding the expanded node of the forward search to calculating an estimated cost, and taking the node with the minimum estimated cost as the starting point of the next forward search; S54, backward search; Will As the starting node, For the target node, the forward search is first straight and then diagonal, and Join In the middle; S55, add the expansion node of backward search; adding the expanded node of the backward search to , calculating an estimated cost, and taking the node with the minimum estimated cost as the starting point of the next backward search; S56, judgment and update; determining and whether there is a same node; if there is a same node, it means that the algorithm finds an optimal path, and the respective parent nodes are traversed in reverse according to the same node and connected to form a path, and the optimal path of the algorithm is obtained by connecting the forward path and the reverse path; if there is no same node, the expansion nodes with the minimum forward estimated cost and the minimum reverse estimated cost are respectively put into and as the starting points of the next round of search, and the algorithm continues to run by returning to S52.

9. An electronic device, comprising: comprising a processor and a memory, the memory storing a computer program, the processor being configured to execute the computer program to implement the method of any one of claims 1-8.

10. A computer storage medium, characterized in that, store a computer program, wherein the computer program is executed by a processor to implement the method of any one of claims 1-8.

Images