A robot path planning method, system and medium based on multi-strategy improvement

Abstract

The present invention provides a robot path planning method, system, and medium based on multi-strategy improvements, relating to the field of path planning technology. The method comprises the following steps: establishing a grid map of the ground environment based on a positioning and navigation system, and correcting and supplementing the grid map in combination with the robot's own real-time environmental information; establishing an objective function for robot path planning based on the corrected and supplemented grid map; and determining the optimal mouse position by performing an optimal position update using an improved rat swarm optimization algorithm based on the objective function. The improved rat swarm optimization algorithm improves the position update formula of the original rat swarm optimization algorithm by introducing the position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm. The optimal path planning result is determined based on the optimal mouse positions that are sequentially updated according to a preset maximum number of iterations. This method overcomes the local optimality problem existing in existing path planning methods and can effectively improve the effectiveness of robot path planning.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a robot path planning method, system and medium based on multi-strategy improvement. Background Art

[0002] Robot path planning technology is a hot topic in artificial intelligence research. First, the robot uses a positioning and navigation system to create a grid map of the ground environment. Second, it uses its real-time environmental information to correct and supplement the grid map. The robot then independently plans an optimal, collision-free path from its starting point to its destination. This optimal path can be shortest, most time-consuming, and most energy-efficient.

[0003] The robot path planning problem can actually be viewed as a complex optimization problem with constraints. Therefore, some intelligent optimization algorithms have played a positive role in improving the effectiveness of robot path planning, and many scholars have carried out extensive research work.

[0004] Based on current research, intelligent optimization algorithms are an effective path planning method. The Rat Swarm Optimization algorithm (RSOA), a novel intelligent optimization algorithm that simulates the behavior of rats chasing and attacking prey, can also be applied to path planning problems. However, RSOA still has some flaws, making it prone to local optimality and low convergence accuracy, often failing to achieve ideal path planning results. Summary of the Invention

[0005] To solve the above problems, the present invention provides a robot path planning method based on multi-strategy improvement, which overcomes the problem of local optimality in existing path planning methods and can effectively improve the effect of robot path planning.

[0006] To achieve the above objectives, the present invention provides the following technical solutions.

[0007] A robot path planning method based on multi-strategy improvement includes the following steps:

[0008] A grid map of the ground environment is established based on the positioning and navigation system, and the grid map is corrected and supplemented by combining the robot's own real-time perception of the environment;

[0009] According to the corrected and supplemented grid map, the objective function of the robot path planning is established with the shortest moving path, the shortest time consumption, or the least energy consumption as constraints;

[0010] A randomly generated mouse population is constructed, with each individual mouse located in a modified and supplemented grid map and corresponding to unique coordinates. Based on the objective function, an improved mouse swarm optimization algorithm is used to update the optimal position and determine the optimal mouse position. The improved mouse swarm optimization algorithm improves the position update formula of the original mouse swarm optimization algorithm by introducing the position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm. The position update is performed by taking into account the optimal position of the mouse in the current iteration, the positions of other mice in the population, and the adaptive step size of the mouse.

[0011] The optimal mouse position is updated in sequence according to the preset maximum number of iterations to determine the optimal path planning result.

[0012] Preferably, the updating of the optimal position by using the improved rat swarm optimization algorithm to determine the optimal rat position comprises the following steps:

[0013] Initialize the mouse population positions using Gaussian mapping;

[0014] The position update method of the teaching and learning optimization algorithm and the educational competition optimization algorithm is introduced into the mouse position update formula to search for the optimal mouse position;

[0015] By bidirectional sine The optimal mouse position is further updated by mutation to determine the updated optimal mouse position.

[0016] Preferably, the initializing the mouse population position using Gaussian mapping comprises the following steps:

[0017] Determine the size of the population N , the mouse finds the lower boundary LB Finding the upper bound with mice UB ;

[0018] Generate random numbers through Gaussian mapping x t :

[0019] ;

[0020] In the formula, mod(·) is the remainder function, x t+1 is the next random number;

[0021] Initialize the mouse position using the generated Gaussian random numbers:

[0022] .

[0023] Preferably, the method of introducing the position updating method of the teaching and learning optimization algorithm and the educational competition optimization algorithm into the mouse position updating formula to search for the optimal mouse position includes the following steps:

[0024] Attack behavior: When attacking prey, mice continuously change the attack angle and speed through spiral motion. The spiral motion behavior is shown in the following formula:

[0025] ;

[0026] Where: x, y, z are the coordinates in three directions, is the radius of each spiral; is a random angle value in the range [0, 2π]; u and v is the relevant constant that defines the shape of the spiral; e is the base of natural logarithms;

[0027] The position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm is introduced. The improved mouse position update formula is as follows:

[0028] ;

[0029] in:

[0030] ;

[0031] ;

[0032] ;

[0033] Where: For the current prey; is the position of the i-th mouse at the t+1th iteration; is the position of the i-th mouse at the t-th iteration; is the exploration parameter; is a random number in the range [1,2]; Miter is the maximum number of iterations; To develop parameters, , is a random number in the range [0,1]; represents the optimal position of the mouse at the tth iteration; rand is a random number between [0,1]; is a random number between [0,1]; and is a random integer between [1, N], and The randomly selected and The position of the mouse, ; is the fitness function when calculating the fitness value; is the adaptive step length of the mouse;

[0034] Calculate the fitness value:

[0035] ;

[0036] Where, is the fitness function when calculating the fitness value;

[0037] Record the best mouse in that iteration.

[0038] Preferably, the bidirectional sine The optimal position of the mouse is further updated by mutation, including the following steps:

[0039] For dimensions j , calculated based on the current number of iterations sine Chaos value, and switches between positive and negative directions with equal probability:

[0040] ;

[0041] ;

[0042] Where rand is a random number between 0 and 1; x 0 is the iteration sequence value;

[0043] Perform mutation perturbation on the optimal position:

[0044] ;

[0045] Where: Indicates the t +1 optimal position for iteration No. j dimension;

[0046] Greedy Update:

[0047] ;

[0048] After each dimension has been mutated, stop mutation.

[0049] The present invention also provides a robot path planning system based on multi-strategy improvement, the system comprising:

[0050] processor;

[0051] a memory having stored thereon a computer program executable on the processor;

[0052] Wherein, when the computer program is executed by the processor, the steps of the robot path planning method based on multi-strategy improvement are implemented.

[0053] The present invention also provides a computer-readable storage medium, on which a data processing program is stored. When the data processing program is executed by a processor, the steps of the robot path planning method based on multi-strategy improvement are implemented.

[0054] Beneficial effects of the present invention:

[0055] This paper proposes a multi-strategy-based robot path planning method. It employs an improved mouse optimization algorithm for path planning and improves the mouse position update mechanism by incorporating the position update mechanisms of the teaching-learning optimization algorithm and the educational competitive optimization algorithm. This method leverages the two-stage strategy used in the teaching-learning optimization algorithm to balance global exploration and local development, introducing exploration and exploitation parameters. Furthermore, it leverages the adaptive balancing strategy used in the educational competitive optimization algorithm to improve the position update mechanism of the mouse swarm optimization algorithm. This method achieves more optimal mouse positions, and therefore, more optimal path planning points. This overcomes the local optimality problem of existing path planning methods and effectively improves the robot path planning performance. This method also uses a Gaussian map to initialize the mouse population positions, improving the uniformity and diversity of the population position distribution and thus enhancing the algorithm's stability. Furthermore, this method utilizes a bidirectional sine chaotic map mutation on the optimal mouse, enabling the algorithm to escape from the local optimal solution in the later stages, further enhancing the path optimization performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flowchart of a robot path planning method based on multi-strategy improvement according to an embodiment of the present invention;

[0057] Figure 2 is a path planning result of a robot path planning method based on multi-strategy improvement according to an embodiment of the present invention;

[0058] Figure 3 It is an iterative process curve of a robot path planning method based on multi-strategy improvement in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] Example 1

[0061] The present invention proposes a robot path planning method based on multi-strategy improvement, which addresses several problems existing in RSOA and proposes an improved rat swarm optimization algorithm (IRSOA) for robot path planning. The process of the robot path planning method based on multi-strategy improvement is as follows: Figure 1 The specific steps are as follows:

[0062] S1: Build a grid map of the ground environment based on the positioning and navigation system, and correct and supplement the grid map based on the environmental information perceived by the robot itself.

[0063] S2: Establishing the objective function of robot path planning based on robot vision funtion (Set it to the shortest moving path, shortest time consumption, least energy consumption, etc. according to actual needs), and set the corresponding constraints and the number of key nodes of the path. D .

[0064] S3: Set parameters, including: the size of the mouse population (i.e., the number of individual mice) N, each individual mouse is located in the corrected grid map and corresponds to a unique coordinate; the maximum number of iterations (i.e., the condition for stopping the iteration) Miter ; Mouse search lower boundary LB ; Mouse optimization upper bound UB .

[0065] S4: Determine the size of the population N , the mouse finds the lower boundary LB Finding the upper bound with mice UB ; Introduce Gaussian mapping to initialize the mouse population position, including the following steps:

[0066] Determine the size of the population N , the mouse finds the lower boundary LB Finding the upper bound with mice UB ;

[0067] Generate random numbers through Gaussian mapping x t :

[0068] ;

[0069] In the formula, mod(·) is the remainder function, x t+1 is the next random number;

[0070] Initialize the mouse position using the generated Gaussian random numbers:

[0071] .

[0072] S5: Mouse position update:

[0073] In the original rat swarm optimization algorithm, only the optimal rat position is used for guidance to update the rat position. In order to more effectively improve the global search ability of the rat, the position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm is introduced to improve the rat position update method. The rat position is updated by comprehensively considering different position update modes, the optimal position of the rat in this iteration, the positions of other rats in the population, the adaptive step size of the rat and other factors to avoid local optimality in each iteration, thereby improving the global search ability of the rat swarm optimization algorithm.

[0074] Among them, the Teaching and Learning Optimization (TLBO) algorithm demonstrates significant advantages in its position update mechanism by simulating teaching and learning behaviors. Its core principle is to divide the search process into a "teacher" phase and a "learner" phase. In the "teacher" phase, individuals learn from the group's optimal solution (the teacher) to achieve global guidance, which accelerates the algorithm's convergence to a region of high-quality solutions. In the "learner" phase, individuals randomly select other individuals for interactive learning. This two-phase strategy eliminates the need for a preset step size or learning factor and balances global exploration and local exploitation through adaptive teaching behavior.

[0075] The Educational Competitive Optimization (ECOA) algorithm demonstrates significant advantages in position updating by simulating the staged competition mechanism of the education system. Its core principle is to divide the search process into three phases: primary, secondary, and high school, each employing a different strategy. The primary phase uses the group average position as a guide, directing most solutions toward the central region. The secondary phase combines the average position with the global optimal solution, using a dynamic talent threshold to divide students into two groups and employing more aggressive step-size adjustments for high-potential individuals. The high school phase uses the worst position as a reference, driving all solutions toward the current optimal solution. This progressive strategy achieves an adaptive balance between global exploration and local exploitation through Levy flight, while enhancing diversity by initializing the population using a logical chaos map.

[0076] The present invention considers drawing on the two-stage strategy in the position update of the teaching and learning optimization algorithm, introducing exploration parameters and development parameters to balance global exploration and local development, as well as the adaptive balance strategy in the position update of the educational competition optimization algorithm, to improve the position update mechanism of the rat swarm optimization algorithm.

[0077] Drawing on the position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm, the improved mouse position update formula is as follows:

[0078] ;

[0079] in:

[0080] ;

[0081] ;

[0082] ;

[0083] Where: For the current prey; is the position of the i-th mouse at the t+1th iteration; is the position of the i-th mouse at the t-th iteration; is the exploration parameter; is a random number in the range [1,2]; Miter is the maximum number of iterations; To develop parameters, , is a random number in the range [0,1]; represents the optimal position of the mouse at the tth iteration; rand is a random number between [0,1]; is a random number between [0,1]; and is a random integer between [1, N], and The randomly selected and The position of the mouse, ; is the fitness function when calculating the fitness value; is the adaptive step length of the mouse.

[0084] S6: Calculate the fitness value.

[0085] ;

[0086] Where, is the fitness function when calculating the fitness value;

[0087] S7: Record information and record the best mouse in the iteration.

[0088] S8: Perform bidirectional sine mutation on the optimal mouse dimension by dimension. For dimension j, first calculate the sine chaos value based on the current iteration number and switch the positive and negative directions with equal probability.

[0089] ;

[0090] ;

[0091] Where rand is a random number between 0 and 1; x 0 is the iteration sequence value;

[0092] Perform mutation perturbation on the optimal position:

[0093] ;

[0094] Where: Indicates the t +1 optimal position for iteration No. j dimension;

[0095] Greedy Update:

[0096] ;

[0097] After each dimension has been mutated, stop mutation.

[0098] S9: Record information, record the best mouse in the iteration.

[0099] S10: Repeat steps S5 to S9 until the maximum number of iterations is reached. Miter After that, the algorithm stops and outputs the optimal path result.

[0100] In this embodiment:

[0101] Using MATLAB as the simulation platform, assuming a 20×20 grid map, and aiming for the shortest movement distance, the RSOA and IRSOA methods were analyzed. The parameters for the RSOA algorithm are: N=50, Maxiter=200, LB=1, UB=20; the parameters for the IRSOA algorithm are: N=50, Maxiter=200, LB=1, UB=20. The simulation environment and the movement paths obtained by the two methods are shown in Figure 2. Figure 2 As shown, Figure 3 is the iterative process curve. Table 1 is the comparison of the data results of the two algorithms.

[0102] Table 1. Comparison of algorithm path results

[0103]

[0104] from Figure 2 It can be intuitively found that the moving path obtained by RSOA is longer and more circuitous than that of IRSOA, while the path obtained by IRSOA is more reasonable. Figure 2 and Figure 3 The results show that the RSOA algorithm converges more slowly, while the IRSOA algorithm converges faster and finds a better path more quickly. This shows that the IRSOA algorithm designed in this paper has both faster convergence speed and better accuracy. Simulation results demonstrate that under various identical environments, the IRSOA algorithm has a stronger search capability and obtains more optimal movement paths, validating the algorithm's effectiveness.

[0105] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A robot path planning method based on multi-strategy improvement, characterized in that: The following steps are involved: A grid map of the ground environment is established based on the positioning and navigation system, and the grid map is corrected and supplemented by combining the robot's own real-time perception of the environment; According to the corrected and supplemented grid map, the objective function of the robot path planning is established with the shortest moving path, the shortest time consumption, or the least energy consumption as constraints; A randomly generated mouse population is constructed, with each individual mouse located in a modified and supplemented grid map and corresponding to unique coordinates. Based on the objective function, an improved mouse swarm optimization algorithm is used to update the optimal position and determine the optimal mouse position. The improved mouse swarm optimization algorithm improves the position update formula of the original mouse swarm optimization algorithm by introducing the position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm. The position update is performed by taking into account the optimal position of the mouse in the current iteration, the positions of other mice in the population, and the adaptive step size of the mouse. The optimal mouse position is updated in sequence according to the preset maximum number of iterations to determine the optimal path planning result.

2. The robot path planning method based on multi-strategy improvement according to claim 1 is characterized in that: The method of updating the optimal position by using the improved mouse swarm optimization algorithm to determine the optimal mouse position includes the following steps: Initialize the mouse population positions using Gaussian mapping; The position update method of the teaching and learning optimization algorithm and the educational competition optimization algorithm is introduced into the mouse position update formula to search for the optimal mouse position; By bidirectional sine The optimal mouse position is further updated by mutation to determine the updated optimal mouse position.

3. The robot path planning method based on multi-strategy improvement according to claim 2 is characterized in that: The method of initializing the mouse population position using Gaussian mapping includes the following steps: Determine the size of the population N , the mouse finds the lower boundary LB Finding the upper bound with mice UB ; Generate random numbers through Gaussian mapping x t : ； In the formula, mod(·) is the remainder function, x t+1 is the next random number; Initialize the mouse position using the generated Gaussian random numbers: 。 4. The robot path planning method based on multi-strategy improvement according to claim 2 is characterized in that: The method of introducing the position updating method of the teaching and learning optimization algorithm and the educational competition optimization algorithm into the mouse position updating formula to search for the optimal mouse position includes the following steps: Attack behavior: When attacking prey, mice continuously change the attack angle and speed through spiral motion. The spiral motion behavior is shown in the following formula: ； Where: x, y, z are the coordinates in three directions, is the radius of each spiral; is a random angle value in the range [0, 2π]; u and v is the relevant constant that defines the shape of the spiral; e is the base of natural logarithms; The position update mechanism of the teaching and learning optimization algorithm and the educational competition optimization algorithm is introduced. The improved mouse position update formula is as follows: ； in: ； ； ； Where: For the current prey; is the position of the i-th mouse at the t+1th iteration; is the position of the i-th mouse at the t-th iteration; is the exploration parameter; is a random number in the range [1,2]; Miter is the maximum number of iterations; To develop parameters, , is a random number in the range [0,1]; represents the optimal position of the mouse at the tth iteration; rand is a random number between [0,1]; is a random number between [0,1]; and is a random integer between [1, N], and The randomly selected and The position of the mouse, ; is the fitness function when calculating the fitness value; is the adaptive step length of the mouse; Calculate the fitness value: ； Where, is the fitness function when calculating the fitness value; Record the best mouse in that iteration.

5. The robot path planning method based on multi-strategy improvement according to claim 2 is characterized in that: The bidirectional sine The optimal position of the mouse is further updated by mutation, including the following steps: For dimensions j , calculated based on the current number of iterations sine Chaos value, and switches between positive and negative directions with equal probability: ； ； Where rand is a random number between 0 and 1; x 0 is the iteration sequence value; Perform mutation perturbation on the optimal position: ； Where: Indicates the t +1 optimal position for iteration No. j dimension; Greedy Update: ； After each dimension has been mutated, stop mutation.

6. A robot path planning system based on multi-strategy improvement, characterized in that: The system comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of the robot path planning method based on multi-strategy improvement as claimed in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a data processing program, which, when executed by a processor, implements the steps of the robot path planning method based on multi-strategy improvement according to any one of claims 1 to 5.

Images