Mine robot path planning method and system

Abstract

The present disclosure relates to a mine robot path planning method and system, and relates to the technical field of mine path planning. The mine robot path planning method comprises: acquiring a multi-dimensional search space in a mine and population information of a path corresponding to initial space position information to target position information of the mine robot in the multi-dimensional search space; respectively performing iterative updating on position information corresponding to a finder, a follower and a vigilant person in the population information; when the number of iterations corresponding to the position information of the optimal population individual in the population information reaches a set iteration number, stopping the iterative updating, and completing the path planning of the mine robot. The embodiment of the present disclosure can realize the path planning of the mine robot.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of mine path planning, and particularly relates to a mine robot path planning method and system. BACKGROUND

[0002] The key task of a coal mine inspection robot is to detect harmful gas concentration, temperature and humidity, image information inside the mine, and the position of some areas in the mine environment in real time, and transmit these information to the monitoring center, so as to timely grasp the safety situation of the mine.

[0003] In the existing path planning method, the sparrow search algorithm has some defects: 1. When randomly initializing to generate the initial population, there is strong uncertainty, the population diversity is low, and the convergence ability of the algorithm is weak. 2. In the search process of the sparrow algorithm, the search range decreases with the increase of the number of iterations, which limits the global search ability of the algorithm, and the flexibility of the position update of the guardian is not enough, especially in the case of large or complex search space, it is difficult to effectively explore the global solution space. 3. With the increase of the number of iterations, the convergence of the sparrow population tends to be near a certain individual, which reduces the diversity of the population. If the optimal individual is near the local extremum at this time, the algorithm will fall into local optimum, and the algorithm lacks mutation mechanism, so the estimation algorithm is difficult to jump out of the local optimum, which leads to ignoring the global optimal value.

[0004] Path planning is crucial to the efficiency and safety of the coal mine inspection robot, which can help the robot to efficiently and accurately reach the specified position, avoid obstacles, and ensure its safety during movement. Therefore, the research on the path planning algorithm for the coal mine inspection robot is of great significance, which can improve the execution efficiency and safety of the inspection task. SUMMARY

[0005] The present disclosure provides a mine robot path planning method and system.

[0006] According to an aspect of the present disclosure, a mine robot path planning method is provided, comprising:

[0007] Obtaining the multi-dimensional search space in the mine and the population information of the path corresponding to the initial spatial position information to the target position information of the mine robot in the multi-dimensional search space;

[0008] respectively; wherein the position information corresponding to the discoverer in the population information is iteratively updated by using a normal distribution random number and a dynamic weight factor corresponding to the normal distribution random number; wherein the position information corresponding to the vigilant in the population information is iteratively updated by using a random step length generated by a Levy flight, the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information;

[0009] When the iteration number corresponding to the position information of the best individual in the population information reaches a set iteration number, the iterative updating is stopped, and the path planning of the mine robot is completed.

[0010] Preferably, the method of iteratively updating the position information corresponding to the discoverer in the population information by using a normal distribution random number and a dynamic weight factor corresponding to the normal distribution random number comprises: obtaining the current iteration number and a first maximum iteration number in the iterative updating process, and calculating the ratio of the current iteration number to the first maximum iteration number in the iterative updating process respectively; determining the dynamic weight factor corresponding to the ratio in the iterative updating process respectively; multiplying the dynamic weight factor corresponding to the ratio and the normal distribution random number corresponding to the dynamic weight factor to obtain an update coefficient; and iteratively updating the position information corresponding to the discoverer in the population information by using the update coefficient.

[0011] Preferably, the method of determining the dynamic weight factor corresponding to the ratio in the iterative updating process respectively comprises: calculating the difference between 1 and the ratio; and squaring the difference between 1 and the ratio to obtain the dynamic weight factor corresponding to the ratio.

[0012] Preferably, the method of iteratively updating the position information corresponding to the discoverer in the population information by using the update coefficient respectively comprises: multiplying the position information corresponding to the discoverer in the population information by the update coefficient to obtain the position information corresponding to the update coefficient; and adding the position information corresponding to the discoverer in the population information to the position information corresponding to the update coefficient to obtain the position information of the discoverer after the iterative updating.

[0013] Preferably, the method for iteratively updating the position information corresponding to the scout in the population information by using the random step length generated by the Levy flight, the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information comprises: if the fitness value corresponding to the scout at the current iteration number is greater than the best fitness, calculating a first absolute difference matrix corresponding to the difference matrix between the position information corresponding to the scout at the current iteration number and the best fitness; after the first absolute difference matrix is multiplied by the random step length generated by the Levy flight, adding the position information corresponding to the best individual at the current iteration number to obtain the iteratively updated position information corresponding to the scout; if the fitness value corresponding to the scout at the current iteration number is equal to the best fitness, calculating a second absolute difference matrix corresponding to the difference matrix between the best fitness and the worst fitness; after the second absolute difference matrix is multiplied by the random step length generated by the Levy flight, adding the position information corresponding to the scout at the current iteration number to obtain the iteratively updated position information corresponding to the scout; after the iteratively updated position information corresponding to the scout is obtained, updating the fitness values corresponding to the position information corresponding to the best individual and the position information corresponding to the worst individual in the population information by using the iteratively updated position information corresponding to the discoverer, the follower and the scout in the population information, and determining the best fitness and the worst fitness corresponding to the previous iteration number according to the updated fitness values.

[0014] Preferably, in the method for updating the fitness values corresponding to the position information corresponding to the best individual and the position information corresponding to the worst individual in the population information in real time during the iteration updating process, the method comprises: updating the position information corresponding to the best individual and the position information corresponding to the worst individual in the population information in real time during the iteration updating process by using the iteratively updated position information corresponding to the discoverer, the follower and the scout in the population information; updating the population information matrix by using the iteratively updated position information corresponding to the discoverer, the follower and the scout in the population information; and calculating the updated fitness values corresponding to the position information of each individual in the updated population information matrix according to the fitness function.

[0015] Preferably, the method for determining the random step length generated by the Levy flight comprises: obtaining a step length parameter corresponding to the Levy flight, a first random number and a second random number conforming to a normal distribution, and a set parameter less than 1; and determining the random step length generated by the Levy flight based on the step length parameter corresponding to the Levy flight, the first random number and the second random number conforming to the normal distribution, and the set parameter less than 1.

[0016] Preferably, the method for determining the random step length generated by the Levy flight based on the step length parameter corresponding to the Levy flight, the first random number and the second random number conforming to the normal distribution, and the setting parameter less than 1 comprises: taking the inverse of the step length parameter corresponding to the Levy flight to obtain a step length parameter inverse; multiplying the step length parameter inverse raised to the power corresponding to the first random number divided by the second random number by the setting parameter less than 1 to obtain the random step length generated by the Levy flight.

[0017] Preferably, the method for iteratively updating the position information corresponding to the follower in the population information comprises: determining the position information corresponding to the best individual of the discoverer in the population information and the position information corresponding to the worst individual in the population information; and iteratively updating the position information corresponding to the follower in the population information according to the position information corresponding to the best individual of the discoverer in the population information and the position information corresponding to the worst individual in the population information determined according to the population information matrix.

[0018] Preferably, the method for determining the position information corresponding to the best individual of the discoverer in the population information and the position information corresponding to the worst individual in the population information matrix comprises: calculating the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix according to the fitness function; determining the position information corresponding to the best individual of the discoverer in the population information based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix; calculating the fitness value corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix according to the fitness function; and determining the position information corresponding to the worst individual in the population information based on the fitness value corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix.

[0019] The method for determining the position information corresponding to the best individual of the discoverer in the population information based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix comprises: sorting the fitness values corresponding to the iteratively updated position information of the discoverer in the population information matrix from small to large to obtain sorted fitness values; and configuring the position information corresponding to the first individual as the position information corresponding to the best individual of the discoverer in the population information.

[0020] Preferably, the fitness value corresponding to the iteratively updated position information of the discoverer, follower and vigilant in the population information matrix is used to determine the position information corresponding to the worst population individual in the population information; the fitness values corresponding to the iteratively updated position information of the discoverer, follower and vigilant in the population information matrix are sorted from small to large to obtain sorted fitness values; and the position information corresponding to the last population individual corresponding to the sorted fitness values is configured as the position information corresponding to the worst population individual in the population information.

[0021] The method for iteratively updating the position information corresponding to the follower in the population information according to the population information matrix, the optimal population individual corresponding to the discoverer in the population information and the position information corresponding to the worst population individual in the population information, comprises: in the iterative updating process, the position information corresponding to the optimal population individual of the discoverer is updated in real time using the iteratively updated position information corresponding to the discoverer in the population information, and the position information corresponding to the worst population individual in the population information is updated in real time using the iteratively updated position information corresponding to the discoverer, follower and vigilant in the population information; the position information of the worst population individual is used for iterative updating for the follower corresponding to a number greater than a set number, and the position information of the optimal population individual of the discoverer is used for iterative updating for the follower corresponding to a number less than or equal to the set number; wherein the set number is less than the number of population individuals in the population information matrix.

[0022] Preferably, the method for updating the position information corresponding to the optimal population individual of the discoverer in real time using the iteratively updated position information corresponding to the discoverer in the population information comprises: sorting the update fitness values corresponding to the iteratively updated position information of the discoverer in the population information matrix from small to large to obtain sorted update fitness values; and configuring the position information corresponding to the first discoverer corresponding to the sorted update fitness values as the updated position information corresponding to the optimal population individual of the discoverer in the population information.

[0023] Preferably, the method for updating the position information corresponding to the worst population individual in the population information in real time using the iteratively updated position information corresponding to the discoverer, follower and vigilant in the population information comprises: sorting the update fitness values corresponding to the iteratively updated position information of the discoverer, follower and vigilant in the population information matrix from small to large to obtain sorted update fitness values; and configuring the updated position information corresponding to the last population individual corresponding to the sorted update fitness values as the updated position information corresponding to the worst population individual in the population information.

[0024] Preferably, the method for updating the position information corresponding to the optimal population individual and the position information corresponding to the worst population individual by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information in real time comprises: updating the population information matrix by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information; calculating the update fitness value corresponding to the position information of each individual in the updated population information matrix according to the fitness function; determining the updated position information corresponding to the optimal population individual and the updated position information corresponding to the worst population individual based on the update fitness value corresponding to the position information of each population individual in the population information matrix.

[0025] Preferably, the method for iteratively updating the position information of the follower greater than the set number by using the position information corresponding to the worst population individual comprises: calculating the difference value matrix between the position information corresponding to the worst population individual at the current iteration number and the position information corresponding to the follower at the current iteration number; performing an exponential operation on the position information corresponding to the follower at the current iteration number after the difference value matrix between the position information corresponding to the worst population individual and the position information corresponding to the follower at the current iteration number is divided by the square of the position corresponding to the follower at the current iteration number, to obtain exponential position information; multiplying the exponential position information by a random number subject to a normal distribution to obtain the iteratively updated position information corresponding to the follower greater than the first set number.

[0026] Preferably, the method for iteratively updating the position information of the follower less than or equal to the set number by using the position information corresponding to the optimal population individual in the discoverer comprises: calculating the absolute value matrix of the difference value matrix between the position information corresponding to the optimal population individual in the discoverer at the current iteration number and the position information corresponding to the follower at the current iteration number; calculating the product of a set matrix and a transpose matrix corresponding to the set matrix, calculating the inverse matrix of the product of the set matrix and the transpose matrix corresponding to the set matrix, and calculating the product of the transpose matrix and the inverse matrix; adding the position information corresponding to the optimal population individual in the discoverer at the current iteration number to the product of the absolute value matrix, the transpose matrix, the all-1 matrix and the inverse matrix corresponding to the product, to obtain the iteratively updated position information corresponding to the follower less than or equal to the set number.

[0027] Preferably, the set number is configured as the average value corresponding to the number of population individuals in the population information matrix.

[0028] Preferably, before the corresponding position information of the discoverer whose random early warning value in the population information is less than the set safety value is iteratively updated by using the normally distributed random number and the corresponding dynamic weight factor, the discoverer is assigned a corresponding random early warning value; the corresponding position information of the discoverer whose random early warning value in the population information is less than the set safety value is iteratively updated by using the normally distributed random number and the corresponding dynamic weight factor; the corresponding position information of the discoverer whose random early warning value in the population information is greater than or equal to the set safety value is iteratively updated by using the normally distributed random number and the set all-1 matrix.

[0029] Preferably, the method for iteratively updating the corresponding position information of the discoverer whose random early warning value in the population information is greater than or equal to the set safety value by using the normally distributed random number and the set all-1 matrix comprises: calculating the normally distributed random number multiplied by the set all-1 matrix to obtain an update matrix; iteratively updating the corresponding position information of the discoverer whose random early warning value in the population information is greater than or equal to the set safety value by using the update matrix.

[0030] Preferably, the method for iteratively updating the corresponding position information of the discoverer whose random early warning value in the population information is greater than or equal to the set safety value by using the update matrix comprises: adding the update matrix to the corresponding position information of the discoverer whose random early warning value in the population information is greater than or equal to the set safety value to obtain the iteratively updated position information of the discoverer whose random early warning value is greater than or equal to the set safety value.

[0031] Preferably, before the corresponding position information of the discoverer, the follower and the vigilant person in the population information is iteratively updated respectively, the population information is subjected to chaotic mapping to obtain chaotic mapping population information; and then, the corresponding position information of the discoverer, the follower and the vigilant person in the chaotic mapping population information is iteratively updated respectively.

[0032] Preferably, the method of chaotically mapping the population information comprises: obtaining a first set control parameter, a second set control parameter greater than the first set control parameter, and a second maximum iteration number; if the position information corresponding to the population individual of the last iteration is between 0 and the first set control parameter, the position information corresponding to the population individual of the current iteration is configured by dividing the position information corresponding to the population individual of the last iteration by the first set control parameter; if the position information corresponding to the population individual of the last iteration is between the first set control parameter and the second set control parameter, a first difference between the position information corresponding to the population individual of the last iteration and the first set control parameter is calculated, and a second difference between the second set control parameter and the first set control parameter is calculated; the position information corresponding to the population individual of the current iteration is configured by dividing the first difference by the second difference; if the position information corresponding to the population individual of the last iteration is between the second set control parameter and 1 minus the first set control parameter, a third difference between 1 minus the first set control parameter and the position information corresponding to the population individual of the last iteration is calculated, and a fourth difference between the second set control parameter and the first set control parameter is calculated; the position information corresponding to the population individual of the current iteration is configured by dividing the third difference by the fourth difference; if the position information corresponding to the population individual of the last iteration is between 1 minus the first set control parameter and 1, a fifth difference between 1 and the position information corresponding to the population individual of the last iteration is calculated; the position information corresponding to the population individual of the current iteration is configured by dividing the fifth difference by the first set control parameter; and the chaotic mapping is stopped when the iteration number meets the second maximum iteration number.

[0033] Preferably, in the process of respectively iteratively updating the position information corresponding to the discoverer, the follower, and the wary in the population information, the position information corresponding to the optimal population individual is subjected to mutation disturbance, and a first fitness value corresponding to before the mutation disturbance and a second fitness value corresponding to after the mutation disturbance are calculated; the fitness value with a better fitness value between the first fitness value and the second fitness value is configured as the fitness value corresponding to the optimal population individual.

[0034] According to an aspect of the present disclosure, a path planning system / apparatus of a mine robot is provided, comprising:

[0035] A first unit is configured to obtain a multi-dimensional search space in a mine and population information of a path corresponding to an initial spatial position information to a target position information of the mine robot in the multi-dimensional search space;

[0036] The second unit is configured to iteratively update the position information of the discoverer, the follower and the vigilant in the population information respectively; wherein the position information of the discoverer with a random early warning value less than a set safety value in the population information is iteratively updated by using a normal distribution random number and a corresponding dynamic weight factor; and the position information of the vigilant in the population information is iteratively updated by using a random step length generated by a Levy flight, the position information of the best individual in the population information and the position information of the worst individual in the population information.

[0037] The third unit is configured to stop the iterative update when the iteration number of the position information of the best individual in the population information reaches a set iteration number, and complete the path planning of the mine robot.

[0038] According to an aspect of the present disclosure, there is provided a path planning system / apparatus for a mine robot, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the path planning method for the mine robot.

[0039] According to an aspect of the present disclosure, there is provided a path planning system / apparatus for a mine robot, comprising: a computer readable storage medium having stored thereon computer program instructions, the computer program instructions being executed by a processor to implement the path planning method for the mine robot.

[0040] According to an aspect of the present disclosure, there is provided a path planning system / apparatus for a mine robot, comprising: a computer program product comprising computer program / instructions, the computer program / instructions being executed by a processor to implement the path planning method for the mine robot.

[0041] According to an aspect of the present disclosure, there is provided a mine robot comprising or applying the path planning method for the mine robot as described above; or comprising the path planning system / apparatus for the mine robot as described above.

[0042] In the embodiments of the present disclosure, the technical solutions of the path planning method and system for the mine robot are proposed to improve the execution efficiency and safety of the mine robot inspection task.

[0043] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure.

[0044] Other features and aspects of the present disclosure will become apparent from the following detailed description of example embodiments, taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments that conform to the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure.

[0046] Figure 1 A flow chart of a path planning method of a mine robot according to an embodiment of the present disclosure is shown;

[0047] Figure 2 A convergence curve on a unimodal reference function according to an embodiment of the present disclosure is shown;

[0048] Figure 3 A convergence curve on a multimodal reference function according to an embodiment of the present disclosure is shown;

[0049] Figure 4 A convergence curve on a constant dimension multimodal function according to an embodiment of the present disclosure is shown;

[0050] Figure 5 Shortest paths of four algorithms in a 15x15 grid map according to an embodiment of the present disclosure are shown;

[0051] Figure 6 Convergence curves of four algorithms in a 15x15 grid map according to an embodiment of the present disclosure are shown;

[0052] Figure 7 Shortest paths of four algorithms in a 20x20 grid map according to an embodiment of the present disclosure are shown;

[0053] Figure 8 Convergence curves of four algorithms in a 20x20 grid map according to an embodiment of the present disclosure are shown;

[0054] Figure 9 Shortest paths of four algorithms in a 25x25 grid map according to an embodiment of the present disclosure are shown;

[0055] Figure 10 Convergence curves of four algorithms in a 25x25 grid map according to an embodiment of the present disclosure are shown;

[0056] Figure 11 A specific implementation scheme according to an embodiment of the present disclosure is shown;

[0057] Figure 12 Path planning results of the MSSA algorithm in a simulated mine environment according to an embodiment of the present disclosure are shown;

[0058] Figure 13 is a block diagram of an electronic device 800 according to an exemplary embodiment;

[0059] Figure 14 is a block diagram of an electronic device 1900 according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in different drawings denote the same or similar elements. Although various aspects of embodiments are illustrated in the drawings, the drawings are not necessarily drawn to scale unless specifically noted.

[0061] The term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations.

[0062] The term "and / or", merely describes association relationship of associated objects, and means that three relationships can exist, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of multiple or any combination of at least two of multiple, for example, at least one of A, B and C includes any one or more elements selected from the set consisting of A, B and C.

[0063] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the specific embodiments below. Those skilled in the art should understand that the present disclosure can also be implemented without some specific details. In some examples, methods, means, elements and circuits well known to those skilled in the art are not described in detail, in order to highlight the main idea of the present disclosure.

[0064] It can be understood that the above-mentioned various mine robot path planning method embodiments of the present disclosure can be combined with each other to form combined embodiments without deviating from the principle logic. Due to the limited length, the present disclosure will not be described again.

[0065] In addition, the present disclosure also provides a mine robot path planning device or system, an electronic device, a computer readable storage medium, and a program product, which can be used to implement any mine robot path planning method provided by the present disclosure. The corresponding technical solutions and descriptions are described in the mine robot path planning method part and will not be described again.

[0066] Figure 1 A flowchart of a mine robot path planning method according to an embodiment of the present disclosure is shown as follows, Figure 1As shown, the path planning method of the mine robot comprises the following steps: S101: acquiring multi-dimensional search space in the mine and population information of a path corresponding to initial spatial position information to target position information of the mine robot in the multi-dimensional search space; S102: iteratively updating position information corresponding to the discoverer, the follower and the vigilant in the population information; wherein the position information corresponding to the discoverer with a random early warning value less than a set safety value in the population information is iteratively updated by using a normal distribution random number and a corresponding dynamic weight factor; wherein the position information corresponding to the vigilant in the population information is iteratively updated by using a random step length generated by the Levy flight, the position information corresponding to the optimal population individual and the position information corresponding to the worst population individual in the population information; S103: when the iteration number of the position information corresponding to the optimal population individual in the population information reaches a set iteration number, stopping the iterative updating, and completing the path planning of the mine robot. The execution efficiency and safety of the mine robot inspection task are improved.

[0067] The sparrow algorithm is a kind of population optimization algorithm simulating the foraging behavior of sparrows. According to the foraging behavior, the population is divided into discoverers and followers. The discoverers undertake the task of foraging search of the population, and widely search in the detection area to provide the direction and range of foraging for the whole population. The followers will approach the food according to the information provided by the discoverers, and search in the periphery. When the sparrows forage, the identity of the discoverer and the identity of the follower can be converted to each other according to different foraging scenes, so as to improve the success rate of foraging. In addition, due to the existence of external enemies, the sparrows will keep vigilant when foraging, and will fly to other places when they feel danger to increase the safety of foraging.

[0068] The flow of the whole algorithm is as follows: first, the position information of the population is initialized, then the fitness value of the sparrow individual is calculated by the adaptive function, the fitness value is sorted according to the size, then the population division of the discoverer and the follower is carried out according to the sorting result, and the position of the discoverer and the follower is updated, and the vigilant is randomly selected in proportion, and its position is updated. Then, the fitness value of each individual is recalculated according to the updated position, and the optimal one is reserved and reordered. Finally, it is judged whether the end condition is met. If it is met, the global optimal solution corresponding to the position information of the population is output, if it is not met, the iteration is continued until the end condition is met.

[0069] Step S101: acquiring multi-dimensional search space in the mine and population information of a path corresponding to initial spatial position information to target position information of the mine robot in the multi-dimensional search space.

[0070] In embodiments of the present disclosure and possible embodiments thereof, the multi-dimensional search space can be configured as a D-dimensional search space. Further, the population information of the path corresponding to the initial spatial position information to the target position information of the mine robot in the D-dimensional search space can be determined.

[0071] In embodiments of the present disclosure and possible embodiments thereof, the population information X of the path corresponding to the initial spatial position information to the target position information of the mine robot in the D-dimensional search space.

[0072] For example, assuming that in the D-dimensional search space, when using the sparrow search algorithm, the population information matrix X composed of N sparrows corresponding to the population individuals is as follows:

[0073]

[0074] Wherein, the dimension of the population information matrix X corresponding to the population information is NxD, wherein each row X[i,:](i.e. [x i1 ,x i2 ,…,x iD ]) of the population information matrix X represents the specific position of the i-th sparrow individual (individual or population individual) in the D-dimensional search space. x i,j represents the position coordinates of the i-th sparrow in the j-th dimensional search space in the D-dimensional search space.

[0075] Step S102: iteratively updating the position information corresponding to the discoverer, follower and vigilant in the population information respectively; wherein the normal distribution random number randN and its corresponding dynamic weight factor (1-t / T max 2 The position information corresponding to the discoverer in the population information whose random early warning value R2 is less than the set safety value ST is iteratively updated; wherein the position information corresponding to the best population individual and the worst population individual in the population information is iteratively updated by using the random step length generated by the Levy flight, the position information corresponding to the best population individual and the worst population individual in the population information.

[0076] In embodiments of the present disclosure and possible embodiments thereof, when the sparrow search algorithm is searching, the sparrow population is divided into three categories, namely discoverer (high fitness value), follower and vigilant. Among them, the discoverer has strong adaptability, high fitness, and is more likely to find food. The discoverer searches in the area responsible by it and leads other sparrows in the population to the food.

[0077] ​In embodiments of this disclosure, the method for iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using a normally distributed random number randN and its corresponding dynamic weighting factor includes: obtaining the current iteration number t and the first maximum iteration number T during the iterative update process. max And calculate the ratio t / T between the current iteration number and the first maximum iteration number in the iterative update process. max Based on the ratio t / T during the iterative update process respectively max Determine the corresponding dynamic weighting factor (1-t / T) max ) 2 ; respectively assign the corresponding dynamic weighting factors (1-t / T) max ) 2 Multiply the corresponding normally distributed random number randN to obtain the corresponding update coefficient (1-t / T). max ) 2 ·randN; respectively using the update coefficients (1-t / T) max ) 2 ·randN represents the location information of discoverers whose warning values ​​are randomly lower than a set safety value from the population information. Iterative updates will be performed.

[0078] In embodiments of this disclosure, the method for determining the corresponding dynamic weight factors based on the ratios during the iterative update process includes: calculating the ratio t / T between 1 and the corresponding ratio. max The difference between 1-t / T max The difference between 1 and the corresponding ratio is 1-t / T. max Squaring (1-t / T) max ) 2 The corresponding dynamic weighting factor (1-t / T) is obtained. max ) 2 .

[0079] In embodiments of this disclosure, the method of iteratively updating the location information corresponding to discoverers whose random warning values ​​are less than a set safety value in the population information using the update coefficient includes: updating the location information corresponding to discoverers whose random warning values ​​are less than a set safety value... Multiply by the corresponding update coefficient (1-t / T) max ) 2 Then, the position information corresponding to the update coefficient is obtained. The location information corresponding to the update coefficient, plus the location information of the discoverer whose random warning value is less than the set safety value, is... The iteratively updated location information of the discoverer whose random warning value is less than the set safety value is obtained.

[0080] In an embodiment of the present disclosure, before the position information corresponding to the discoverer whose random early warning value in the population information is less than the set safety value is iteratively updated by using a normally distributed random number and its corresponding dynamic weight factor, the discoverer is assigned a corresponding random early warning value; the position information corresponding to the discoverer whose random early warning value in the population information is less than the set safety value is iteratively updated by using a normally distributed random number and its corresponding dynamic weight factor; and the position information corresponding to the discoverer whose random early warning value in the population information is greater than or equal to the set safety value is iteratively updated by using a normally distributed random number and a set all-1 matrix.

[0081] In an embodiment of the present disclosure, the method for iteratively updating the position information corresponding to the discoverer whose random early warning value R2 in the population information is greater than or equal to the set safety value ST by using a normally distributed random number Q and a set all-1 matrix L includes: calculating the product of the normally distributed random number Q and the set all-1 matrix L to obtain an update matrix Q·L; and iteratively updating the position information corresponding to the discoverer whose random early warning value in the population information is greater than or equal to the set safety value by using the update matrix Q·L.

[0082] In an embodiment of the present disclosure, the method for iteratively updating the position information corresponding to the discoverer whose random early warning value in the population information is greater than or equal to the set safety value by using the update matrix includes: adding the update matrix Q·L to the position information corresponding to the discoverer whose random early warning value in the population information is greater than or equal to the set safety value to obtain the iteratively updated position information corresponding to the discoverer whose random early warning value is greater than or equal to the set safety value.

[0083] In an embodiment of the present disclosure and possible embodiments thereof, the iterative update formula of the position information corresponding to the discoverer is as follows:

[0084]

[0085] In the formula, t is the iteration number, j represents the dimension of the solution j = 1, 2, …, D, X i,j represents the position information of sparrow i in the jth dimension in the D-dimensional search space, T max is the first maximum iteration number, α is a random number in (0, 1], Q is a normally distributed random number, R2 is a random early warning value, ST is a set safety value, R2 ∈ [0, 1], ST ∈ [0.5, 1], for example, ST is configured as 0.8. L is a 1 × D all-1 matrix.

[0086] ​​In the above formula, when R2< ST, it indicates that the sparrow population is in a safe range at this time, and the finder conducts extensive search in the area. When R2≥ ST, it indicates that there are external predators in the area, and the search is stopped, and all sparrows need to go to other places to ensure the safety of the population.

[0087] In the iterative updating formula of the position information corresponding to the finder in the embodiments of the present disclosure and possible embodiments thereof, when R2< ST, the finder position change coefficient is exp(-i / α·T max ), it can be seen that the value of the coefficient is always less than 1, so that the value of each dimension of the finder sparrow will decrease with the increase of the iteration number, and approach to the origin of the coordinate axis, resulting in the loss of part of the effective solution and reducing the population diversity. From the above characteristics, it can be seen that when the optimal solution of the problem is near the origin, the updating formula will quickly converge to the origin; if the optimal solution is not at the origin, the convergence speed and accuracy of the algorithm will be reduced. Therefore, in this paper, a dynamic weight factor is used to improve the original iterative updating formula of the position information corresponding to the finder, and the improved formula is as follows:

[0088]

[0089] In the formula, randN represents a normally distributed random number with a mean of 0 and a variance of 1, (1-t / T max ) 2 is a dynamic weight factor of the normally distributed random number, which is used to control the search range of the finder. The factor will gradually decrease with the increase of the iteration number, thereby improving the search accuracy of the algorithm.

[0090] In the embodiments of the present disclosure, the random step length lv generated by the Levy flight, the position information corresponding to the optimal population individual in the population information and the position information corresponding to the worst population individual The method for iteratively updating the position information corresponding to the alarmers in the population information includes: if the fitness value f i of the alarmers corresponding to the current iteration number is greater than the optimal fitness f b , calculating the first absolute difference matrix corresponding to the difference matrix between the position information corresponding to the alarmers of the current iteration number and the optimal fitness , multiplying the first absolute difference matrix by the random step length lv generated by the Levy flight, and adding the position information corresponding to the optimal population individual of the current iteration number to obtain the iteratively updated position information of the alarmers If the fitness value f i of the alarmers corresponding to the current iteration number is equal to the optimal fitness fb then a second absolute difference matrix corresponding to the difference matrix between the optimal fitness and the worst fitness of the current iteration number is calculated In the second absolute difference matrix After multiplying the random step length lv generated by the Levy flight, the position information corresponding to the vigilante of the current iteration number is added The iteration updated position information corresponding to the vigilante is obtained After the iteration updated position information corresponding to the vigilante is obtained, the fitness values corresponding to the position information of the optimal population individual and the position information of the worst population individual are updated using the iteration updated position information corresponding to the finder, the follower and the vigilante in the population information, and the fitness values f i The optimal fitness corresponding to the previous iteration number is determined and the worst fitness

[0091] In the embodiments of the present disclosure and its possible embodiments, during the entire foraging process, 10% to 20% of sparrows are randomly selected as vigilantes, and when danger is encountered, the iteration updated formula of the position information corresponding to the vigilante is as follows:

[0092]

[0093] In the formula, is the position of the sparrow with the optimal fitness corresponding to the tth iteration of the population, is the position of the sparrow with the worst fitness corresponding to the tth iteration of the population, and β is a random number subject to a standard normal distribution and is used as a step length for controlling movement. K ∈ [-1, 1], f i is the fitness value of the current sparrow individual i, f b and f w are the optimal fitness (the optimal fitness is the minimum fitness corresponding to all fitnesses) and the worst fitness of the population, respectively. ε is a minimum constant for avoiding division by 0.

[0094] In the embodiments of the present disclosure and possible embodiments thereof, the alert formula is improved by adopting a Levy flight strategy, which is a strategy proposed by simulating the moving track of animal predation and has the characteristics of jumping and randomness. The small-step sparrow individuals are moved in a small range, while the long-distance jumping is also retained, which can help the sparrow search algorithm to expand the search range and jump out of the local optimal solution to find the global optimal solution. In the iterative updating formula of the position information corresponding to the alert, β is a normally distributed random number, which is not conducive to the large-range jumping search and small-range local development of the alert. Therefore, the Levy flight step is introduced, and the iterative updating formula of the position information corresponding to the alert is simplified to obtain the improved formula as follows:

[0095]

[0096] In the formula, X represents the position of the ith sparrow in the tth iteration, X best and X worst represent the positions of the sparrow with the best fitness and the sparrow with the worst fitness in the population.

[0097] As can be seen from the improved formula, by using the characteristics of randomness and jumping of Levy flight, the search ability of the alert sparrow is enhanced, the position change of the sparrow at the edge of the population becomes more flexible, and the search range of the sparrow at the center of the population is increased, so that the algorithm is further freed from the limitation of local extreme value and the search ability of the algorithm is improved.

[0098] In the embodiments of the present disclosure, in the method for updating the position information corresponding to the optimal population individual and the position information corresponding to the worst population individual by using the iteratively updated position information corresponding to the discoverer, the follower and the alert in the population information in real time in the iterative updating process, the method comprises the following steps of: in the iterative updating process, the position information corresponding to the optimal population individual and the position information corresponding to the worst population individual are updated by using the iteratively updated position information corresponding to the discoverer, the follower and the alert in the population information in real time; the population information matrix is updated by using the iteratively updated position information corresponding to the discoverer, the follower and the alert in the population information; and the updated fitness value corresponding to the position information of each individual in the updated population information matrix is calculated according to the fitness function f.

[0099] In the embodiments of the present disclosure and possible embodiments thereof, each sparrow represents a group of solutions in a D-dimensional search space. The fitness function f can be used to evaluate the quality of the solution, and the fitness value of the sparrow population can be represented as:

[0100]

[0101] FX is a fitness matrix corresponding to the fitness value of each sparrow individual (population individual) in the sparrow population (population information), the fitness matrix F X Each row f ([x i1 ,x i2 ,…,x iD ]) of the fitness matrix F i represents the fitness value of the i-th sparrow individual (population individual) x

[0102] In an embodiment of the present disclosure, the method for determining the random step length lv generated by the Levy flight includes: obtaining a step length parameter corresponding to the Levy flight, a first random number and a second random number conforming to a normal distribution, and a set parameter less than 1; determining the random step length lv generated by the Levy flight based on the step length parameter λ corresponding to the Levy flight, the first random number μ and the second random number v conforming to the normal distribution, and the set parameter less than 1, 0.01.

[0103] In an embodiment of the present disclosure, the method for determining the random step length generated by the Levy flight based on the step length parameter corresponding to the Levy flight, the first random number and the second random number conforming to the normal distribution, and the set parameter less than 1 includes: taking the reciprocal of the step length parameter λ corresponding to the Levy flight to obtain the step length parameter reciprocal 1 / λ; after dividing the first random number μ by the step length parameter reciprocal corresponding to the second random number v 1 / λ , multiplying the set parameter less than 1, 0.01, to obtain the random step length 0.01×μ / |v 1 / λ generated by the Levy flight.

[0104] In an embodiment of the present disclosure and possible embodiments thereof, a person skilled in the art can configure the set parameter less than 1 according to actual needs. For example, it can be configured as 0.01 or other numerical values; for example, 0.02, 0.04, 0.05 or other possible numerical values.

[0105] In an embodiment of the present disclosure and possible embodiments thereof, lv is the random step length generated by the Levy flight, and the calculation formula is as follows:

[0106]

[0107] In the formula, λ is the Levy step length parameter, generally taking a value of 1.5, μ and v are the first random number and the second random number conforming to the normal distribution, and the specific distribution is as follows:

[0108]

[0109] In the formula, σ μ , σ ν is calculated by the following formula:

[0110]

[0111] where τ is a gamma distribution function and λ is a Levy step parameter.

[0112] In an embodiment of the present disclosure, the method for iteratively updating the position information corresponding to the follower in the population information comprises: determining the position information X P corresponding to the best individual of the discoverer in the population information and the position information X worst corresponding to the worst individual in the population information; and iteratively updating the position information corresponding to the follower in the population information according to the position information X P corresponding to the best individual of the discoverer and the position information X worst corresponding to the worst individual in the population information.

[0113] In an embodiment of the present disclosure, the method for determining the position information corresponding to the best individual of the discoverer in the population information and the position information corresponding to the worst individual in the population information matrix comprises: calculating the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix according to the fitness function; determining the position information X P corresponding to the best individual of the discoverer in the population information based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix; and calculating the fitness value corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix according to the fitness function; determining the position information X worst corresponding to the worst individual in the population information based on the fitness value corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix.

[0114] In an embodiment of the present disclosure, the method for determining the position information corresponding to the best individual of the discoverer based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix comprises: sorting the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix from small to large to obtain the sorted fitness value; and configuring the position information corresponding to the first individual of the sorted fitness value as the position information X P corresponding to the best individual of the discoverer in the population information.

[0115] In the embodiments of the present disclosure, the fitness value corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix is used to determine the position information corresponding to the worst population individual in the population information; the fitness values corresponding to the iteratively updated position information of the discoverer, the follower and the vigilant in the population information matrix are sorted from small to large to obtain the sorted fitness values; and the position information corresponding to the last population individual corresponding to the sorted fitness values is configured as the position information X corresponding to the worst population individual in the population information. worst .

[0116] In the embodiments of the present disclosure, the position information corresponding to the optimal population individual of the discoverer in the population information and the position information corresponding to the worst population individual in the population information are determined according to the population information matrix, and the position information corresponding to the follower in the population information is iteratively updated, including: in the iterative updating process, the position information corresponding to the optimal population individual of the discoverer is updated in real time by using the iteratively updated position information corresponding to the discoverer in the population information, and the position information corresponding to the worst population individual in the population information is updated in real time by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information; the position information of the follower corresponding to a number greater than a set number is iteratively updated by using the position information X corresponding to the worst population individual in the population information worst , the position information of the follower corresponding to a number less than or equal to the set number is iteratively updated by using the position information X corresponding to the optimal population individual of the discoverer in the population information P ; wherein the set number is less than the number N of population individuals in the population information matrix.

[0117] In the embodiments of the present disclosure, the method for updating the position information corresponding to the optimal population individual of the discoverer in the population information in real time by using the iteratively updated position information corresponding to the discoverer in the population information includes: sorting the update fitness values corresponding to the iteratively updated position information corresponding to the discoverer in the population information matrix from small to large to obtain the sorted update fitness values; and configuring the position information corresponding to the first discoverer corresponding to the sorted update fitness values as the updated position information X corresponding to the optimal population individual of the discoverer in the population information P .

[0118] In the embodiments of the present disclosure, the method for updating the position information corresponding to the worst population individual in the population information in real time by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information comprises: sorting the update fitness values corresponding to the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information matrix from small to large to obtain sorted update fitness values; and configuring the updated position information corresponding to the last population individual corresponding to the sorted update fitness values as the updated position information X corresponding to the worst population individual in the population information worst .

[0119] In the embodiments of the present disclosure, the method for updating the position information corresponding to the best population individual and the position information corresponding to the worst population individual in real time by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information comprises: updating the population information matrix by using the iteratively updated position information corresponding to the discoverer, the follower and the vigilant in the population information; calculating the update fitness values corresponding to the position information of each individual in the updated population information matrix according to the fitness function; and determining the updated position information corresponding to the best population individual and the updated position information corresponding to the worst population individual based on the update fitness values corresponding to the position information of each population individual in the population information matrix.

[0120] In the embodiments of the present disclosure, the method for iteratively updating the position information of the follower greater than the first set number by using the position information corresponding to the worst population individual comprises: calculating the difference matrix between the position information corresponding to the worst population individual and the position information corresponding to the follower in the current iteration number dividing the difference matrix between the position information corresponding to the worst population individual and the position information corresponding to the follower in the current iteration number by the square of the position i corresponding to the follower in the current iteration number performing an exponential operation to obtain exponential position information the exponential position information multiplying the exponential position information by a random number Q subject to a normal distribution to obtain the iteratively updated position information corresponding to the follower greater than the first set number

[0121] In the embodiments of the present disclosure, the method for iteratively updating the position information of the follower less than or equal to the set number by using the position information corresponding to the best population individual in the discoverer comprises: calculating the absolute value matrix of the difference matrix between the position information corresponding to the best population individual in the discoverer and the position information corresponding to the follower in the current iteration number calculating a set matrix A and a transpose matrix A corresponding to the set matrix A TThe product of AA T Calculate the product AA of the set matrix and the transpose of the set matrix. T The inverse matrix (AA) T ) -1 And calculate the transpose matrix A T and the inverse matrix (AA) T ) -1 The product A + =A T (AA T ) -1 ; in the absolute value matrix Multiply by the transpose matrix, the all-ones matrix L, and the inverse matrix A + corresponding product Then, add the location information of the best individual in the population corresponding to the discoverer at the current iteration number. Obtain the iteratively updated position information of the followers corresponding to the number less than or equal to the set number.

[0122]

[0123] In the embodiments of this disclosure, the set number is configured as the average number N / 2 corresponding to the number of individuals in the population information matrix.

[0124] In the embodiments and possible embodiments of this disclosure, all individuals in the population other than the discoverer are considered followers. During foraging, followers will follow and monitor the discoverer to increase their predation rate. The position update formula for followers is as follows:

[0125]

[0126] In the formula, X P This represents the best position of the sparrow among the discoverers (the position of the discoverer sparrow corresponding to the optimal fitness value / minimum fitness value among all discoverers), X worst Let A represent the position of the sparrow with the worst fitness among all sparrows (the position of the sparrow corresponding to the worst fitness value / the position of the sparrow with the highest fitness value). Let A be a 1×D matrix where each element is randomly assigned a value of -1 or 1. + =A T (AA T ) -1 When i > N / 2, it indicates that the follower has poor fitness, has not obtained food, and needs to adjust its strategy to fly to other places to forage.

[0127] In the embodiments of the present disclosure, before the position information corresponding to the discoverer, the follower and the vigilant in the population information is iteratively updated, the population information is subjected to chaotic mapping to obtain chaotic mapping population information; and then the position information corresponding to the discoverer, the follower and the vigilant in the chaotic mapping population information is iteratively updated.

[0128] In the embodiments of the present disclosure, the population information x = [x i1 ,x i2 ,…,x iD ], i = 1, 2,..,N is subjected to chaotic mapping to obtain chaotic mapping population information, comprising: acquiring a first set control parameter p, a second set control parameter greater than the first set control parameter and a second maximum iteration number; if the position information x t of the population individual corresponding to the last iteration is between 0 and the first set control parameter, the position information x t+1 of the population individual corresponding to the present iteration is configured after the position information of the population individual corresponding to the last iteration is divided by the first set control parameter; if the position information of the population individual corresponding to the last iteration is between the first set control parameter and the second set control parameter, a first difference value between the position information of the population individual corresponding to the last iteration and the first set control parameter is calculated, and a second difference value between the second set control parameter and the first set control parameter is calculated; the position information of the population individual corresponding to the present iteration is configured after the first difference value is divided by the second difference value; if the position information of the population individual corresponding to the last iteration is between the second set control parameter and 1-the first set control parameter, a third difference value between 1-the first set control parameter and the position information of the population individual corresponding to the last iteration is calculated, and a fourth difference value between the second set control parameter and the first set control parameter is calculated; the position information of the population individual corresponding to the present iteration is configured after the third difference value is divided by the fourth difference value; if the position information of the population individual corresponding to the last iteration is between 1-the first set control parameter and 1, a fifth difference value between 1 and the position information of the population individual corresponding to the last iteration is calculated; the position information of the population individual corresponding to the present iteration is configured after the fifth difference value is divided by the first set control parameter; and until the iteration number satisfies the second maximum iteration number, the chaotic mapping is stopped; the position information x i of the population individual corresponding to the population at the time when the chaotic mapping is stopped is processed by using the upper bound ub and the lower bound lb corresponding to the search space to obtain the position information x i new .

[0129] In the embodiments of the present disclosure and possible embodiments thereof, considering that the Piecewise chaotic mapping is not sensitive to initial values and has high uniformity, when the position information of each sparrow (population individual) in the sparrow population is randomly initialized, the Piecewise chaotic mapping is used to replace random initialization in this paper, the diversity of the population is increased, and the convergence speed and global search ability of the algorithm are improved. The expression of the Piecewise chaotic mapping is as follows: i1 ,x i2 ,…,x iD ], i = 1, 2,.., N.

[0130]

[0131] In the formula, p is a first set control parameter, generally taking 0.4, t is the number of iterations, and a second set control parameter can be configured as 0.5 or other values greater than the first set control parameter and less than 1-p.

[0132] Therefore, the steps of the initialization based on the Piecewise chaotic mapping are as follows: Step 1: generating the population information x0= [x 0,1 ,x 0,2 ,…,x 0,D ] of D dimensions; Step 2: generating the chaotic mapping population information corresponding to the subsequent chaotic sequence according to the expression of the Piecewise chaotic mapping;

[0133] Step 3: iterating to the second maximum number of iterations, and finally obtaining the chaotic mapping population information X corresponding to the chaotic sequence; Step 4: after obtaining the chaotic mapping population information X corresponding to the chaotic sequence, it is necessary to map it to the search space, and finally obtain the initial population X new . The specific mapping formula is as follows:

[0134] x i new = lb+(ub-lb)x i .

[0135] In the formula, ub and lb are the upper and lower bounds of the search space of D dimensions, respectively.

[0136] In the embodiments of the present disclosure, in the process of respectively iteratively updating the position information of the discoverer, the follower and the wary in the population information, the position information corresponding to the optimal population individual is disturbed and disturbed, and the first fitness value corresponding to the disturbance before the disturbance and the second fitness value corresponding to the disturbance after the disturbance are calculated; the fitness value with the better fitness value in the first fitness value and the second fitness value is configured as the fitness value corresponding to the optimal population individual.

[0137] In the embodiments of the present disclosure and possible embodiments thereof, the position information corresponding to the optimal population individual is subjected to mutation disturbance, which is configured as dynamic Cauchy-Gaussian mutation disturbance. In the sparrow algorithm search, as the iteration proceeds, the individuals in the sparrow algorithm tend to gather around the local optimal solution, and then the entire population can be misled to the local optimal solution, thereby losing the opportunity to explore the global optimal solution, resulting in reduced population diversity and difficulty in getting rid of the limitation of the local optimum. In order to reduce the risk of falling into the local optimum and increase the population diversity, a Cauchy-Gaussian mixed mutation strategy based on dynamic adjustment of the number of iterations is proposed to disturb the current optimal individual to find the global optimal solution.

[0138] In the embodiments of the present disclosure and possible embodiments thereof, according to the probability density function curves of Gaussian distribution and Cauchy distribution, the peak value of Cauchy distribution is low, the curve is flat and wide at both ends, which means that it can generate random values far from the center point; while Gaussian distribution presents symmetrical and concentrated characteristics, most values are concentrated around the mean value, and fewer values are far from the mean value. Therefore, compared with Gaussian mutation, Cauchy mutation is more likely to produce a larger change step, which helps the algorithm search in the global range and avoid falling into the local optimum; while Gaussian mutation is more likely to produce a smaller change step, which helps the algorithm search in the local range. In order to meet the different needs of the algorithm for mutation in different search stages.

[0139] A nonlinear dynamic weighting method combining Cauchy and Gaussian mutation operators is proposed in this paper, forming a dynamic Cauchy-Gaussian mutation operator, the specific formula of which is as follows:

[0140]

[0141] In the formula, and are the position of the optimal individual and the position after mutation at the tth iteration, ζ(t) is the dynamic weight factor, Cauchy(0, 1) is a random variable satisfying the standard Cauchy distribution, and Gauss(0, 1) is a random variable satisfying the standard normal distribution.

[0142] It can be seen from the above formula that the value of ζ(t) is small and the value of 1-ζ(t) is large at the early stage of iteration, at this time the Cauchy mutation plays a major role and can disturb the optimal individual in a large range, enhancing the global exploration ability; as the iteration proceeds, the value of ζ(t) gradually increases, at this time the role of Gaussian mutation is continuously enhanced, which is conducive to the local search development of the optimal individual and improves the convergence accuracy. Finally, the fitness values of the optimal individual before and after disturbance are calculated, and the better position is selected to enter the next iteration.

[0143] Step S103: When the position information of the optimal population individual in the population information corresponds to a set iteration number, stop the iteration update, and complete the path planning of the mine robot.

[0144] Overall, the improved multi-strategy fusion improved sparrow search algorithm (MSSA) is implemented as follows: (1) initialize parameters, including population size N, dimension D, upper and lower limits ub and lb of the search space, number of discoverers and vigilantes PD, SD, and maximum iteration number T max ; (2) generate the population information matrix X corresponding to the initial population by using the Piecewise chaotic mapping; (3) calculate the fitness values of the sparrows in the population information matrix X corresponding to the initial population according to the fitness function, and arrange them from small to large to obtain the current optimal population individual and the worst population individual ; (4) select the PD sparrows with the best fitness in the population as discoverers, update their positions according to the corresponding iteration update and improvement formula, and update the positions of the remaining sparrows as followers according to the corresponding iteration update formula; (5) randomly select SD sparrows as vigilantes, and update their positions by using the corresponding iteration update and improvement formula; (6) update the values of the population fitness, select and reserve the optimal one, and reorder the updated fitness to update the current optimal population individual and the worst population individual ; (7) use the dynamic Cauchy-Gaussian mutation operator to mutate the position information of the current optimal sparrow individual (optimal population individual) according to the corresponding formula, compare the fitness values (fitness values) before and after the mutation, and select the individual with better fitness to enter the next iteration; (8) judge whether the termination condition is met, if yes, execute step (9), otherwise return to step (4); (9) output the position information and fitness of the optimal sparrow individual (optimal population individual) (X best , F best ).

[0145] The execution subject of the mine robot path planning method can be a mine robot or a path planning device. For example, the mine robot path planning method can be executed by a terminal device or a server or other processing device. The terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the mine robot path planning method can be realized by calling the computer readable instructions stored in the memory by the processor.

[0146] Those skilled in the art can understand that, in the above path planning method of the mine robot in the specific embodiment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process, and the specific execution order of each step should be determined according to its function and possible internal logic.

[0147] The embodiment of the present disclosure also provides a path planning device / system of a mine robot, comprising: a first unit configured to acquire a multi-dimensional search space in a mine and population information of a path corresponding to initial spatial position information to target position information of the mine robot in the multi-dimensional search space; a second unit configured to iteratively update position information corresponding to a finder, a follower and a vigilant person in the population information; wherein the position information corresponding to the finder in the population information whose random early warning value is less than a set safety value is iteratively updated by using a normal distribution random number and a corresponding dynamic weight factor; wherein the position information corresponding to the vigilant person in the population information is iteratively updated by using a random step length generated by a Levy flight, position information corresponding to an optimal population individual in the population information and position information corresponding to a worst population individual; and a third unit configured to stop the iterative update when the position information of the optimal population individual in the population information reaches a set iteration number, thereby completing the path planning of the mine robot.

[0148] The embodiment of the present disclosure also provides a path planning device / system of a mine robot, comprising: a processor; a memory configured to store processor-executable instructions; wherein the processor is configured to call the instructions stored in the memory to execute the path planning method of the mine robot.

[0149] The embodiment of the present disclosure also provides a path planning device / system of a mine robot, comprising: a computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions are executed by a processor to implement the path planning method of the mine robot.

[0150] The embodiment of the present disclosure also provides a path planning device / system of a mine robot, comprising: a computer program product comprising computer programs / instructions, wherein the computer programs / instructions are executed by a processor to implement the path planning method of the mine robot.

[0151] The embodiment of the present disclosure also provides a mine robot, comprising or applying the path planning method of the mine robot as described above; wherein the path planning method of the mine robot is integrated in a global path planner.

[0152] The embodiment of the present disclosure also provides a mine robot, comprising or applying: a global path planner configured to execute the path planning method of the mine robot as described above.

[0153] The embodiment of the present disclosure also provides a mine robot, comprising or applying the path planning system / device of the mine robot.

[0154] In some embodiments, the device provided by the embodiment of the present disclosure has functions or contains modules which can be used to execute the mine robot path planning method described in the above method embodiment, and the specific implementation can refer to the description of the mine robot path planning method embodiment above. For the sake of brevity, it will not be repeated here.

[0155] The embodiment of the present disclosure also provides a computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions are executed by a processor to implement the mine robot path planning method described above. The computer readable storage medium can be a non-volatile computer readable storage medium.

[0156] The embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to implement the mine robot path planning method described above. The electronic device can be provided as a terminal, a server or other forms of devices.

[0157] The embodiment of the present disclosure also provides a computer program product comprising computer programs / instructions, which, when executed by a processor, implement the mine robot path planning method described above.

[0158] In the embodiment of the present disclosure and its possible embodiments, the multi-strategy fusion improved sparrow search algorithm (MSSA) proposed in this paper is compared with the particle swarm algorithm (PSO), the sparrow search algorithm (SSA), the dung beetle algorithm (DBO) and the improved sparrow search algorithm: spiral adaptive step length chaotic sparrow search algorithm (CLSSA) through comparative experiments. Before the start of the comparative experiment, benchmark functions are introduced, and the advantages and disadvantages of the algorithm can be tested by the benchmark functions. In this paper, 14 benchmark functions are selected to compare and analyze the above algorithms, in order to highlight the superiority of the MSSA algorithm. The benchmark functions are shown in Table 1, which contains the type, expression, value range, minimum value (f min ) and dimension of the function, etc. Among them, F1-F6 are high-dimensional unimodal benchmark functions, which are used to test the development optimization convergence ability and convergence precision of the algorithm; F7-F 10 are high-dimensional multimodal benchmark functions, which exist multiple local extrema in the search space, and are usually used to evaluate the global search ability of the algorithm; F 11 -F 14 are fixed-dimension multimodal benchmark functions, which are used to evaluate the comprehensive development ability of the algorithm.

[0159] Table 1 Benchmark test function

[0160]

[0161]

[0162] In the embodiments of the present disclosure and its possible embodiments, the size N of all populations is set to 30, the maximum number of iterations T max is 1000. In the PSO algorithm, the inertia weight ω = 0.9-0.5(t / T max ), the learning factors c1 and c2 are both set to 1.5; in the DBO algorithm, the parameter b = 0.3, the deflection coefficient k = 0.1, and the parameter R = 1-t / T max ; in the SSA, CLSSA and MSSA algorithms, the safety value ST is set to 0.8, the number of discoverers PD is set to 0.2N, and the number of vigilantes SD is set to 0.2N; in the CLSSA algorithm, the probability parameter p = 0.5, and the parameter l = 2(1-t / T max )-1. Considering the effectiveness of the algorithm results, each experiment is run 30 times independently, and the performance of the algorithm is evaluated according to the average value (Mean) and the standard deviation (Std) calculated by the experiment. The experimental results will be analyzed in detail below.

[0163] 1. Unimodal benchmark function optimization analysis

[0164] (1) Convergence accuracy comparison: In the optimization test of high-dimensional unimodal benchmark functions, Table 2 shows the performance of the five algorithms, with the optimal result value in bold. The average fitness value of the MSSA algorithm on functions F1 to F4 reaches the optimal value, i.e., it achieves the global optimal solution, which is better than the other four algorithms. For functions F5 and F6, although all algorithms do not completely reach the optimal value, the convergence accuracy of the MSSA algorithm is significantly better than that of the other algorithms, especially in F5, which is improved by three orders of magnitude compared to the SSA algorithm, and in F6, which is improved by two orders of magnitude, showing the improvement of the MSSA algorithm in optimization accuracy.

[0165] (2) Stability analysis: According to the data in Table 2, the standard deviation Std of the MSSA algorithm on F1 to F4 is zero, showing excellent convergence stability. On F5 and F6, the accuracy of the MSSA algorithm reaches 10 -7 and 10 -5 , respectively, and the standard deviation Std is also better than that of the other algorithms, further proving its stability.

[0166] (3) Convergence speed evaluation: Figure 2 shows the convergence curve on the unimodal benchmark function according to the embodiments of the present disclosure, Figure 2It is shown that the convergence speed of the MSSA algorithm on F1 to F4 is obviously faster than other algorithms, and quickly approaches the optimal value, indicating that the MSSA algorithm has strong global search ability. On F5, although the PSO and DBO algorithms quickly converge, they fall into local optimum, while the MSSA, CLSSA and SSA algorithms can continuously improve the precision, and the precision of the MSSA is the highest. For F6, the MSSA algorithm not only quickly converges, but also effectively avoids local extreme value, further improving the convergence precision.

[0167] Table 2 Experimental results on unimodal benchmark functions

[0168]

[0169]

[0170] 2. Multi-peak benchmark function optimization analysis

[0171] (1) Convergence precision analysis: In the test of function F7, the DBO algorithm leads with the highest convergence precision, and the MSSA algorithm follows closely, and compared with the SSA and CLSSA algorithms, the MSSA shows obvious improvement in convergence precision. Further observation of function F8 shows that the MSSA, CLSSA and SSA algorithms all successfully converge to the optimal value, which is better than the PSO and DBO algorithms. In the test of functions F9 and F 10 , the average convergence precision of the MSSA, CLSSA, SSA and DBO algorithms is the same, which is higher than that of the PSO algorithm.

[0172] (2) Convergence stability analysis: In the test of function F7, the SSA algorithm shows the best convergence stability with the smallest standard deviation Std, but its convergence precision is not high. For function F8, the standard deviation Std of the MSSA, CLSSA and SSA algorithms is 0, which indicates that their convergence stability is better than that of the PSO and DBO algorithms. In the test of functions F 10 , the standard deviation of the PSO algorithm fails to reach 0, showing poor convergence stability, while the other four algorithms all show good convergence stability. Mean represents the mean value.

[0173] (3) Convergence speed analysis: Figure 3 show the convergence curves on multi-peak benchmark functions according to the embodiments of the present disclosure, Figure 3 show that the MSSA algorithm on functions F8 to F 10The MSSA algorithm has the fastest convergence speed, followed by the CLSSA algorithm. In contrast, the PSO algorithm is not only slow in convergence speed but also prone to getting trapped in local optima. In the test on function F7, although the MSSA algorithm is slightly slower than the CLSSA and SSA algorithms in the initial convergence speed, it continues to converge during the iteration process and eventually achieves a higher convergence accuracy than the CLSSA and SSA algorithms.

[0174] Table 3 Experimental results on the multimodal reference function

[0175]

[0176] 3. Fixed-dimensional multimodal function optimization analysis

[0177] (1) Convergence accuracy analysis: As shown in Table 4, in the function F 11 ~F 14 Among them, the MSSA algorithm's optimization result is closest to the theoretical value, and its average convergence accuracy is better than the other four algorithms. In the function F... 13 and F 14 In this study, the MSSA algorithm showed a significant improvement over the SSA algorithm.

[0178] (2) Convergence and stability analysis: For function F 11 F 13 and F 14 MSSA exhibits the best stability, with a standard deviation accuracy of 10. -6 10 -6 and 10 -5 Compared to the SSA algorithm, this method shows a significant improvement in stability. And for the function F... 12 The standard deviations of the five algorithms are not significantly different, all being on the same order of magnitude. However, MSSA has the smallest standard deviation and is more stable in convergence.

[0179] (3) Convergence rate analysis: Figure 4 The following diagram illustrates a convergence curve on a fixed-dimensional multimodal function according to an embodiment of the present disclosure: Figure 4 As shown, in function F 11 Among them, MSSA, CLSSA, and SSA algorithms converge faster, while PSO and DBO algorithms converge slightly slower. For F... 12 The five algorithms are not significantly different; all of them find the optimal value and converge quickly in the early stages of iteration. For the function F... 13 and F 14 MSSA, CLSSA, and DBO all showed relatively fast convergence speeds, but MSSA converged slightly faster than the other algorithms.

[0180] Table 4. Experimental results on fixed-dimensional multimodal functions.

[0181]

[0182] In summary, the MSSA algorithm proposed in this paper shows significant superiority in the test of unimodal, multimodal and fixed-dimension multimodal functions in multiple dimensions. Compared with PSO, DBO, SSA and CLSSA algorithms, MSSA is more excellent in solving performance. Specifically, in dealing with high-dimensional unimodal functions, MSSA algorithm shows the ability to quickly find the global optimal solution of F1 to F4 functions. In F5 and F6 functions, MSSA significantly improves the optimization accuracy, showing strong convergence performance. When facing high-dimensional multimodal functions, MSSA not only has faster convergence speed, but also in F7 function, thanks to the introduction of Levy flight strategy and dynamic Cauchy Gaussian disturbance, MSSA can effectively escape from local optimum, enhance the global search ability, and surpass SSA and CLSSA algorithms in convergence accuracy. In the solution of fixed-dimension multimodal functions, MSSA shows excellent optimization ability. Thanks to the assistance of multiple optimization strategies, the algorithm can quickly approach the global optimal solution in the early iteration, thereby improving the convergence speed and stability. Overall, MSSA algorithm performs well in global search and local development, and is superior to other algorithms compared in this paper in terms of convergence speed, accuracy and stability.

[0183] Simulation experiment: In order to verify the superiority of the algorithm (multi-strategy fusion improved sparrow algorithm MSSA) proposed in this paper in the mine simulation environment, the algorithm in this paper is compared with some mainstream algorithms (i.e. particle swarm optimization algorithm PSO, sparrow algorithm SSA, spiral self-adaptive step sparrow algorithm CLSSA). This paper uses grid map to build three different sizes of simulation environment, in which the size of grid map is set to 15x15, 20x20 and 25x25 respectively, the population number is uniformly set to 50, the iteration number is set to 200, and other parameters are consistent with the above. In order to ensure the fairness of the experimental results, each algorithm needs to run 20 independent experiments. The experimental results will be evaluated and compared according to the three indexes of the shortest path length, the average path length and the standard deviation of the path length.

[0184] Firstly, the path planning simulation experiment is carried out in the 15x15 grid map, and the simulation diagrams of the four algorithms are as shown in Figure 5 Figure 5 The shortest path of four algorithms in 15x15 grid map according to the embodiments of the present disclosure is shown in Figure 5 ​As can be seen, on a map with a starting point of (0.5, 0.5) and an ending point of (14.5, 14.5), all algorithms planned a path to avoid obstacles. Due to the relatively small map size, all algorithms performed well. The simulation results of each algorithm are shown in Table 5. Among them, the shortest path length obtained by the PSO algorithm is 22.728, which is inferior to the 21.556 of the MSSA, CLSSA, and SSA algorithms. For the average path length, the MSSA algorithm performed the best, reaching 22.437, which is 8.81%, 2.96%, and 1.82% shorter than the PSO, SSA, and CLSSA algorithms, respectively. Moreover, the standard deviation of MSSA is smaller than that of other algorithms, indicating that this algorithm has good search ability and stability.

[0185] Table 5. Experimental Results of Path Planning on 15×15 Raster Map

[0186]

[0187]

[0188] Figure 6 The convergence curves of four algorithms in a 15×15 raster map according to embodiments of this disclosure are shown. Figure 6 The convergence curves show that the MSSA and CLSSA algorithms have similar convergence speeds, but MSSA is slightly faster. Both MSSA and CLSSA convergence speeds are significantly faster than PSO and SSA. Therefore, based on a comprehensive comparison, the MSSA algorithm proposed in this paper performs better on 15×15 raster maps.

[0189] To further test the performance of the algorithms, the four algorithms were simulated on a 20×20 raster map. The simulation results are as follows. Figure 7 As shown in Table 6. Figure 7 The table shows the shortest paths found by four algorithms in a 20×20 raster map according to embodiments of the present disclosure. Simulation results for the 20×20 raster map, as shown in Table 6, indicate that the MSSA algorithm finds an optimal path length of 29.799, outperforming the other three algorithms, followed by the CLSSA algorithm, while the PSO algorithm performs the worst. Regarding average path length, the MSSA algorithm finds an average path length of 31.087, which is 12.69%, 5.59%, and 3.28% shorter than the PSO, SSA, and CLSSA algorithms, respectively. In terms of path search stability, the MSSA algorithm has a standard deviation of 1.217, making it more stable than the other algorithms.

[0190] Figure 8 The diagram shows convergence curves for four algorithms in a 20×20 raster map according to embodiments of the present disclosure. Figure 8As shown by the convergence curves, the MSSA algorithm converges faster than the other three algorithms and can escape local optima, further improving convergence accuracy and thus finding a shorter path. The simulation results indicate that in a 20×20 raster map, the MSSA algorithm outperforms the other three algorithms in overall performance.

[0191] Table 6. Experimental Results of Path Planning on 20×20 Raster Map

[0192]

[0193] Figure 9 The diagram illustrates the shortest path algorithms for a 25×25 grid map according to embodiments of this disclosure. For example... Figure 9 As shown, in a 25×25 raster map, the number of environmental graticules increases, and the environment becomes more complex. Although all four algorithms can obtain a path from the starting point (0.5, 0.5) to the target point (24.5, 24.5), their performance varies. The MSSA algorithm finds the shortest path length at 38.042, significantly better than the shortest paths of PSO (43.556), SSA (41.456), and CLSSA (40.385). Furthermore, the MSSA algorithm has the shortest average path length, improving upon PSO, SSA, and CLSSA by 14.49%, 9.12%, and 5.24%, respectively. Regarding algorithm stability, the MSSA algorithm has the smallest standard deviation, followed by the CLSSA algorithm, demonstrating greater stability in path finding compared to the other two algorithms.

[0194] Table 7. Experimental Results of Path Planning on 25×25 Raster Map

[0195]

[0196] Figure 10 The convergence curves of four algorithms in a 25×25 raster map according to embodiments of the present disclosure are shown. From Figure 10 As can be seen from the convergence curves, the CLSSA algorithm converges slightly faster, achieving rapid convergence in the early stages of iteration, but it gets trapped in local optima. While the MSSA algorithm converges slightly slower than the CLSSA algorithm in the early stages of iteration, it can escape local optima and further shorten the path length by introducing various optimization strategies.

[0197] From the above experimental analysis, it can be seen that the SSA algorithm has the shortcomings of insufficient global search ability, easy to fall into local optimum and slow convergence speed in solving path planning problems. In the MSSA algorithm proposed in this paper, the improvement of the discoverer formula balances the global and local search ability of the discoverer sparrow, and the introduction of Levy flight random step and dynamic Cauchy-Gaussian variation disturbance can make the sparrow in the search space avoid falling into local extreme value, so the improved MSSA algorithm proposed in this paper can have excellent performance in path planning problems. When the environment becomes complex, the MSSA algorithm can still plan a shorter path, and has better convergence speed and stability. In summary, the MSSA algorithm proposed in this paper has outstanding search ability in path planning, compared with other algorithms, the MSSA algorithm plans a shorter path, has faster convergence speed and better stability, and has obvious advantages.

[0198] Figure 11 A specific implementation flow according to an embodiment of the present disclosure is shown. As shown in Figure 11 the specific implementation in this paper is based on the ROS robot operating system, and the robot autonomous navigation is realized through the Navigation (navigation function) function package in the system. The robot autonomous navigation in the ROS system software mainly relies on the Navigation function package, and the functions in this function include mapping, positioning and path planning. In the overall framework corresponding to the specific implementation flow of the embodiment of the present disclosure, the move_base node plays a core role in the navigation function package. It is mainly responsible for coordinating the work of the global path planner (global_planner) and the local path planner (local_planner). The move_base node receives the navigation target position from the client, and transmits the position information to the global path planner. At the same time, it also depends on the map data provided by the map_server node, which is used to generate the global cost map (global_costmap). The move_base node updates the global cost map and the local cost map by subscribing to sensor data to reflect the latest state of the environment. In addition, the move_base node also subscribes to the tf tree constructed by the AMCL (adaptive Monte Carlo localization algorithm), the tf transformation broadcaster and the odometry information. This tf tree provides real-time transformation information between different reference systems in the robot system. Finally, the local path planner calculates the speed command of the robot according to these information, and controls the movement of the robot by publishing to the cmd_vel topic. These speed commands are received by the base_controller node subscribing to the cmd_vel topic, and then control the motor of the robot to realize the navigation function.

[0199] In the specific implementation, the MASS algorithm proposed in the present application is burned to the simulated mine platform for testing and inspection. The target position is specified by using the 2D Nav Goal (a self-defined navigation function) function in the Rviz tool. After receiving the target position information, the robot performs global path planning and generates a global path information from the starting point to the end point.

[0200] Figure 12 The MSSA algorithm path planning result in the simulated mine environment according to the embodiment of the present application is shown. As shown in Figure 12 , based on the ROS platform, the MSSA algorithm is imported into the mine robot, and the global path generated in the mine simulation map environment is as shown in Figure 12 , the global path generated by the MSSA algorithm has no excessive bending and can maintain a relatively regular straight line except for the turning, and the path quality is high.

[0201] Figure 13 is a block diagram of an electronic device 800 according to an exemplary embodiment. The electronic device 800 can be, for example, a terminal such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0202] Referring to Figure 13 , the electronic device 800 can include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0203] The processing component 802 usually controls the overall operation of the electronic device 800, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 802 can include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. In addition, the processing component 802 can include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0204] The memory 804 is configured to store various types of data to support the operation of the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or nonvolatile memory, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disc, or optical disc.

[0205] The power supply component 806 supplies power for various components of the electronic device 800. The power supply component 806 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0206] The multimedia component 808 includes a screen providing an output interface between the electronic device 800 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action. In some embodiments, the multimedia component 808 includes a front camera and / or a back camera. The front camera and / or the back camera can receive external multimedia data when the electronic device 800 is in an operation mode, such as a photographing mode or a video mode. Each of the front camera and the back camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0207] The audio component 810 is configured to output and / or input an audio signal. For example, the audio component 810 includes a microphone (MIC) configured to receive an external audio signal when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting an audio signal.

[0208] The I / O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which can be a keypad, a click wheel, buttons, etc. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0209] The sensor component 814 includes one or more sensors for providing status assessments for various aspects of the electronic device 800. For example, the sensor component 814 can detect an open / closed position of the electronic device 800, relative positioning of components, such as a display and a keypad of the electronic device 800, a change in position of the electronic device 800 or a component of the electronic device 800, presence or absence of user contact with the electronic device 800, orientation or acceleration / deceleration / g-force and temperature of the electronic device 800. The sensor component 814 can include an optical sensor for detecting ambient light, a proximity sensor for detecting the presence of nearby objects without any physical touch, a CMOS or CCD image sensor for use in imaging applications, or an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor in some embodiments.

[0210] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a corresponding communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an example embodiment, the communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0211] In an example embodiment, the electronic device 800 can be implemented using one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements to perform the above-described methods.

[0212] In an example embodiment, a non-transitory computer-readable storage medium, such as the memory 804 including computer program instructions, is also provided, which can be executed by the processor 820 of the electronic device 800 to perform the above-described methods.

[0213] Figure 14 FIG. 19 is a block diagram of an electronic device 1900 according to an example embodiment. For example, the electronic device 1900 can be provided as a server. Referring to FIG. 19, the electronic device 1900 includes a bus 1901, a processor 1902, a memory 1903, a storage 1904, an input / output (I / O) interface 1905, a display 1906, and a communication interface 1907. Figure 14The electronic device 1900 includes a processing component 1922, which is further composed of one or more processors, and a memory resource represented by the memory 1932 for storing instructions, such as application programs, executable by the processing component 1922. The application programs stored in the memory 1932 can include one or more than one module each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above method.

[0214] The electronic device 1900 can further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0215] In exemplary embodiments, a non-transitory computer readable storage medium, such as the memory 1932 including computer program instructions, is also provided, which can be executed by the processing component 1922 of the electronic device 1900 to complete the above method.

[0216] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0217] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or punched tape, a magneto-optical or other optical medium, and / or any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0218] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0219] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, for example, through the Internet using an Internet Service Provider. In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0220] The computer readable program instructions can also be loaded onto a computing / processing device, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computing / processing device, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computing / processing device, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0221] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data storage cycles that change state. The instructions can be executed by one or more processors of a computer, to cause a series of operational steps to be performed on the computer to produce a computer-implemented process. The instructions can also cause one or more processors of a computer or other programmable data processing apparatus to

[0222] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0223] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0224] Embodiments of the present disclosure have been described above, and the description is intended to be illustrative of the embodiments and not restrictive of the disclosure. Many modifications and variations of the described embodiments are possible in light of this disclosure without departing from the scope and spirit of the described embodiments. The choice of words in this document is intended to best explain the principles of the embodiments, the practical application, or technical improvements over the existing technology, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method of path planning for a mine robot, characterized in that, include: Obtain the multidimensional search space within the mine and the population information of the path from the initial spatial position information of the mine robot to the target position information within the multidimensional search space; The location information corresponding to the discoverer, follower, and vigilant individuals in the population information is iteratively updated. Specifically, the location information corresponding to the discoverer whose random warning value is less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Specifically, the location information corresponding to the vigilant individuals in the population information is iteratively updated using the random step size generated by Levy's flight, the location information corresponding to the best and worst population individuals in the population information. When the number of iterations corresponding to the position information of the optimal individual in the population information reaches the set number of iterations, the iteration update stops, and the path planning of the mining robot is completed.

2. The path planning method for the mining robot according to claim 1, characterized in that, The step of iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors includes: Obtain the current iteration count and the first maximum iteration count during the iterative update process; Calculate the ratio between the current iteration number and the first maximum iteration number in the iterative update process, respectively; The corresponding dynamic weight factors are determined based on the ratios during the iterative update process; The corresponding dynamic weight factor is multiplied by its corresponding normally distributed random number to obtain the corresponding update coefficient; The location information of discoverers whose random warning values ​​are less than the set safety value in the population information is iteratively updated using the update coefficient.

3. The path planning method for the mining robot according to claim 2, characterized in that, The determination of the corresponding dynamic weight factors based on the ratios during the iterative update process includes: Calculate the difference between 1 and the corresponding ratio; The dynamic weighting factor is obtained by squaring the difference between 1 and the corresponding ratio.

4. The path planning method for a mining robot according to any one of claims 2 or 3, characterized in that, The step of iteratively updating the location information corresponding to discoverers whose random warning values ​​are less than a set safety value in the population information using the update coefficient includes: The location information of the discoverer whose random warning value is less than the set safety value is multiplied by the corresponding update coefficient to obtain the location information corresponding to the update coefficient. The location information corresponding to the update coefficient is added to the location information corresponding to the discoverer whose random warning value is less than the set safety value to obtain the iteratively updated location information corresponding to the discoverer whose random warning value is less than the set safety value.

5. The path planning method for a mining robot according to any one of claims 1-3, characterized in that, The iterative update of the position information corresponding to the vigilant individuals in the population information using the random step size generated by Levy's flight, the position information corresponding to the best and worst individuals in the population information, includes: If the fitness value of the vigilant individual in the current iteration is greater than the optimal fitness, then calculate the first absolute difference matrix corresponding to the difference matrix between the location information of the vigilant individual in the current iteration and the optimal fitness; after multiplying the first absolute difference matrix by the random step size generated by the Levi flight, add the location information corresponding to the optimal population individual in the current iteration to obtain the updated location information of the vigilant individual. If the fitness value of the vigilant at the current iteration number is equal to the optimal fitness, then calculate the second absolute difference matrix corresponding to the difference matrix between the optimal fitness and the worst fitness at the current iteration number; after multiplying the second absolute difference matrix by the random step size generated by the Levi flight, add the position information corresponding to the vigilant at the current iteration number to obtain the iteratively updated position information corresponding to the vigilant. After obtaining the iteratively updated position information corresponding to the vigilant individuals, the fitness values ​​corresponding to the position information of the best and worst individuals in the population are updated using the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information. The optimal fitness and worst fitness corresponding to the previous iteration number are determined based on the updated fitness values.

6. The path planning method for a mining robot according to claim 4, characterized in that, The iterative update of the position information corresponding to the vigilant individuals in the population information using the random step size generated by Levy's flight, the position information corresponding to the best and worst individuals in the population information, includes: If the fitness value of the vigilant individual in the current iteration is greater than the optimal fitness, then calculate the first absolute difference matrix corresponding to the difference matrix between the location information of the vigilant individual in the current iteration and the optimal fitness; after multiplying the first absolute difference matrix by the random step size generated by the Levi flight, add the location information corresponding to the optimal population individual in the current iteration to obtain the updated location information of the vigilant individual. If the fitness value of the vigilant at the current iteration number is equal to the optimal fitness, then calculate the second absolute difference matrix corresponding to the difference matrix between the optimal fitness and the worst fitness at the current iteration number; after multiplying the second absolute difference matrix by the random step size generated by the Levi flight, add the position information corresponding to the vigilant at the current iteration number to obtain the iteratively updated position information corresponding to the vigilant. After obtaining the iteratively updated position information corresponding to the vigilant individuals, the fitness values ​​corresponding to the position information of the best and worst individuals in the population are updated using the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information. The optimal fitness and worst fitness corresponding to the previous iteration number are determined based on the updated fitness values.

7. The path planning method for a mining robot according to claim 5, characterized in that, During the iterative update process, the fitness values ​​corresponding to the position information of the best and worst individuals in the population are updated in real time using the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information. This includes: During the iterative update process, the location information corresponding to the best population individual and the worst population individual are updated in real time using the iteratively updated location information of the discoverer, follower and vigilant in the population information. The population information matrix is ​​updated using the iteratively updated position information corresponding to the discoverers, followers, and vigilant individuals in the population information; the updated fitness value corresponding to the position information of each individual in the updated population information matrix is ​​calculated according to the fitness function.

8. The path planning method for a mining robot according to claim 6, characterized in that, During the iterative update process, the fitness values ​​corresponding to the position information of the best and worst individuals in the population are updated in real time using the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information. This includes: During the iterative update process, the location information corresponding to the best population individual and the worst population individual are updated in real time using the iteratively updated location information of the discoverer, follower and vigilant in the population information. The population information matrix is ​​updated using the iteratively updated position information corresponding to the discoverers, followers, and vigilant individuals in the population information; the updated fitness value corresponding to the position information of each individual in the updated population information matrix is ​​calculated according to the fitness function.

9. The path planning method for a mining robot according to any one of claims 1-3 and 6-8, characterized in that, Determining the random step size generated by the Levi flight includes: Obtain the step size parameters corresponding to Levi's flight, the first and second random numbers that conform to a normal distribution, and the set parameters that are less than 1; Based on the step size parameter corresponding to the Levi flight, the first random number and the second random number that conform to the normal distribution, and the set parameter less than 1, the random step size generated by the Levi flight is determined.

10. The path planning method for a mining robot according to claim 4, characterized in that, Determining the random step size generated by the Levi flight includes: Obtain the step size parameters corresponding to Levi's flight, the first and second random numbers that conform to a normal distribution, and the set parameters that are less than 1; Based on the step size parameter corresponding to the Levi flight, the first random number and the second random number that conform to the normal distribution, and the set parameter less than 1, the random step size generated by the Levi flight is determined.

11. The path planning method for a mining robot according to claim 5, characterized in that, Determining the random step size generated by the Levi flight includes: Obtain the step size parameters corresponding to Levi's flight, the first and second random numbers that conform to a normal distribution, and the set parameters that are less than 1; Based on the step size parameter corresponding to the Levi flight, the first random number and the second random number that conform to the normal distribution, and the set parameter less than 1, the random step size generated by the Levi flight is determined.

12. The path planning method for a mining robot according to claim 9, characterized in that, The determination of the random step size generated by the Levy flight based on the step size parameter corresponding to the Levy flight, the first random number and the second random number conforming to a normal distribution, and the set parameter less than 1 includes: The reciprocal of the step size parameter corresponding to the Levi flight is obtained; The random step size generated by the Levi flight is obtained by dividing the first random number by the reciprocal of the step size parameter corresponding to the second random number and multiplying it by the set parameter which is less than 1.

13. The path planning method for a mining robot according to any one of claims 10 or 11, characterized in that, The determination of the random step size generated by the Levy flight based on the step size parameter corresponding to the Levy flight, the first random number and the second random number conforming to a normal distribution, and the set parameter less than 1 includes: The reciprocal of the step size parameter corresponding to the Levi flight is obtained; The random step size generated by the Levi flight is obtained by dividing the first random number by the reciprocal of the step size parameter corresponding to the second random number and multiplying it by the set parameter which is less than 1.

14. The path planning method for a mining robot according to any one of claims 1-3, 6-8, and 10-12, characterized in that, Iterative updates are performed on the position information corresponding to followers in the population information, including: Determine the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information; Based on the population information matrix, determine the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information, and iteratively update the position information corresponding to the followers in the population information.

15. The path planning method for a mining robot according to claim 4, characterized in that, Iterative updates are performed on the position information corresponding to followers in the population information, including: Determine the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information; Based on the population information matrix, determine the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information, and iteratively update the position information corresponding to the followers in the population information.

16. The path planning method for a mining robot according to claim 5, characterized in that, Iterative updates are performed on the position information corresponding to followers in the population information, including: Determine the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information; Based on the population information matrix, determine the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information, and iteratively update the position information corresponding to the followers in the population information.

17. The path planning method for a mining robot according to claim 9, characterized in that, Iterative updates are performed on the position information corresponding to followers in the population information, including: Determine the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information; Based on the population information matrix, determine the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information, and iteratively update the position information corresponding to the followers in the population information.

18. The path planning method for a mining robot according to claim 13, characterized in that, Iterative updates are performed on the position information corresponding to followers in the population information, including: Determine the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information; Based on the population information matrix, determine the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information, and iteratively update the position information corresponding to the followers in the population information.

19. The path planning method for a mining robot according to claim 14, characterized in that, Determining the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information includes: Calculate the fitness value of the discoverer in the population information matrix according to the fitness function after iteratively updated position information; Based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix, determine the position information corresponding to the optimal population individual of the discoverer in the population information. Based on the fitness function, calculate the fitness values ​​corresponding to the iteratively updated position information of the discoverer, follower, and vigilant in the population information matrix; Based on the fitness values ​​corresponding to the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information matrix, the position information of the worst-performing individual in the population information is determined.

20. The path planning method for a mining robot according to any one of claims 15-19, characterized in that, Determining the location information corresponding to the best individual in the population information and the location information corresponding to the worst individual in the population information includes: Calculate the fitness value of the discoverer in the population information matrix according to the fitness function after iteratively updated position information; Based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix, determine the position information corresponding to the optimal population individual of the discoverer in the population information. Based on the fitness function, calculate the fitness values ​​corresponding to the iteratively updated position information of the discoverer, follower, and vigilant in the population information matrix; Based on the fitness values ​​corresponding to the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information matrix, the position information of the worst-performing individual in the population information is determined.

21. The path planning method for a mining robot according to claim 19, characterized in that, The step of determining the position information corresponding to the optimal individual in the population information of the discoverer based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix includes: The fitness values ​​corresponding to the iteratively updated position information of the discoverers in the population information matrix are sorted from smallest to largest to obtain the sorted fitness values. The location information corresponding to the first individual in the population with the sorted fitness value is configured as the location information corresponding to the optimal individual in the population information of the discoverer.

22. The path planning method for a mining robot according to claim 20, characterized in that, The step of determining the position information corresponding to the optimal individual in the population information of the discoverer based on the fitness value corresponding to the iteratively updated position information of the discoverer in the population information matrix includes: The fitness values ​​corresponding to the iteratively updated position information of the discoverers in the population information matrix are sorted from smallest to largest to obtain the sorted fitness values. The location information corresponding to the first individual in the population with the sorted fitness value is configured as the location information corresponding to the optimal individual in the population information of the discoverer.

23. The path planning method for a mining robot according to any one of claims 19, 21, and 22, characterized in that, The step of determining the position information of the worst-performing individual in the population information based on the fitness values ​​corresponding to the iteratively updated position information of discoverers, followers, and vigilant individuals in the population information matrix includes: The fitness values ​​corresponding to the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information matrix are sorted from smallest to largest to obtain the sorted fitness values. The position information corresponding to the last individual in the population after sorting the fitness values ​​is configured as the position information corresponding to the worst individual in the population information.

24. The path planning method for a mining robot according to claim 20, characterized in that, The step of determining the position information of the worst-performing individual in the population information based on the fitness values ​​corresponding to the iteratively updated position information of discoverers, followers, and vigilant individuals in the population information matrix includes: The fitness values ​​corresponding to the iteratively updated position information of the discoverers, followers, and vigilant individuals in the population information matrix are sorted from smallest to largest to obtain the sorted fitness values. The position information corresponding to the last individual in the population after sorting the fitness values ​​is configured as the position information corresponding to the worst individual in the population information.

25. The path planning method for a mining robot according to claim 14, characterized in that, The step of determining the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information based on the population information matrix, and iteratively updating the position information corresponding to the followers in the population information, includes: During the iterative update process, the location information corresponding to the best individual in the population of the discoverer is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information, and the location information corresponding to the worst individual in the population information is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information. For followers exceeding a set number, iterative updates are performed using the location information corresponding to the worst-performing individual in the population. Followers whose numbers are less than or equal to the set number are iteratively updated using the position information of the best individual in the population among the discoverers; wherein, the set number is less than the number of individuals in the population information matrix.

26. The path planning method for a mining robot according to any one of claims 15-19, 21, 22, and 24, characterized in that, The step of determining the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information based on the population information matrix, and iteratively updating the position information corresponding to the followers in the population information, includes: During the iterative update process, the location information corresponding to the best individual in the population of the discoverer is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information, and the location information corresponding to the worst individual in the population information is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information. For followers exceeding a set number, iterative updates are performed using the location information corresponding to the worst-performing individual in the population. Followers whose numbers are less than or equal to the set number are iteratively updated using the position information of the best individual in the population among the discoverers; wherein, the set number is less than the number of individuals in the population information matrix.

27. The path planning method for a mining robot according to claim 20, characterized in that, The step of determining the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information based on the population information matrix, and iteratively updating the position information corresponding to the followers in the population information, includes: During the iterative update process, the location information corresponding to the best individual in the population of the discoverer is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information, and the location information corresponding to the worst individual in the population information is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information. For followers exceeding a set number, iterative updates are performed using the location information corresponding to the worst-performing individual in the population. Followers whose numbers are less than or equal to the set number are iteratively updated using the position information of the best individual in the population among the discoverers; wherein, the set number is less than the number of individuals in the population information matrix.

28. The path planning method for a mining robot according to claim 23, characterized in that, The step of determining the position information corresponding to the best individual in the population information and the position information corresponding to the worst individual in the population information based on the population information matrix, and iteratively updating the position information corresponding to the followers in the population information, includes: During the iterative update process, the location information corresponding to the best individual in the population of the discoverer is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information, and the location information corresponding to the worst individual in the population information is updated in real time using the iteratively updated location information of the discoverer, followers and vigilant individuals in the population information. For followers exceeding a set number, iterative updates are performed using the location information corresponding to the worst-performing individual in the population. Followers whose numbers are less than or equal to the set number are iteratively updated using the position information of the best individual in the population among the discoverers; wherein, the set number is less than the number of individuals in the population information matrix.

29. The path planning method for a mining robot according to any one of claims 25, 27, and 28, characterized in that, The step of updating the location information of the optimal individual in the population corresponding to the discoverer in real time using the iteratively updated location information of the discoverer in the population information includes: The update fitness values ​​corresponding to the iteratively updated position information of the discoverers in the population information matrix are sorted from smallest to largest to obtain the sorted update fitness values. The position information of the first discoverer corresponding to the sorted updated fitness value is configured as the updated position information of the optimal population individual of the discoverer in the population information.

30. The path planning method for a mining robot according to claim 26, characterized in that, The step of updating the location information of the optimal individual in the population corresponding to the discoverer in real time using the iteratively updated location information of the discoverer in the population information includes: The update fitness values ​​corresponding to the iteratively updated position information of the discoverers in the population information matrix are sorted from smallest to largest to obtain the sorted update fitness values. The position information of the first discoverer corresponding to the sorted updated fitness value is configured as the updated position information of the optimal population individual of the discoverer in the population information.

31. The path planning method for a mining robot according to any one of claims 25, 27, 28, and 30, characterized in that, The step of updating the position information of the worst-performing individual in the population information in real time using the iteratively updated position information corresponding to discoverers, followers, and vigilant individuals in the population information includes: The update fitness values ​​corresponding to the iteratively updated position information of the discoverer, follower, and vigilant in the population information matrix are sorted from smallest to largest to obtain the sorted update fitness values. The updated position information of the last individual in the population corresponding to the sorted updated fitness value is configured as the updated position information of the worst individual in the population information.

32. The path planning method for a mining robot according to claim 26, characterized in that, The step of updating the position information of the worst-performing individual in the population information in real time using the iteratively updated position information corresponding to discoverers, followers, and vigilant individuals in the population information includes: The update fitness values ​​corresponding to the iteratively updated position information of the discoverer, follower, and vigilant in the population information matrix are sorted from smallest to largest to obtain the sorted update fitness values. The updated position information of the last individual in the population corresponding to the sorted updated fitness value is configured as the updated position information of the worst individual in the population information.

33. The path planning method for a mining robot according to claim 29, characterized in that, The step of updating the position information of the worst-performing individual in the population information in real time using the iteratively updated position information corresponding to discoverers, followers, and vigilant individuals in the population information includes: The update fitness values ​​corresponding to the iteratively updated position information of the discoverer, follower, and vigilant in the population information matrix are sorted from smallest to largest to obtain the sorted update fitness values. The updated position information of the last individual in the population corresponding to the sorted updated fitness value is configured as the updated position information of the worst individual in the population information.

34. The path planning method for a mining robot according to any one of claims 7 or 8, characterized in that, The real-time updating of the location information corresponding to the best and worst population individuals using the iteratively updated location information corresponding to discoverers, followers, and vigilant individuals in the population information includes: The population information matrix is ​​updated using the iteratively updated position information corresponding to the discoverers, followers, and vigilant individuals in the population information. Based on the fitness function, calculate the updated fitness value corresponding to the position information of each individual in the updated population information matrix; Based on the updated fitness value corresponding to the position information of each individual in the population information matrix, the updated position information corresponding to the best individual and the updated position information corresponding to the worst individual are determined.

35. The path planning method for a mining robot according to any one of claims 25, 27, 28, 30, 32, and 33, characterized in that, The number of followers exceeding a set number is iteratively updated using the position information corresponding to the worst-performing individual in the population, including: Calculate the difference matrix between the position information of the worst individual in the current iteration and the position information of the follower in the current iteration; The difference matrix between the position information corresponding to the worst individual in the population and the position information corresponding to the follower at the current iteration number is divided by the square of the position of the follower at the current iteration number, and then an exponential operation is performed to obtain the exponential position information. The index position information is multiplied by a random number that follows a normal distribution to obtain the iteratively updated position information corresponding to a number of followers that is greater than a first set number.

36. The path planning method for a mining robot according to claim 26, characterized in that, The number of followers exceeding a set number is iteratively updated using the position information corresponding to the worst-performing individual in the population, including: Calculate the difference matrix between the position information of the worst individual in the current iteration and the position information of the follower in the current iteration; The difference matrix between the position information corresponding to the worst individual in the population and the position information corresponding to the follower at the current iteration number is divided by the square of the position of the follower at the current iteration number, and then an exponential operation is performed to obtain the exponential position information. The index position information is multiplied by a random number that follows a normal distribution to obtain the iteratively updated position information corresponding to a number of followers that is greater than a first set number.

37. The path planning method for a mining robot according to claim 29, characterized in that, The number of followers exceeding a set number is iteratively updated using the position information corresponding to the worst-performing individual in the population, including: Calculate the difference matrix between the position information of the worst individual in the current iteration and the position information of the follower in the current iteration; The difference matrix between the position information corresponding to the worst individual in the population and the position information corresponding to the follower at the current iteration number is divided by the square of the position of the follower at the current iteration number, and then an exponential operation is performed to obtain the exponential position information. The index position information is multiplied by a random number that follows a normal distribution to obtain the iteratively updated position information corresponding to a number of followers that is greater than a first set number.

38. The path planning method for a mining robot according to claim 31, characterized in that, The number of followers exceeding a set number is iteratively updated using the position information corresponding to the worst-performing individual in the population, including: Calculate the difference matrix between the position information of the worst individual in the current iteration and the position information of the follower in the current iteration; The difference matrix between the position information corresponding to the worst individual in the population and the position information corresponding to the follower at the current iteration number is divided by the square of the position of the follower at the current iteration number, and then an exponential operation is performed to obtain the exponential position information. The index position information is multiplied by a random number that follows a normal distribution to obtain the iteratively updated position information corresponding to a number of followers that is greater than a first set number.

39. The path planning method for a mining robot according to any one of claims 25, 27, 28, 30, 32, 33, and 36-38, characterized in that, The followers corresponding to the number less than or equal to the set number are iteratively updated using the position information of the optimal individual in the population among the discoverers, including: Calculate the absolute value matrix of the difference matrix between the position information of the best individual in the discoverer at the current iteration number and the position information of the follower at the current iteration number; Calculate the product of the given matrix and the transpose of the given matrix, calculate the inverse of the product of the given matrix and the transpose of the given matrix, and calculate the product of the transpose and the inverse. After multiplying the absolute value matrix by the transpose matrix, the all-ones matrix, and the inverse matrix, the position information of the best individual in the current iteration is added to obtain the iteratively updated position information of the followers corresponding to the set number of followers.

40. The path planning method for a mining robot according to claim 26, characterized in that, The followers corresponding to the number less than or equal to the set number are iteratively updated using the position information of the optimal individual in the population among the discoverers, including: Calculate the absolute value matrix of the difference matrix between the position information of the best individual in the discoverer at the current iteration number and the position information of the follower at the current iteration number; Calculate the product of the given matrix and the transpose of the given matrix, calculate the inverse of the product of the given matrix and the transpose of the given matrix, and calculate the product of the transpose and the inverse. After multiplying the absolute value matrix by the transpose matrix, the all-ones matrix, and the inverse matrix, the position information of the best individual in the current iteration is added to obtain the iteratively updated position information of the followers corresponding to the set number of followers.

41. The path planning method for a mining robot according to claim 29, characterized in that, The followers corresponding to the number less than or equal to the set number are iteratively updated using the position information of the optimal individual in the population among the discoverers, including: Calculate the absolute value matrix of the difference matrix between the position information of the best individual in the discoverer at the current iteration number and the position information of the follower at the current iteration number; Calculate the product of the given matrix and the transpose of the given matrix, calculate the inverse of the product of the given matrix and the transpose of the given matrix, and calculate the product of the transpose and the inverse. After multiplying the absolute value matrix by the transpose matrix, the all-ones matrix, and the inverse matrix, the position information of the best individual in the current iteration is added to obtain the iteratively updated position information of the followers corresponding to the set number of followers.

42. The path planning method for a mining robot according to claim 31, characterized in that, The followers corresponding to the number less than or equal to the set number are iteratively updated using the position information of the optimal individual in the population among the discoverers, including: Calculate the absolute value matrix of the difference matrix between the position information of the best individual in the discoverer at the current iteration number and the position information of the follower at the current iteration number; Calculate the product of the given matrix and the transpose of the given matrix, calculate the inverse of the product of the given matrix and the transpose of the given matrix, and calculate the product of the transpose and the inverse. After multiplying the absolute value matrix by the transpose matrix, the all-ones matrix, and the inverse matrix, the position information of the best individual in the current iteration is added to obtain the iteratively updated position information of the followers corresponding to the set number of followers.

43. The path planning method for a mining robot according to claim 35, characterized in that, The followers corresponding to the number less than or equal to the set number are iteratively updated using the position information of the optimal individual in the population among the discoverers, including: Calculate the absolute value matrix of the difference matrix between the position information of the best individual in the discoverer at the current iteration number and the position information of the follower at the current iteration number; Calculate the product of the given matrix and the transpose of the given matrix, calculate the inverse of the product of the given matrix and the transpose of the given matrix, and calculate the product of the transpose and the inverse. After multiplying the absolute value matrix by the transpose matrix, the all-ones matrix, and the inverse matrix, the position information of the best individual in the current iteration is added to obtain the iteratively updated position information of the followers corresponding to the set number of followers.

44. The path planning method for a mining robot according to claim 39, characterized in that, The set number is configured as the average number of individuals in the population information matrix.

45. The path planning method for a mining robot according to any one of claims 40-43, characterized in that, The set number is configured as the average number of individuals in the population information matrix.

46. ​​The path planning method for a mining robot according to any one of claims 1-3, 6-8, 10-12, 15-19, 21, 22, 24, 25, 27, 28, 30, 32, 33, 36-38, 40-44, is characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

47. The path planning method for a mining robot according to claim 4, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

48. The path planning method for a mining robot according to claim 5, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

49. The path planning method for a mining robot according to claim 9, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

50. The path planning method for a mining robot according to claim 13, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

51. The path planning method for a mining robot according to claim 14, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

52. The path planning method for a mining robot according to claim 20, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

53. The path planning method for a mining robot according to claim 23, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

54. The path planning method for a mining robot according to claim 26, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

55. The path planning method for a mining robot according to claim 29, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

56. The path planning method for a mining robot according to claim 31, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

57. The path planning method for a mining robot according to claim 34, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

58. The path planning method for a mining robot according to claim 35, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

59. The path planning method for a mining robot according to claim 39, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

60. The path planning method for a mining robot according to claim 45, characterized in that, Before iteratively updating the location information of discoverers whose random warning values ​​are less than a set safety value in the population information using normally distributed random numbers and their corresponding dynamic weighting factors, the process includes: Assign a corresponding random warning value to the discoverer; The location information of discoverers whose random warning values ​​are less than a set safety value in the population information is iteratively updated using normally distributed random numbers and their corresponding dynamic weighting factors. Using random numbers that follow a normal distribution and a set matrix of all ones, the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated.

61. The path planning method for a mining robot according to claim 46, characterized in that, The step of iteratively updating the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information using normally distributed random numbers and a set all-one matrix includes: The update matrix is ​​obtained by multiplying the normally distributed random number by the set all-one matrix; The location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated using the update matrix.

62. The path planning method for a mining robot according to any one of claims 47-60, characterized in that, The step of iteratively updating the location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information using normally distributed random numbers and a set all-one matrix includes: The update matrix is ​​obtained by multiplying the normally distributed random number by the set all-one matrix; The location information of discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information is iteratively updated using the update matrix.

63. The path planning method for a mining robot according to claim 61, characterized in that, The step of iteratively updating the location information corresponding to discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information using the update matrix includes: The update matrix is ​​added to the location information of the discoverers whose random warning values ​​are greater than or equal to the set safety value from the population information to obtain the iteratively updated location information of the discoverers whose random warning values ​​are greater than or equal to the set safety value.

64. The path planning method for a mining robot according to claim 62, characterized in that, The step of iteratively updating the location information corresponding to discoverers whose random warning values ​​are greater than or equal to a set safety value in the population information using the update matrix includes: The update matrix is ​​added to the location information of the discoverers whose random warning values ​​are greater than or equal to the set safety value from the population information to obtain the iteratively updated location information of the discoverers whose random warning values ​​are greater than or equal to the set safety value.

65. The path planning method for a mining robot according to any one of claims 1-3, 6-8, 10-12, 15-19, 21, 22, 24, 25, 27, 28, 30, 32, 33, 36-38, 40-44, 47-61, 63, and 64, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

66. The path planning method for a mining robot according to claim 4, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

67. The path planning method for a mining robot according to claim 5, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

68. The path planning method for a mining robot according to claim 9, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

69. The path planning method for a mining robot according to claim 13, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

70. The path planning method for a mining robot according to claim 14, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

71. The path planning method for a mining robot according to claim 20, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

72. The path planning method for a mining robot according to claim 23, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

73. The path planning method for a mining robot according to claim 26, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

74. The path planning method for a mining robot according to claim 29, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

75. The path planning method for a mining robot according to claim 31, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

76. The path planning method for a mining robot according to claim 34, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

77. The path planning method for a mining robot according to claim 35, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

78. The path planning method for a mining robot according to claim 39, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

79. The path planning method for a mining robot according to claim 45, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

80. The path planning method for a mining robot according to claim 46, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

81. The path planning method for a mining robot according to claim 62, characterized in that, Before iteratively updating the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, the process includes: The population information is subjected to chaotic mapping to obtain chaotic mapped population information; The location information corresponding to the discoverer, follower, and vigilant in the chaotic mapping population information is iteratively updated respectively.

82. The path planning method for a mining robot according to claim 65, characterized in that, The step of performing chaotic mapping on the population information to obtain chaotic mapped population information includes: Obtain a first set control parameter, a second set control parameter that is greater than the first set control parameter, and a second maximum number of iterations; If the location information corresponding to the population individual in the previous iteration is between 0 and the first set control parameter, the location information corresponding to the population individual in the previous iteration is divided by the first set control parameter and then configured as the location information corresponding to the population individual in the current iteration. If the location information of the population individual in the previous iteration is between the first set control parameter and the second set control parameter, then calculate the first difference between the location information of the population individual in the previous iteration and the first set control parameter, and calculate the second difference between the second set control parameter and the first set control parameter. After dividing the first difference by the second difference, the position information corresponding to the individual in the population in this iteration is configured. If the location information corresponding to the population individual in the previous iteration is between the second set control parameter and 1 - the first set control parameter, then calculate the third difference between 1 - the first set control parameter and the population individual in the previous iteration, and calculate the fourth difference between the second set control parameter and the first set control parameter. After dividing the third difference by the fourth difference, the position information corresponding to the individual in the population in this iteration is configured. If the location information of the population individual in the previous iteration is between 1 and the first set control parameter and 1, then calculate the fifth difference between 1 and the location information of the population individual in the previous iteration; divide the fifth difference by the first set control parameter and configure it as the location information of the population individual in the current iteration. Chaotic mapping stops once the number of iterations satisfies the second maximum number of iterations. By processing the positional information of the individuals in the population at the point of stopping chaotic mapping using the upper and lower bounds of the search space, a chaotic mapping population is obtained.

83. The path planning method for a mining robot according to any one of claims 66-81, characterized in that, The step of performing chaotic mapping on the population information to obtain chaotic mapped population information includes: Obtain a first set control parameter, a second set control parameter that is greater than the first set control parameter, and a second maximum number of iterations; If the location information corresponding to the population individual in the previous iteration is between 0 and the first set control parameter, the location information corresponding to the population individual in the previous iteration is divided by the first set control parameter and then configured as the location information corresponding to the population individual in the current iteration. If the location information of the population individual in the previous iteration is between the first set control parameter and the second set control parameter, then calculate the first difference between the location information of the population individual in the previous iteration and the first set control parameter, and calculate the second difference between the second set control parameter and the first set control parameter. After dividing the first difference by the second difference, the position information corresponding to the individual in the population in this iteration is configured. If the location information corresponding to the population individual in the previous iteration is between the second set control parameter and 1 - the first set control parameter, then calculate the third difference between 1 - the first set control parameter and the population individual in the previous iteration, and calculate the fourth difference between the second set control parameter and the first set control parameter. After dividing the third difference by the fourth difference, the position information corresponding to the individual in the population in this iteration is configured. If the location information of the population individual in the previous iteration is between 1 and the first set control parameter and 1, then calculate the fifth difference between 1 and the location information of the population individual in the previous iteration; divide the fifth difference by the first set control parameter and configure it as the location information of the population individual in the current iteration. Chaotic mapping stops once the number of iterations satisfies the second maximum number of iterations. By processing the positional information of the individuals in the population at the point of stopping chaotic mapping using the upper and lower bounds of the search space, a chaotic mapping population is obtained.

84. The path planning method for a mining robot according to any one of claims 1-3, 6-8, 10-12, 15-19, 21, 22, 24, 25, 27, 28, 30, 32, 33, 36-38, 40-44, 47-61, 63, 64, 66-82, is characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

85. The path planning method for a mining robot according to claim 4, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

86. The path planning method for a mining robot according to claim 5, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

87. The path planning method for a mining robot according to claim 9, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

88. The path planning method for a mining robot according to claim 13, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

89. The path planning method for a mining robot according to claim 14, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

90. The path planning method for a mining robot according to claim 20, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

91. The path planning method for a mining robot according to claim 23, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

92. The path planning method for a mining robot according to claim 26, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

93. The path planning method for a mining robot according to claim 29, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

94. The path planning method for a mining robot according to claim 31, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

95. The path planning method for a mining robot according to claim 34, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

96. The path planning method for a mining robot according to claim 35, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

97. The path planning method for a mining robot according to claim 39, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

98. The path planning method for a mining robot according to claim 45, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

99. The path planning method for a mining robot according to claim 46, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

100. The path planning method for a mining robot according to claim 62, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

101. The path planning method for a mining robot according to claim 65, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

102. The path planning method for a mining robot according to claim 83, characterized in that, The process of iteratively updating the location information corresponding to the discoverer, follower, and vigilant individuals in the population information includes: performing a mutation perturbation on the location information corresponding to the optimal population individual, and calculating the first fitness value before the mutation perturbation and the second fitness value after the mutation perturbation; configuring the fitness value with the better fitness value among the first fitness value and the second fitness value as the fitness value corresponding to the optimal population individual.

103. A path planning system for a mining robot, characterized in that, include: The first unit is used to acquire a multi-dimensional search space within the mine and population information of the path from the initial spatial position information of the mine robot to the target position information within the multi-dimensional search space. The second unit is used to iteratively update the location information corresponding to the discoverers, followers, and vigilant individuals in the population information, respectively. Specifically, it uses normally distributed random numbers and their corresponding dynamic weighting factors to iteratively update the location information corresponding to discoverers whose random warning values ​​are less than a set safety value. Furthermore, it uses the random step size generated by Levi's flight, the location information corresponding to the best and worst individuals in the population information to iteratively update the location information corresponding to vigilant individuals in the population information. In the third unit, when the number of iterations corresponding to the position information of the optimal individual in the population information reaches the set number of iterations, the iteration update is stopped, and the path planning of the mining robot is completed.

104. A path planning system for a mining robot, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the path planning method of the mining robot according to any one of claims 1 to 102.

105. A path planning system for a mining robot, characterized in that, include: A computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the path planning method of the mining robot according to any one of claims 1 to 102.

106. A path planning system for a mining robot, characterized in that, include: A computer program product, comprising a computer program / instruction, characterized in that, when executed by a processor, the computer program / instruction implements the path planning method for the mining robot according to any one of claims 1 to 102.

107. A mining robot, characterized in that, The path planning method for the mining robot as described in any one of claims 1 to 102 is applied; wherein the path planning method for the mining robot is integrated into a global path planner.

108. A mining robot, characterized in that, include: A global path planner for performing the path planning method for the mining robot as described in any one of claims 1 to 102.

109. A mining robot, characterized in that, include: The path planning system for a mining robot as described in any one of claims 103 to 106.

Images