Path planning method and system for mobile robot

Abstract

The invention discloses a path optimization method and system for a mobile robot, and the method comprises the steps: obtaining a starting position and an ending position of the mobile robot, and a preset fitness function, a reward lookup table and a bee physical force threshold value; according to the termination position, performing initialization path construction on the initial position to obtain an initial feasible path; according to the fitness function, the reward lookup table and the bee physical strength threshold, performing artificial bee colony path optimization on the initial feasible path to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each bee colony optimization path; and according to the fitness function and each bee colony path probability, performing path optimal screening on all the bee colony optimization paths to obtain a target optimization path. According to the method, computing resources and time consumption required by path planning can be effectively reduced, and the effectiveness of a path planning result is improved. The invention relates to the technical field of path planning processing.

Description

Technical Field

[0001] The present application relates to the technical field of path planning and processing, and in particular to a path planning method and system for a mobile robot. Background Art

[0002] A mobile robot is an intelligent device that can independently perform specific tasks in a complex environment. The mobile robot can be roughly divided into three modules: information perception, path planning, and motion control. Among them, the path planning module is an important basic part for the mobile robot system to realize autonomous mobility, which is used to determine the moving path of the mobile robot.

[0003] At present, the existing technology usually uses the Artificial Bee Colony (ABC) algorithm to realize the path planning of mobile robots. This method requires more computing resources, takes a long time to plan the path, and is prone to fall into the local optimal solution. The effectiveness of the path planning result is poor.

[0004] Therefore, the problems existing in the prior art still need to be solved and optimized. Summary of the invention

[0005] In order to solve at least one of the above-mentioned technical problems, the present application provides a path optimization method and system for a mobile robot, wherein the method can effectively reduce the computing resources and time required for path planning and improve the effectiveness of the path planning results.

[0006] According to a first aspect of the present application, a path optimization method for a mobile robot is provided, comprising:

[0007] Obtain the starting and ending positions of the mobile robot, as well as the preset fitness function, reward lookup table, and bee physical strength threshold;

[0008] According to the end position, initializing the path construction for the start position to obtain an initial feasible path;

[0009] According to the fitness function, the reward lookup table and the bee physical strength threshold, the initial feasible path is optimized by an artificial bee colony path to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths;

[0010] According to the fitness function and the probability of each swarm path, all swarm optimization paths are screened for optimal paths to obtain a target optimization path.

[0011] In some embodiments, the artificial bee colony path optimization is performed on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold to obtain several bee colony optimization paths, including:

[0012] Acquire a first path dimension of the initial feasible path;

[0013] According to the reward lookup table, updating the first path dimension to obtain a second path dimension;

[0014] According to the second path dimension, a dimension neighborhood search is performed on the initial feasible path to obtain a first intermediate optimal path and the remaining physical strength of the bees corresponding to the first intermediate optimal path;

[0015] According to the fitness function, the bee physical strength threshold and the bee remaining physical strength, the first intermediate optimization path is updated multiple times to obtain the bee colony optimization path.

[0016] In some embodiments, updating the first path dimension according to the reward lookup table to obtain the second path dimension includes:

[0017] Selecting an execution action from the reward lookup table to obtain a target execution action;

[0018] Performing an action according to the target, updating the action reward of the first path dimension, and obtaining the second path dimension;

[0019] The method further comprises:

[0020] Obtaining the action value and action reward of the target execution action;

[0021] The reward lookup table is updated according to the action reward and the action value to obtain an updated reward lookup table.

[0022] In some embodiments, the first intermediate optimization path is updated multiple times according to the fitness function, the bee physical strength threshold and the bee remaining physical strength to obtain the bee colony optimization path, including:

[0023] According to the bee physical strength threshold, the remaining physical strength of the bees is compared to obtain a physical strength comparison result;

[0024] If the physical strength comparison result is that the remaining physical strength of the bee is less than the bee physical strength threshold, the first intermediate optimization path is determined as the bee colony optimization path; or, if the physical strength comparison result is that the remaining physical strength of the bee is greater than or equal to the bee physical strength threshold, the fitness of the first intermediate optimization path is updated according to the fitness function.

[0025] In some embodiments, updating the fitness of the first intermediate optimization path according to the fitness function includes:

[0026] Obtaining the initial node fitness of the initial feasible path;

[0027] According to the fitness function, calculating the first node fitness of the first intermediate optimization path to obtain the first path node fitness;

[0028] Comparing the initial node fitness with the first path node fitness to obtain a first fitness comparison result;

[0029] If the first fitness comparison result is that the first path node fitness is less than the initial node fitness, the number of visits to the first intermediate optimizing path is reset to zero, and then the path nodes of the initial feasible path are updated according to the path nodes of the first intermediate optimizing path, and then the step of obtaining the first path dimension of the initial feasible path is returned to execute; or, if the first fitness comparison result is that the first path node fitness is greater than or equal to the initial node fitness, the number of visits to the first intermediate optimizing path is updated, and then the step of obtaining the first path dimension of the initial feasible path is returned to execute.

[0030] In some embodiments, the step of performing path optimization screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path includes:

[0031] Get the preset path node access threshold;

[0032] According to the probability of each swarm path, all the swarm optimization paths are probabilistically selected to obtain a second intermediate optimization path;

[0033] According to the fitness function, performing an optimization neighborhood search on the second intermediate optimization path to obtain a third intermediate optimization path;

[0034] According to the path node access threshold, the third intermediate optimizing path is screened by path threshold to obtain the target optimizing path.

[0035] In some embodiments, performing an optimization neighborhood search on the second intermediate optimization path according to the fitness function to obtain a third intermediate optimization path includes:

[0036] Performing a differential neighborhood search on the second intermediate optimizing path to obtain a fourth intermediate optimizing path;

[0037] According to the fitness function, performing a second node fitness calculation on the second intermediate optimizing path to obtain a second path node fitness, and according to the fitness function, performing a third node fitness calculation on the fourth intermediate optimizing path to obtain a third path node fitness;

[0038] Comparing the second path node fitness with the third path node fitness to obtain a second fitness comparison result;

[0039] If the result of the second fitness comparison is that the fitness of the third path node is less than the fitness of the second path node, the number of visits to the fourth intermediate optimizing path is reset to zero, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path; or, if the result of the second fitness comparison is that the fitness of the third path node is greater than or equal to the fitness of the second path node, the number of visits to the fourth intermediate optimizing path is updated, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path.

[0040] In some embodiments, performing path threshold screening on the third intermediate optimizing path according to the path node access threshold to obtain the target optimizing path includes:

[0041] According to the path node access threshold, all path nodes in the third intermediate optimization path are screened by the node threshold to obtain a plurality of first nodes and a plurality of second nodes, wherein the first nodes are path nodes whose node access times are less than the path node access threshold, and the second nodes are path nodes whose node access times are greater than or equal to the path node access threshold;

[0042] Perform node position update on all the second nodes to obtain a plurality of third nodes, each of the third nodes corresponding to one second node;

[0043] The target optimizing path is obtained according to all the first nodes and all the third nodes.

[0044] In some embodiments, obtaining the target optimization path according to all the first nodes and all the third nodes includes:

[0045] Get the preset optimization conditions and current optimization information;

[0046] Obtaining a fifth intermediate optimal path according to all of the first nodes and all of the third nodes;

[0047] According to the optimization condition, condition verification is performed on the current optimization information to obtain a condition verification result;

[0048] If the result of the condition verification is that the current optimization information does not meet the optimization condition, the initial feasible path is updated according to the fifth intermediate optimization path, and then the process returns to execute the step of performing artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain several bee colony optimization paths and the bee colony path probability corresponding to each of the bee colony optimization paths; or, if the result of the condition verification is that the current optimization information meets the optimization condition, the fifth intermediate optimization path is determined as the target optimization path.

[0049] According to a second aspect of the present application, a path optimization system for a mobile robot is provided, comprising:

[0050] A first processing unit is used to obtain the starting position and the ending position of the mobile robot, as well as a preset fitness function, a reward lookup table and a bee physical strength threshold;

[0051] A second processing unit is used to construct an initial path for the starting position according to the ending position to obtain an initial feasible path;

[0052] A third processing unit is used to perform artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths;

[0053] The fourth processing unit is used to perform optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path.

[0054] According to a third aspect of the present application, a computer device is provided, comprising:

[0055] at least one processor;

[0056] at least one memory for storing at least one program;

[0057] When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of the above aspects.

[0058] According to a fourth aspect of the present application, a computer-readable storage medium is provided, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the method described in any of the above aspects.

[0059] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0060] The present application provides a path optimization method and system for a mobile robot, wherein the method obtains a starting position and an ending position of the mobile robot, as well as a preset fitness function, a reward lookup table, and a bee physical strength threshold; based on the ending position, an initial path construction is performed on the starting position to obtain an initial feasible path; based on the fitness function, the reward lookup table, and the bee physical strength threshold, an artificial bee colony path optimization is performed on the initial feasible path to obtain a plurality of bee colony optimization paths, and a bee colony path probability corresponding to each of the bee colony optimization paths; based on the fitness function and each of the bee colony path probabilities, all of the bee colony optimization paths are screened for the best path to obtain a target optimization path. This method performs artificial bee colony path optimization on the initial feasible path based on the reward lookup table. It can dynamically adjust the number of dimensions of the optimization path, which is conducive to finding the global optimal or suboptimal path under the optimal dimension, increasing the chance of obtaining the optimal path planning, thereby improving the effectiveness of the path planning results; at the same time, this method also additionally introduces a bee physical strength threshold in the artificial bee colony path optimization process, which is conducive to accelerating the convergence speed of the artificial bee colony path optimization process and improving the operating efficiency of the artificial bee colony path optimization process, thereby reducing the computing resources and time required for path planning, and effectively avoiding falling into the situation of local optimal solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A schematic diagram of a flow chart of a path optimization method for a mobile robot provided in an embodiment of the present application;

[0062] Figure 2 A schematic diagram of a mobile robot in a two-dimensional simulation environment provided by an embodiment of the present application;

[0063] Figure 3 A detailed flow chart of step S130 provided in an embodiment of the present application;

[0064] Figure 4 A detailed flow chart of step A2 provided in an embodiment of the present application;

[0065] Figure 5 A detailed flow chart of step A5 provided in an embodiment of the present application;

[0066] Figure 6 A detailed flow chart of step S140 provided in an embodiment of the present application;

[0067] Figure 7 A detailed flow chart of step B3 provided in an embodiment of the present application;

[0068] Figure 8 A detailed flow chart of step B4 provided in an embodiment of the present application;

[0069] Fig. 9 A schematic diagram of a framework of a path optimization system for a mobile robot provided in an embodiment of the present application;

[0070] Fig.10 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0072] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0073] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0074] At present, the existing technology usually uses the Artificial Bee Colony (ABC) algorithm to realize the path planning of mobile robots. The algorithm of this method has a slow convergence speed, requires more computing resources, takes a long time to plan the path, and is prone to fall into the local optimal solution. The effectiveness of the path planning result is poor.

[0075] In view of this, an embodiment of the present application provides a path optimization method and system for a mobile robot, wherein the method performs artificial bee colony path optimization on an initial feasible path based on a reward lookup table, and can dynamically adjust the number of dimensions of the optimization path based on Q reinforcement learning, which is beneficial for the colony to find the global optimal or suboptimal path under the optimal dimension, and increases the chance of obtaining the optimal path planning, thereby improving the effectiveness of the path planning results; at the same time, the method also additionally introduces a bee physical strength threshold in the artificial bee colony path optimization process, which is beneficial to accelerate the convergence speed of the artificial bee colony path optimization process and reduce the running time, and can effectively improve the running efficiency of the artificial bee colony path optimization process, thereby reducing the computing resources and time required for path planning, and effectively avoiding falling into the situation of local optimal solution.

[0076] A path optimization method and system for a mobile robot provided in an embodiment of the present application can be specifically illustrated by the following embodiments. First, a path optimization method for a mobile robot in an embodiment of the present application is described.

[0077] The mobile robot path optimization method provided in the embodiment of the present application can be applied to the mobile robot path planning application scenario. In the mobile robot path planning application scenario, the mobile robot path planning service provider can plan the mobile path of the mobile robot through the method provided in the embodiment of the present application, which can obtain the mobile planning path of the mobile robot more quickly and improve the effectiveness of the result of the obtained mobile planning path.

[0078] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0079] Reference Figure 1 , Figure 1 It is an optional flowchart of a path optimization method for a mobile robot provided in an embodiment of the present application, which may include but is not limited to steps S110 to S140.

[0080] Step S110, obtaining the starting position and ending position of the mobile robot, as well as the preset fitness function, reward lookup table and bee physical strength threshold;

[0081] In the embodiment of the present application, the starting position of the mobile robot may be the current real-time position of the mobile robot, and the ending position may be the target position to which the mobile robot is to move. The fitness function is used to evaluate the quality of the optimal path, and there are many specific expressions of the fitness function, which will not be described in detail in this application.

[0082] It can be understood that the reward lookup table can be a Q value table in Q reinforcement learning, which is used to evaluate the expected utility of executing a certain execution action under a certain execution state, which includes execution actions, execution states and action values, and each execution action and execution state combination corresponds to an action value. In addition, the bee physical strength threshold is the upper limit of the action physical strength of each bee in the artificial bee colony algorithm bee population, and the specific value of the bee physical strength threshold can be set according to actual conditions.

[0083] Step S120: construct an initial path for the starting position according to the ending position to obtain an initial feasible path;

[0084] Reference Figure 2 In the embodiment of the present application, a two-dimensional simulation environment can be established based on the actual situation around the starting position and the ending position of the mobile robot, and the movement environment of the mobile robot can be simulated using a black and white grid. Figure 2 A grid in represents a node position. A black grid indicates an obstacle, and a white grid indicates no obstacle. The starting position and ending position of the mobile robot are Figure 2 The upper left circle and the lower right circle in .

[0085] It can be understood that after establishing a two-dimensional simulation environment, one or several initial feasible paths can be randomly generated based on the population initialization operation in the artificial bee colony algorithm. Each initial feasible path corresponds to a bee in a bee colony. The embodiment of the present application takes the number of initial feasible paths as 1 as an example. The contents of the remaining initial feasible paths are similar, and there are many specific ways to initialize the population, which will not be repeated in this application.

[0086] Step S130, performing artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths;

[0087] In an embodiment of the present application, an artificial bee colony path optimization can be performed on the initial feasible path based on the Q value table of Q reinforcement learning and the additionally introduced bee physical strength threshold, so as to obtain several bee colony optimization paths, each of which corresponds to a bee in the colony.

[0088] It is understandable that after obtaining the swarm optimization paths of all bees, the swarm path probability corresponding to each swarm optimization path can be determined based on the path fitness of each swarm optimization path. Exemplarily, the embodiment of the present application takes the swarm optimization path corresponding to one of the bees as an example. For a certain swarm optimization path, the equivalent expression of the swarm path probability corresponding to it can be:

[0089]

[0090] Among them, p i The swarm path probability of finding the optimal path for the i-th swarm; fitness i The path fitness of the optimal path for the i-th swarm; m is the path fitness of the mth swarm’s optimal path; SN is the total number of swarm’s optimal paths.

[0091] Reference Figure 3 In some embodiments, the step S130, according to the fitness function, the reward lookup table and the bee physical strength threshold, performs artificial bee colony path optimization on the initial feasible path to obtain several bee colony optimization paths, including:

[0092] A1. Obtaining a first path dimension of the initial feasible path;

[0093] A2. According to the reward lookup table, the first path dimension is updated to obtain a second path dimension;

[0094] Reference Figure 4 Further, the step A2, updating the first path dimension according to the reward lookup table to obtain the second path dimension, includes:

[0095] A21, selecting an execution action from the reward lookup table to obtain a target execution action;

[0096] A22. Execute an action according to the target, update the action reward of the first path dimension, and obtain the second path dimension;

[0097] In an embodiment of the present application, first, the number of dimensions of the initial feasible path in the solution space can be obtained, and the obtained number of dimensions can be recorded as the first path dimension; then, the first path dimension can be dynamically adjusted based on the reward lookup table in Q reinforcement learning to obtain the first path dimension after dimension adjustment, and the first path dimension after dimension adjustment can be determined as the second path dimension.

[0098] It can be understood that step A21 can be to randomly select an execution action in the reward lookup table as the target execution action in the current artificial bee colony path optimization process; step A22 can be to determine the corresponding target action value based on the target execution action and the first path dimension, specifically, different path dimensions can be matched one by one with the execution state in the reward lookup table, and then the target action value is determined as the action reward ratio, and the second path dimension is obtained by multiplying it with the number of dimensions of the first path dimension and rounding it up. Specifically, the equivalent expression of the second path dimension in the embodiment of the present application can be:

[0099] D n =ceil(d ratio ×D p )

[0100] Among them, D n is the second path dimension; ceil(·) is the rounding operation; d ratio is the action reward ratio corresponding to the target action value; Dp is the first path dimension.

[0101] The method further comprises:

[0102] A23, obtaining the action value and action reward of the target execution action;

[0103] A24. Update the reward lookup table according to the action reward and the action value to obtain an updated reward lookup table.

[0104] In an embodiment of the present application, after obtaining the second path dimension, the action reward (Reward) corresponding to the target execution action can also be obtained, and then the reward lookup table is updated based on the action reward and the action value (Q-Value) to obtain an updated reward lookup table. The updated reward lookup table can be used as a reward lookup table in the next artificial bee colony path optimization process.

[0105] For example, for a certain action value of the updated reward lookup table, its equivalent expression may be:

[0106]

[0107] Among them, Q nrw (·) is the action value of the reward lookup table after the update; Q(·) is the action value of the reward lookup table before the update; s t is the execution state; a t is the execution action; α is the learning rate, α∈[0,1]; γ is the loss rate, γ∈[0,1]; r t+1 The action reward for performing the action for the target; max a Q(s t+1 ,a) is in the next execution state s t+1 The maximum action value among all possible actions a.

[0108] A3. Performing a dimension neighborhood search on the initial feasible path according to the second path dimension to obtain a first intermediate optimal path and the remaining physical strength of the bees corresponding to the first intermediate optimal path;

[0109] In an embodiment of the present application, step A3 may be to perform a neighborhood search on the initial feasible path within the dimension indicated by the second path dimension to obtain a first intermediate optimizing path. There are many specific neighborhood search methods, which will not be described in detail in this application.

[0110] It can be understood that for a certain bee, the bee performs neighborhood search on the surrounding neighborhood of the initial feasible path, and the equivalent expression of the remaining physical strength of the bee can be:

[0111]

[0112] Among them, B i ′ B is the remaining energy of the bee after searching in the neighborhood; i is the remaining physical strength of the bee before searching the neighborhood; a∈{1,2,…,FES}; FES is an integer multiple of the bee population.

[0113] A4. According to the fitness function, the bee physical strength threshold and the bee remaining physical strength, the first intermediate optimization path is updated multiple times to obtain the bee colony optimization path.

[0114] Reference Figure 5 Further, the step A4, performing multiple updates on the first intermediate optimization path according to the fitness function, the bee physical strength threshold and the bee remaining physical strength to obtain the bee colony optimization path, includes:

[0115] A41. Comparing the remaining physical strength of the bees according to the physical strength threshold of the bees to obtain a physical strength comparison result;

[0116] A42. If the physical strength comparison result is that the remaining physical strength of the bees is less than the bee physical strength threshold, determining the first intermediate optimization path as the bee colony optimization path;

[0117] In the embodiment of the present application, step A41 may be to compare the magnitude relationship between the bee physical strength threshold and the bee remaining physical strength, and generate a physical strength comparison result according to the magnitude relationship between the two. Specifically, if the physical strength comparison result is that the bee remaining physical strength is less than the bee physical strength threshold, the current first intermediate optimization path may be used as the bee colony optimization path.

[0118] Alternatively, A43, if the physical strength comparison result is that the remaining physical strength of the bee is greater than or equal to the bee physical strength threshold, then according to the fitness function, the fitness of the first intermediate optimization path is updated.

[0119] Furthermore, the step A43, updating the fitness of the first intermediate optimization path according to the fitness function, includes:

[0120] A431, obtaining the initial node fitness of the initial feasible path;

[0121] A432. Calculate the first node fitness of the first intermediate optimization path according to the fitness function to obtain the first path node fitness;

[0122] A433, comparing the initial node fitness and the first path node fitness to obtain a first fitness comparison result;

[0123] A434. If the first fitness comparison result is that the first path node fitness is less than the initial node fitness, the number of visits to the first intermediate optimization path is reset to zero, and then the path nodes of the initial feasible path are updated according to the path nodes of the first intermediate optimization path, and then the step of obtaining the first path dimension of the initial feasible path is returned to be executed;

[0124] Alternatively, A435, if the first fitness comparison result is that the first path node fitness is greater than or equal to the initial node fitness, the number of visits to the first intermediate optimization path is updated, and then the step of obtaining the first path dimension of the initial feasible path is returned to.

[0125] In the embodiment of the present application, if the physical strength comparison result is that the remaining physical strength of the bee is greater than or equal to the physical strength threshold of the bee, the first intermediate optimization path can be continuously updated according to the fitness function. Specifically, the embodiment of the present application can obtain the initial node fitness of the initial feasible path and the first path node fitness of the first intermediate optimization path according to the fitness function, and the path node of the initial node fitness corresponds to the path node of the first path node fitness; then, the size relationship between the initial node fitness and the first path node fitness is compared to obtain the first fitness comparison result.

[0126] It can be understood that if the first fitness comparison result is that the fitness of the first path node is less than the fitness of the initial node, it means that the path node of the first intermediate optimizing path is better than the path node of the initial feasible path. At this time, the number of visits to the first intermediate optimizing path can be reset to zero, and then the path nodes of the first intermediate optimizing path can be used to replace the path nodes in the initial feasible path, and then return to execute step A1; or, if the first fitness comparison result is that the fitness of the first path node is greater than or equal to the fitness of the initial node, it means that the path node of the initial feasible path is better than the path node of the first intermediate optimizing path. At this time, the number of visits to the first intermediate optimizing path can be increased by 1, and the number of visits to the first intermediate optimizing path can be retained, and then return to execute step A1.

[0127] It can be understood that in the first cycle of steps A1 to A4, the initial feasible path can be the original feasible path to be optimized for the artificial bee colony path, and in the second and subsequent cycles, the current initial feasible path can be the first intermediate optimization path in the previous cycle or the initial feasible path in the previous cycle, which will not be repeated in this application.

[0128] It should be noted that, if the result of the first fitness comparison is that the fitness of the first path node is less than the fitness of the initial node, the action reward corresponding to the first intermediate optimization path can be set to 1, and the action reward corresponding to the first intermediate optimization path can be used as the action reward for the target execution action in step A23; or, if the result of the first fitness comparison is that the fitness of the first path node is greater than or equal to the fitness of the initial node, the action reward corresponding to the first intermediate optimization path can be set to 0, and the action reward corresponding to the first intermediate optimization path can be used as the action reward for the target execution action in step A23.

[0129] Step S140: performing optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path.

[0130] In an embodiment of the present application, after obtaining the swarm optimization path and swarm path probability corresponding to each bee, the target optimization path as the optimal solution can be selected from all swarm optimization paths based on the fitness function and each swarm path probability.

[0131] Reference Figure 6 In some embodiments, the step S140, performing optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path, includes:

[0132] B1. Obtaining a preset path node access threshold;

[0133] B2. Probabilistically select all the bee swarm optimization paths according to the probability of each bee swarm path to obtain a second intermediate optimization path;

[0134] In an embodiment of the present application, first, a path node access threshold can be obtained, which is the upper limit of the number of visits to the path node; then, step B2 can be based on the swarm path probability corresponding to each swarm optimization path, and a roulette wheel selection strategy is used to perform probability-based random selection on all swarm optimization paths, so as to determine the selected swarm optimization path as the second intermediate optimization path.

[0135] B3. Performing an optimization neighborhood search on the second intermediate optimization path according to the fitness function to obtain a third intermediate optimization path;

[0136] Reference Figure 7 Further, the step B3, performing an optimization neighborhood search on the second intermediate optimization path according to the fitness function to obtain a third intermediate optimization path, includes:

[0137] B31. Perform a differential neighborhood search on the second intermediate optimizing path to obtain a fourth intermediate optimizing path;

[0138] B32. According to the fitness function, performing a second node fitness calculation on the second intermediate optimizing path to obtain a second path node fitness, and according to the fitness function, performing a third node fitness calculation on the fourth intermediate optimizing path to obtain a third path node fitness;

[0139] B33, comparing the second path node fitness and the third path node fitness to obtain a second fitness comparison result;

[0140] B34. If the second fitness comparison result is that the third path node fitness is less than the second path node fitness, the number of visits to the fourth intermediate optimizing path is reset to zero, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path;

[0141] Alternatively, B35, if the second fitness comparison result is that the third path node fitness is greater than or equal to the second path node fitness, the number of visits to the fourth intermediate optimizing path is updated, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path.

[0142] In an embodiment of the present application, step B31 may be to use a differential evolution algorithm (DE) to perform a global neighborhood search on the path nodes of the second intermediate optimizing path to obtain a fourth intermediate optimizing path; then, the fitness of the second path nodes corresponding to the path nodes in the second intermediate optimizing path and the fitness of the third path nodes corresponding to the path nodes of the fourth intermediate optimizing path are calculated respectively through the fitness function.

[0143] It can be understood that step B33 can be to compare the size relationship between the second path node fitness and the third path node fitness, so as to obtain the second fitness comparison result. Specifically, if the second fitness comparison result is that the third path node fitness is less than the second path node fitness, it means that the path node of the fourth intermediate optimization path is better than the path node of the second intermediate optimization path. At this time, the number of visits to the fourth intermediate optimization path can be reset to zero, and then the fourth intermediate optimization path is determined as the third intermediate optimization path; or, if the second fitness comparison result is that the third path node fitness is greater than or equal to the second path node fitness, it means that the path node of the second intermediate optimization path is better than the path node of the fourth intermediate optimization path. At this time, the number of visits to the fourth intermediate optimization path can be increased by 1, and the number of visits to the fourth intermediate optimization path is retained, and then the fourth intermediate optimization path is determined as the third intermediate optimization path.

[0144] It should be noted that since the optimal path of the mobile robot from the starting position to the ending position is composed of several path nodes, the update of the number of visits to the optimal path can also be an update of the number of visits to the path nodes of the optimal path. The specific update can be a reset to zero or a plus 1 operation, etc., which will not be repeated in this application.

[0145] B4. Perform path threshold screening on the third intermediate optimizing path according to the path node access threshold to obtain the target optimizing path.

[0146] Reference Figure 8 Further, the step B4, performing path threshold screening on the third intermediate optimal path according to the path node access threshold to obtain the target optimal path, includes:

[0147] B41. According to the path node access threshold, perform node threshold screening on all path nodes in the third intermediate optimization path to obtain a plurality of first nodes and a plurality of second nodes, wherein the first nodes are path nodes whose node access times are less than the path node access threshold, and the second nodes are path nodes whose node access times are greater than or equal to the path node access threshold;

[0148] B42. Update the node positions of all the second nodes to obtain a plurality of third nodes, each of which corresponds to one second node.

[0149] In an embodiment of the present application, after obtaining the third intermediate optimizing path, the number of visits corresponding to each path node in the third intermediate optimizing path can be compared according to the path node access threshold, and the path node whose node access number is greater than or equal to the path node access threshold is determined as the second node, and the path node whose node access number is less than the path node access threshold is determined as the first node.

[0150] It is understandable that step B42 may be to update the positions of all second nodes to obtain a third node corresponding to each second node, and the third node may be obtained by performing a local search near the second node.

[0151] B43. Obtain the target optimization path according to all the first nodes and all the third nodes.

[0152] Further, the step B43, obtaining the target optimization path according to all the first nodes and all the third nodes, includes:

[0153] B431. Obtain preset optimization conditions and current optimization information;

[0154] B432. Obtain a fifth intermediate optimal path according to all the first nodes and all the third nodes;

[0155] B433. Perform condition verification on the current optimization information according to the optimization condition to obtain a condition verification result;

[0156] B434. If the result of the condition verification is that the current optimization information does not meet the optimization condition, the initial feasible path is updated according to the fifth intermediate optimization path, and then the process returns to the step of performing artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain a plurality of bee colony optimization paths, and a bee colony path probability corresponding to each of the bee colony optimization paths;

[0157] Alternatively, B435, if the condition verification result is that the current optimization information satisfies the optimization condition, the fifth intermediate optimization path is determined as the target optimization path.

[0158] In the embodiment of the present application, the optimization condition may be any one of the conditions for finding a satisfactory solution, the result convergence condition, and the maximum number of iterations from step S110 to step S140, and the current optimization information is the information corresponding to the optimization condition. Specifically, if the optimization condition is the maximum number of iterations, the corresponding optimization information may be the current number of iterations, etc., and the present application does not limit this.

[0159] It can be understood that after obtaining all the third nodes, the optimization path can be reconstructed based on all the first nodes and the third nodes, and the reconstructed optimization path can be determined as the fifth intermediate optimization path; then, it is determined whether the current optimization information meets the optimization conditions to obtain the condition verification result.

[0160] Specifically, the embodiment of the present application takes the optimization condition as the maximum number of iterations as an example. If the current number of iterations is less than the maximum number of iterations, the condition verification result obtained is that the current optimization information does not meet the optimization conditions. At this time, the path nodes of the initial feasible path can be replaced and updated according to the path nodes of the fifth intermediate optimization path to obtain an updated initial feasible path. The updated initial feasible path is used as the initial feasible path for the next number of iterations; or, if the current number of iterations is greater than or equal to the maximum number of iterations, the condition verification result obtained is that the current optimization information meets the optimization conditions. At this time, the fifth intermediate optimization path can be used as the optimal target optimization path.

[0161] Fig. 9 A schematic diagram of a framework of a path optimization system for a mobile robot provided in an embodiment of the present application includes:

[0162] A first processing unit is used to obtain the starting position and the ending position of the mobile robot, as well as a preset fitness function, a reward lookup table and a bee physical strength threshold;

[0163] A second processing unit is used to construct an initial path for the starting position according to the ending position to obtain an initial feasible path;

[0164] A third processing unit is used to perform artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths;

[0165] The fourth processing unit is used to perform optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path.

[0166] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0167] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of the present application includes:

[0168] at least one processor 980;

[0169] At least one memory 920, used to store at least one program;

[0170] When the at least one program is executed by the at least one processor 980, the at least one processor 980 implements the methods described in the foregoing embodiments.

[0171] An embodiment of the present application also provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor 980, it is used to implement the methods described in the above embodiments.

[0172] Fig.10 Specifically, the computer device may be a user terminal or a server.

[0173] The present application embodiment takes the computer device as a user terminal as an example, and the details are as follows:

[0174] like Fig.10As shown, the computer device 900 may include an RF (Radio Frequency) circuit 910, a memory 920 including one or more computer-readable storage media, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a WiFi module 970, a processor 980 including one or more processing cores, and a power supply 990. Those skilled in the art will appreciate that Fig.10 The device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0175] The RF circuit 910 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is handed over to one or more processors 980 for processing; in addition, the data related to the uplink is sent to the base station. Generally, the RF circuit 910 includes but is not limited to an antenna, at least one amplifier, a tuner, one or more oscillators, a user identity module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. In addition, the RF circuit 910 can also communicate with the network and other devices through wireless communication. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0176] The memory 920 can be used to store software programs and modules. The processor 980 executes various functional applications and data processing by running the software programs and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the device 900 (such as audio data, a phone book, etc.), etc. In addition, the memory 920 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 920 may also include a memory controller to provide the processor 980 and the input unit 930 with access to the memory 920. Although Fig.10 The RF circuit 910 is shown, but it is understandable that it is not an essential component of the device 900 and can be omitted as required without changing the essence of the invention.

[0177] The input unit 930 can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit 930 may include a touch-sensitive surface 932 and other input devices 931. The touch-sensitive surface 932, also known as a touch display screen or a touch pad, can collect user touch operations on or near it (such as operations performed by users using fingers, styluses, or any other suitable objects or accessories on or near the touch-sensitive surface 932), and drive corresponding connection devices according to a pre-set program. Optionally, the touch-sensitive surface 932 may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 980, and can receive and execute commands sent by the processor 980. In addition, the touch-sensitive surface 932 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch-sensitive surface 932, the input unit 930 may further include other input devices 931. Specifically, the other input devices 931 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0178] The display unit 940 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the device 900, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit 940 may include a display panel 941. Optionally, the display panel 941 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface 932 may be covered on the display panel 941. When the touch-sensitive surface 932 detects a touch operation on or near it, it is transmitted to the processor 980 to determine the type of touch event. Subsequently, the processor 980 provides a corresponding visual output on the display panel 941 according to the type of touch event. Although in Fig.10 In the embodiment, the touch-sensitive surface 932 and the display panel 941 are implemented as two independent components to implement input and output functions, but in some embodiments, the touch-sensitive surface 932 and the display panel 941 can be integrated to implement input and output functions.

[0179] The computer device 900 may also include at least one sensor 950, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 941 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 941 and / or the backlight when the device 900 is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that can also be configured in the device 900, they will not be repeated here.

[0180] The audio circuit 960, the speaker 961, and the microphone 962 can provide an audio interface between the user and the device 900. The audio circuit 960 can transmit the electrical signal converted from the received audio data to the speaker 961, which is converted into a sound signal for output; on the other hand, the microphone 962 converts the collected sound signal into an electrical signal, which is received by the audio circuit 960 and converted into audio data, and then the audio data is processed by the output processor 980 and sent to another control device through the RF circuit 910, or the audio data is output to the memory 920 for further processing. The audio circuit 960 may also include an earplug jack to provide communication between an external headset and the device 900.

[0181] The device 900 can transmit information with the wireless transmission module set on the fighting device through the WiFi module 970.

[0182] The processor 980 is the control center of the device 900. It uses various interfaces and lines to connect various parts of the entire control device. It executes various functions of the device 900 and processes data by running or executing software programs and / or modules stored in the memory 920, and calling data stored in the memory 920, so as to monitor the control device as a whole. Optionally, the processor 980 may include one or more processing cores; optionally, the processor 980 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 980.

[0183] The device 900 also includes a power supply 990 (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the processor 980 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 990 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0184] Although not shown, the device 900 may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0185] An embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the method described in the above embodiments.

[0186] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0187] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0188] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0189] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0192] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0193] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Technical personnel familiar with the field may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A path optimization method for a mobile robot, characterized in that: include: Obtain the starting and ending positions of the mobile robot, as well as the preset fitness function, reward lookup table, and bee physical strength threshold; According to the end position, initializing the path construction for the start position to obtain an initial feasible path; According to the fitness function, the reward lookup table and the bee physical strength threshold, the initial feasible path is optimized by an artificial bee colony path to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths; According to the fitness function and the probability of each swarm path, all swarm optimization paths are screened for optimal paths to obtain a target optimization path.

2. The path optimization method according to claim 1, characterized in that: The method of performing artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold to obtain a plurality of bee colony optimization paths includes: Acquire a first path dimension of the initial feasible path; According to the reward lookup table, updating the first path dimension to obtain a second path dimension; According to the second path dimension, a dimension neighborhood search is performed on the initial feasible path to obtain a first intermediate optimal path and the remaining physical strength of the bees corresponding to the first intermediate optimal path; According to the fitness function, the bee physical strength threshold and the bee remaining physical strength, the first intermediate optimization path is updated multiple times to obtain the bee colony optimization path.

3. The path optimization method according to claim 2, characterized in that: The step of updating the first path dimension according to the reward lookup table to obtain the second path dimension includes: Selecting an execution action from the reward lookup table to obtain a target execution action; Performing an action according to the target, updating the action reward of the first path dimension, and obtaining the second path dimension; The method further comprises: Obtaining the action value and action reward of the target execution action; The reward lookup table is updated according to the action reward and the action value to obtain an updated reward lookup table.

4. The path optimization method according to claim 2, characterized in that: The step of performing multiple updates on the first intermediate optimization path according to the fitness function, the bee physical strength threshold and the bee remaining physical strength to obtain the bee colony optimization path includes: According to the bee physical strength threshold, the remaining physical strength of the bees is compared to obtain a physical strength comparison result; If the physical strength comparison result is that the remaining physical strength of the bee is less than the bee physical strength threshold, the first intermediate optimization path is determined as the bee colony optimization path; or, if the physical strength comparison result is that the remaining physical strength of the bee is greater than or equal to the bee physical strength threshold, the fitness of the first intermediate optimization path is updated according to the fitness function.

5. The path optimization method according to claim 4, characterized in that: The updating of the fitness of the first intermediate optimization path according to the fitness function includes: Obtaining the initial node fitness of the initial feasible path; According to the fitness function, calculating the first node fitness of the first intermediate optimization path to obtain the first path node fitness; Comparing the initial node fitness with the first path node fitness to obtain a first fitness comparison result; If the first fitness comparison result is that the first path node fitness is less than the initial node fitness, the number of visits to the first intermediate optimizing path is reset to zero, and then the path nodes of the initial feasible path are updated according to the path nodes of the first intermediate optimizing path, and then the step of obtaining the first path dimension of the initial feasible path is returned to execute; or, if the first fitness comparison result is that the first path node fitness is greater than or equal to the initial node fitness, the number of visits to the first intermediate optimizing path is updated, and then the step of obtaining the first path dimension of the initial feasible path is returned to execute.

6. The path optimization method according to claim 1, characterized in that: The step of performing optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path includes: Get the preset path node access threshold; According to the probability of each swarm path, all the swarm optimization paths are probabilistically selected to obtain a second intermediate optimization path; According to the fitness function, performing an optimization neighborhood search on the second intermediate optimization path to obtain a third intermediate optimization path; According to the path node access threshold, the third intermediate optimizing path is screened by path threshold to obtain the target optimizing path.

7. The path optimization method according to claim 6, characterized in that: The step of performing an optimization neighborhood search on the second intermediate optimization path according to the fitness function to obtain a third intermediate optimization path includes: Performing a differential neighborhood search on the second intermediate optimizing path to obtain a fourth intermediate optimizing path; According to the fitness function, performing a second node fitness calculation on the second intermediate optimizing path to obtain a second path node fitness, and according to the fitness function, performing a third node fitness calculation on the fourth intermediate optimizing path to obtain a third path node fitness; Comparing the second path node fitness with the third path node fitness to obtain a second fitness comparison result; If the result of the second fitness comparison is that the fitness of the third path node is less than the fitness of the second path node, the number of visits to the fourth intermediate optimizing path is reset to zero, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path; or, if the result of the second fitness comparison is that the fitness of the third path node is greater than or equal to the fitness of the second path node, the number of visits to the fourth intermediate optimizing path is updated, and then the fourth intermediate optimizing path is determined as the third intermediate optimizing path.

8. The path optimization method according to claim 6, characterized in that: The step of performing path threshold screening on the third intermediate optimizing path according to the path node access threshold to obtain the target optimizing path includes: According to the path node access threshold, all path nodes in the third intermediate optimization path are screened by the node threshold to obtain a plurality of first nodes and a plurality of second nodes, wherein the first nodes are path nodes whose node access times are less than the path node access threshold, and the second nodes are path nodes whose node access times are greater than or equal to the path node access threshold; Perform node position update on all the second nodes to obtain a plurality of third nodes, each of the third nodes corresponding to one second node; The target optimizing path is obtained according to all the first nodes and all the third nodes.

9. The path optimization method according to claim 8, characterized in that: The step of obtaining the target optimization path according to all the first nodes and all the third nodes includes: Get the preset optimization conditions and current optimization information; Obtaining a fifth intermediate optimal path according to all of the first nodes and all of the third nodes; According to the optimization condition, condition verification is performed on the current optimization information to obtain a condition verification result; If the result of the condition verification is that the current optimization information does not meet the optimization condition, the initial feasible path is updated according to the fifth intermediate optimization path, and then the process returns to execute the step of performing artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain several bee colony optimization paths and the bee colony path probability corresponding to each of the bee colony optimization paths; or, if the result of the condition verification is that the current optimization information meets the optimization condition, the fifth intermediate optimization path is determined as the target optimization path.

10. A path optimization system for a mobile robot, characterized in that: include: The first processing unit is used to obtain the starting position and the ending position of the mobile robot, as well as a preset fitness function, a reward lookup table and a bee physical strength threshold; A second processing unit is used to construct an initial path for the starting position according to the ending position to obtain an initial feasible path; A third processing unit is used to perform artificial bee colony path optimization on the initial feasible path according to the fitness function, the reward lookup table and the bee physical strength threshold, to obtain a plurality of bee colony optimization paths and a bee colony path probability corresponding to each of the bee colony optimization paths; The fourth processing unit is used to perform optimal path screening on all the swarm optimization paths according to the fitness function and each swarm path probability to obtain a target optimization path.

Images