A method and system for artificial intelligence robot path planning

Abstract

The present invention relates to the field of artificial intelligence robot path planning technology, belongs to the field of robot and group intelligence technology, and specifically relates to an artificial intelligence robot path planning method and system; the present invention provides an artificial intelligence robot path planning method and system, when establishing a grid map, first compare the initial grid size and the maximum obstacle area, if the maximum obstacle area is smaller than the initial grid size, then use the recommended number of grids to establish the grid map, so that the planned route will not be blocked by obstacles and become an invalid route; if the maximum obstacle area is greater than or equal to the initial grid size, it is necessary to expand the grid size, at this time, use an artificial intelligence model to determine a more appropriate number of grids to establish the map, so as to take into account the accuracy of grid map establishment and the efficiency of path planning operations.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence robot path planning, which belongs to the technical field of robots and swarm intelligence, and specifically to an artificial intelligence robot path planning method and system. Background Art

[0002] For artificial intelligence robots, how to achieve efficient movement is the focus of their research and development. The core of path planning lies in the path planning algorithm, which can find the optimal or suboptimal path from the starting point to the end point in a given environment. Path planning algorithms are mainly divided into two categories: traditional path planning algorithms and intelligent optimization algorithms. Their research is of great significance in the field of artificial intelligence robots and has attracted the attention of many researchers at home and abroad.

[0003] In the prior art, there are schemes for using various intelligent optimization algorithms to plan the path of artificial intelligence robots. For example, a Chinese invention patent (CN110095122A) discloses an artificial intelligence robot path planning method based on an improved ant colony algorithm, which includes the following steps: S1, using a grid method to create a robot environment map; S2, using an ant colony algorithm to find the shortest path in the environment, and the ant colony algorithm includes the following steps: S21, initializing the parameters of the ant colony algorithm; S22, placing m ants at the starting point to start searching; S23, using a distance heuristic function to select the next moving grid; S24, judging whether all ants have reached the destination Punctuation, if yes, proceed to step S25, if not, return to step S23; S25, optimize all feasible paths of the current iteration through route redundancy elimination strategy; S26, use path deviation amplification strategy to update pheromones; S27, determine whether the maximum number of iterations has been reached, if yes, end; if not, add 1 to the number of iterations and return to step S22; S3, take the shortest path obtained in step S2 as the optimal path for planning; However, the above scheme has the problem of rough grid map establishment when using ant colony algorithm for path planning, resulting in low accuracy and efficiency of the calculation process, and low robustness of the ant colony algorithm. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence robot path planning method and system for improving the accuracy, efficiency and robustness of the artificial intelligence robot path planning.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions: a path planning method for an artificial intelligence robot, specifically comprising the steps of:

[0006] S1: Use the grid method to model the working environment of the artificial intelligence robot and establish a grid map;

[0007] The grid method is used to model the environment; the grid method divides the operating environment of the artificial intelligence robot into squares of equal size, and each square is a grid;

[0008] The method to determine the number of grids is:

[0009] Sa: Get the total area S of the operating environment of the artificial intelligence robot t ;

[0010] Sb: Get the maximum obstacle area S in the operating environment of the artificial intelligence robot z ;

[0011] Sc: Set the initial recommended grid number N of the operating environment of the artificial intelligence robot;

[0012] Sd: According to the total area of ​​the operating environment S t And the initial recommended grid number N to get the initial grid size S m ;

[0013] Se: Compare the initial grid size S m and the maximum obstacle area S z , if the initial grid size S m Greater than the maximum obstacle area S z , then the initial recommended grid number N is the final grid number N t , otherwise, go to the next step;

[0014] Sf: Use the grid number determination model to determine the final grid number N t ;

[0015] S2: Using an improved ant colony algorithm to perform path planning for the artificial intelligence robot;

[0016] The S2 is specifically:

[0017] S2.1: Initialize the parameters of the ant colony algorithm;

[0018] S2.2: placing all ants at the starting point of the grid map and establishing a taboo table;

[0019] S2.3: Update the taboo table to record the nodes that the ants have passed;

[0020] S2.4: Determine whether the ant has reached the end point. If so, record the path taken by the ant and go to the next step. Otherwise, go to step S2.3.

[0021] S2.5: Determine whether the maximum number of ants has been reached; if so, go to the next step; otherwise, add 1 to the number of ants and execute step S2.2;

[0022] S2.6: Get the optimal path based on the path of each ant;

[0023] S3: Using the optimal path as the planned path for the artificial intelligence robot.

[0024] Preferably, the Sb is specifically: collecting an image of the operating environment of the artificial intelligence robot; then manually identifying the obstacle area in the image, and calculating the total obstacle area S in the operating environment of the artificial intelligence robot according to the obstacle area in the image. z .

[0025] Preferably, in the Sc, the initial recommended number of grids is 400.

[0026] Preferably, in the Sd, the initial grid size S m The calculation formula is:

[0027] .

[0028] Preferably, the grid quantity determination model is a deep learning model, specifically one of a feedforward neural network, a generative adversarial network, and deep reinforcement learning.

[0029] Preferably, the input of the deep learning model is the total area of ​​the artificial intelligence robot operating environment, the maximum obstacle area in the artificial intelligence robot operating environment, the number of obstacles in the artificial intelligence robot operating environment, the total area of ​​obstacles in the artificial intelligence robot operating environment; the initial number of grids; and the output of the deep learning model is the final number of grids.

[0030] Preferably, in S2.1, the parameters for initializing the ant colony algorithm are specifically: the number of ants, pheromone constant, pheromone volatility factor, distance heuristic function factor, area heuristic factor, maximum number of iterations, and the starting point and end point of the artificial intelligence robot.

[0031] Preferably, the ant search efficiency is adjusted by adjusting the pheromone volatility factor;

[0032] Among them, the formula for determining the pheromone volatility factor ρ is:

[0033]

[0034] Where ρ0 is the initial pheromone volatilization factor, Lm is the path length explored by ant m, Nc is the current number of iterations, Nmax is the preset maximum number of iterations, and μ is a constant.

[0035] Preferably, different initial pheromone volatility factors ρ0 are set according to different grid maps established in S1; when the number of grids in the grid map is the initial recommended number of grids, the initial pheromone volatility factor ρ 0= 0.5; otherwise, the formula for determining the initial pheromone volatility factor ρ0 is:

[0036]

[0037] Where N is the number of initial recommended grids, N t is the final number of grids, and a is the adjustment coefficient.

[0038] According to another aspect of the present invention, there is provided an artificial intelligence robot path planning system, the system adopts the above-mentioned artificial intelligence robot path planning method, and the system further comprises:

[0039] A grid map building module is used to model the working environment of the artificial intelligence robot using a grid method and build a grid map;

[0040] An optimal path planning module, used to perform path planning for the artificial intelligence robot using an improved ant colony algorithm;

[0041] The optimal path execution module is used to use the optimal path as the planned path of the artificial intelligence robot.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention provides an artificial intelligence robot path planning method and system. When establishing a grid map, the initial grid size and the maximum obstacle area are first compared. If the maximum obstacle area is smaller than the initial grid size, the recommended number of grids is used to establish the grid map, so that the planned route will not be blocked by obstacles and become an invalid route; if the maximum obstacle area is greater than or equal to the initial grid size, the grid size needs to be expanded. At this time, an artificial intelligence model is used to determine a more appropriate number of grids to establish the map, so as to take into account the accuracy of grid map establishment and the efficiency of path planning operations;

[0044] At the same time, the present invention improves the ant colony algorithm so that in the early stage of the algorithm, under the control of the pheromone volatilization factor, ants can have more possibilities to find more routes, and in the later stage, the ants can focus on routes with more pheromones, thereby improving efficiency; in addition, different initial pheromone volatilization factors are set according to different grid maps, thereby improving the robustness of the improved ant colony algorithm applied to different types of artificial intelligence robot operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0046] Figure 1 A flow chart of an artificial intelligence robot path planning method provided by an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a grid method provided by an embodiment of the present invention;

[0048] Figure 3 A flowchart of a method for determining the number of grids provided in an embodiment of the present invention;

[0049] Figure 4 A flowchart of using an improved ant colony algorithm to perform path planning for the artificial intelligence robot is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] The following first describes the concepts involved in the present application in conjunction with the accompanying drawings. It should be noted that the following description of each concept is only to make the content of the present application easier to understand, and does not limit the scope of protection of the present application; at the same time, the embodiments and features in the embodiments of the present application can be combined with each other in the absence of conflict. The present application will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments.

[0052] Path planning technology uses sensors and other devices to perceive the working environment and its own status, so that artificial intelligence robots can find the best path from the starting point to the target point in a complex environment to achieve effective movement and task execution. Path planning not only pursues the shortest path, but also needs to make reasonable decisions based on environmental characteristics, task requirements and other factors, such as the shortest time, optimal distance or minimum energy consumption. To achieve these goals, various path planning algorithms are used, such as ant colony algorithms. The successful application of path planning technology enables artificial intelligence robots to navigate and perform tasks in dynamic and complex environments safely and efficiently.

[0053] like Figure 1As shown, the present invention provides an artificial intelligence robot path planning method, which specifically includes the steps of:

[0054] S1: Use the grid method to model the working environment of the artificial intelligence robot and establish a grid map;

[0055] Artificial intelligence robots use various sensors to perceive the surrounding environment, process and analyze the information obtained, and finally build a model of the environment in order to better understand and respond to the surrounding situation. Environmental modeling is the premise of path planning. The core of environmental modeling is to choose a suitable way to describe the surrounding environment to ensure that artificial intelligence robots can accurately understand and effectively respond to various situations in the environment. This includes choosing an appropriate map representation method, ensuring the accuracy and update speed of information, and ensuring that the model can adapt to different environments and task requirements. In short, environmental modeling is to create a map or model for artificial intelligence robots that accurately describes their working environment, including the location and characteristics of objects such as obstacles and markers.

[0056] In the research field of artificial intelligence robot path planning, it is crucial to choose a suitable environment modeling method because it directly affects the efficiency of the robot's extraction of environmental information and path planning. The grid method is a commonly used modeling method for robot path planning. Therefore, this embodiment uses the grid method for environment modeling; the grid method divides the operating environment of the artificial intelligence robot into squares of equal size, and each square is a grid.

[0057] As attached Figure 2 As shown, the grid method divides the operating environment of the artificial intelligence robot into grids, where each grid represents a specific area in the operating environment. Then, the artificial intelligence robot collects the environmental data of each grid through its own sensor, and determines whether there are obstacles based on the collected environmental data, where the squares without obstacles are white and the squares with obstacles are black.

[0058] It should be noted that when the grid method is used to model the operating environment of an artificial intelligence robot, the number of grids is a key concern. A large number of grids can provide more accurate environmental information, but will increase storage costs and computational complexity. A small number of grids can reduce storage and computational burdens, but may reduce the accuracy of environmental modeling. Therefore, when determining the number of grids, a trade-off needs to be made based on actual application requirements. In the prior art, when the grid method is used for modeling, the number of grids is usually determined by the size of the obstacle being an integer multiple of the grid size. However, the above method for determining the number of grids is relatively rough and has low adaptability and robustness to different types of robot operating environments.

[0059] Therefore, in this embodiment, as shown in the attached Figure 3As shown, the method for determining the number of grids is:

[0060] Sa: Get the total area S of the operating environment of the artificial intelligence robot t ;

[0061] Among them, the total area of ​​the artificial intelligence robot operating environment is S t The total area of ​​the operating environment for path planning of the artificial intelligence robot, generally the working operation area of ​​the artificial intelligence robot;

[0062] Sb: Get the maximum obstacle area S in the operating environment of the artificial intelligence robot z ;

[0063] Wherein, the Sb is specifically: collecting the image of the operating environment of the artificial intelligence robot; then identifying the obstacle area in the image by manual identification, and calculating the total obstacle area S in the operating environment of the artificial intelligence robot according to the obstacle area in the image z ;

[0064] It is worth emphasizing that, generally, obstacles are of irregular shapes, and they need to be regularized to obtain obstacles and the maximum obstacle area;

[0065] Sc: Set the initial recommended grid number N of the operating environment of the artificial intelligence robot;

[0066] Based on the consideration of computing equipment and environmental modeling habits in the industry, in this embodiment, the initial recommended number of grids is 400;

[0067] Sd: According to the total area of ​​the operating environment S t And the initial recommended grid number N to get the initial grid size S m ;

[0068] Among them, the initial grid size S m The calculation formula is:

[0069] ;

[0070] Se: Compare the initial grid size S m and the maximum obstacle area S z , if the initial grid size S m Greater than the maximum obstacle area S z , then the initial recommended grid number N is the final grid number N t , otherwise, go to the next step;

[0071] In this step, the initial grid size is compared with the maximum obstacle area, and then the number of grids is determined in different ways, which improves the adaptability of modeling the operating environment of the artificial intelligence robot.

[0072] Sf: Use the grid number determination model to determine the final grid number N t ;

[0073] The grid quantity determination model is a deep learning model, specifically one of a feedforward neural network (Feedforward Neural Networks), a generative adversarial network (GANs), and a deep reinforcement learning (DRL);

[0074] Among them, the input of the deep learning model is the total area of ​​the artificial intelligence robot operating environment, the maximum obstacle area in the artificial intelligence robot operating environment, the number of obstacles in the artificial intelligence robot operating environment, the total area of ​​obstacles in the artificial intelligence robot operating environment; the initial number of grids; the output of the deep learning model is the final number of grids.

[0075] This embodiment first compares the initial grid size and the maximum obstacle area. If the maximum obstacle area is smaller than the initial grid size, the recommended number of grids is used to establish a grid map, so that the planned route will not be blocked by obstacles and become an invalid route; if the maximum obstacle area is greater than or equal to the initial grid size, the grid size needs to be expanded. At this time, an artificial intelligence model is used to determine a more appropriate number of grids to establish a map, so as to take into account the accuracy of grid map establishment and the efficiency of path planning operations.

[0076] S2: Using an improved ant colony algorithm to perform path planning for the artificial intelligence robot;

[0077] The ant colony optimization algorithm simulates the behavior of ants passing pheromones to each other when searching for food. During the foraging process, ants use the pheromones secreted by previous ants to choose a path and release their own pheromones during movement. Over time, the pheromone concentration on the path will change as the pheromones accumulate, evaporate, and diffuse, thus affecting the choices of subsequent ants and finding the optimal foraging route.

[0078] Among them, as attached Figure 4 As shown, the S2 is specifically:

[0079] S2.1: Initialize the parameters of the ant colony algorithm;

[0080] In this embodiment, the parameters for initializing the ant colony algorithm are specifically: the number of ants, the pheromone constant, the pheromone volatility factor, the distance heuristic function factor, the regional heuristic factor, the maximum number of iterations, the starting point and the end point of the artificial intelligence robot;

[0081] S2.2: placing all ants at the starting point of the grid map and establishing a taboo table;

[0082] S2.3: Update the taboo table to record the nodes that the ants have walked through;

[0083] In said S2.3, in updating the taboo table, the traditional ant colony algorithm is improved, and the ant search efficiency is adjusted by adjusting the pheromone volatilization factor;

[0084] Among them, the formula for determining the pheromone volatility factor ρ is:

[0085]

[0086] Where ρ0 is the initial pheromone volatilization factor, Lm is the path length explored by ant m, Nc is the current number of iterations, Nmax is the preset maximum number of iterations, and μ is a constant;

[0087] Through the above settings, in the early stage of the algorithm, under the control of the pheromone volatilization factor, the ants can have more possibilities to find more routes, and in the later stage, the ants can focus on the routes with more pheromones, thereby improving efficiency;

[0088] Furthermore, a more preferred embodiment is: different initial pheromone volatilization factors ρ0 are set according to different grid maps established in S1;

[0089] Specifically, when the number of grids in the grid map is the initial recommended number of grids, the initial pheromone volatility factor ρ is set 0= 0.5; otherwise, the formula for determining the initial pheromone volatility factor ρ0 is:

[0090]

[0091] Where N is the number of initial recommended grids, N t is the final number of grids, a is the adjustment coefficient;

[0092] Through the above steps, not only can the ant algorithm achieve better optimization accuracy in the artificial intelligence robot operating environment with a large maximum obstacle, but it also improves the robustness of the improved ant colony algorithm applied to different types of artificial intelligence robot operating environments.

[0093] S2.4: Determine whether the ant has reached the end point. If so, record the path taken by the ant and go to the next step. Otherwise, go to step S2.3.

[0094] S2.5: Determine whether the maximum number of ants has been reached; if so, go to the next step; otherwise, add 1 to the number of ants and execute step S2.2;

[0095] S2.6: Get the optimal path based on the path of each ant;

[0096] In this embodiment, the shortest path is taken as the optimal path.

[0097] S3: Using the optimal path as the planned path for the artificial intelligence robot.

[0098] Embodiment 2, this embodiment also includes an artificial intelligence robot path planning system, the system adopts an artificial intelligence robot path planning method of embodiment 1, and the system also includes:

[0099] A grid map building module is used to model the working environment of the artificial intelligence robot using a grid method and build a grid map;

[0100] An optimal path planning module, used to perform path planning for the artificial intelligence robot using an improved ant colony algorithm;

[0101] The optimal path execution module is used to use the optimal path as the planned path of the artificial intelligence robot.

[0102] Embodiment three, this embodiment includes an electronic device, including a processor and a memory, the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the various steps of an artificial intelligence robot path planning method in embodiment one are implemented, and the same technical effect can be achieved.

[0103] Embodiment 4: This embodiment includes a computer-readable storage medium on which a data processing program is stored. The data processing program is executed by a processor to perform various steps of an artificial intelligence robot path planning method in embodiment 1.

[0104] It should be understood by those skilled in the art that the embodiments of this article can be provided as methods, devices (equipment), or computer program products. Therefore, this article can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media generally contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0105] This document is described with reference to flowcharts and / or block diagrams of methods, apparatuses (devices), and computer program products according to the embodiments of this document. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] The embodiments and / or implementation methods described above are only used to illustrate the preferred embodiments and / or implementation methods of the technology of the present invention, and are not intended to impose any formal restrictions on the implementation methods of the technology of the present invention. Any person skilled in the art may make some changes or modifications to other equivalent embodiments without departing from the scope of the technical means disclosed in the content of the present invention, but they should still be regarded as the technology or embodiments that are essentially the same as the present invention. Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described here, and that various obvious changes, readjustments and substitutions can be made to those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention is described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A path planning method for an artificial intelligence robot, characterized in that: The specific steps include: S1: Use the grid method to model the working environment of the artificial intelligence robot and establish a grid map; The grid method is used to model the environment; the grid method divides the operating environment of the artificial intelligence robot into squares of equal size, and each square is a grid; The method to determine the number of grids is: Sa: Get the total area S of the operating environment of the artificial intelligence robot t ; Sb: Get the maximum obstacle area S in the operating environment of the artificial intelligence robot z ; Sc: Set the initial recommended grid number N of the operating environment of the artificial intelligence robot; Sd: According to the total area of ​​the operating environment S t And the initial recommended grid number N to get the initial grid size S m ; Se: Compare the initial grid size S m and the maximum obstacle area S z , if the initial grid size S m Greater than the maximum obstacle area S z , then the initial recommended grid number N is the final grid number N t , otherwise, go to the next step; Sf: Use the grid number determination model to determine the final grid number N t ; S2: Using an improved ant colony algorithm to perform path planning for the artificial intelligence robot; The S2 is specifically: S2.1: Initialize the parameters of the ant colony algorithm; S2.2: placing all ants at the starting point of the grid map and establishing a taboo table; S2.3: Update the taboo table to record the nodes that the ants have passed; Adjust the ant search efficiency by adjusting the pheromone volatility factor; Among them, the formula for determining the pheromone volatility factor ρ is: ； Wherein, ρ0 is the initial pheromone volatility factor, Lm is the path length explored by ant m, Nc is the current number of iterations, Nmax is the preset maximum number of iterations, and μ is a constant; different initial pheromone volatility factors ρ0 are set according to different grid maps established in S1; when the number of grids in the grid map is the initial recommended number of grids, the initial pheromone volatility factor ρ is set 0= 0.5; otherwise, the formula for determining the initial pheromone volatility factor ρ0 is: ； Where N is the number of initial recommended grids, N t is the final number of grids, a is the adjustment coefficient; S2.4: Determine whether the ant has reached the end point. If so, record the path taken by the ant and go to the next step. Otherwise, go to step S2.

3. S2.5: Determine whether the maximum number of ants has been reached; if so, go to the next step; otherwise, add 1 to the number of ants and execute step S2.2; S2.6: Get the optimal path based on the path of each ant; S3: Using the optimal path as the planned path for the artificial intelligence robot.

2. The artificial intelligence robot path planning method according to claim 1, characterized in that: The Sb is specifically: collecting the image of the artificial intelligence robot's operating environment; then manually identifying the obstacle area in the image, and calculating the total obstacle area S in the artificial intelligence robot's operating environment according to the obstacle area in the image. z .

3. The artificial intelligence robot path planning method according to claim 1, characterized in that: In the Sc, the initial recommended number of grids is 400.

4. The artificial intelligence robot path planning method according to claim 1, characterized in that: The Sd, the initial grid size S m The calculation formula is: 。 5. The artificial intelligence robot path planning method according to claim 1, characterized in that: The grid quantity determination model is a deep learning model, specifically one of a feedforward neural network, a generative adversarial network, and deep reinforcement learning.

6. The artificial intelligence robot path planning method according to claim 5, characterized in that: The input of the deep learning model is the total area of ​​the artificial intelligence robot's operating environment, the maximum obstacle area in the artificial intelligence robot's operating environment, the number of obstacles in the artificial intelligence robot's operating environment, the total area of ​​obstacles in the artificial intelligence robot's operating environment, and the initial number of grids; the output of the deep learning model is the final number of grids.

7. The artificial intelligence robot path planning method according to claim 1, characterized in that: In S2.1, the parameters for initializing the ant colony algorithm are specifically: the number of ants, the pheromone constant, the pheromone volatility factor, the distance heuristic function factor, the area heuristic factor, the maximum number of iterations, and the starting point and end point of the artificial intelligence robot.

8. An artificial intelligence robot path planning system, characterized in that: The system adopts an artificial intelligence robot path planning method according to any one of claims 1 to 7, and the system further comprises: A grid map building module is used to model the working environment of the artificial intelligence robot using a grid method and build a grid map; An optimal path planning module, used to perform path planning for the artificial intelligence robot using an improved ant colony algorithm; The optimal path execution module is used to use the optimal path as the planned path of the artificial intelligence robot.

Images