A substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm

Abstract

The application relates to a power substation unmanned aerial vehicle (UAV) three-dimensional path planning method based on an improved ant colony algorithm, which comprises the following steps: generating a power UAV inspection three-dimensional environment model and performing adaptive grid division; initializing the ant colony in the power UAV inspection three-dimensional environment model after grid division to perform path searching; each ant individual in the ant colony selects a next node according to a dynamic transfer probability calculation model, the ant individual determines an actually moved next node through a variable step length search behavior, and records path information from a starting point to an ending point of each ant individual; when all the ant individuals reach the ending point, the optimal ant individual of this iteration is screened and a worker ant foraging behavior is performed, and pheromone concentration of each path in the space is updated; iteration is repeated until a preset iteration number is reached, and the path with the highest pheromone concentration is selected as a final path of the UAV.

Description

TECHNICAL FIELD

[0001] The application relates to a power substation unmanned aerial vehicle (UAV) three-dimensional path planning method based on an improved ant colony algorithm, and belongs to the technical field of UAV path planning. BACKGROUND

[0002] At present, most domestic power substations still rely on inspection robots to inspect equipment. However, due to the variety of equipment in the power substation and the different installation positions and heights, the inspection robot can only take "overhead shots" on the ground, limiting its ability to comprehensively and accurately obtain the running status of the equipment. Especially in a complex equipment environment, the perspective and movement range of the inspection robot are restricted, and it is difficult to cover all key parts of the equipment. Therefore, it is particularly necessary to use a more maneuverable UAV to replace the inspection robot. The UAV can flexibly perform multi-directional inspection at different heights and angles to ensure comprehensive monitoring of the equipment status. However, how to plan the inspection route of the power substation UAV to improve the inspection efficiency is still a major challenge currently faced.

[0003] In order to design an efficient path planning scheme in the power substation, it is necessary to accurately divide the three-dimensional map into grids. The commonly used grid method divides along the coordinate axis according to a fixed size, and when a grid vertex touches an obstacle, the grid will be marked as a forbidden grid. The grid size determines the size and number of grids, thereby affecting the path planning accuracy and calculation speed of the ant colony algorithm. SUMMARY

[0004] In order to solve the problems existing in the prior art, the application provides a power substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm.

[0005] The technical scheme of the application is as follows:

[0006] On the one hand, the application provides a power substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm, comprising the following steps:

[0007] A power unmanned aerial vehicle (UAV) inspection three-dimensional environment model is generated, and adaptive grid division is performed on the power UAV inspection three-dimensional environment model;

[0008] An ant colony is initialized to search for a path in the grid-divided power UAV inspection three-dimensional environment model, and the starting point and the ending point of the UAV are set as the starting point and the ending point of the ant colony;

[0009] Each ant individual in the ant colony selects the next node according to a dynamic transition probability calculation model, and the ant individual determines the next node actually moved through a variable step search behavior, and records the path information of each ant individual from the starting point to the ending point;

[0010] Once all individual ants have reached the destination, the best individual ant in this iteration is selected and worker ant foraging behavior is executed, and the pheromone concentration of each path in the space is updated.

[0011] Repeat the iteration until the preset number of iterations is reached, then end the iteration and select the path with the highest pheromone concentration as the final path of the drone.

[0012] As a preferred embodiment of the present invention, the steps for adaptive grid division of the three-dimensional environment model of the power drone inspection are as follows:

[0013] Set the latitude and divide the space of the 3D environment model of the power drone inspection into multiple slices according to the slice latitude. Each slice is a grid.

[0014] When a grid vertex touches an obstacle, the grid adaptively adjusts the size in the direction of that vertex, as shown in the following formula:

[0015]

[0016] in: Indicates the first The size and length of the grid during the next adjustment; Indicates the initial length of the grid; This indicates adjusting the step size.

[0017] In a preferred embodiment of the present invention, the dynamic transition probability calculation model is specifically shown in the following formula:

[0018]

[0019]

[0020] in: Represents an individual ant From node Move to node The probability of; express Time Side pheromone concentration; express Time Side heuristic function; Represents an individual ant At the node Total number of next nodes that can be selected; Represents an individual ant At the node Select the next node; express Time Side pheromone concentration; represents the time edge heuristic function; represents the iteration factor threshold value; represents the iteration factor; represents the current iteration number; represents the maximum iteration number.

[0021] As a preferred embodiment of the present application, the variable step search behavior is specifically a variable step random search in the grid formed by the next node and the current node before the ant individual moves to the next node, and is specifically as follows:

[0022]

[0023]

[0024] wherein: represents the next node coordinate calculated by the variable step random search; represents the candidate next node coordinate calculated by the dynamic transfer probability calculation model; represents the current node coordinate; represents a random number; represents the step factor; represents the variable step factor.

[0025] As a preferred embodiment of the present application, the ant individual of the optimal path in each generation of ants is regarded as a worker ant that finds food, and other ant individuals are called to approach, and the formula of the calling ant colony behavior is as follows:

[0026]

[0027] wherein: the new position of the called ant individual ; represents the current position of the ant individual ; represents the position of the ant individual of the optimal path.

[0028] As a preferred embodiment of the present application, the optimal ant individual search behavior formula is as follows:

[0029]

[0030] wherein: represents the position of the ant individual of the optimal path obtained by the next search; represents the adjustment coefficient.

[0031] On the other hand, the present application also provides a transformer station unmanned aerial vehicle three-dimensional path planning system based on an improved ant colony algorithm, comprising a grid division module and an ant colony path planning module.

[0032] The grid division module is used for generating a power unmanned aerial vehicle inspection three-dimensional environment model and performing adaptive grid division on the power unmanned aerial vehicle inspection three-dimensional environment model.

[0033] The ant colony path planning module is used for initializing the ant colony to search a path in the power unmanned aerial vehicle inspection three-dimensional environment model after grid division, setting a starting point and an ending point of the unmanned aerial vehicle as a starting point and an ending point of the ant colony, selecting a next node by each ant individual in the ant colony according to a dynamic transition probability calculation model, determining an actually moved next node by the ant individual through a variable step search behavior, recording path information of each ant individual from the starting point to the ending point, screening an optimal ant individual in this iteration when all the ant individuals reach the ending point and performing a worker ant foraging behavior to update pheromone concentration of each path in the space, repeating iteration until a preset iteration number is reached, and ending iteration, and selecting a path with the highest pheromone concentration as a final path of the unmanned aerial vehicle.

[0034] In another aspect, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method according to any one of the embodiments of the present application.

[0035] In another aspect, the present application also provides a computer readable storage medium, which stores a computer program executable by a processor to implement the method according to any one of the embodiments of the present application.

[0036] The present application has the following beneficial effects:

[0037] 1. The present application introduces dynamic probability transition selection, variable step search behavior and worker ant foraging behavior and other improved strategies, which significantly improves the optimization ability and path planning accuracy of the algorithm, effectively reduces the distance of the planned path, and thus improves the inspection efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 The present application is a method flowchart;

[0039] Figure 2 The present application is a traditional grid segmentation schematic diagram;

[0040] Figure 3 The present application is an adaptive grid segmentation schematic diagram. DETAILED DESCRIPTION

[0041] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts are within the scope of the present application.

[0042] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0043] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0044] The terms "comprise" and "include" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0045] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations thereof, and includes these combinations.

[0046] Embodiment one:

[0047] Referring to Figure 1 A substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm, comprising the following steps:

[0048] A power unmanned aerial vehicle inspection three-dimensional environment model is generated, and the power unmanned aerial vehicle inspection three-dimensional environment model is adaptively gridded;

[0049] The ant colony is initialized to search for a path in the gridded power unmanned aerial vehicle inspection three-dimensional environment model, and the starting point and the ending point of the unmanned aerial vehicle are set as the starting point and the ending point of the ant colony;

[0050] Each ant individual in the ant colony selects the next node according to a dynamic transition probability calculation model, and the ant individual determines the next node actually moved through a variable step search behavior, and records the path information of each ant individual from the starting point to the ending point;

[0051] When all ant individuals reach the ending point, the optimal ant individual of this iteration is screened and the worker ant foraging behavior is performed, and the pheromone concentration of each path in the space is updated;

[0052] The iteration is repeated until a preset number of iterations is reached, and the path with the highest pheromone concentration is selected as the final path of the unmanned aerial vehicle;

[0053] The ant colony algorithm simulates the foraging behavior of ants in nature and uses "pheromones" for communication and decision-making. Specifically, ants will choose a path according to a certain probability based on the pheromones left behind, and leave new pheromones on the path they pass through. Subsequent ants will be influenced by the accumulated, diffused and volatilized pheromones, thereby deciding the path selection. The higher the pheromone concentration, the greater the probability of subsequent ants choosing this path, and ultimately forming the optimal path found by the ant colony. The key behaviors of the ant colony algorithm include state transition probability judgment and pheromone update.

[0054] Before using the ant colony algorithm (ACO) for inspection path planning, the optimization space needs to be divided into grids. The commonly used grid method uniformly divides along the coordinate axis direction according to a fixed size. When the vertex of a certain grid touches an obstacle, the grid will be marked as a forbidden grid, and the ant colony will not choose this grid in path selection. This grid method is suitable for two-dimensional and three-dimensional spaces, and is an equal division of the optimization space. The grid size directly determines the size and number of grids, thereby affecting the path planning accuracy and calculation speed of the ant colony algorithm; therefore, a reasonable consideration needs to be made between balancing the grid size and the algorithm efficiency.

[0055] As a preferred embodiment of the present embodiment, the steps of adaptively dividing the power unmanned aerial vehicle inspection three-dimensional environment model are as follows:

[0056] Set the latitude, and equally divide the power unmanned aerial vehicle inspection three-dimensional environment model space into multiple slices according to the slice latitude, and each slice is a grid;

[0057] When the vertex of the grid touches an obstacle, the grid adaptively adjusts the size in the direction of the vertex, as shown in the following formula:

[0058]

[0059] wherein: represents the size length of the grid in the th adjustment; represents the initial length of the grid; represents the adjustment step.

[0060] The comparison of the traditional grid method and the adaptive grid method in the three-dimensional space division model is shown in Figure 2 and Figure 3 The adaptive grid method can increase the grid density in the area near the obstacle without changing the global grid size, thereby improving the accuracy of grid division and helping to optimize the path optimization accuracy.

[0061] The traditional ant colony algorithm is prone to excessive concentration of pheromone in the later iteration, which leads to the algorithm falling into a local optimal solution and being difficult to get out of the dilemma. In order to enhance the optimization ability of the algorithm in the later iteration, as a preferred embodiment of the present embodiment, the dynamic transfer probability calculation model is specifically as follows:

[0062]

[0063]

[0064] Wherein: represents an ant individual from node to node The probability of moving to node represents the pheromone concentration of edge at time t; represents the heuristic function of edge at time t; represents the total number of selectable next nodes of ant individual at node ; represents the selected next node of ant individual at node ; represents the pheromone concentration of edge at time t; represents the heuristic function of edge at time t; represents the iteration factor threshold value; represents the iteration factor; represents the current iteration number; represents the maximum iteration number; by introducing the iteration factor , the way of path selection of the ant is dynamically adjusted with the change of the iteration number, in the early iteration, the value is small, the algorithm is more inclined to the traditional probability transfer function, which can quickly find the obviously superior path, and at the same time, the good convergence of the ant colony algorithm is reserved; with the increase of the iteration number, the value increases, the path selection of the ant colony gradually tilts to the random mode, which weakens the influence of excessive accumulation of pheromone and enhances the ability of the algorithm to get out of the local optimal solution.

[0065] The traditional ant colony algorithm divides the map by using a grid division method, and the top point of each grid is used as the path endpoint that can be selected by the ant, which results in low accuracy of path optimization. As a preferred embodiment of the present embodiment, the variable step search behavior is specifically a variable step random search in a grid formed by the next node and the current node before the ant individual moves to the next node, and is specifically as follows:

[0066]

[0067]

[0068] wherein: represents the next node coordinate calculated by the variable step random search; represents the candidate next node coordinate calculated by the dynamic transition probability calculation model; represents the current node coordinate; represents a random number; represents a step factor; represents a variable step factor.

[0069] In nature, when a worker ant finds food, it will pass the position of the food to other ants to gather an ant colony to carry the food together. By introducing this behavior into the ant colony algorithm, the ant individual of the optimal path in each generation of ants can be regarded as a worker ant that finds food, and other ant individuals are gathered to approach, while the worker ant continues to search for food. In this way, the search ability and convergence speed of the algorithm can be effectively improved.

[0070] As a preferred embodiment of the present embodiment, the ant individual of the optimal path in each generation of ants is regarded as a worker ant that finds food, and other ant individuals are gathered to approach, and the formula of the gathering ant behavior is as follows:

[0071]

[0072] wherein: the new position of the gathered ant individual ; represents the current position of the ant individual ; represents the position of the ant individual of the optimal path.

[0073] As a preferred embodiment of the present embodiment, the formula of the optimal ant individual search behavior is as follows:

[0074]

[0075] wherein: represents the position of the ant individual of the optimal path obtained by the next search; represents an adjustment coefficient.

[0076] Embodiment Two:

[0077] The application discloses a power unmanned aerial vehicle (UAV) three-dimensional path planning system based on an improved ant colony algorithm, which comprises a grid division module and an ant colony path planning module.

[0078] The grid division module is used for generating a power UAV inspection three-dimensional environment model and performing adaptive grid division on the power UAV inspection three-dimensional environment model.

[0079] The ant colony path planning module is used for initializing the ant colony to search a path in the power UAV inspection three-dimensional environment model after grid division, setting a starting point and an ending point of the UAV as a starting point and an ending point of the ant colony, selecting a next node by each ant individual in the ant colony according to a dynamic transition probability calculation model, determining an actually moved next node by the ant individual through a variable step search behavior, recording path information from the starting point to the ending point of each ant individual, screening an optimal ant individual in this iteration when all the ant individuals reach the ending point, and performing a worker ant foraging behavior to update pheromone concentration of each path in the space; and the iteration is repeated until a preset iteration number is reached, and a path with the highest pheromone concentration is selected as a final path of the UAV.

[0080] The system implements the method in embodiment one, and details are not repeated here.

[0081] Embodiment three

[0082] The embodiment provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the method according to any one of the embodiments of the application when executing the program.

[0083] Embodiment four

[0084] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method according to any one of the embodiments of the application.

[0085] In the embodiments of the application, "at least one" means one or more, and "multiple" means two or more than two. "And / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which means that A exists alone, A and B exist together, and B exists alone. Wherein A and B can be singular or plural. The character " / " generally represents that the associated objects before and after it are in an "or" relationship. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can mean: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b and c can be single or multiple.

[0086] Those skilled in the art can clearly understand that the units and algorithm steps described in the embodiments disclosed herein can be realized by electronic hardware, computer software and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0088] In several embodiments provided in the present application, any function realized in the form of a software function unit and sold or used as an independent product can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory; hereinafter referred to as: ROM), a random access memory (Random Access Memory; hereinafter referred to as: RAM), a magnetic disk or an optical disk and various program code storage media.

[0089] The above is only the embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation based on the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm, characterized in that, The method comprises the following steps: generating a power unmanned aerial vehicle (UAV) inspection three-dimensional environment model and performing adaptive grid division on the power UAV inspection three-dimensional environment model; initializing an ant colony to search for a path in the power UAV inspection three-dimensional environment model after grid division, and setting a starting point and an ending point of the UAV as starting and ending points of the ant colony; each ant individual in the ant colony selects a next node according to a dynamic transition probability calculation model, determines an actually moved next node through a variable step search behavior, and records path information from the starting point to the ending point of each ant individual; after all ant individuals arrive at the ending point, the optimal ant individual in this iteration is screened and a worker ant foraging behavior is performed, and pheromone concentrations of each path in the space are updated; the iteration is repeated until a preset iteration number is reached, and a path with the highest pheromone concentration is selected as a final path of the UAV; the dynamic transition probability calculation model is specifically as follows: wherein: represents an ant individual from node moves to node with probability; represents the pheromone concentration of edge at time instant represents the heuristic function of edge at time instant represents an ant individual at node the total number of selectable next nodes; represents an ant individual at node the selected next node; represents the pheromone concentration of edge at time instant represents the heuristic function of edge at time instant represents the iteration factor threshold value; represents the iteration factor; represents the current iteration number; represents the maximum iteration number; represents the pheromone importance factor; represents the expected heuristic factor.

2. The substation unmanned aerial vehicle three-dimensional path planning method based on the improved ant colony algorithm according to claim 1, characterized in that, the step of performing adaptive grid division on the power UAV inspection three-dimensional environment model comprises the following steps: a latitude is set, and the power UAV inspection three-dimensional environment model space is equally divided into multiple slices according to the slice latitude, and each slice is a grid; when a grid vertex touches an obstacle, the grid adaptively adjusts the size of the direction in which the vertex is located, and is specifically as follows: wherein: represents the size length of the grid at the adjustment; represents the initial length of the grid; represents the adjustment step.

3. The substation unmanned aerial vehicle three-dimensional path planning method based on the improved ant colony algorithm according to claim 1, characterized in that, the variable step search behavior is specifically that, before the ant individual moves to the next node, a variable step random search is performed in a grid formed by the next node and a current node, and is specifically as follows: wherein: represents a next node coordinate of a variable step size random search computation; represents a candidate next node coordinate of a dynamic transition probability computation model computation; represents a current node coordinate; represents a random number; represents a step size factor; represents a variable step size factor.

4. The substation unmanned aerial vehicle three-dimensional path planning method based on the improved ant colony algorithm according to claim 3, characterized in that, the optimal path ant individual in each generation of the ant colony is regarded as a worker ant that finds food, and other ant individuals are called to approach, and a call ant behavior formula is as follows: wherein: the new position of the called ant individual ; denotes the current position of the ant individual ; denotes the position of the ant individual on the optimal path.

5. The substation unmanned aerial vehicle three-dimensional path planning method based on the improved ant colony algorithm according to claim 4, characterized in that, an optimal ant individual search behavior formula is as follows: wherein: represents the position of the ant individual that represents the optimal path found by the next search; represents an adjustment coefficient.

6. A substation unmanned aerial vehicle three-dimensional path planning system based on an improved ant colony algorithm, used for the method of any one of claims 1 to 5, characterized in that, The method comprises the following steps: The method comprises the following steps: The method comprises the following steps:

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 5 when executing the program.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1 to 5.

Images