A Double-Layer Optimized UAV Path Planning Method and Related Equipment

Abstract

The present application relates to the technical field of UAV path planning, and provides a method for double-layer optimized UAV path planning and related devices. The method includes: obtaining the positions of the base station of the target UAV and the positions of a plurality of inspection target points; constructing a path optimization function of the target UAV based on the position of the base station and the positions of all inspection target points; using a genetic algorithm and a tabu search algorithm to solve the path optimization function to obtain an optimal path planning scheme for the target UAV; and controlling the target UAV to inspect all inspection target points according to the optimal path planning scheme. The method of the present application can improve the accuracy of UAV path planning.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned aerial vehicle path planning, and in particular to a double-layer optimized unmanned aerial vehicle path planning method and related equipment. Background Art

[0002] With the rapid development of wireless communication, sensor technology and UAV (Unmanned Aerial Vehicle) systems, UAVs are playing an increasingly important role in various applications, especially in the field of inspection. With their unique mobility and flexibility, UAVs have become an indispensable and important tool, playing an irreplaceable role in key tasks such as real-time monitoring, data collection and emergency response. When actually performing these tasks, in order to efficiently complete image acquisition, UAVs must carefully design flight paths based on diverse inspection needs, and the scientificity and rationality of path planning are directly related to the quality and efficiency of the entire inspection task.

[0003] In recent years, the academic community has shown a booming trend in the research of UAV path planning and task scheduling. Many scholars have devoted themselves to it and achieved a series of remarkable results. In the existing research, a considerable part of the literature focuses on the path planning problem of a single task. For example, some are committed to exploring the shortest path to reduce the flight distance, some focus on energy optimization to extend the endurance of the UAV, and some pursue the minimization of flight time to improve the timeliness of task execution. These studies provide valuable ideas and methods for UAV path planning from different perspectives, but there are still certain limitations when dealing with complex and changeable practical application scenarios.

[0004] Aiming at the core problem of UAV path planning, many algorithms have been proposed and widely used in various scenarios. Common path planning algorithms include classic heuristic search algorithms, such as variable step length in UAV path planning. Algorithms, such as the classic graph algorithm Dijkstra's algorithm, perform well in simple scenarios. However, when dealing with path planning problems under complex tasks and multiple constraints, they often suffer from large computational amounts and low solution efficiency. To overcome this deficiency, researchers have started to use evolutionary algorithms and swarm intelligence algorithms to solve the UAV path planning problem. As a classic optimization method, the genetic algorithm is widely used in UAV path planning, especially in multi-objective optimization and complex constraint problems. The genetic algorithm has global search capabilities and can effectively avoid local optimal solutions, but it is prone to getting stuck in a high computational complexity dilemma in large-scale problems. In addition, tabu search (TS) as a local search method is often used in optimization problems, especially suitable for large-scale combinatorial optimization problems. Tabu search can break through the limitation of local optimality by continuously adjusting the neighborhood structure of the solution, thereby searching for the global optimal solution. In recent years, the combination of tabu search and the genetic algorithm has become a popular research direction. Integrating the advantages of both can effectively improve the efficiency and accuracy of path planning. In addition, natural heuristic algorithms such as particle swarm optimization (PSO) and ant colony optimization (ACO) have also been applied in UAV path planning. These algorithms can find effective paths in complex environments by simulating the behaviors of organisms in nature and have strong robustness.

[0005] In actual inspection tasks, the requirements for image acquisition accuracy of task objectives are not single, but show obvious hierarchical differences, that is, there are high-value targets and low-value targets, and different types of targets have different requirements for image acquisition accuracy. According to the logical judgment of the actual situation, high-precision image acquisition data can meet the requirements of low-precision acquisition, but the reverse is not possible. This inconsistency in the requirements for image acquisition accuracy of task objectives undoubtedly greatly increases the complexity and challenge of path planning, resulting in low accuracy of UAV path planning. Summary of the Invention

[0006] This application provides a double-layer optimized UAV path planning method and related devices, which can solve the problem of low accuracy of UAV path planning.

[0007] In a first aspect, an embodiment of this application provides a double-layer optimized UAV path planning method. The UAV path planning method includes:

[0008] Obtain the position of the base station of the target UAV and the positions of multiple inspection target points; the inspection target points are either high-precision inspection target points or low-precision inspection target points;

[0009] Construct a path optimization function for the target UAV based on the positions of the base station and all inspection target points; the path optimization function is used to describe the total inspection time, total battery replacement time, and total flight time required for the target UAV to inspect all inspection target points.

[0010] Use the genetic algorithm and tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme for the target UAV; the individuals in the genetic algorithm are the path planning schemes of the target UAV, and the path planning scheme includes the inspection path of each flight of the target UAV and the inspection accuracy.

[0011] Control the target UAV to inspect all inspection target points according to the optimal path planning scheme.

[0012] Optionally, the inspection target points are high-precision inspection target points or low-precision inspection target points, and the path optimization function is:

[0013] ;

[0014] Among them, represents the final total time required for the target UAV to complete the inspection and return to the base station, represents the total flight time of the target UAV to complete all flight paths, represents the total inspection time for the target UAV to inspect all inspection target points, represents the total battery replacement time for the target UAV to replace the battery at the base station:

[0015] ;

[0016] ;

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] Among them, represents the total number of UAV flights, represents the total number of inspection target points, represents the th flight of the target UAV flying from the base station to the th inspection target point, represents the th flight of the target UAV returning from the th inspection target point to the base station, When the th inspection target point is a base station, represents the distance between the position of the th inspection target point and the position of the th inspection target point, represents the flight speed of the target UAV, represents the inspection accuracy of the th inspection target point in the th voyage, represents low accuracy, represents high accuracy, represents the inspection accuracy of the th inspection target point in the th voyage, represents the time spent on high-precision inspection, represents the time spent on low-precision inspection, represents the time spent on battery replacement, represents whether the th voyage requires battery replacement, represents that battery replacement is required, represents that battery replacement is not required, represents the set of inspection target points for actual low-precision inspection, represents the set of inspection target points for actual high-precision inspection, represents the set of low-precision inspection target points, represents the set of high-precision inspection target points, represents the maximum flight time of the target UAV for a single voyage, represents a constraint.

[0022] Optionally, use the genetic algorithm and the tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme of the target UAV, including:

[0023] Generate multiple individuals in the genetic algorithm;

[0024] Increment the iteration count by 1 and determine whether the iteration count is greater than or equal to the maximum iteration count;

[0025] If so, select the optimal individual from all individuals according to the path optimization function, and use the path planning scheme described by the optimal individual as the optimal path planning scheme;

[0026] Otherwise, update all individuals using the genetic algorithm to obtain multiple updated individuals, and use the tabu search algorithm to perform an optimization search on each updated individual to obtain the relatively optimal individual corresponding to each updated individual, and use the multiple relatively optimal individuals as multiple individuals, and return to the step of incrementing the iteration count by 1 and determining whether the iteration count is greater than or equal to the maximum iteration count.

[0027] Optionally, according to the path optimization function, select the optimal individual from all individuals, including:

[0028] For each individual respectively, substitute the path planning scheme described by the individual into the path optimization function, and calculate the corresponding final total time of the individual;

[0029] Take the individual corresponding to the final total time with the smallest value as the optimal individual.

[0030] Optionally, use the genetic algorithm to update all individuals to obtain multiple updated individuals, including:

[0031] Calculate the fitness of each individual according to the path optimization function;

[0032] Select multiple parent individuals from all individuals according to all fitnesses;

[0033] Perform crossover operations on all parent individuals to obtain multiple offspring individuals, and perform mutation operations on all offspring individuals to obtain multiple mutated offspring individuals;

[0034] Calculate the fitness of each mutated offspring individual according to the path optimization function, and sort all mutated offspring individuals in descending order of fitness, and select the first multiple mutated offspring individuals in the sorting result as updated individuals.

[0035] Optionally, use the tabu search algorithm to perform an optimization search on each updated individual to obtain a better individual corresponding to each updated individual, including:

[0036] For each updated individual respectively, perform the following steps:

[0037] Judge whether there is a voyage that mixes low-precision inspection target points and high-precision inspection target points in the path planning scheme described by the updated individual;

[0038] If so, use the tabu search algorithm to perform a neighborhood search on the updated individual to obtain a better individual corresponding to the updated individual;

[0039] Otherwise, take the updated individual as the better individual corresponding to itself.

[0040] Optionally, use the tabu search algorithm to perform a neighborhood search on the updated individual to obtain a better individual corresponding to the updated individual, including:

[0041] Initialize the tabu list;

[0042] Select a target neighborhood search operation from multiple neighborhood search operations;

[0043] Perform neighborhood search on the updated individual using the target neighborhood search operation to obtain a candidate individual of the updated individual, and add the target neighborhood search operation to the taboo list;

[0044] When the taboo list does not include all neighborhood search operations, select a target neighborhood search operation from all other neighborhood search operations that have not been added to the taboo list, and return the step of performing neighborhood search on the updated individual using the target neighborhood search operation to obtain a candidate individual of the updated individual, and adding the target neighborhood search operation to the taboo list;

[0045] When the taboo list includes all neighborhood search operations, calculate the fitness of each candidate individual according to the path optimization function, and use the candidate individual with the maximum fitness value as the better individual of the updated individual.

[0046] Optionally, multiple neighborhood search operations include:

[0047] The first neighborhood search operation: In the voyage that mixes low-precision inspection target points and high-precision inspection target points, delete all high-precision cruise target points from the voyage;

[0048] The second neighborhood search operation: In the voyage that mixes low-precision inspection target points and high-precision inspection target points, delete all low-precision cruise target points from the voyage;

[0049] The third neighborhood search operation: Perform neighborhood transformation on the voyage that mixes low-precision inspection target points and high-precision inspection target points to obtain another voyage that mixes low-precision inspection target points and high-precision inspection target points.

[0050] In a second aspect, an embodiment of the present application provides a double-layer optimized UAV path planning device, including:

[0051] An acquisition module, configured to acquire the position of the base station of the target UAV and the positions of multiple inspection target points; the inspection target points are one of high-precision inspection target points or low-precision inspection target points;

[0052] A construction module, configured to construct a path optimization function of the target UAV based on the position of the base station and the positions of all inspection target points; the path optimization function is used to describe the total inspection time, total battery replacement time, and total flight time required for the target UAV to inspect all inspection target points;

[0053] A solution module, configured to solve the path optimization function using a genetic algorithm and a taboo search algorithm to obtain an optimal path planning scheme for the target UAV; the individual in the genetic algorithm is the path planning scheme of the target UAV, and the path planning scheme includes the inspection path of each voyage of the target UAV and the inspection accuracy;

[0054] The patrol module is used to control the target UAV to patrol all the patrol target points according to the optimal path planning scheme.

[0055] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned double-layer optimized UAV path planning method is implemented.

[0056] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned double-layer optimized UAV path planning method is implemented.

[0057] The above solution of the present application has the following beneficial effects:

[0058] In some embodiments of the present application, by obtaining the base station position of the target UAV and the positions of multiple patrol target points, then constructing a path optimization function of the target UAV based on the base station position and the positions of all patrol target points, and then using the genetic algorithm and the tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme of the target UAV, and finally controlling the target UAV to patrol all the patrol target points according to the optimal path planning scheme. Among them, constructing the path optimization function can represent the final total time required for the patrol. Combining the genetic algorithm and the tabu search algorithm can effectively overcome the limitations of the two algorithms respectively, improve the global search ability and local optimization performance of the path planning, and have good adaptability. By solving the path optimization function in this way, the final total time required for the patrol can be considered, the accuracy and execution efficiency of the path planning scheme can be improved, and the accuracy of the UAV path planning can be effectively improved.

[0059] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. Description of the Drawings

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0061] Figure 1 It is a flowchart of the double-layer optimized UAV path planning method provided by an embodiment of the present application;

[0062] Figure 2 It is a schematic diagram of an individual in the genetic algorithm provided by an embodiment of the present application;

[0063] Figure 3 Schematic diagram of the order crossover operation provided by an embodiment of the present application;

[0064] Figure 4 Execution schematic diagram of the 3-Opt algorithm provided by an embodiment of the present application;

[0065] Figure 5 Distribution schematic diagram of multiple inspection target points provided by an embodiment of the present application;

[0066] Figure 6 Iterative convergence curve schematic diagram provided by an embodiment of the present application;

[0067] Figure 7 Schematic diagram of the optimal path planning scheme of GA-VRP provided by an embodiment of the present application;

[0068] Figure 8 Schematic diagram of the optimal path planning scheme of GA-VRPHD provided by an embodiment of the present application;

[0069] Figure 9 Schematic diagram of the optimal path planning scheme of the method of the present application provided by an embodiment of the present application;

[0070] Figure 10 Schematic diagram of the structure of the double-layer optimized UAV path planning device provided by an embodiment of the present application;

[0071] Figure 11 Schematic diagram of the structure of the terminal device provided by an embodiment of the present application. Detailed implementation manners

[0072] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0073] It should be understood that when used in the specification and claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0074] It should also be understood that the term "and / or" as used in the specification and claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0075] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0076] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0077] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0078] Aiming at the problem of low accuracy in the existing UAV path planning, the embodiment of this application provides a double-layer optimized UAV path planning method. This UAV path planning method obtains the base station position of the target UAV and the positions of multiple inspection target points, then constructs a path optimization function for the target UAV based on the base station position and the positions of all inspection target points, and then uses the genetic algorithm and the tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme for the target UAV. Finally, according to the optimal path planning scheme, the target UAV is controlled to inspect all inspection target points. Among them, constructing the path optimization function can represent the final total time required for inspection. Combining the genetic algorithm and the tabu search algorithm can effectively overcome the limitations of the two algorithms respectively, improve the global search ability and local optimization performance of path planning, and have good adaptability. By solving the path optimization function in this way, the final total time required for inspection can be considered, the accuracy and execution efficiency of the path planning scheme can be improved, and the accuracy of UAV path planning is effectively improved.

[0079] Next, an exemplary description is given of the double-layer optimized UAV path planning method provided by this application.

[0080] As Figure 1As shown in the figure, the double-layer optimized UAV path planning method provided by this application includes the following steps:

[0081] Step 11: Obtain the base station position of the target UAV and the positions of multiple inspection target points.

[0082] The above inspection target points are the targets that need to be inspected by the UAV. Exemplarily, the above inspection target points can be railway tracks that need to be inspected, etc.

[0083] The inspection target points are high-precision inspection target points or low-precision inspection target points. Multiple inspection target points can include high-precision inspection target points and low-precision inspection target points, or can only include high-precision inspection target points, or can only include low-precision inspection target points. The inspection precision required for high-precision inspection target points is higher than that of low-precision inspection target points. For example, when using a UAV to collect images of inspection target points, the precision of the images of high-precision inspection target points is higher than that of the images of low-precision inspection target points.

[0084] In some embodiments of this application, the base station position of the target UAV and the positions of multiple inspection target points can be obtained through a global positioning system, etc.

[0085] It should be noted that the inspection precision of the UAV is corresponding to the flight altitude of the UAV (for example, when collecting high-precision images, the flight altitude of the UAV is lower than that when collecting low-precision images). Therefore, in one UAV inspection flight, the UAV can only work with the same inspection precision for all targets. And according to actual needs, high-precision inspection can meet the requirements of low-precision inspection target points, but low-precision inspection cannot meet the requirements of high-precision inspection target points, and the time required for the UAV to inspect high-precision inspection target points is greater than the time required for the UAV to inspect low-precision inspection target points.

[0086] Step 12: Construct a path optimization function for the target UAV based on the base station position and the positions of all inspection target points.

[0087] The above path optimization function is used to describe the total inspection time, total battery replacement time, and total flight time required for the target UAV to inspect all inspection target points.

[0088] The total inspection time refers to the total time spent by the target UAV to inspect each inspection target point after reaching it.

[0089] The total battery replacement time refers to the total time spent on replacing the battery during the process of the target UAV inspecting all inspection target points.

[0090] The total flight time refers to the total time spent on flying during the process of the target UAV inspecting all inspection target points.

[0091] The above path optimization function is as follows:

[0092] ;

[0093] Among them, represents the final total time required for the target UAV to complete the inspection and return to the base station, represents the total flight time of the target UAV to complete all flight paths, represents the total inspection time for the target UAV to inspect all inspection target points, represents the total battery replacement time for the target UAV to replace the battery at the base station:

[0094] ;

[0095] ;

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] Among them, represents the total number of UAV flight missions, represents the total number of inspection target points, represents the th flight mission of the target UAV flying from the base station to the th inspection target point, represents the th flight mission of the target UAV returning from the th inspection target point to the base station, means that all flights of the aircraft have to depart from the base station and land at the base station point. When , the th inspection target point is the base station, represents the th inspection target point and the th inspection target point, represents the flight speed of the target UAV, represents the th flight mission and the th inspection accuracy of the represents low accuracy, represents high accuracy, represents the th flight mission and the The inspection accuracy of each inspection target point, Indicates the time spent on high-precision inspection, Indicates the time spent on low-precision inspection, Indicates the time spent on replacing the battery, Indicates the Whether the battery needs to be replaced for the Indicates that the battery needs to be replaced, Indicates that the battery does not need to be replaced, Indicates the set of inspection target points for which low-precision inspections are actually carried out, Indicates the set of inspection target points for which high-precision inspections are actually carried out, Indicates the set of low-precision inspection target points, Indicates the set of high-precision inspection target points, Indicates the maximum flight time of the target UAV for a single voyage, Indicates a constraint.

[0101] It should be noted that the distance between the positions of two inspection target points can be the Euclidean distance, and the expression of the Euclidean distance is:

[0102] ;

[0103] Among them, Indicates the Euclidean distance between the position of the th inspection target point and the position of the th inspection target point, Indicates the abscissa position of the th inspection target point, Indicates the abscissa position of the th inspection target point, Indicates the ordinate position of the th inspection target point, Indicates the ordinate position of the

[0104] Step 13: Use the genetic algorithm and the tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme for the target UAV.

[0105] The individual in the above genetic algorithm is the path planning scheme of the target UAV, and the path planning scheme includes the inspection path of each voyage of the target UAV and the inspection accuracy.

[0106] In some embodiments of the present application, the steps of using the genetic algorithm and the tabu search algorithm to solve the path optimization function to obtain the optimal path planning scheme for the target UAV include:

[0107] Step 1: Generate multiple individuals in the genetic algorithm.

[0108] Specifically, the above individuals include three coding structures:

[0109] 1. Target point visit order coding

[0110] The target point visit order coding represents the visit order of the cruise targets, and this coding structure can directly represent the sequence of the cruise targets.

[0111] 2. Voyage division coding

[0112] It is used to segment the target point visit order to determine which cruise targets should be assigned to a certain voyage and ensure that the cruise targets of each voyage do not exceed the battery capacity limit of the UAV. This step is a key link in the UAV mission planning, aiming to optimize the flight path and mission allocation of the UAV to improve efficiency and avoid energy exhaustion.

[0113] 3. Precision allocation coding

[0114] This coding determines which precision is used for image acquisition for each voyage obtained from the voyage segmentation coding. The voyage precision coding is directly related to the target image acquisition time in the total time. In this coding, the division of high-precision voyages and low-precision voyages can be distinguished by setting different marks, where 0 represents low precision and 1 represents high precision.

[0115] Combining the above three coding structures to obtain the individuals in the genetic algorithm can transform the UAV inspection path problem into an individual representation form suitable for solving by the genetic algorithm.

[0116] Exemplarily, the individual and the decoding of the individual are as Figure 2 shown, where the individual is as Figure 2As shown in a, it includes the target point access order encoding, voyage division encoding, and precision allocation encoding. The target point access order encoding is used to describe the access order of all inspection target points. The voyage division encoding is used to describe the voyage division of the access order of all inspection target points (after dividing the target point access order encoding according to the voyage division encoding and inserting the base station encoding, the number of voyages and the inspection path of each voyage are obtained). The precision allocation encoding is used to describe the precision of each voyage inspection. The target point access order encoding 146235 indicates that the inspection order of the target UAV should follow the encoding of 6 inspection target points in the order of 146235. The voyage division encoding 24 indicates that voyages are divided at the 2nd inspected target point and the 4th inspected target point respectively, that is, the 2nd inspected target point and the 4th inspected target point are respectively used as the last inspection target points of the corresponding voyages. The precision allocation encoding 001 indicates that the inspection precisions of the three voyages obtained by dividing according to the voyage division encoding are low precision, low precision, and high precision respectively. The process of decoding this individual is as Figure 2 As shown in b, divide the target point access order encoding according to the voyage division encoding to obtain the division result: 14, 62, 35. Insert the base station number 0 at the head and tail, and read the precision allocation encoding to obtain three voyages, namely, low-precision voyage 1: 0140 (indicating that the inspection path of this voyage is base station - cruise target point 1 - cruise target point 4 - base station), low-precision voyage 2: 0620 (indicating that the inspection path of this voyage is base station - cruise target point 6 - cruise target point 2 - base station), and high-precision voyage 1: 0350 (indicating that the inspection path of this voyage is base station - cruise target point 3 - cruise target point 5 - base station).

[0117] In the second step, increment the iteration count by 1 and determine whether the iteration count is greater than or equal to the maximum iteration count.

[0118] The initial value of the above iteration count is 0.

[0119] If so, select the optimal individual from all individuals according to the path optimization function, and use the path planning scheme described by the optimal individual as the optimal path planning scheme.

[0120] Specifically, for each individual respectively, substitute the path planning scheme described by the individual into the path optimization function to calculate the corresponding final total time of the individual; take the individual corresponding to the smallest final total time as the optimal individual.

[0121] Otherwise, update all individuals using the genetic algorithm to obtain multiple updated individuals, and perform an optimization search on each updated individual using the tabu search algorithm to obtain the relatively optimal individual corresponding to each updated individual, and use the multiple relatively optimal individuals as multiple individuals, and return to the step of incrementing the iteration count by 1 and determining whether the iteration count is greater than or equal to the maximum iteration count.

[0122] It should be noted that the steps of updating all individuals by using the genetic algorithm to obtain multiple updated individuals include:

[0123] First, calculate the fitness of each individual according to the path optimization function.

[0124] Specifically, substitute the path planning scheme described by each individual into the path optimization function, calculate the final total time corresponding to the individual, and use the final total time as the fitness of the corresponding individual.

[0125] Then, select multiple parent individuals from all individuals according to all fitness values.

[0126] Exemplarily, multiple parent individuals can be selected from all individuals according to all fitness values according to the selection operation in the genetic algorithm (such as ranking selection, roulette wheel selection, etc.).

[0127] Then, perform crossover operations on all parent individuals to obtain multiple offspring individuals, and perform mutation operations on all offspring individuals to obtain multiple mutant offspring individuals.

[0128] Specifically, order crossover operations can be used to perform crossover operations on all parent individuals to obtain multiple offspring individuals. Site mutation, swap mutation, Gaussian mutation, etc. can be used to perform mutation operations on each offspring individual to obtain the corresponding mutant offspring individual for each offspring individual.

[0129] Exemplarily, as Figure 3 shown, based on the access order encoding of the target points in two parent individuals (parent 1 and parent 2), use the order crossover operation to obtain the access order encoding of the target points in offspring 1. First, randomly select a starting point 2 and an ending point 4 from parent 1. Extract the sequence segment from the starting point to the ending point to generate the basis of offspring 1. Delete the nodes in parent 2 that are repeated with the selected sequence, and fill the remaining node order in parent 2 into the blanks in offspring 1 to generate the complete encoding of offspring 1. The encoding of offspring 2 can be generated in the same way.

[0130] Finally, calculate the fitness of each mutant offspring individual according to the path optimization function, sort all mutant offspring individuals in descending order of fitness, and select the top multiple mutant offspring individuals in the sorting result as the updated individuals.

[0131] Specifically, substitute the path planning scheme described by each mutant offspring individual into the path optimization function, calculate the final total time corresponding to the mutant offspring individual, and use the final total time as the fitness of the corresponding mutant offspring individual.

[0132] It should be noted that the steps of using the tabu search algorithm to optimize and search each updated individual to obtain the relatively optimal individual corresponding to each updated individual include:

[0133] For each updated individual, the following steps are performed:

[0134] Determine whether there is a voyage that mixes low-precision inspection target points and high-precision inspection target points in the path planning scheme described by the updated individual.

[0135] If so, use the tabu search algorithm to perform a neighborhood search on the updated individual to obtain the relatively optimal individual corresponding to the updated individual.

[0136] Specifically, initialize the tabu list, then select a target neighborhood search operation from multiple neighborhood search operations (the target neighborhood search operation can be randomly selected), and then use the target neighborhood search operation to perform a neighborhood search on the updated individual to obtain a candidate individual of the updated individual, and add the target neighborhood search operation to the tabu list;

[0137] When the tabu list does not include all neighborhood search operations (i.e., the multiple neighborhood search operations above), select a target neighborhood search operation from all other neighborhood search operations that have not been added to the tabu list (the target neighborhood search operation can be randomly selected), and return the step of using the target neighborhood search operation to perform a neighborhood search on the updated individual to obtain a candidate individual of the updated individual, and adding the target neighborhood search operation to the tabu list;

[0138] When the tabu list includes all neighborhood search operations, calculate the fitness of each candidate individual according to the path optimization function (substitute the path planning scheme described by the candidate individual into the path optimization function to obtain the final total time corresponding to the candidate individual, and use this final total time as the fitness of the candidate individual), and use the candidate individual with the largest fitness value as the relatively optimal individual of the updated individual.

[0139] Otherwise (that is, there is no voyage that mixes low-precision inspection target points and high-precision inspection target points in the path planning scheme described by the updated individual), use the updated individual as the relatively optimal individual corresponding to itself.

[0140] It should be noted that the above multiple neighborhood search operations include:

[0141] The first neighborhood search operation: delete all high-precision cruise target points from the voyage that mixes low-precision inspection target points and high-precision inspection target points;

[0142] The second neighborhood search operation: delete all low-precision cruise target points from the voyage that mixes low-precision inspection target points and high-precision inspection target points;

[0143] Third neighborhood search operation: Perform neighborhood transformation on the voyages of the mixed low-precision inspection target points and high-precision inspection target points to obtain another voyage of the mixed low-precision inspection target points and high-precision inspection target points. That is, by adjusting the access order of each inspection target point within the voyage to optimize the overall efficiency or cost, it can be achieved through the 3-Opt heuristic algorithm (3-Opt, 3-Opt Heuristic Algorithm).

[0144] Exemplarily, the execution of the 3-Opt algorithm is as Figure 4 shown. For six inspection target points ABCDEF, starting from the initial roadbed map shown in Figure 4(a), randomly delete three of its edges, and then randomly combine the remaining edges. For a determined case of deleting three edges, there are 8 possible solutions, as Figure 4 (b) to Figure 4 (i) shown. The dashed lines are the randomly generated edges after deleting the edges, Figure 4 (b) is the first possible cruise path, Figure 4 (c) is the second possible cruise path, Figure 4 (d) is the third possible cruise path, Figure 4 (e) is the fourth possible cruise path, Figure 4 (f) is the fifth possible cruise path, Figure 4 (g) is the sixth possible cruise path, Figure 4 (h) is the seventh possible cruise path, Figure 4 (i) is the eighth possible cruise path.

[0145] Step 14: Control the target UAV to inspect all inspection target points according to the optimal path planning scheme.

[0146] Specifically, through the control system of the target UAV, the UAV can execute each voyage in sequence according to the inspection path and inspection accuracy of each voyage in the optimal path planning scheme to complete the inspection of all inspection target points.

[0147] It is worth mentioning that constructing a path optimization function can represent the total time required for inspection. Combining the genetic algorithm and the tabu search algorithm can effectively overcome the limitations of the two algorithms respectively, improve the global search ability and local optimization performance of path planning, and have good adaptability. By solving the path optimization function in this way, the total time required for inspection can be considered, the accuracy and execution efficiency of the path planning scheme can be improved, and the accuracy of UAV path planning can be effectively improved.

[0148] The following uses a specific example to exemplarily illustrate the method of the present application.

[0149] The algorithm of this application and other basic algorithms are simulated and compared using the Matlab 2024b simulation software. The simulation area is 100 km 100 km, where the location of the base station from which the UAV takes off is at (50, 50). The distribution of 20 target points for image acquisition (i.e., inspection target points) is shown in Figure 5 , among which 4 target points are high-precision acquisition targets ( Figure 5 the pentagon points in Figure 5 ), and 16 target points are low-precision acquisition targets ( Figure 5 the square points in

[0150] Table 1

[0151] ;

[0152] Table 2

[0153] ;

[0154] There are two comparison algorithms for experimental simulation: one is to directly divide the targets into two tasks of high-precision vehicle routing problem (VRP, Vehicle Routing Problem) and low-precision VRP according to the initial image acquisition accuracy requirements. This algorithm also uses the genetic algorithm to plan two independent VRP problems, and the algorithm is called the genetic algorithm for vehicle routing problem (GA-VRP, Genetic Algorithm for Vehicle Routing Problem); the other is to model the problem into a UAV path planning including hierarchical optimization and use the genetic algorithm without tabu search for solution, which is the genetic algorithm for vehicle routing problem with heterogeneous demands (GA-VRPHD, Genetic Algorithm for Vehicle RoutingProblem with Heterogeneous Demands).

[0155] The iterative convergence curves and local enlarged views of the three algorithms are as shown in Figure 6 . Figure 6 In

[0156] As can be seen from the iterative convergence curve, GA-TS achieved the best result, taking 16.2766 hours. The result is better than that of GA-VRP and GA-VRPHD. Moreover, by observing the local enlarged curve, it can be found that the convergence speed of GA-TS is also the fastest. This is in line with expectations. In the two-layer optimization, using the tabu search algorithm can better perform low-precision and high-precision voyage divisions, thus better jumping out of the local optimal solution. By comparing GA-VRP and GA-VRPHD, it can be found that the result of GA-VRPHD is better than that of GA-VRP, indicating that the two-layer optimization modeling of UAVs is better than directly and rigidly dividing the tasks into high-precision acquisition voyages and low-precision acquisition voyages and then separately performing path planning.

[0157] The optimal path planning scheme obtained by GA-VRP is as Figure 7 shown. The horizontal axis and the vertical axis are the coordinate axes. The pentagonal points represent high-precision inspection target points, the quadrilateral points represent low-precision inspection target points, the pentagram points represent base stations, the solid lines are low-precision voyages, and the dashed lines are high-precision voyages.

[0158] It can be seen from the results that the genetic algorithm works independently to achieve high-precision and low-precision UAV path planning. In the obtained paths, there is no situation where low-precision and high-precision targets are mixed in one voyage. This rigid voyage division ignores some voyage combinations of high-precision and low-precision combinations with short distances but better overall results. Because it is just a simple VRP modeling, the solution complexity is low, which is consistent with the Figure 6 iterative convergence curve in. The optimal solution is obtained when iterating to about 100.

[0159] The optimal path planning scheme obtained by GA-VRPHD is as Figure 8 shown. The horizontal axis and the vertical axis are the coordinate axes. The pentagonal points represent high-precision inspection target points, the quadrilateral points represent low-precision inspection target points, the pentagram points represent base stations, the solid lines represent low-precision voyages, and the dashed lines represent high-precision voyages.

[0160] It can be seen that in high-precision voyages 1, 2, and 3 of the path, there are situations where high-precision and low-precision targets are mixed in one voyage. However, there is only one high-precision target in high-precision voyages 1 and 2. Due to the acquisition equipment limitation of each acquisition voyage, only one acquisition precision can be used, so the other low-precision acquisition targets in high-precision voyages 1 and 2 use high-precision equipment to collect data, resulting in a longer acquisition time. Because there is no task optimization for the low-level voyage division in GA-VRPHD, only the confirmation of the low-precision and high-precision task matching is carried out. Therefore, for this two-layer optimization algorithm, GA-VRPH is prone to fall into the local optimal point. From Figure 6It can be seen that a feasible solution was obtained when iterating to the 243rd round.

[0161] The optimal path planning scheme obtained by the method of this application is as Figure 9 shown. The horizontal axis and the vertical axis are coordinate axes. The points of the pentagon represent high-precision inspection target points, the points of the quadrilateral represent low-precision inspection target points, the points of the pentagram represent base stations, the solid lines represent low-precision voyages, and the dashed lines represent high-precision voyages.

[0162] In Figure 9 there is a path intersection between the low-precision voyage 3 and the high-precision voyage 1. In traditional path planning algorithms, it is basically considered that the optimal result has not been found. However, because the time required for target image acquisition of the high-precision voyage is higher than that of the low-precision voyage, the path planning obtained is actually relatively optimal. There is no intersection between low-precision voyages, and there is no intersection between high-precision voyages either. Due to the hierarchy of the double-layer optimization and the conflict between the low-level optimization and the high-level optimization, it is almost impossible to find the optimal solution by the double-layer optimization. In the Figure 6 iteration convergence curve of GA-TS, it has the fastest convergence speed among the three algorithms and obtains the best result.

[0163] It can be seen from this that the method of this application can effectively solve the reasonable allocation problem of high-precision and low-precision inspections, and fully considers the battery capacity limit in path planning, thereby optimizing the inspection efficiency of the unmanned aerial vehicle. Compared with the traditional single algorithm, the method of this application has significant advantages in the collaborative optimization of task precision division and path planning, and can improve the path planning accuracy and execution efficiency in complex inspection tasks.

[0164] In addition, the research of this application also shows that the hybrid optimization method combining tabu search and genetic algorithm can effectively overcome the limitations of the two algorithms respectively and improve the global search ability and local optimization performance of the path planning algorithm. Especially when facing practical problems such as task target precision differences and battery constraints, this method has good adaptability and solving ability. In addition, with the continuous progress of unmanned aerial vehicle technology and computing power, future research can consider path planning problems in large-scale and multi-task scenarios to further improve the application effect of unmanned aerial vehicles in fields such as inspections.

[0165] Next, an exemplary description will be given of the double-layer optimized unmanned aerial vehicle path planning device provided by this application.

[0166] As Figure 10 shown, the embodiment of this application provides a double-layer optimized unmanned aerial vehicle path planning device. The double-layer optimized unmanned aerial vehicle path planning device 1000 includes:

[0167] An acquisition module 1001 is configured to acquire the base station location of a target unmanned aerial vehicle (UAV) and the locations of a plurality of inspection target points; the inspection target points are either high-precision inspection target points or low-precision inspection target points;

[0168] A construction module 1002 is configured to construct a path optimization function of the target UAV based on the base station location and the locations of all inspection target points; the path optimization function is used to describe the total inspection time, the total battery replacement time, and the total flight time required for the target UAV to inspect all inspection target points;

[0169] A solution module 1003 is configured to solve the path optimization function by using a genetic algorithm and a tabu search algorithm to obtain an optimal path planning scheme for the target UAV; an individual in the genetic algorithm is a path planning scheme of the target UAV, and the path planning scheme includes the inspection path of each flight of the target UAV and the inspection accuracy;

[0170] An inspection module 1004 is configured to control the target UAV to inspect all inspection target points according to the optimal path planning scheme.

[0171] It should be noted that, for the information interaction, execution process, etc. between the above-mentioned devices / units, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought thereby can be specifically referred to the method embodiment part, and will not be elaborated here.

[0172] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above-mentioned system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0173] As Figure 11 shown, an embodiment of the present application provides a terminal device. The terminal device D10 in this embodiment includes: at least one processor D100 ( Figure 11only shows one processor), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, it implements the steps in any of the above method embodiments.

[0174] Specifically, when the processor D100 executes the computer program D102, it obtains the base station position of the target unmanned aerial vehicle (UAV) and the positions of multiple inspection target points, then constructs a path optimization function for the target UAV based on the base station position and the positions of all inspection target points. Then, it uses a genetic algorithm and a tabu search algorithm to solve the path optimization function to obtain an optimal path planning scheme for the target UAV. Finally, it controls the target UAV to inspect all inspection target points according to the optimal path planning scheme. Among them, constructing the path optimization function can represent the final total time required for inspection. Combining the genetic algorithm and the tabu search algorithm can effectively overcome the limitations of the two algorithms respectively, improve the global search ability and local optimization performance of path planning, and have good adaptability. By solving the path optimization function in this way, it can consider the final total time required for inspection, improve the accuracy and execution efficiency of the path planning scheme, and effectively improve the accuracy of UAV path planning.

[0175] The so-called processor D100 may be a central processing unit (CPU, Central Processing Unit), and this processor D100 may also be other general-purpose processors, digital signal processors (DSP, Digital Signal Processor), application specific integrated circuits (ASIC, Application Specific Integrated Circuit), field-programmable gate arrays (FPGA, Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0176] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In some other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device D10. Further, the memory D101 may also include both the internal storage unit and the external storage device of the terminal device D10. The memory D101 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as program codes of the computer program. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0177] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0178] An embodiment of the present application provides a computer program product, and when the computer program product runs on a terminal device, the terminal device can implement the steps in the above method embodiments when executed.

[0179] 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, to implement all or part of the processes in the above method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the double-layer optimized unmanned aerial vehicle path planning method device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc.

[0180] In the above embodiments, the descriptions of the various embodiments each have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0181] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented with electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0182] The above is the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art of this technology, without departing from the principle described in this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A double-layer optimized UAV path planning method, characterized in that, Including: Obtain the base station location of the target unmanned aerial vehicle (UAV) and the locations of multiple inspection target points; Construct a path optimization function for the target UAV based on the base station location and the locations of all inspection target points; The path optimization function is used to describe the total inspection time, total battery replacement time, and total flight time required for the target UAV to inspect all inspection target points; Use a genetic algorithm and a tabu search algorithm to solve the path optimization function to obtain an optimal path planning scheme for the target UAV; an individual in the genetic algorithm is a path planning scheme for the target UAV, and the path planning scheme includes the inspection path and inspection accuracy for each flight of the target UAV; Control the target UAV to inspect all inspection target points according to the optimal path planning scheme; Among them, using a genetic algorithm and a tabu search algorithm to solve the path optimization function to obtain an optimal path planning scheme for the target UAV includes: Generate multiple individuals in the genetic algorithm; Increment the iteration count by 1, and determine whether the iteration count is greater than or equal to the maximum iteration count; If so, select the optimal individual from all individuals according to the path optimization function, and use the path planning scheme described by the optimal individual as the optimal path planning scheme; Otherwise, use the genetic algorithm to update all individuals to obtain multiple updated individuals, use the tabu search algorithm to perform an optimization search on each updated individual to obtain a relatively optimal individual corresponding to each updated individual, and use the multiple relatively optimal individuals as multiple individuals, and return to the step of incrementing the iteration count by 1 and determining whether the iteration count is greater than or equal to the maximum iteration count.

2. The drone path planning method according to claim 1, wherein, The inspection target points are high-precision inspection target points or low-precision inspection target points; The path optimization function is: ； Among them, represents the final total time required for the target UAV to complete the inspection and return to the base station, represents the total flight time for the target UAV to complete all flight paths, represents the total inspection time for the target UAV to inspect all inspection target points, represents the total battery replacement time for the target UAV to replace the battery at the base station: ； ； ； ； ； ； Among them, represents the total number of UAV flight missions, represents the total number of inspection target points, represents the whether the target UAV in the flight mission flies from the th inspection target point to the th inspection target point, represents the target UAV in the flight mission flies from the base station to the represents the target UAV in the flight mission returns from the th inspection target point to the base station, when the th inspection target point is the base station, represents the distance between the positions of the th inspection target point and the represents the flight speed of the target UAV, represents the th inspection accuracy of the represents low accuracy, represents high accuracy, represents the th inspection accuracy of the represents the time spent on high-precision inspection, represents the time spent on low-precision inspection, represents the time spent on battery replacement, represents the whether the th flight mission requires battery replacement, represents that battery replacement is required, represents the set of inspection target points for actual low-precision inspection, represents the set of inspection target points for actual high-precision inspection, represents the set of low-precision inspection target points, represents the set of high-precision inspection target points, represents the maximum flight time of the target UAV in a single flight mission, represents a constraint.

3. The drone path planning method according to claim 1, wherein The selecting the optimal individual from all individuals according to the path optimization function includes: For each individual respectively, substitute the path planning scheme described by the individual into the path optimization function to calculate the final total time corresponding to the individual; Use the individual corresponding to the smallest final total time as the optimal individual.

4. The drone path planning method according to claim 1, wherein The using the genetic algorithm to update all individuals to obtain multiple updated individuals includes: Calculate the fitness of each individual according to the path optimization function; Select multiple parent individuals from all individuals according to all fitness values; Perform a crossover operation on all parent individuals to obtain multiple offspring individuals, and perform a mutation operation on all offspring individuals to obtain multiple mutant offspring individuals; Calculate the fitness of each mutant offspring individual according to the path optimization function, sort all mutant offspring individuals in descending order of fitness, and select the first multiple mutant offspring individuals in the sorting result as updated individuals.

5. The drone path planning method according to claim 4, wherein, The using the tabu search algorithm to perform an optimization search on each updated individual to obtain a relatively optimal individual corresponding to each updated individual includes: For each updated individual respectively, perform the following steps: Determine whether there is a flight with a mixture of low-precision inspection target points and high-precision inspection target points in the path planning scheme described by the updated individual; If so, use the tabu search algorithm to perform a neighborhood search on the updated individual to obtain a relatively optimal individual corresponding to the updated individual; Otherwise, use the updated individual as the superior individual corresponding thereto.

6. The drone path planning method according to claim 5, wherein The step of using the tabu search algorithm to perform neighborhood search on the updated individual to obtain the superior individual corresponding to the updated individual includes: Initialize the tabu list; Select a target neighborhood search operation from multiple neighborhood search operations; Perform neighborhood search on the updated individual using the target neighborhood search operation to obtain a candidate individual of the updated individual, and add the target neighborhood search operation to the tabu list; When the tabu list does not include all neighborhood search operations, select a target neighborhood search operation from all other neighborhood search operations that have not been added to the tabu list, and return to the step of performing neighborhood search on the updated individual using the target neighborhood search operation to obtain a candidate individual of the updated individual, and adding the target neighborhood search operation to the tabu list; When the tabu list includes all neighborhood search operations, calculate the fitness of each candidate individual according to the path optimization function, and use the candidate individual with the maximum fitness value as the superior individual of the updated individual.

7. The drone path planning method according to claim 6, wherein, The multiple neighborhood search operations include: The first neighborhood search operation: delete all high-precision cruise target points from the voyage that mixes low-precision inspection target points and high-precision inspection target points; The second neighborhood search operation: delete all low-precision cruise target points from the voyage that mixes low-precision inspection target points and high-precision inspection target points; The third neighborhood search operation: perform neighborhood transformation on the voyage that mixes low-precision inspection target points and high-precision inspection target points to obtain another voyage that mixes low-precision inspection target points and high-precision inspection target points.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the double-layer optimized UAV path planning method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the double-layer optimized UAV path planning method according to any one of claims 1 to 7.

Images