Unmanned aerial vehicle inspection path planning method and device, terminal equipment and storage medium

Abstract

The invention discloses an unmanned aerial vehicle inspection path planning method and device, terminal equipment and a storage medium, and belongs to the technical field of path planning, and the method comprises the steps: taking an access point sequence in a to-be-inspected region as an individual of a population; performing population initialization processing based on the individuals, after the population is initialized, constructing a fitness function by using the total path distance, the energy consumption factor and the time factor, and calculating a fitness value of each individual according to the fitness function; performing genetic algorithm iteration processing based on the fitness value of each individual, and obtaining a new population when iteration reaches a preset condition; and taking an access point set in the new population as a control point initial set, and generating a first inspection path according to the control point initial set by adopting a B-spline algorithm. Through implementation of the method, the problems that in the prior art, a path planned based on a static environment is composed of discrete points, the discrete path can increase the flight distance and time of an unmanned aerial vehicle, and the flight speed is low can be solved. And the inspection efficiency of the unmanned aerial vehicle is relatively low.

Description

Technical Field

[0001] The present invention relates to the field of path planning technology, and in particular to a method, device, terminal equipment and storage medium for planning an unmanned aerial vehicle inspection path. Background Art

[0002] With the rapid development of low-altitude economy and intelligent technology, the importance of drone path inspection as a core means to improve industry operation and maintenance efficiency and ensure operational safety has become increasingly prominent.

[0003] Existing drone inspection path planning methods usually perform path planning based on static environment models. However, the path planned based on the static environment is composed of discrete points. The discrete path increases the drone's flight distance and time, resulting in low drone inspection efficiency. Summary of the Invention

[0004] The present invention provides a method, device, terminal device and storage medium for planning a drone inspection path, so as to solve the technical problem that the existing drone inspection path planning method based on a static environment plans a path composed of discrete points, which increases the drone's flight distance and time, resulting in low drone inspection efficiency.

[0005] The present invention provides a method for planning a UAV inspection path, comprising:

[0006] The sequence of access points in the area to be inspected is regarded as individuals of the population;

[0007] Initializing the population based on the individuals, constructing a fitness function based on the total path distance, energy consumption factor, and time factor after the population is initialized, and calculating the fitness value of each individual according to the fitness function;

[0008] The genetic algorithm is iterated based on the fitness value of each individual, and a new population is obtained when the iteration reaches the preset conditions;

[0009] The access point set in the new population is used as an initial set of control points, and a first inspection path is generated according to the initial set of control points using a B-spline algorithm.

[0010] Furthermore, the generating of the first inspection path according to the initial set of control points using the B-spline algorithm includes:

[0011] According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain a first inspection path, wherein the expression of the first inspection path is as follows:

[0012]

[0013] Wherein, S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

[0014] Furthermore, after using the access point set in the new population as the initial set of control points and using the B-spline algorithm to generate a first inspection path according to the initial set of control points, the method further includes:

[0015] The first inspection path is optimized based on a nonlinear least squares method to obtain a second inspection path, wherein an objective function of the nonlinear least squares method is constructed based on the initial control point and the smoothing factor.

[0016] Furthermore, before optimizing the first inspection path based on the nonlinear least squares method to obtain the second inspection path, the method further includes:

[0017] Dynamic constraints of the first inspection path are set, where the dynamic constraints include a maximum flight speed constraint, a minimum flight speed constraint, an acceleration constraint, and a jerk constraint.

[0018] Furthermore, after optimizing the first inspection path based on the nonlinear least squares method to obtain the second inspection path, the method further includes:

[0019] Determining the obstacle distribution area in the area to be inspected, and constructing an obstacle distance field based on the obstacle distribution area;

[0020] An obstacle avoidance cost function is constructed based on the obstacle distance field, the second inspection path is adjusted, and a third inspection path is obtained when the cost calculated according to the obstacle avoidance cost function is minimized.

[0021] Furthermore, the iterative processing of the genetic algorithm based on the fitness value of each individual includes:

[0022] Sort each individual according to the fitness value;

[0023] Select the corresponding individual with the fitness value that meets the preset conditions as the parent;

[0024] Randomly select two parents to perform crossover operations to generate the corresponding initial offspring;

[0025] Performing a mutation operation on the initial offspring to obtain a final offspring;

[0026] The parent generation and the final offspring generation form a candidate population, and the candidate population is used for iterative genetic algorithm processing.

[0027] The present invention also provides a UAV inspection path planning device, comprising:

[0028] An individual determination module, configured to take a sequence of access points in the area to be inspected as individuals of the population;

[0029] a fitness calculation module, configured to initialize the population based on the individuals, construct a fitness function based on the total path distance, energy consumption factor, and time factor after the population is initialized, and calculate the fitness value of each individual according to the fitness function;

[0030] Iterative processing module, used to perform genetic algorithm iterative processing based on the fitness value of each individual, and obtain a new population when the iteration reaches the preset condition;

[0031] The first inspection path generation module is configured to use the access point set in the new population as an initial set of control points and adopt a B-spline algorithm to generate a first inspection path according to the initial set of control points.

[0032] Furthermore, the first inspection path generating module is further configured to:

[0033] According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain a first inspection path, wherein the expression of the first inspection path is as follows:

[0034]

[0035] Wherein, S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

[0036] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the drone inspection path planning method as described above is implemented.

[0037] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the drone inspection path planning method as described above.

[0038] The embodiment of the present invention uses the B-spline algorithm to adjust the control points in the population individuals optimized by the genetic algorithm, thereby generating a continuous and smooth inspection path, thereby avoiding increasing the additional flight distance and time of the drone. It can also adapt to environmental changes and dynamic target tasks based on real-time access point updates and path replanning, thereby effectively improving the drone inspection efficiency.

[0039] Furthermore, an embodiment of the present invention introduces the distance field into the trajectory optimization process, and dynamically avoids obstacles through a penalty mechanism to iteratively update the control point position to minimize the total obstacle avoidance cost (including path length, smoothness, obstacle avoidance penalty, etc.), thereby generating a final third inspection path. It can not only effectively suppress the influence of dangerous control points through the penalty mechanism of the obstacle avoidance cost function, but also achieve high-order continuity of the path based on the B-spline basis function, thereby achieving global smoothness of the path, effectively avoiding the problem of increased drone inspection time due to path non-smoothness, effectively improving the efficiency of drone inspection, and can be applied to a variety of mission scenarios, including drone inspection in complex environments such as substation inspection and logistics distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for planning a UAV inspection path according to an embodiment of the present invention;

[0041] Figure 2 This is another flowchart of the method for planning a UAV inspection path provided by an embodiment of the present invention;

[0042] Figure 3 It is a structural diagram of the UAV inspection path planning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0045] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0046] See also Figure 1 In order to solve the technical problem that the path planned in the prior art based on a static environment is composed of discrete points, which increases the flight distance and time of the drone, resulting in low efficiency of drone inspection, the present invention provides a drone inspection path planning method, including:

[0047] S1, taking the sequence of access points in the area to be inspected as individuals of the population;

[0048] In this embodiment of the present invention, all access points within the area to be inspected are determined. Access points are locations that the drone needs to reach, and do not include fixed starting and ending points. In this embodiment of the present invention, an individual can be a randomly arranged sequence of access points, with the starting and ending points being city numbers.

[0049] By using the access point sequence in the area to be inspected as individuals in the population, the embodiment of the present invention can ensure that the generated path meets the basic requirements of the inspection task, that is, starting from a fixed starting point, passing through multiple access points, and finally returning to a fixed end point.

[0050] S2. Initialize the population based on individuals. After initializing the population, construct a fitness function based on the total path distance, energy consumption factor, and time factor. Calculate the fitness value of each individual based on the fitness function.

[0051] In an embodiment of the present invention, the path distance can be calculated using a given distance matrix, and the energy consumption factor and time factor can be determined based on the performance of the drone and the inspection mission requirements, and their weights can be adjusted. The total cost of each path is output by the objective function as the basis for population evolution.

[0052] The embodiment of the present invention constructs a fitness function by comprehensively considering the total path distance, energy consumption factor and time factor, which can fully consider the influencing factors of path planning, thereby facilitating improving the comprehensiveness and reliability of path planning.

[0053] S3, performing iterative processing of the genetic algorithm based on the fitness value of each individual, and obtaining a new population when the iteration reaches the preset condition;

[0054] In an embodiment of the present invention, when evaluating individuals, the fitness value of each individual in the population can be calculated, and the lowest fitness value in the current generation, that is, the lowest cost path, can be recorded as the current optimal solution.

[0055] S4. Using the access point set in the new population as the initial set of control points, a B-spline algorithm is used to generate a first inspection path according to the initial set of control points.

[0056] In an embodiment of the present invention, by adopting the B-spline algorithm, the control points in the population individuals optimized by the genetic algorithm are adjusted, so that a continuous and smooth inspection path can be generated, thereby avoiding increasing the additional flight distance and time of the drone, and can adapt to environmental changes and dynamic target tasks based on real-time access point updates and path replanning, thereby effectively improving the drone inspection efficiency.

[0057] In one embodiment, step S4, using a B-spline algorithm to generate a first inspection path according to an initial set of control points, includes:

[0058] According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain the first inspection path, where the expression of the first inspection path is as follows:

[0059]

[0060] Wherein, S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

[0061] In an embodiment of the present invention, linear interpolation processing is performed on the initial set of control points in combination with the spline order, the number of control points and the spline basis function to obtain the first inspection path. Linear interpolation processing is performed based on multiple influencing factors, which can effectively reduce the trajectory curvature fluctuation of the path, thereby planning a continuous and smooth inspection path, effectively improving the inspection efficiency of the drone.

[0062] In one embodiment, after step S4, in which the access point set in the new population is used as the initial set of control points and the B-spline algorithm is used to generate the first inspection path according to the initial set of control points, the method further includes:

[0063] S5. Optimize the first inspection path based on a nonlinear least squares method to obtain a second inspection path, wherein the objective function of the nonlinear least squares method is constructed based on the initial control point and the smoothing factor.

[0064] In this embodiment of the present invention, the objective function of the nonlinear least squares method is:

[0065] min x ||F(x)|| 2

[0066] Where F(x) represents the residual vector, including the trajectory smoothing error, dynamic limit error, and obstacle avoidance error. x is the optimization problem definition of the nonlinear least squares method, which can be:

[0067]

[0068] Where β is the smoothing factor.

[0069] The expression of F(x) is as follows:

[0070]

[0071] Among them, f smooth is the smoothing term, f dynamics is a dynamic constraint term, f fobstacle To avoid obstacles, and are the square roots of the weights corresponding to the smoothing term, dynamic constraint term, and obstacle avoidance term, respectively.

[0072] The embodiment of the present invention optimizes the first inspection path based on the nonlinear least squares method to obtain the second inspection path. By using the nonlinear least squares method to adjust the initial control points and smoothing factors of the first path, the path error can be minimized, and a continuous and smooth trajectory route can be further obtained.

[0073] In one embodiment, before step S5, optimizing the first inspection path based on the nonlinear least squares method to obtain the second inspection path, the method further includes:

[0074] The dynamic constraints of the first inspection path are set, where the dynamic constraints include a maximum flight speed constraint, a minimum flight speed constraint, an acceleration constraint, and a jerk constraint.

[0075] In an embodiment of the present invention, by setting the dynamic constraints of the first inspection path, the dynamic constraints include maximum flight speed constraints, minimum flight speed constraints, acceleration constraints and jerk constraints, the speed of the inspection path can be dynamically limited to ensure that the trajectory is executable and the flight is stable.

[0076] In one embodiment, after optimizing the first inspection path based on the nonlinear least squares method to obtain the second inspection path in step S5, the method further includes:

[0077] S6. Determine the obstacle distribution area in the area to be inspected, and construct an obstacle distance field based on the obstacle distribution area;

[0078] In an embodiment of the present invention, the environment of the area to be inspected can be discretized into a grid map, and the obstacle range is marked as a non-communicable area according to the obstacle radius. The distance from each grid to the nearest obstacle is calculated through Euclidean transformation to obtain a distance field.

[0079] S7. Construct an obstacle avoidance cost function based on the obstacle distance field, adjust the second inspection path, and obtain a third inspection path when the cost calculated according to the obstacle avoidance cost function is minimized.

[0080] The expression of the third inspection path is as follows:

[0081]

[0082] Among them, S_final(t) is the third inspection path, F obs (x) is the obstacle avoidance cost function, EDT is the distance field, safe_distance is the safe distance; penalty is the penalty term.

[0083] The embodiment of the present invention introduces the distance field into the trajectory optimization process, and dynamically avoids obstacles through a penalty mechanism to iteratively update the control point positions to minimize the total obstacle avoidance cost (including path length, smoothness, obstacle avoidance penalty, etc.), thereby generating the final third inspection path. It can not only effectively suppress the influence of dangerous control points through the penalty mechanism of the obstacle avoidance cost function, but also realize the high-order continuity of the path based on the B-spline basis function, thereby realizing global smoothness of the path, effectively avoiding the problem of increased drone inspection time due to path non-smoothness, and effectively improving the efficiency of drone inspection.

[0084] In one embodiment, step S3, performing genetic algorithm iterative processing based on the fitness value of each individual, includes:

[0085] S31. Sort each individual according to the fitness value;

[0086] S32, selecting the corresponding individual with the fitness value that meets the preset conditions as the parent generation;

[0087] S33, randomly select two parent generations to perform a crossover operation to generate corresponding initial offspring;

[0088] S34, performing a mutation operation on the initial offspring to obtain a final offspring;

[0089] S35. The parent generation and the final offspring generation are formed into a candidate population, and the candidate population is subjected to iterative processing of the genetic algorithm.

[0090] In the embodiment of the present invention, the access point sequence of the area to be inspected can be effectively optimized through iterative processing of the genetic algorithm, thereby ensuring the optimality of the global path.

[0091] See also Figure 2, which is another flow chart of a method for planning a drone inspection path provided by one embodiment of the present invention. In this embodiment of the present invention, the starting point, end point, and target to be inspected are determined, where the target to be inspected is the access point. A traveling salesman problem is solved based on a genetic algorithm, including population initialization and objective function calculation. Population update is achieved through a GA optimization process, individual evaluation, selection / crossover / mutation operations, and an inspection sequence is obtained. The drone trajectory planning based on B-spline and nonlinear least squares optimization includes: Uniform B-spline initialization and setting of dynamic constraints, followed by obstacle environment modeling to achieve trajectory smoothing based on soft optimization, and obtain the final drone inspection path, so that the drone reaches the desired location at the desired speed and velocity according to the planned inspection path, thereby completing the inspection task.

[0092] The implementation of the present invention has the following beneficial effects:

[0093] The embodiment of the present invention uses the B-spline algorithm to adjust the control points in the population individuals optimized by the genetic algorithm, thereby generating a continuous and smooth inspection path, thereby avoiding increasing the additional flight distance and time of the drone. It can also adapt to environmental changes and dynamic target tasks based on real-time access point updates and path replanning, thereby effectively improving the drone inspection efficiency.

[0094] Furthermore, an embodiment of the present invention introduces the distance field into the trajectory optimization process, and dynamically avoids obstacles through a penalty mechanism to iteratively update the control point position to minimize the total obstacle avoidance cost (including path length, smoothness, obstacle avoidance penalty, etc.), thereby generating a final third inspection path. It can not only effectively suppress the influence of dangerous control points through the penalty mechanism of the obstacle avoidance cost function, but also achieve high-order continuity of the path based on the B-spline basis function, thereby achieving global smoothness of the path, effectively avoiding the problem of increased drone inspection time due to path non-smoothness, effectively improving the efficiency of drone inspection, and can be applied to a variety of mission scenarios, including drone inspection in complex environments such as substation inspection and logistics distribution.

[0095] See also Figure 3 Based on the same inventive concept as the above embodiment, the present invention also provides a UAV inspection path planning device, comprising:

[0096] An individual determination module 10 is configured to use a sequence of access points in the area to be inspected as individuals of the population;

[0097] The fitness calculation module 20 is used to initialize the population based on individuals. After the population is initialized, a fitness function is constructed based on the total path distance, energy consumption factor, and time factor, and the fitness value of each individual is calculated based on the fitness function.

[0098] Iterative processing module 30, used to perform genetic algorithm iterative processing based on the fitness value of each individual, and obtain a new population when the iteration reaches a preset condition;

[0099] The first inspection path generating module 40 is configured to use the access point set in the new population as an initial set of control points and to generate a first inspection path according to the initial set of control points using a B-spline algorithm.

[0100] In one embodiment, the first inspection path generating module 40 is further configured to:

[0101] According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain the first inspection path, where the expression of the first inspection path is as follows:

[0102]

[0103] Where S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

[0104] In one embodiment, the UAV inspection path planning device further includes a second inspection path generation module, which is configured to:

[0105] The first inspection path is optimized based on a nonlinear least squares method to obtain a second inspection path, wherein the objective function of the nonlinear least squares method is constructed according to the initial control point and the smoothing factor.

[0106] In one embodiment, the second inspection path generating module is further configured to:

[0107] The dynamic constraints of the first inspection path are set, where the dynamic constraints include a maximum flight speed constraint, a minimum flight speed constraint, an acceleration constraint, and a jerk constraint.

[0108] In one embodiment, the UAV inspection path planning device further includes a third inspection path generation module, which is configured to:

[0109] Determine the obstacle distribution area in the area to be inspected and construct an obstacle distance field based on the obstacle distribution area;

[0110] An obstacle avoidance cost function is constructed based on the obstacle distance field, the second inspection path is adjusted, and a third inspection path is obtained when the cost calculated according to the obstacle avoidance cost function is minimized.

[0111] In one embodiment, the iterative processing module 30 is further configured to:

[0112] Sort each individual according to the fitness value;

[0113] Select the corresponding individual with the fitness value that meets the preset conditions as the parent;

[0114] Randomly select two parents to perform crossover operations to generate the corresponding initial offspring;

[0115] Perform mutation operations on the initial offspring to obtain the final offspring;

[0116] The parent generation and the final offspring are formed into a candidate population, and the candidate population is used for iterative genetic algorithm processing.

[0117] Accordingly, an embodiment of the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the drone inspection path planning method of any one of the above embodiments is implemented.

[0118] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and capable of running on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiment are realized, such as the first inspection path generating module 40 .

[0119] For example, a computer program can be divided into one or more modules / units, one or more of which are stored in a memory and executed by a processor to implement the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in a terminal device. For example, the first patrol path generation module 40 is configured to use the access point set in the new population as the initial set of control points and employ a B-spline algorithm to generate a first patrol path based on the initial set of control points.

[0120] Terminal devices can be computing devices such as desktop computers, laptops, PDAs, and cloud servers. Terminal devices may include, but are not limited to, processors and memory. Those skilled in the art will appreciate that the schematic diagrams are merely examples of terminal devices and do not limit the scope of terminal devices. Terminal devices may include more or fewer components than shown, or combinations of certain components, or different components. For example, terminal devices may also include input / output devices, network access devices, buses, and the like.

[0121] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.

[0122] The memory can be used to store computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created based on the use of the mobile terminal, etc. In addition, the memory can include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0123] If the module / unit integrated into the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process in the above-mentioned embodiment method, and can also be completed by a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0124] Accordingly, an embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the drone inspection path planning method of any one of the above embodiments.

[0125] The above specific embodiments further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for planning a UAV inspection path, characterized in that: include: The sequence of access points in the area to be inspected is regarded as individuals of the population; Initializing the population based on the individuals, constructing a fitness function based on the total path distance, energy consumption factor, and time factor after the population is initialized, and calculating the fitness value of each individual according to the fitness function; The genetic algorithm is iterated based on the fitness value of each individual, and a new population is obtained when the iteration reaches the preset conditions; The access point set in the new population is used as an initial set of control points, and a first inspection path is generated according to the initial set of control points using a B-spline algorithm.

2. The UAV inspection path planning method according to claim 1, characterized in that: The step of generating a first inspection path according to the initial set of control points using a B-spline algorithm includes: According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain a first inspection path, wherein the expression of the first inspection path is as follows: Wherein, S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

3. The UAV inspection path planning method according to claim 2, characterized in that: After using the access point set in the new population as the initial set of control points and using the B-spline algorithm to generate a first inspection path according to the initial set of control points, the method further includes: The first inspection path is optimized based on a nonlinear least squares method to obtain a second inspection path, wherein an objective function of the nonlinear least squares method is constructed based on the initial control point and the smoothing factor.

4. The UAV inspection path planning method according to claim 3, wherein: Before optimizing the first inspection path based on the nonlinear least squares method to obtain the second inspection path, the method further includes: Dynamic constraints of the first inspection path are set, where the dynamic constraints include a maximum flight speed constraint, a minimum flight speed constraint, an acceleration constraint, and a jerk constraint.

5. The UAV inspection path planning method according to claim 3, wherein: After optimizing the first inspection path based on a nonlinear least squares method to obtain a second inspection path, the method further includes: Determining the obstacle distribution area in the area to be inspected, and constructing an obstacle distance field based on the obstacle distribution area; An obstacle avoidance cost function is constructed based on the obstacle distance field, the second inspection path is adjusted, and a third inspection path is obtained when the cost calculated according to the obstacle avoidance cost function is minimized.

6. The UAV inspection path planning method according to claim 1, wherein: The iterative processing of the genetic algorithm based on the fitness value of each individual includes: Sort each individual according to the fitness value; Select the corresponding individual with the fitness value that meets the preset conditions as the parent; Randomly select two parents to perform crossover operations to generate the corresponding initial offspring; Performing a mutation operation on the initial offspring to obtain a final offspring; The parent generation and the final offspring generation form a candidate population, and the candidate population is used for iterative genetic algorithm processing.

7. A UAV inspection path planning device, characterized in that: include: An individual determination module, configured to take a sequence of access points in the area to be inspected as individuals of the population; a fitness calculation module, configured to initialize the population based on the individuals, construct a fitness function based on the total path distance, energy consumption factor, and time factor after the population is initialized, and calculate the fitness value of each individual according to the fitness function; Iterative processing module, used to perform genetic algorithm iterative processing based on the fitness value of each individual, and obtain a new population when the iteration reaches the preset condition; The first inspection path generation module is configured to use the access point set in the new population as an initial set of control points and adopt a B-spline algorithm to generate a first inspection path according to the initial set of control points.

8. The UAV inspection path planning device according to claim 7, characterized in that: The first inspection path generating module is further configured to: According to the set spline order, number of control points, and spline basis function, linear interpolation processing is performed on the initial set of control points to obtain a first inspection path, wherein the expression of the first inspection path is as follows: Wherein, S(t) is the first inspection path, N is the number of control points, Ni,k(t) is the spline basis function, and pi is the initial control point in the initial set of control points.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for planning a drone inspection path according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the drone inspection path planning method according to any one of claims 1 to 7.

Images