Path planning method and system for intelligent engineering inspection equipment

Abstract

The invention relates to unmanned aerial vehicle inspection, in particular to a path planning method and system for intelligent engineering inspection equipment, and the method comprises the steps: obtaining a plurality of unmanned aerial vehicle inspection paths through a triangular path method, and building an unmanned aerial vehicle inspection path set; taking the unmanned aerial vehicle inspection path set as an initial population, and performing optimization by adopting an improved genetic algorithm to obtain a first unmanned aerial vehicle inspection planned path; performing three-dimensional scanning on the inspection area by using camera equipment carried by the unmanned aerial vehicle to generate corresponding point cloud data; registering the point cloud data, and constructing a point cloud map; extracting feature information of the point cloud map, and performing path planning on the point cloud map by adopting a Fermat curve path planning algorithm to obtain a second unmanned aerial vehicle inspection planning path; generating an unmanned aerial vehicle inspection planned path by combining the first unmanned aerial vehicle inspection planned path and the second unmanned aerial vehicle inspection planned path; according to the technical scheme provided by the invention, the defect that the inspection path cannot be flexibly generated according to the actual condition of the construction site in the prior art can be overcome.

Description

Technical Field

[0001] The present invention relates to unmanned aerial vehicle inspection, and in particular to a path planning method and system for intelligent engineering inspection equipment. Background Art

[0002] Inspection of construction sites is an important means to avoid safety accidents caused by insufficient monitoring and untimely correction. It is also an effective way to understand the situation of the construction site and assist in supervision and management. At present, the inspection of construction sites is usually carried out by inspection personnel at irregular intervals. This inspection method is easily restricted by time and space. Especially in difficult and large-scale construction projects, it will be affected by objective environmental, geographical, climatic and subjective personnel conditions, making it difficult to ensure the quality and frequency of inspections.

[0003] With the rapid development of drone technology, the use of drones for construction site inspections has gradually been applied. However, most existing drone inspection systems are manually operated and cannot flexibly generate inspection paths based on the actual conditions of the construction site, thus failing to achieve automated inspections, resulting in low inspection efficiency and poor inspection results. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a path planning method and system for intelligent engineering inspection equipment, which can effectively overcome the defect of the prior art that the inspection path cannot be flexibly generated according to the actual situation at the construction site.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A path planning method for intelligent engineering inspection equipment includes the following steps:

[0009] S1. Use the triangular route method to obtain multiple drone inspection paths and establish a drone inspection path set;

[0010] S2, taking the UAV inspection path set as the initial population, using the improved genetic algorithm to find the optimal solution, and obtaining the first UAV inspection planning path;

[0011] S3, using the camera equipment carried by the drone to perform a three-dimensional scan of the inspection area and generate corresponding point cloud data;

[0012] S4, registering the point cloud data and constructing a point cloud map;

[0013] S5, extracting feature information of the point cloud map, and using the Fermat curve path planning algorithm to perform path planning on the point cloud map to obtain a second UAV inspection planning path;

[0014] S6. Combine the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

[0015] Preferably, in S1, a triangular route method is used to obtain multiple drone inspection paths and establish a drone inspection path set, including:

[0016] S11. Determine the inspection starting point and the inspection end point in the inspection area, and draw multiple drone inspection paths using the triangular route method based on the inspection starting point and the inspection end point;

[0017] S12. Perform a collision test on the multiple drawn drone inspection paths, retain the drone inspection paths that pass the collision test, and establish a drone inspection path set.

[0018] Preferably, in S2, the UAV inspection path set is used as the initial population, and an improved genetic algorithm is used for optimization to obtain the first UAV inspection planning path, including:

[0019] S21, taking the UAV inspection path set as the initial population, and calculating the initial fitness value of each UAV inspection path;

[0020] S22, performing individual selection according to the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm;

[0021] S23, performing a crossover operation on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm;

[0022] S24, using the fitness function to evaluate each drone inspection path in the updated particle swarm and calculate the corresponding fitness value;

[0023] S25, record and update the global optimal solution;

[0024] S26. Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to S22. Otherwise, use the current global optimal solution as the first UAV inspection planning path.

[0025] Preferably, in S23, a crossover operation is performed on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm, including:

[0026] Based on the preset collision crossover strategy, the UAV inspection paths that failed the collision test were cross-calculated with each UAV inspection path in the genetic particle swarm with a preset probability to obtain an updated particle swarm.

[0027] Preferably, S4 registers the point cloud data to construct a point cloud map, including:

[0028] S41, determining a reference coordinate system, and transforming the point cloud data into the reference coordinate system;

[0029] S42, using a nearest neighbor algorithm to find matching point pairs between the point cloud data and the target point cloud data;

[0030] S43, with the goal of minimizing the distance error of the matching point pairs, calculating the translation matrix and the rotation matrix to obtain the registration parameters;

[0031] S44, transforming the point cloud data into the target coordinate system using the registration parameters, and fusing them to obtain a point cloud map.

[0032] Preferably, in S42, a nearest neighbor algorithm is used to find matching point pairs between the point cloud data and the target point cloud data, including:

[0033] S421, calculating the distances between the point cloud data and all points in the target point cloud data, and sorting them from small to large;

[0034] S422, in the target point cloud data, taking the first m closest target points as the nearest neighbor points of the point cloud data;

[0035] S423, calculating the distance between the nearest neighbor point of the point cloud data and all the points in the point cloud data, and sorting them from small to large;

[0036] S424. In the point cloud data, the first n closest points are taken as the nearest neighbor points of the target point, and the nearest neighbor points of the point cloud data and the nearest neighbor points of the target point are taken as matching point pairs.

[0037] Preferably, in S43, the translation matrix and the rotation matrix are calculated with the goal of minimizing the distance error of the matching point pair to obtain the registration parameters, including:

[0038] S431, fitting the distance error function between the point cloud data and the target point cloud data using the least square method according to the matching points;

[0039] S432, deriving the distance error function, calculating the translation matrix and the rotation matrix, and obtaining the registration parameters.

[0040] Preferably, in S5, feature information of the point cloud map is extracted, and a Fermat curve path planning algorithm is used to perform path planning on the point cloud map to obtain a second UAV inspection planning path, including:

[0041] S51, extracting feature information of the point cloud map using a convolutional neural network;

[0042] S52, constructing a Cartesian parameter equation of a Fermat curve, and calculating equation expressions of a first segment Fermat clothoid curve and a second segment Fermat clothoid curve according to different initial points and initial cutting angles at different turns;

[0043] S53, treating the first segment of the Fermat clothoid curve and the second segment of the Fermat clothoid curve as the same segment of the curve with opposite directions, and calculating the velocity and acceleration parameter equations of the Fermat clothoid curve;

[0044] S54, eliminate singularities by changing variables, and simplify velocity and acceleration parameter equations by using amplitude-phase expression;

[0045] S55. After eliminating the singular point, the FS curve is used for path tracking, and at the same time, path planning is performed on the feature information of the point cloud map to obtain the second UAV inspection planning path.

[0046] A path planning system for smart engineering inspection equipment, comprising a drone inspection path set establishment module, a first drone inspection planning path generation module, a point cloud data acquisition module, a point cloud map construction module, a second drone inspection planning path generation module and a drone inspection planning path generation module;

[0047] The UAV inspection path set establishment module uses the triangulation route method to obtain multiple UAV inspection paths and establish the UAV inspection path set;

[0048] The first UAV inspection planning path generation module uses the UAV inspection path set as the initial population and uses an improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path;

[0049] The point cloud data acquisition module receives the 3D scanning data of the inspection area from the camera device carried by the drone and generates the corresponding point cloud data;

[0050] Point cloud map construction module, which registers point cloud data and builds point cloud maps;

[0051] The second UAV inspection planning path generation module extracts the feature information of the point cloud map and uses the Fermat curve path planning algorithm to plan the path of the point cloud map to obtain the second UAV inspection planning path;

[0052] The UAV inspection planning path generation module combines the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

[0053] Preferably, the first UAV inspection planning path generation module uses the UAV inspection path set as the initial population and uses an improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path, including:

[0054] The UAV inspection path set is used as the initial population, and the initial fitness value of each UAV inspection path is calculated;

[0055] Individual selection is performed based on the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm;

[0056] Based on the preset collision crossover strategy, the genetic particle swarm is cross-operated to obtain an updated particle swarm;

[0057] The fitness function is used to evaluate each UAV inspection path in the updated particle swarm and calculate the corresponding fitness value;

[0058] Record and update the global optimal solution;

[0059] Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to the above step of obtaining the genetic particle swarm, otherwise the current global optimal solution is used as the first UAV inspection planning path.

[0060] (III) Beneficial effects

[0061] Compared with the prior art, the path planning method and system of intelligent engineering inspection equipment provided by the present invention has the following beneficial effects:

[0062] 1) A triangular route method is used to obtain multiple UAV inspection paths, and a UAV inspection path set is established. The UAV inspection path set is used as the initial population, and individual selection is performed according to the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm. The genetic particle swarm is cross-operated based on the preset collision crossover strategy to obtain an updated particle swarm. By using the improved genetic algorithm for iterative optimization, the optimized first UAV inspection planning path can be obtained;

[0063] 2) Using the camera equipment carried by the drone to perform a three-dimensional scan of the inspection area, generate corresponding point cloud data, register the point cloud data, construct a point cloud map, extract feature information of the point cloud map, and use the Fermat curve path planning algorithm to plan the path of the point cloud map, so that the second drone inspection planning path can be obtained according to the feature information of the point cloud map;

[0064] 3) Combine the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path, so that a UAV inspection planning path with better optimization can be flexibly generated according to the actual situation of the inspection area, effectively improving the inspection efficiency and inspection effect of the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 It is a schematic diagram of the process of the present invention;

[0067] Figure 2 A schematic diagram of a process for obtaining a first unmanned aerial vehicle inspection planning path in the present invention;

[0068] Figure 3 The figure is a schematic diagram of the process of registering point cloud data and constructing a point cloud map in the present invention. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] A path planning method for smart engineering inspection equipment, such as Figure 1 and Figure 2 As shown, S1, using the triangular route method to obtain multiple drone inspection paths, and establish a drone inspection path set, specifically including:

[0071] S11. Determine the inspection starting point and the inspection end point in the inspection area, and draw multiple drone inspection paths using the triangular route method based on the inspection starting point and the inspection end point;

[0072] S12. Perform a collision test on the multiple drawn drone inspection paths, retain the drone inspection paths that pass the collision test, and establish a drone inspection path set.

[0073] like Figure 1 and Figure 2 As shown, S2, the UAV inspection path set is used as the initial population, and the improved genetic algorithm is used to optimize to obtain the first UAV inspection planning path, which specifically includes:

[0074] S21, taking the UAV inspection path set as the initial population, and calculating the initial fitness value of each UAV inspection path;

[0075] S22, performing individual selection according to the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm;

[0076] S23, performing a crossover operation on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm;

[0077] S24, using the fitness function to evaluate each drone inspection path in the updated particle swarm and calculate the corresponding fitness value;

[0078] S25, record and update the global optimal solution;

[0079] S26. Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to S22. Otherwise, use the current global optimal solution as the first UAV inspection planning path.

[0080] Specifically, in S23, a crossover operation is performed on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm, including:

[0081] Based on the preset collision crossover strategy, the UAV inspection paths that failed the collision test were cross-calculated with each UAV inspection path in the genetic particle swarm with a preset probability to obtain an updated particle swarm.

[0082] The above technical scheme adopts the triangular route method to obtain multiple UAV inspection paths, establishes a UAV inspection path set, uses the UAV inspection path set as the initial population, performs individual selection according to the fitness value of each UAV inspection path and the preset triangular segmentation algorithm, obtains a genetic particle swarm, performs crossover operation on the genetic particle swarm based on the preset collision crossover strategy, obtains an updated particle swarm, and uses the improved genetic algorithm for iterative optimization to obtain the optimized first UAV inspection planning path.

[0083] like Figure 1 As shown, S3 uses the camera equipment carried by the drone to perform a three-dimensional scan of the inspection area to generate corresponding point cloud data.

[0084] S4. Register the point cloud data and build a point cloud map, such as Figure 3 As shown, specifically including:

[0085] S41, determining a reference coordinate system, and transforming the point cloud data into the reference coordinate system;

[0086] S42, using a nearest neighbor algorithm to find matching point pairs between the point cloud data and the target point cloud data;

[0087] S43, with the goal of minimizing the distance error of the matching point pairs, calculating the translation matrix and the rotation matrix to obtain the registration parameters;

[0088] S44, transforming the point cloud data into the target coordinate system using the registration parameters, and fusing them to obtain a point cloud map.

[0089] 1) In S42, the nearest neighbor algorithm is used to find the matching point pairs between the point cloud data and the target point cloud data, such as Figure 3 As shown, including:

[0090] S421, calculating the distances between the point cloud data and all points in the target point cloud data, and sorting them from small to large;

[0091] S422, in the target point cloud data, taking the first m closest target points as the nearest neighbor points of the point cloud data;

[0092] S423, calculating the distance between the nearest neighbor point of the point cloud data and all the points in the point cloud data, and sorting them from small to large;

[0093] S424. In the point cloud data, the first n closest points are taken as the nearest neighbor points of the target point, and the nearest neighbor points of the point cloud data and the nearest neighbor points of the target point are taken as matching point pairs.

[0094] 2) In S43, the translation matrix and the rotation matrix are calculated with the goal of minimizing the distance error of the matching point pairs to obtain the registration parameters, such as Figure 3 As shown, including:

[0095] S431, fitting the distance error function between the point cloud data and the target point cloud data using the least square method according to the matching points;

[0096] S432, deriving the distance error function, calculating the translation matrix and the rotation matrix, and obtaining the registration parameters.

[0097] S5. Extract feature information of the point cloud map, and use the Fermat curve path planning algorithm to plan the path of the point cloud map to obtain the second UAV inspection planning path, which specifically includes:

[0098] S51, extracting feature information of the point cloud map using a convolutional neural network;

[0099] S52, constructing a Cartesian parameter equation of a Fermat curve, and calculating equation expressions of a first segment Fermat clothoid curve and a second segment Fermat clothoid curve according to different initial points and initial cutting angles at different turns;

[0100] S53, treating the first segment of the Fermat clothoid curve and the second segment of the Fermat clothoid curve as the same segment of the curve with opposite directions, and calculating the velocity and acceleration parameter equations of the Fermat clothoid curve;

[0101] S54, eliminate singularities by changing variables, and simplify velocity and acceleration parameter equations by using amplitude-phase expression;

[0102] S55. After eliminating the singular point, the FS curve is used for path tracking, and at the same time, path planning is performed on the feature information of the point cloud map to obtain the second UAV inspection planning path.

[0103] The above technical solution uses the camera equipment carried by the drone to perform a three-dimensional scan of the inspection area, generate corresponding point cloud data, align the point cloud data, construct a point cloud map, extract the feature information of the point cloud map, and use the Fermat curve path planning algorithm to plan the path of the point cloud map, so that the second drone inspection planning path can be obtained according to the feature information of the point cloud map.

[0104] S6. Combine the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

[0105] The above technical solution combines the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path, so that it can flexibly generate a UAV inspection planning path with better optimization according to the actual situation of the inspection area, effectively improving the inspection efficiency and inspection effect of the construction site.

[0106] On the basis of the path planning method of the smart engineering inspection equipment disclosed above, the technical solution of the present application also discloses a path planning system for smart engineering inspection equipment, including a drone inspection path set establishment module, a first drone inspection planning path generation module, a point cloud data acquisition module, a point cloud map construction module, a second drone inspection planning path generation module and a drone inspection planning path generation module;

[0107] The UAV inspection path set establishment module uses the triangulation route method to obtain multiple UAV inspection paths and establish the UAV inspection path set;

[0108] The first UAV inspection planning path generation module uses the UAV inspection path set as the initial population and uses an improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path;

[0109] The point cloud data acquisition module receives the 3D scanning data of the inspection area from the camera device carried by the drone and generates the corresponding point cloud data;

[0110] Point cloud map construction module, which registers point cloud data and builds point cloud maps;

[0111] The second UAV inspection planning path generation module extracts the feature information of the point cloud map and uses the Fermat curve path planning algorithm to plan the path of the point cloud map to obtain the second UAV inspection planning path;

[0112] The UAV inspection planning path generation module combines the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

[0113] Specifically, the first UAV inspection planning path generation module uses the UAV inspection path set as the initial population, and uses the improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path, including:

[0114] The UAV inspection path set is used as the initial population, and the initial fitness value of each UAV inspection path is calculated;

[0115] Individual selection is performed based on the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm;

[0116] Based on the preset collision crossover strategy, the genetic particle swarm is cross-operated to obtain an updated particle swarm;

[0117] The fitness function is used to evaluate each UAV inspection path in the updated particle swarm and calculate the corresponding fitness value;

[0118] Record and update the global optimal solution;

[0119] Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to the above step of obtaining the genetic particle swarm, otherwise the current global optimal solution is used as the first UAV inspection planning path.

[0120] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A path planning method for intelligent engineering inspection equipment, characterized in that: The following steps are involved: S1. Use the triangular route method to obtain multiple drone inspection paths and establish a drone inspection path set; S2, taking the UAV inspection path set as the initial population, using the improved genetic algorithm to find the optimal solution, and obtaining the first UAV inspection planning path; S3, using the camera equipment carried by the drone to perform a three-dimensional scan of the inspection area and generate corresponding point cloud data; S4, registering the point cloud data and constructing a point cloud map; S5, extracting feature information of the point cloud map, and using the Fermat curve path planning algorithm to perform path planning on the point cloud map to obtain a second UAV inspection planning path; S6. Combine the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

2. The path planning method of the intelligent engineering inspection equipment according to claim 1 is characterized in that: In S1, the triangular route method is used to obtain multiple drone inspection paths and establish a drone inspection path set, including: S11. Determine the inspection starting point and the inspection end point in the inspection area, and draw multiple drone inspection paths using the triangular route method based on the inspection starting point and the inspection end point; S12. Perform a collision test on the multiple drawn drone inspection paths, retain the drone inspection paths that pass the collision test, and establish a drone inspection path set.

3. The path planning method of the intelligent engineering inspection equipment according to claim 2 is characterized in that: In S2, the UAV inspection path set is used as the initial population, and the improved genetic algorithm is used for optimization to obtain the first UAV inspection planning path, including: S21, taking the UAV inspection path set as the initial population, and calculating the initial fitness value of each UAV inspection path; S22, performing individual selection according to the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm; S23, performing a crossover operation on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm; S24, using the fitness function to evaluate each drone inspection path in the updated particle swarm and calculate the corresponding fitness value; S25, record and update the global optimal solution; S26. Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to S22. Otherwise, use the current global optimal solution as the first UAV inspection planning path.

4. The path planning method of the intelligent engineering inspection equipment according to claim 3 is characterized by: In S23, a crossover operation is performed on the genetic particle swarm based on a preset collision crossover strategy to obtain an updated particle swarm, including: Based on the preset collision crossover strategy, the UAV inspection paths that failed the collision test were cross-calculated with each UAV inspection path in the genetic particle swarm with a preset probability to obtain an updated particle swarm.

5. The path planning method of the intelligent engineering inspection equipment according to claim 1 is characterized in that: S4 aligns the point cloud data and builds a point cloud map, including: S41, determining a reference coordinate system, and transforming the point cloud data into the reference coordinate system; S42, using a nearest neighbor algorithm to find matching point pairs between the point cloud data and the target point cloud data; S43, with the goal of minimizing the distance error of the matching point pairs, calculating the translation matrix and the rotation matrix to obtain the registration parameters; S44, transforming the point cloud data into the target coordinate system using the registration parameters, and fusing them to obtain a point cloud map.

6. The path planning method of the intelligent engineering inspection equipment according to claim 5 is characterized by: In S42, the nearest neighbor algorithm is used to find matching point pairs between the point cloud data and the target point cloud data, including: S421, calculating the distances between the point cloud data and all points in the target point cloud data, and sorting them from small to large; S422, in the target point cloud data, taking the first m closest target points as the nearest neighbor points of the point cloud data; S423, calculating the distance between the nearest neighbor point of the point cloud data and all the points in the point cloud data, and sorting them from small to large; S424. In the point cloud data, the first n closest points are taken as the nearest neighbor points of the target point, and the nearest neighbor points of the point cloud data and the nearest neighbor points of the target point are taken as matching point pairs.

7. The path planning method of the intelligent engineering inspection equipment according to claim 5 is characterized by: In S43, the translation matrix and the rotation matrix are calculated with the goal of minimizing the distance error of the matching point pairs to obtain the registration parameters, including: S431, fitting the distance error function between the point cloud data and the target point cloud data using the least square method according to the matching points; S432, deriving the distance error function, calculating the translation matrix and the rotation matrix, and obtaining the registration parameters.

8. The path planning method of the intelligent engineering inspection equipment according to claim 5 is characterized by: S5 extracts the feature information of the point cloud map, and uses the Fermat curve path planning algorithm to plan the path of the point cloud map to obtain the second UAV inspection planning path, including: S51, extracting feature information of the point cloud map using a convolutional neural network; S52, constructing a Cartesian parameter equation of a Fermat curve, and calculating equation expressions of a first segment Fermat clothoid curve and a second segment Fermat clothoid curve according to different initial points and initial cutting angles at different turns; S53, treating the first segment of the Fermat clothoid curve and the second segment of the Fermat clothoid curve as the same segment of the curve with opposite directions, and calculating the velocity and acceleration parameter equations of the Fermat clothoid curve; S54, eliminate singularities by changing variables, and simplify velocity and acceleration parameter equations by using amplitude-phase expression; S55. After eliminating the singular point, the FS curve is used for path tracking, and at the same time, path planning is performed on the feature information of the point cloud map to obtain the second UAV inspection planning path.

9. A path planning system for smart engineering inspection equipment, used to execute the path planning method for smart engineering inspection equipment according to claim 1, characterized in that: It includes a UAV inspection path set establishment module, a first UAV inspection planning path generation module, a point cloud data acquisition module, a point cloud map construction module, a second UAV inspection planning path generation module and a UAV inspection planning path generation module; The UAV inspection path set establishment module uses the triangulation route method to obtain multiple UAV inspection paths and establish the UAV inspection path set; The first UAV inspection planning path generation module uses the UAV inspection path set as the initial population and uses an improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path; The point cloud data acquisition module receives the 3D scanning data of the inspection area from the camera device carried by the drone and generates the corresponding point cloud data; Point cloud map construction module, which registers point cloud data and builds point cloud maps; The second UAV inspection planning path generation module extracts the feature information of the point cloud map and uses the Fermat curve path planning algorithm to plan the path of the point cloud map to obtain the second UAV inspection planning path; The UAV inspection planning path generation module combines the first UAV inspection planning path and the second UAV inspection planning path to generate a UAV inspection planning path.

10. The path planning system for intelligent engineering inspection equipment according to claim 9, characterized in that: The first UAV inspection planning path generation module uses the UAV inspection path set as the initial population and uses an improved genetic algorithm to perform optimization to obtain the first UAV inspection planning path, including: The UAV inspection path set is used as the initial population, and the initial fitness value of each UAV inspection path is calculated; Individual selection is performed based on the fitness value of each UAV inspection path and the preset triangular segmentation algorithm to obtain a genetic particle swarm; Based on the preset collision crossover strategy, the genetic particle swarm is cross-operated to obtain an updated particle swarm; The fitness function is used to evaluate each UAV inspection path in the updated particle swarm and calculate the corresponding fitness value; Record and update the global optimal solution; Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to the above step of obtaining the genetic particle swarm, otherwise the current global optimal solution is used as the first UAV inspection planning path.

Images