Method and system for optimizing inspection path of unmanned aerial vehicle

Abstract

The invention relates to the technical field of unmanned aerial vehicle inspection, in particular to an unmanned aerial vehicle inspection path optimization method and system, and the method comprises the steps: obtaining a plurality of inspection regions in a stock ground global map, and determining the scanning density of the inspection regions; according to the scanning density, calculating the scanning electric quantity for scanning each inspection area along a preset track; in response to the situation that the residual electric quantity of the unmanned aerial vehicle is not smaller than the electric quantity required by the global optimal path, taking the global optimal path as an inspection path, otherwise, deleting any inspection area in the global optimal path until the residual electric quantity is not smaller than the electric quantity required by the global optimal path, and obtaining the inspection path; and obtaining inspection paths of the deleted inspection areas until all the inspection paths cover all the inspection areas. According to the technical scheme of the invention, the optimization result of the inspection path can be accurately obtained on the premise that the unmanned aerial vehicle can return safely.

Description

Technical Field

[0001] This application relates to the technical field of UAV inspection, and in particular, to an optimization method and system for the inspection path of a UAV. Background Art

[0002] As a storage place for materials such as sand, gravel, and production raw materials, the material yard undertakes the tasks of storing and transferring materials; the amount of materials in the material yard has a significant impact on the production scheduling plan of the enterprise. Therefore, it is necessary to inspect the material yard regularly or irregularly to obtain the amount of materials in the material yard.

[0003] Currently, the patent application document with the publication number CN111256703A discloses a multi-rotor UAV inspection path planning method. The method includes: taking the minimum battery energy consumption and the cost of avoiding backlight as the objective function, and completing the path planning through an improved ant colony algorithm and an improved A* hybrid algorithm; the specific steps are as follows: Step 1, to ensure the safety and low energy consumption of the inspection, establish an objective function with the minimum battery energy consumption and the cost of avoiding backlight; Step 2, analyze the influencing factors of the battery energy consumption of the multi-rotor UAV during inspection, and determine the hovering energy consumption and the cruising energy consumption; Step 3, determine the relationship between the sunlight and the inspection track of the multi-rotor UAV; Step 4, model the three-dimensional point cloud model of the object to be inspected obtained by scanning, and input all the viewpoint coordinates during the cruising process at the same time; Step 5, use the improved ant colony algorithm to output the optimal cruising path, use the improved A* hybrid algorithm to output the optimal flight path between adjacent viewpoints, and finally output the optimal track.

[0004] The above method takes the minimum battery energy consumption and the cost of avoiding backlight as the objective function, and provides an optimal path with low energy consumption and avoiding backlight for UAV inspection; however, the above method does not consider the impact of the remaining battery power of the UAV during the inspection process on the inspection path, and cannot ensure that the UAV obtains an accurate inspection path on the premise of being able to return safely. Summary of the Invention

[0005] In order to solve the technical problem of inaccurate UAV inspection paths, this application provides an optimization method and system for UAV inspection paths, which can ensure the optimization result of accurately obtaining the inspection path on the premise that the UAV can return safely.

[0006] In the first aspect of the present application, an optimization method for the inspection path of an unmanned aerial vehicle is provided. The optimization method includes: performing threshold segmentation on the global map of the stockyard to obtain multiple inspection areas, and determining the scanning density of each inspection area according to the complexity of the gradient information within each inspection area; determining the preset trajectory of each inspection area, and calculating the scanning power required to scan each inspection area along the preset trajectory; in response to the remaining power of the unmanned aerial vehicle being not less than the power required for the global optimal path, taking the global optimal path as the inspection path, otherwise, deleting any inspection area in the global optimal path until the remaining power is not less than the power required for the global optimal path, and obtaining the inspection path; obtaining the inspection path of the deleted inspection area until each inspection path covers all inspection areas. The method for obtaining the global optimal path is: obtaining the permutations and combinations of the preset trajectories of each inspection area; taking the charging position as the initial position, obtaining the flight paths from the initial position to the two endpoints of the first preset trajectory in any permutation and combination, taking the endpoint with the shortest flight path as the starting point and the other endpoint as the ending point; taking the ending point of the first preset trajectory as the initial position, successively obtaining the starting point and the ending point of each preset trajectory, and obtaining the flight path from the ending point of the last preset trajectory to the charging position, to obtain the global path of the permutation and combination; the global optimal path is the global path with the minimum total length.

[0007] The global map of the stockyard is obtained by using the image acquisition device deployed in the stockyard, and then the material stacking area in the stockyard is determined, and the material stacking area is used as the inspection area; the complexity of the gradient information within the inspection area is used to measure the scanning difficulty within the inspection area, and a larger scanning density is assigned to the inspection area with a larger complexity to accurately calculate the material quantity of each inspection area; further, the scanning power required to scan each inspection area along the preset trajectory is calculated, and the power required for the global optimal path is obtained, and the remaining power of the unmanned aerial vehicle is compared with the power required for the global optimal path. If the remaining power of the unmanned aerial vehicle is not less than the power required for the global optimal path, then the global optimal path is taken as the inspection path, otherwise, any inspection area in the global optimal path is deleted until the inspection path is obtained; the inspection path of the deleted inspection area is obtained again until each inspection path covers all inspection areas; realizing the automatic batching of the inspection tasks to ensure that the unmanned aerial vehicle can accurately obtain the optimization result of the inspection path on the premise of being able to return safely.

[0008] Preferably, the step of obtaining multiple inspection areas includes: converting the global map of the stockyard to the HSV space to obtain the hue channel map; using the maximum inter-class variance method to determine the segmentation threshold of the hue channel map, and performing threshold segmentation on the hue channel map to obtain a binary map; performing connected component analysis on the binary map, obtaining multiple connected components, and taking the circumscribed rectangle of each connected component as the inspection area.

[0009] Precisely identify the stacking area of materials in the stockyard, and use the material stacking area as the inspection area. During the drone inspection process, only by using the lidar carried by the drone to scan the inspection area, the volume of materials in the inspection area can be calculated.

[0010] Preferably, the scanning density of the inspection area is: where is the density reference value, is the complexity of the gradient information within the inspection area, is the maximum allowable value of the gradient information, and is a preset coefficient. When the complexity of the gradient information is large, it means that the materials are stacked with irregular thickness in the inspection area. To accurately obtain the thickness of each position point in the inspection area and then accurately calculate the volume of materials in the inspection area, it is necessary to increase the scanning density of the inspection area.

[0011] Preferably, the method for obtaining the preset coefficient includes: scanning the inspection area with any scanning density to obtain the material thickness at each scanning position in the inspection area, interpolating the material thickness at each scanning position to obtain the material thickness at each position point in the inspection area; integrating the material thickness at each position point on the plane where the inspection area is located to obtain the material quantity in the inspection area; plotting a material quantity curve with the scanning density as the abscissa and the material quantity as the ordinate, and taking the scanning density corresponding to the inflection point in the material quantity curve as the density label of the inspection area; calculating the preset coefficient based on the complexity of the inspection area and the density label.

[0012] Preferably, determining the preset trajectory of each inspection area includes: obtaining the size information of the inspection area, where the size information includes the length and width; dividing the shortest side of the length and width according to the scanning width of the lidar

[0013] to obtain a plurality of scanning sub-areas, and constructing the preset trajectory of the inspection area based on the midlines of each scanning sub-area.

[0014] Preferably, calculating the scanning power consumption for scanning each inspection area along the preset trajectory according to the scanning density includes: obtaining the scanning power corresponding to the scanning density of the inspection area; the scanning power consumption of the inspection area is: where ; and are the flight power and the scanning power respectively, is the preset flight speed, is the length of the preset trajectory.

[0015] Due to the different scanning densities in each inspection area, the scanning power consumption for completing each inspection area is different. Accurately calculating the scanning power consumption for each inspection area provides a data basis for ensuring the safe return of the UAV during the subsequent path optimization process.

[0016] Preferably, the power required for the globally optimal path is the sum of the scanning power consumption for each inspection area and the flight power consumption for the flight paths between the inspection areas.

[0017] Accurately quantify the power required for the UAV to complete the scanning of each inspection area along the globally optimal path.

[0018] Preferably, deleting any inspection area in the globally optimal path includes: obtaining the globally optimal path again after deleting any inspection area and calculating the reduction in the power required for the globally optimal path after deleting the inspection area; deleting the inspection area corresponding to the maximum reduction.

[0019] The larger the reduction, the greater the impact of the inspection area on the power required for the globally optimal path. Deleting this inspection area can effectively reduce the power required for the globally optimal path, thereby quickly obtaining the inspection path.

[0020] Preferably, after completing the scanning of each inspection area along each inspection path, the optimization method further includes: interpolating the material thickness at each scanning position in the inspection area to obtain the material thickness at each position point in the inspection area; integrating the material thickness at each position point on the plane where the inspection area is located to obtain the material quantity in the inspection area; taking the sum of the material quantities in each inspection area as the total material quantity in the material yard.

[0021] In the second aspect of the present application, an optimization system for the UAV inspection path is further provided, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the optimization method for the UAV inspection path according to the first aspect of the present application is implemented.

[0022] The technical solution of the present application has the following beneficial technical effects: Use the image acquisition device deployed in the storage yard to obtain the global map of the storage yard, and then determine the material stacking area in the storage yard. Take the material stacking area as the inspection area. Measure the scanning difficulty in the inspection area according to the complexity of the gradient information in the inspection area, and allocate a larger scanning density to the inspection area with a larger complexity to accurately calculate the material quantity in each inspection area. Further, calculate the scanning power for scanning each inspection area along the preset trajectory according to the scanning density, and obtain the power required for the global optimal path. Compare the remaining power of the drone with the power required for the global optimal path. If the remaining power of the drone is not less than the power required for the global optimal path, then take the global optimal path as the inspection path. Otherwise, delete any inspection area in the global optimal path until the inspection path is obtained. Obtain the inspection path of the deleted inspection area again until each inspection path covers all inspection areas. On the premise of ensuring that the drone can return safely, realize the automatic batching of the inspection task, accurately obtain the optimization result of the inspection path, and then accurately obtain the material quantity in the storage yard. Description of the Drawings

[0023] Figure 1 is a flowchart of an optimization method for an unmanned aerial vehicle (UAV) inspection path according to an embodiment of the present application.

[0024] Figure 2 is a schematic diagram of scanning an inspection area along a preset trajectory according to an embodiment of the present application.

[0025] Figure 3 is a structural block diagram of an optimization system for an unmanned aerial vehicle (UAV) inspection path according to an embodiment of the present application. Detailed Embodiments

[0026] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0027] According to a first aspect of the present application, the present application provides an optimization method for an unmanned aerial vehicle (UAV) inspection path, which is used to inspect the material stacking area in a storage yard and determine the inspection path to accurately obtain the material quantity in the storage yard. Figure 1 is a flowchart of an optimization method for an unmanned aerial vehicle (UAV) inspection path according to an embodiment of the present application. As Figure 1 shown, the optimization method for the unmanned aerial vehicle (UAV) inspection path includes steps S101 to S103, which are described in detail below.

[0028] S101. Perform threshold segmentation on the overall view of the storage yard to obtain multiple inspection areas, and obtain the complexity of the gradient information in each inspection area. Determine the scanning density of the inspection area according to the complexity.

[0029] In one embodiment, the storage yard can be regarded as a warehouse for storing materials. The overall view of the storage yard is collected by an image acquisition device deployed inside the storage yard. The overall view of the storage yard is an RGB image, and the overall view of the storage yard can cover all positions in the storage yard. The overall view of the storage yard can reflect the material stacking areas in the storage yard. The purpose of using a drone to inspect the storage yard is to inspect each material stacking area, and then obtain the volume of all materials in the storage yard.

[0030] The material stacking areas in the overall view of the storage yard can be obtained according to the color difference between the materials and the ground of the storage yard. The material stacking areas are the inspection areas. Specifically, the step of obtaining multiple inspection areas includes: converting the overall view of the storage yard to the HSV space to obtain the hue channel map; using the Otsu method to determine the segmentation threshold of the hue channel map, and performing threshold segmentation on the hue channel map to obtain a binary image; performing connected component analysis on the binary image, obtaining multiple connected components, and taking the circumscribed rectangles of each connected component as the inspection areas.

[0031] Among them, the multiple connected components are multiple material stacking areas.

[0032] In this way, accurately identify the material stacking areas in the storage yard, and use the material stacking areas as the inspection areas. During the drone inspection process, only need to use the lidar carried by the drone to scan the inspection areas, and then the volume of the materials in the inspection areas can be calculated.

[0033] In one embodiment, the drone is equipped with a lidar to scan each inspection area to collect the material thickness at each position point in any inspection area, and then calculate the volume of the materials in the inspection area. Considering that the complexity of material stacking in different inspection areas is different, the difficulty of calculating the volume of materials in each inspection area will also vary. For example, if the materials are laid flat in the inspection area with the same thickness, scanning the inspection area with a smaller scanning density can accurately collect the material thickness, and then accurately calculate the volume of the materials in the inspection area. If the materials are stacked with irregular thickness in the inspection area, a smaller scanning density will ignore the thickness changes of the materials. Therefore, it is necessary to increase the scanning density to accurately obtain the thickness at each position point in the inspection area, and then accurately calculate the volume of the materials in the inspection area.

[0034] After grayscale processing the global map of the stockyard, calculate the gradient information of each position point within any inspection area. If the materials are laid flat in the inspection area with the same thickness, the gradient information of each position point is 0; on the contrary, if the materials are piled up with irregular thickness in the inspection area, for the position points with thickness changes, their gradient information is a value greater than 0, and the greater the thickness change, the greater the value of the gradient information; therefore, the scanning density of the inspection area can be determined according to the complexity of the gradient information within the inspection area.

[0035] Specifically, the complexity of the gradient information within the inspection area is the average gradient value within the inspection area and satisfies the relationship: ; is the allowable maximum value of the gradient information, and is the occurrence frequency of the gradient information within the inspection area

[0036] Furthermore, according to the complexity of the gradient information within the inspection area to determine the scanning density of the inspection area, the scanning density of the inspection area is: , is the density reference value, and is the complexity of the gradient information within the inspection area, is the allowable maximum value of the gradient information, and

[0037] is a preset coefficient. Among them, the value of the density reference value is , is the unit of the scanning density, indicating the number of laser points per square meter; the allowable maximum value of the gradient information is 255, which is used to normalize the complexity

[0038] Among them, the greater the complexity, the greater the scanning density needs to be increased to accurately calculate the material volume. The preset coefficient can control the growth rate of the scanning density with the complexity, and the value of the preset coefficient can be determined based on the historical scanning process. Specifically, the method for obtaining the preset coefficient includes: scanning the inspection area with an arbitrary scanning density to obtain the material thickness at each scanning position in the inspection area, interpolating the material thickness at each scanning position to obtain the material thickness at each position point in the inspection area; integrating the material thickness at each position point on the plane where the inspection area is located to obtain the material quantity in the inspection area; plotting a material quantity curve with the scanning density as the abscissa and the material quantity as the ordinate, and taking the scanning density corresponding to the inflection point in the material quantity curve as the density label of the inspection area; calculating the preset coefficient according to the complexity and density label of the inspection area.

[0039] It can be understood that when the scanning density is small, the material thickness at each position point in the inspection area cannot be accurately collected, and there is a large error in the obtained material quantity at this time; as the scanning density increases, the number of position points between adjacent scanning positions becomes smaller, and it is more able to accurately collect the material thickness at each position point in the inspection area, and the material quantity gradually approaches the true value; when the scanning density reaches the scanning density corresponding to the inflection point, the material quantity tends to be stable. At this time, increasing the scanning density further will not only not greatly increase the accuracy of the material quantity but also introduce a large amount of computational effort. Therefore, taking the scanning density corresponding to the inflection point as the density label can balance the material quantity accuracy and the computational effort.

[0040] In this way, determine the stacking area of the materials in the stockyard according to the global map of the stockyard, use the stacking area as the inspection area in the subsequent inspection process, and determine the scanning density of each inspection area in the inspection process according to the complexity of the gradient information to ensure that the material quantity in the stockyard can be accurately obtained after the inspection is completed.

[0041] S102, determine the preset trajectory of each inspection area, and calculate the scanning power consumption for scanning each inspection area along the preset trajectory according to the scanning density.

[0042] In one embodiment, the inspection area is a rectangular area. When the drone scans the inspection area along the preset trajectory at a preset flight height, a preset flight speed, and a corresponding scanning density, the larger the size information of the inspection area, the greater the scanning density, and the longer the scanning duration required, resulting in a greater scanning power consumption for completing the scanning.

[0043] Please refer to Figure 2 , which is a schematic diagram of scanning the inspection area along the preset trajectory according to an embodiment of the present application. The preset trajectory of the inspection area is related to the size information of the inspection area, and the size information of the inspection area includes the length and width; to reduce the number of times the drone changes the flight direction in the preset trajectory, according to the scanning width of the lidar Divide the shortest side among the length and width to obtain multiple scanning sub-regions, and construct a preset trajectory of the inspection area according to the mid-line of each scanning sub-region; Figure 2 A total of 4 scanning sub-regions are obtained for the shown inspection area. When the UAV flies along the mid-line of any scanning sub-region, all position points within the scanning sub-region can be scanned. Therefore, Figure 2 The preset trajectory shown includes the mid-lines of 4 scanning sub-regions and 3 turnings of the flight direction.

[0044] In one embodiment, since the scanning densities of each inspection area are different, resulting in different scanning power consumptions for completing each inspection area, to ensure that the UAV can safely return after the inspection, it is necessary to accurately predict the scanning power consumption of each inspection area based on the size information and scanning density of each inspection area. Specifically, calculating the scanning power consumption for scanning each inspection area along the preset trajectory includes: obtaining the scanning power corresponding to the scanning density of the inspection area; the scanning power consumption of the inspection area is: ; and are the flight power and the scanning power respectively, is the preset flight speed, is the length of the preset trajectory. Among them, the flight power is related to the model of the UAV.

[0045] In this way, the scanning power consumption of each inspection area is determined.

[0046] S103, in response to the remaining power of the UAV being not less than the required power of the global optimal path, use the global optimal path as the inspection path; otherwise, delete any inspection area in the global optimal path until the remaining power is not less than the required power of the global optimal path to obtain the inspection path.

[0047] In one embodiment, the obtaining of the global optimal path includes: obtaining the permutations and combinations of the preset trajectories of each inspection area; taking the charging position as the initial position, obtaining the flight paths from the initial position to the two endpoints of the first preset trajectory in any permutation and combination, taking the endpoint with the shortest flight path as the starting point and the other endpoint as the ending point; taking the ending point of the first preset trajectory as the initial position, successively obtaining the starting points and ending points of each preset trajectory, and obtaining the flight path from the ending point of the last preset trajectory to the charging position to obtain the global path of the permutation and combination; taking the global path with the minimum total length as the global optimal path.

[0048] Exemplarily, for the convenience of description, the five inspection areas are sequentially denoted as a, b, c, d, and e, and the charging position is denoted as 0; each inspection area corresponds to a preset trajectory, and each preset trajectory corresponds to two endpoints. The two endpoints in the preset trajectory corresponding to the inspection area a are denoted as a1 and a2. For the permutation and combination cdeab, first, taking the charging position 0 as the initial position, the flight paths from the initial position to the two endpoints of the first preset trajectory (i.e., the preset trajectory corresponding to the inspection area c) are obtained by using the path planning algorithm, and are respectively denoted as and ; and the flight path with the shortest flight path is Taking as the starting point of the first preset trajectory, as the ending point of the first preset trajectory; further, taking the ending point of the first preset trajectory as the initial position, the flight paths from the initial position to the two endpoints of the next preset trajectory (i.e., the preset trajectory corresponding to the inspection area d) are obtained, and then the starting point and ending point of the next preset trajectory are determined. In this way, the starting points and ending points of all preset trajectories in the permutation and combination cdeab are obtained. Please refer to Table 1, which shows the starting points and ending points of each preset trajectory in the permutation and combination cdeab.

[0049] Table 1 Starting points and ending points of each preset trajectory

[0050] In this way, the global path of the permutation and combination cdeab is obtained as follows: ; where is the preset trajectory corresponding to the inspection area c, is the flight path obtained by using the path planning algorithm from to ; The path planning algorithm can adopt the A* algorithm or the artificial potential field method, and the present application does not make any restrictions. After obtaining the global paths of all permutations and combinations, the global path with the minimum total length is taken as the global optimal path. In one embodiment, the required power of the global optimal path is the sum of the scanning power of each inspection area and the flight power consumption of the flight paths between each inspection area.

[0051] After obtaining the flight path, calculate the flight power consumption of each flight path. In the scenario of the embodiment of the present application, the unmanned aerial vehicle conducts inspections at a set flight altitude and a set flight speed, and the unmanned aerial vehicle does not need to perform scanning during the process of flying along the flight path to the next inspection area. Therefore, the ratio of the length of any flight path to the set flight speed is taken as the predicted flight time, and the product of the predicted flight time and the flight power is taken as the flight power consumption of the flight path.

[0052] In one embodiment, in response to the remaining power of the drone being not less than the required power of the globally optimal path, it indicates that the remaining power of the drone can complete the scanning work of each inspection area and safely return to the charging position. The globally optimal path is used as the inspection path to obtain the optimization result of the drone inspection path. Conversely, in response to the remaining power of the drone being less than the required power of the globally optimal path, it indicates that the remaining power of the drone cannot support the scanning of all inspection areas. Any inspection area in the globally optimal path is deleted, and the remaining power is compared with the required power of the updated globally optimal path until the remaining power is not less than the required power of the updated globally optimal path, and the updated globally optimal path is used as the inspection path.

[0053] Among them, deleting any inspection area in the globally optimal path includes: the any inspection area is the last inspection area in the globally optimal path. Exemplarily, if the globally optimal path is: ; and the last inspection area is b, then after deleting the last inspection area in the globally optimal path, the updated globally optimal path obtained is: .

[0054] In another embodiment, deleting any inspection area in the globally optimal path includes: obtaining the globally optimal path again after deleting any inspection area, and calculating the reduction amount of the required power of the globally optimal path after deleting the inspection area; deleting the inspection area corresponding to the maximum reduction amount.

[0055] Among them, the larger the reduction amount, the greater the influence degree of the inspection area on the required power of the globally optimal path. Deleting this inspection area can effectively reduce the required power of the globally optimal path, so as to quickly obtain the inspection path.

[0056] In this way, the globally optimal path covering all inspection areas is obtained. The globally optimal path includes the preset trajectories within each inspection area and the flight paths between each inspection area. The preset trajectories can ensure the scanning accuracy of each inspection area and accurately calculate the material quantity of each scanning area; the flight paths can ensure the shortest path between each inspection area and ensure the inspection efficiency. Further, the automatic batching of the inspection tasks is realized by comparing the remaining power of the drone and the required power of the globally optimal path, and the subsequent inspection areas in the globally optimal path are deleted to ensure that the drone can return safely.

[0057] S104, obtain the inspection paths of the deleted inspection areas until each inspection path covers all inspection areas.

[0058] In one embodiment, when a patrol path cannot cover all the patrol areas, it is necessary to obtain the globally optimal path of each deleted patrol area again as the patrol path of each deleted patrol area until all the patrol paths cover all the patrol areas and the scanning of all the patrol areas can be completed.

[0059] It should be noted that to complete the scanning of all the patrol areas, at least one patrol path will be obtained. Multiple drones can be deployed, and one drone can conduct patrols along one patrol path simultaneously to improve the patrol efficiency. Or only one drone can be deployed. When the drone finishes patrolling one patrol path, it returns to the charging position and starts patrolling the next patrol path after charging is completed.

[0060] In one embodiment, after scanning each patrol area along each patrol path, the optimization method further includes: interpolating the material thickness at each scanned position in the patrol area to obtain the material thickness at each position point in the patrol area; integrating the material thickness at each position point on the plane where the patrol area is located to obtain the material quantity in the patrol area; and taking the sum of the material quantities in each patrol area as the total material quantity in the stockyard.

[0061] Among them, the patrol area of the material quantity is: ; and are the width and length of the patrol area respectively, and is the material thickness at the position point in the patrol area.

[0062] In this way, the patrol task of the stockyard is completed, and the total material quantity in the stockyard is accurately calculated.

[0063] According to the second aspect of the present application, the present application also provides an optimization system for the patrol path of drones. Figure 3 is a structural block diagram of an optimization system for the patrol path of drones according to an embodiment of the present application. As Figure 3 shown, the system 50 includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the optimization method for the patrol path of drones according to the first aspect of the present application is implemented. The system also includes a communication bus and a communication interface and other components well known to those skilled in the art. Their settings and functions are known in the art, so they will not be described in detail here.

[0064] It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application.

Claims

1. An optimization method for the inspection path of an unmanned aerial vehicle, characterized in that, The optimization method includes: Performing threshold segmentation on the global map of the stockyard to obtain multiple inspection areas, and determining the scanning density of each inspection area according to the complexity of the gradient information within each inspection area; determining the preset trajectory of each inspection area, and calculating the scanning power for scanning each inspection area along the preset trajectory according to the scanning density; In response to the remaining power of the drone being not less than the required power of the global optimal path, taking the global optimal path as the inspection path; otherwise, deleting any inspection area in the global optimal path until the remaining power is not less than the required power of the global optimal path to obtain the inspection path; Obtaining the inspection paths of the deleted inspection areas until each inspection path covers all inspection areas; The method for obtaining the global optimal path is: obtaining the permutations and combinations of the preset trajectories of each inspection area; taking the charging position as the initial position, obtaining the flight paths from the initial position to the two endpoints of the first preset trajectory in any permutation and combination, taking the endpoint with the shortest flight path as the starting point and the other endpoint as the ending point; taking the ending point of the first preset trajectory as the initial position, sequentially obtaining the starting points and ending points of each preset trajectory, and obtaining the flight path from the ending point of the last preset trajectory to the charging position to obtain the global path of the permutation and combination; the global optimal path is the global path with the minimum total length.

2. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, wherein The step of obtaining multiple inspection areas includes: converting the global map of the stockyard to the HSV space to obtain the hue channel map; using the Otsu method to determine the segmentation threshold of the hue channel map, and performing threshold segmentation on the hue channel map to obtain a binary map; performing connected component analysis on the binary map to obtain multiple connected components and taking the circumscribed rectangles of each connected component as the inspection areas.

3. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, wherein, Inspection area The scanning density of is as follows: , is the density reference value, is the complexity of the gradient information within the inspection area , is the maximum allowable value of the gradient information, is a preset coefficient.

4. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 3, characterized in that, The method for obtaining the preset coefficient includes: Scanning the inspection area with an arbitrary scanning density to obtain the material thickness at each scanning position within the inspection area, and interpolating the material thickness at each scanning position to obtain the material thickness at each position point within the inspection area; Integrating the material thickness at each position point on the plane where the inspection area is located to obtain the material quantity within the inspection area; taking the scanning density as the abscissa and the material quantity as the ordinate to plot the material quantity curve, and taking the scanning density corresponding to the inflection point in the material quantity curve as the density label of the inspection area; calculating the preset coefficient according to the complexity and density label of the inspection area.

5. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, wherein Determining the preset trajectory of each inspection area includes: Obtaining the size information of the inspection area, where the size information includes the length and width; Dividing the shortest side of the length and width according to the scanning width of the lidar to obtain multiple scanning sub-areas, and constructing the preset trajectory of the inspection area according to the midlines of each scanning sub-area.

6. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, characterized in that Calculating the scanning power for scanning each inspection area along the preset trajectory according to the scanning density includes: Obtaining the scanning power corresponding to the scanning density of the inspection area; Inspection area Scanning power consumption is as follows: ; and are the flight power and scanning power respectively, is the preset flight speed, is the length of the preset trajectory.

7. A method for optimizing the inspection path of an unmanned aerial vehicle according to claim 1, characterized in that The required power of the global optimal path is the sum of the scanning power of each inspection area and the flight power consumption of the flight paths between each inspection area.

8. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, wherein Deleting any inspection area in the global optimal path includes: deleting any inspection area and then obtaining the global optimal path again, and calculating the reduction amount of the required power of the global optimal path after deleting the inspection area; deleting the inspection area corresponding to the maximum reduction amount.

9. The optimization method for the inspection path of an unmanned aerial vehicle according to claim 1, characterized in that, After completing the scanning of each inspection area along each inspection path, the optimization method further includes: Interpolating the material thickness at each scanned position in the inspection area to obtain the material thickness at each position point in the inspection area; Integrating the material thickness at each position point on the plane where the inspection area is located to obtain the material quantity in the inspection area; taking the sum of the material quantities in each inspection area as the total material quantity in the stockyard.

10. An optimization system for the inspection path of an unmanned aerial vehicle, characterized in that, It includes a processor and a memory, and the memory stores computer program instructions, which, when executed by the processor, implement an optimization method for an unmanned aerial vehicle inspection path according to any one of claims 1 to 9.

Images