A method and system for unmanned aerial vehicle navigation dynamic programming based on a patrol vehicle

Abstract

The application provides a kind of unmanned aerial vehicle navigation dynamic programming method and system based on inspection vehicle, it is related to tunnel inspection technology field, method includes following steps: S1, obtain the task amount that current inspection vehicle is patrolled in tunnel inside;S2, the navigation state of current unmanned aerial vehicle is global positioning mode, unmanned aerial vehicle obtains position information by multi-sensor fusion in global positioning mode;S3, detect whether the remaining power of current unmanned aerial vehicle is reduced to preset threshold;S4, whether current unmanned aerial vehicle can complete task amount in global positioning mode is judged in real time according to first flown distance and first power consumption;S5, according to tunnel inside, the target line located in tunnel inside and extending along tunnel is obtained, and the inspection car is patrolled in tunnel inside in the extension direction of target line, then the navigation state of current unmanned aerial vehicle is changed to target tracking mode, and the position information of unmanned aerial vehicle is obtained by inspection car in target tracking mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel inspection, in particular to a UAV navigation dynamic planning method and system based on an inspection vehicle. BACKGROUND

[0002] Due to the structural characteristics and terrain restrictions of the tunnel, the complexity and difficulty of its inspection are particularly prominent among numerous transportation infrastructure inspections. With the maturity of UAV technology, UAVs have been widely used in rescue, monitoring and other scenarios in recent years. UAVs have high flexibility and maneuverability, can easily cope with complex environments in tunnels, and have low cost, flexible and compact equipment, and high operational convenience, which has obvious advantages in tunnel inspection scenarios. However, there is no gnss signal in the tunnel, and the scene has high repetition and few geometric features in the movement direction, making it difficult for traditional slam algorithms to complete positioning. Therefore, current tunnel inspection generally needs to be assisted by a wheeled trolley, an odometer, RFID, and track markers to complete positioning.

[0003] However, the above method can only achieve positioning in the tunnel and cannot meet the actual intelligent demand of tunnel inspection. The UAV also needs to complete autonomous path planning and flight in the tunnel to achieve one-key inspection and improve the efficiency of tunnel inspection. Among them, the UAV that can stably fly in the tunnel is usually limited by the size of the aircraft and battery technology, and the flight time is generally 15-30 minutes, which is difficult to meet the demand of long tunnel autonomous inspection. SUMMARY

[0004] The purpose of the present application is to provide a UAV navigation dynamic planning method and system based on an inspection vehicle, which sets a navigation method for the UAV on the inspection vehicle to enable autonomous path planning and flight. Moreover, the energy consumption problem of the UAV is considered, and different navigation methods are set for the UAV to enable the UAV to automatically select and switch according to the energy consumption, thereby meeting the demand of long tunnel autonomous inspection.

[0005] To solve the above technical problems, the present application adopts the following scheme:

[0006] A UAV navigation dynamic planning method based on an inspection vehicle, the inspection vehicle inspects the inside of a tunnel, and a UAV machine box for charging a UAV and the UAV are provided on the inspection vehicle, and the dynamic planning method comprises the following steps:

[0007] S1, obtaining the task amount of the current inspection vehicle for inspecting the inside of a tunnel;

[0008] S2, matching the navigation state of the current UAV during the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current UAV is a global positioning mode, the UAV obtains position information through multi-sensor fusion in the global positioning mode, and then step S3 is performed.

[0009] S3, detecting whether the remaining power of the current UAV decreases to a preset threshold, if yes, turning to step S4;

[0010] S4, obtaining a first flown distance and a first power consumption generated by the UAV in the process of the current inspection vehicle inspecting the tunnel, and judging whether the current UAV can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption, if not, turning to step S5;

[0011] S5, changing the navigation state of the current UAV to a target tracking mode according to a target line located in the tunnel and extending along the tunnel, and obtaining the position information of the UAV by the inspection vehicle in the target tracking mode.

[0012] Further, in S2, the process of the UAV obtaining the position information by multi-sensor fusion in the global positioning mode is: in the global positioning mode, when the UAV inspects that there is a defect in the tunnel, the position information of the UAV is obtained by fusing the relative pose sensor carried by the UAV and the inertial sensor, the laser radar and the wheel odometer carried on the inspection vehicle.

[0013] Further, in S5, the process of the UAV obtaining the position information by the inspection vehicle in the target tracking mode is: in the target tracking mode, the inspection vehicle inspects the tunnel in the extension direction of the target line, and when the UAV inspects that there is a defect in the tunnel, the forward distance of the inspection vehicle is obtained by the wheel odometer carried on the inspection vehicle, and the position information of the UAV is obtained according to the forward distance of the inspection vehicle.

[0014] Further, the task amount includes a tunnel inspection range, and in the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current UAV is the global positioning mode, the UAV will autonomously plan a path according to the tunnel inspection range to obtain a first target path of the UAV, and fly along the first target path as navigation.

[0015] Further, the first flown distance is a flown distance generated when the UAV flies along the first target path as navigation in the global positioning mode, and the first power consumption is a power consumption generated when the UAV flies along the first target path as navigation in the global positioning mode.

[0016] Further, in S4, the process of judging whether the current UAV can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption is specifically:

[0017] The first target path corresponding to the first flown distance and the first power consumption amount is calculated to obtain the remaining first target path of the current UAV, the remaining first target path is taken as navigation to fly, the power drop amount generated when the UAV flies the remaining first target path as navigation in the global positioning mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the global positioning mode, and vice versa.

[0018] Further, the method further comprises a step S6, and the step S6 is:

[0019] S6, when the navigation state of the current UAV is the target tracking mode, the second flown distance and the second power consumption amount generated by the UAV in the process of the current inspection vehicle inspecting the tunnel are obtained, whether the current UAV can complete the task amount in the target tracking mode is judged in real time according to the second flown distance and the second power consumption amount, if not, the UAV navigation return value is controlled to the UAV case.

[0020] Further, the task amount includes a tunnel inspection range, when the navigation state of the current UAV is the target tracking mode in the process of the current inspection vehicle inspecting the tunnel, the UAV will plan a path according to the tunnel inspection range and the target line to obtain a second target path of the UAV, the second target path coincides with the target line, and the second target path is taken as navigation to fly.

[0021] Further, in the step S6, the process that whether the current UAV can complete the task amount in the target tracking mode is judged in real time according to the second flown distance and the second power consumption amount specifically includes:

[0022] The second target path corresponding to the second flown distance and the second power consumption amount is calculated to obtain the remaining second target path of the current UAV, the remaining second target path is taken as navigation to fly, the power drop amount generated when the UAV flies the remaining second target path as navigation in the target tracking mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the target tracking mode, and vice versa.

[0023] A UAV navigation dynamic planning system based on an inspection vehicle, applying the UAV navigation dynamic planning method based on the inspection vehicle, comprising:

[0024] An inspection task amount acquisition module: obtaining a task amount of the current inspection vehicle inspecting the inside of the tunnel;

[0025] The global positioning module of the unmanned plane: in the process of the current inspection vehicle inspecting the tunnel, the navigation state of the current unmanned plane is matched, if the navigation state of the current unmanned plane is the global positioning mode, the unmanned plane obtains the position information through multi-sensor fusion in the global positioning mode;

[0026] The power detection module: whether the remaining power of the current unmanned plane decreases to the preset threshold value is detected;

[0027] The unmanned plane navigation judgment module: the first flown distance and the first power consumption generated by the unmanned plane in the process of the current inspection vehicle inspecting the tunnel are obtained, and whether the current unmanned plane can complete the task amount in the global positioning mode is judged in real time according to the first flown distance and the first power consumption;

[0028] The unmanned plane navigation switching module: according to the target line located in the tunnel and extending along the tunnel obtained in the tunnel, the inspection vehicle inspects the inside of the tunnel in the extension direction of the target line, and the navigation state of the current unmanned plane is changed to the target tracking mode, and the unmanned plane obtains the position information through the inspection vehicle in the target tracking mode.

[0029] The beneficial effects of the present application are as follows:

[0030] The present application provides a kind of unmanned plane navigation dynamic programming method and system based on inspection vehicle, mainly applied to tunnel inspection, detects the defect in tunnel using inspection vehicle and unmanned plane, inspection vehicle and unmanned plane can communicate with each other, realize cooperative positioning, it is convenient to obtain accurate defect position, improve the inspection efficiency, however, in this scenario, the flight time of unmanned plane is generally 15~30min due to the limitation of aircraft size and battery technology, it is difficult to meet the demand of long tunnel autonomous inspection, therefore, the present application focuses on setting different navigation methods for inspection vehicle and unmanned plane, not only can make unmanned plane carry out autonomous path planning and flight, but also can make unmanned plane can automatically select and switch according to energy consumption, meet the demand of long tunnel autonomous inspection. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 It is the step schematic view of dynamic programming method in embodiment 1 of the present application;

[0032] Figure 2 It is the flow schematic view of fusing APF and BRRT* algorithm in embodiment 1 of the present application;

[0033] Figure 3 It is the flow schematic view of flying along fixed tracking object in embodiment 1 of the present application;

[0034] Figure 4 It is the flow schematic view of flying along fixed axis in embodiment 1 of the present application;

[0035] Figure 5 Figure 1 is a flowchart illustrating the process of autonomous navigation for the UAV returning to the unmanned vehicle to charge in Embodiment 1 of the present application;

[0036] Figure 6 Figure 2 is a flowchart illustrating the overall process of the dynamic programming method in Embodiment 1 of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The description of the at least one exemplary embodiment is actually only illustrative, but not as any limitation on the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort fall within the scope of the present application.

[0038] Unless otherwise specified, the relative arrangement, numerical expressions and values of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0039] It should be understood that the sizes of the various parts shown in the drawings are not drawn in accordance with the actual proportional relationship for the convenience of description.

[0040] In addition, the description of the well-known structures, functions and configurations can be omitted for the sake of clarity and conciseness. Those of ordinary skill in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0041] The technology, methods and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered as part of the authorized specification where appropriate.

[0042] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary, and not as a limitation. Thus, other examples of the exemplary embodiments can have different values.

[0043] The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments:

[0044] Embodiment 1

[0045] Due to the structural characteristics of the tunnel and the topographic restrictions, the complexity and difficulty of the inspection are particularly prominent among numerous traffic infrastructure inspections. With the maturity of unmanned aerial vehicle technology, unmanned aerial vehicles have been widely used in rescue, monitoring and other scenarios in recent years. Unmanned aerial vehicles have high flexibility and maneuverability, can easily cope with complex environments in tunnels, and have obvious advantages in tunnel inspection scenarios due to their low cost, flexible and compact equipment, and high operational convenience. However, there is no gnss signal in the tunnel, and the scene has high repeatability and few geometric features in the direction of motion, making it difficult for traditional active slam algorithms to complete positioning. Therefore, current tunnel inspections generally require the assistance of wheeled vehicles, odometers, RFID, and track markers to complete positioning.

[0046] However, the above method can only achieve positioning within the tunnel and cannot meet the actual intelligent tunnel inspection requirements. Unmanned aerial vehicles also need to complete autonomous path planning and flight within the tunnel to achieve one-key inspection and improve tunnel inspection efficiency. Unmanned aerial vehicles that can fly stably in tunnels are usually limited by aircraft size and battery technology, with a flight duration of generally 15-30 minutes, making it difficult to meet the needs of long tunnel autonomous inspection.

[0047] Therefore, in this embodiment, a method for navigating an unmanned aerial vehicle based on an inspection vehicle is proposed. The inspection vehicle inspects the inside of the tunnel, and the inspection vehicle is provided with an unmanned aerial vehicle case for charging the unmanned aerial vehicle and an unmanned aerial vehicle, as shown in Figure 1 The method includes the following steps:

[0048] S1, obtaining the task amount of the current inspection vehicle inspecting the inside of the tunnel;

[0049] S2, matching the navigation state of the current unmanned aerial vehicle during the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current unmanned aerial vehicle is a global positioning mode, the unmanned aerial vehicle obtains position information through multi-sensor fusion in the global positioning mode, then step S3 is performed;

[0050] S3, detecting whether the remaining power of the current unmanned aerial vehicle decreases to a preset threshold, if yes, step S4 is performed;

[0051] S4, obtaining a first flown distance and a first power consumption amount generated by the unmanned aerial vehicle during the process of the current inspection vehicle inspecting the tunnel, and determining whether the current unmanned aerial vehicle can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption amount, if not, step S5 is performed;

[0052] S5, obtaining a target line located inside the tunnel and extending along the tunnel inside the tunnel according to the tunnel, and the inspection vehicle inspects the inside of the tunnel in the extension direction of the target line, then the navigation state of the current unmanned aerial vehicle is changed to a target tracking mode, and the unmanned aerial vehicle obtains position information through the inspection vehicle in the target tracking mode.

[0053] In an embodiment, in S2, the process of obtaining position information by multi-sensor fusion of the unmanned aerial vehicle in the global positioning mode is as follows: in the global positioning mode, when the unmanned aerial vehicle inspects that there is a defect inside the tunnel, the position information of the unmanned aerial vehicle is obtained by fusing the relative pose sensor carried by the unmanned aerial vehicle and the inertial sensor, the laser radar, and the wheel mileage sensor carried on the inspection vehicle.

[0054] The global positioning mode is an autonomous path planning mode of the unmanned aerial vehicle. In the global positioning mode, the unmanned aerial vehicle can realize positioning inside the tunnel through multi-sensor fusion technology, can accurately master the position information of the unmanned aerial vehicle inside the tunnel, and can lock the position of the defect through the three-dimensional coordinates of the unmanned aerial vehicle when the defect is inspected. Therefore, in the embodiment, the unmanned aerial vehicle can first perform autonomous path planning in the global positioning mode. Here, the APF and BRRT* algorithms are fused, and an energy consumption optimization target is introduced to realize collaborative optimization of path safety and energy consumption efficiency. Specifically, as shown in Figure 2 .

[0055] First step: constructing a potential field by APF, the potential field including an attractive field and a repulsive field, the attractive field attracting the unmanned aerial vehicle to move towards a target point, and the repulsive field repelling the unmanned aerial vehicle away from an obstacle, the unmanned aerial vehicle being driven to move towards the target point and avoid the obstacle under the influence of the attractive force and the repulsive force.

[0056] Second step: optimizing the path to generate a random tree from the start point and the end point, and guiding the tree expansion through the attractive field (start point) and the repulsive field (end point).

[0057] Third step: optimizing energy consumption and collision risk, the fusion of the APF and the BRRT* algorithm being excellent in terms of avoiding obstacles and quickly generating an optimal path, but not considering the energy consumption optimization target, and the path generated in a complex environment being possibly not smooth enough. Therefore, the generated path is filtered and smoothed in this step, and a gradient descent function is used to solve each item in a multi-objective cost function, as follows:

[0058] ;

[0059] wherein, is a multi-objective cost function, is a path length term, using Euclidean distance or reachable distance under dynamic constraints; is an energy consumption term, representing energy consumption from a current node to a next node; is a safety term, representing a quantified collision risk, respectively represent the weights of each item.

[0060] Fourth step: constraints are used to ensure the safe flight of the UAV, and parameters such as the heading angle, height, and flight distance can be constrained to avoid collisions with obstacles in the tunnel or other situations. The heading angle constraint is that the heading angle of adjacent waypoints does not change by more than 30 degrees. The UAV height constraint is that the UAV flies at a constant height h or width w. The safe distance constraint is that the distance D between the UAV and the tunnel facility or obstacle is greater than Dsafe. The above constraints can be adjusted according to the specific inspection scenario.

[0061] In one embodiment, in S5, the process of the UAV obtaining position information through the inspection vehicle in the target tracking mode is as follows: in the target tracking mode, the inspection vehicle inspects the inside of the tunnel in the direction of the extension of the target line. When the UAV inspects a defect in the inside of the tunnel, the forward distance of the inspection vehicle is obtained through the wheel odometer mounted on the inspection vehicle, and the position information of the UAV is obtained according to the forward distance of the inspection vehicle.

[0062] The target tracking mode is another autonomous path planning mode of the UAV. Specifically, the target tracking mode refers to a reactive flight mode. When the remaining power cannot complete the inspection task, the reactive flight mode that consumes less power is switched. The reactive flight mode does not need to obtain positioning information of the UAV, and the types of required sensors and computing resources are less. The inspection vehicle is used to locate the UAV. Specifically, the forward distance of the inspection vehicle on the target line can be obtained through the wheel odometer of the inspection vehicle. The forward distance of the inspection vehicle on the target line is directly used as the forward distance of the UAV on the target line. The coordinates of the UAV on the z-axis are obtained, which can meet the basic requirements of inspection.

[0063] In one embodiment, when the remaining power cannot complete the inspection task, the reactive flight mode that consumes less power is switched. In the reactive flight mode, a corresponding mode can be selected according to whether there are continuous markers inside the tunnel. The target line in the reactive flight mode is determined according to the inside of the tunnel. When there are continuous markers inside the tunnel, such as road marking lines in a highway tunnel, tracks in a railway tunnel, and continuous pipe galleries in municipal pipelines, a virtual target line can be generated according to the continuous markers, and the UAV flies along the virtual target line, which is equivalent to flying along a fixed tracking object. When there are no continuous markers inside the tunnel, such as a mine tunnel and a fire passage, a fixed axis can be used as the target line, and the fixed axis can be the central axis of the mine tunnel, so that the UAV flies along the central axis.

[0064] Specifically, flying along a fixed tracking object is equivalent to flying along a fixed axis. Figure 3 ​As shown, first, image preprocessing is performed on the image collected in the target tracking mode, including gray scale conversion, Gaussian filter denoising, and histogram equalization to enhance contrast; edge processing is performed thereon, and the Canny algorithm can be used to extract lane line edges, and the edge position is determined through gradient amplitude and direction; then, through Hough transform, continuous marker lines in the image space are mapped to the parameter space to detect straight lines or curves; finally, through real-time tracking detection by the improved YOLOv4-tiny algorithm, flight along a fixed tracking object can be realized.

[0065] Specifically, flight along a fixed axis is as follows Figure 4 As shown, first, radar point cloud data is obtained according to the laser radar, and then the centroid coordinates are calculated, and the initial yaw angle is calculated, and through negative feedback calculation, the yaw angle at the nth point is obtained Among them, the axial direction of the tunnel can be defined as the Z direction, that is, the forward direction of the UAV, and the horizontal and left-right directions of the transverse section of the tunnel are defined as the Y direction. Taking the cross-section point cloud scanned by the single-line laser radar as an example, the yaw angle is calculated.

[0066] In an embodiment, the task amount includes a tunnel inspection range. During the process of inspecting the tunnel by the current unmanned aerial vehicle, if the navigation state of the current unmanned aerial vehicle is the global positioning mode, the unmanned aerial vehicle will autonomously plan a path according to the tunnel inspection range to obtain a first target path of the unmanned aerial vehicle, and fly along the first target path as navigation. Specifically, the first target path refers to a virtual line formed by the forward flight distance of the unmanned aerial vehicle autonomously planning a path according to the tunnel inspection range. At this time, the unmanned aerial vehicle can plan a path for the unmanned aerial vehicle in real time according to the tunnel inspection range and the global positioning information of the unmanned aerial vehicle, so that the unmanned aerial vehicle flies along the path to realize navigation of the unmanned aerial vehicle.

[0067] In an embodiment, the first flown distance is the flight distance generated when the unmanned aerial vehicle flies along the first target path as navigation in the global positioning mode, and the first power consumption amount is the power drop amount generated when the unmanned aerial vehicle flies along the first target path as navigation in the global positioning mode.

[0068] In an embodiment, in S4, the process of determining whether the current unmanned aerial vehicle can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption amount is as follows:

[0069] The first target path remaining for the current UAV is calculated according to the first target path corresponding to the first flown distance and the first power consumption amount, the first target path remaining is taken as the navigation for flight, the power drop amount generated when the UAV flies the first target path remaining as the navigation in the global positioning mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the global positioning mode, and vice versa.

[0070] Specifically, in the embodiment, the UAV on the inspection vehicle needs to complete the inspection task, the forward distance required for the UAV to complete the inspection task can be obtained in advance according to the inspection task, and the first target path remaining for the current UAV, that is, the remaining forward distance, can be obtained according to the first flown distance of the UAV and the forward distance required for the UAV to complete the inspection task.

[0071] In an embodiment, the method further comprises step S6, which is:

[0072] S6, when the navigation state of the current UAV is the target tracking mode, the second flown distance and the second power consumption amount generated by the UAV in the process of the current inspection vehicle inspecting the tunnel are obtained, whether the current UAV can complete the task amount in the target tracking mode is judged in real time according to the second flown distance and the second power consumption amount, if not, the UAV is controlled to navigate back to the UAV case.

[0073] In an embodiment, the task amount includes a tunnel inspection range, when the navigation state of the current UAV is the target tracking mode in the process of the current inspection vehicle inspecting the tunnel, the UAV will plan a path according to the tunnel inspection range and the target line to obtain a second target path of the UAV, the second target path coincides with the target line, and the second target path is taken as the navigation for flight.

[0074] Specifically, the second target path refers to a virtual line formed by the forward distance of the UAV flying in tracking of the target line in the process of the UAV planning a path according to the tunnel inspection range and the target line, at this time, the virtual line is equivalent to part of the target line, and the UAV can be navigated according to the tunnel inspection range and the target line.

[0075] In an embodiment, in S6, the process of judging whether the current UAV can complete the task amount in the target tracking mode in real time according to the second flown distance and the second power consumption amount is specifically:

[0076] The second target path remaining of the current UAV is calculated according to the second target path corresponding to the second flown distance and the second power consumption amount, the UAV flies with the second target path remaining as the navigation, the power drop amount generated when the UAV flies with the second target path remaining as the navigation in the target tracking mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the target tracking mode, and vice versa.

[0077] Specifically, in the embodiment, the UAV can obtain the forward distance required for completing the inspection task in advance according to the inspection task, and the second target path remaining of the current UAV, i.e., the remaining forward distance, can be obtained according to the second flown distance of the UAV and the forward distance required for completing the inspection task.

[0078] In an embodiment, in the process of judging whether the current UAV can complete the task amount in the global positioning mode according to the first flown distance and the first power consumption amount, and in the process of judging whether the current UAV can complete the task amount in the target tracking mode according to the second flown distance and the second power consumption amount, the wind resistance information collected in the flight process and the remaining path length can also be combined to judge whether the remaining power of the UAV can complete the inspection task in the mode. And if it is judged that the remaining power can complete the flight task after switching the mode, the navigation mode switching is performed.

[0079] In an embodiment, since the UAV needs to return to the unmanned vehicle for charging autonomously, in the tunnel, the UAV and the unmanned vehicle cooperatively complete the inspection task, in the area where the unmanned vehicle can reach, the unmanned vehicle and the UAV almost keep the same progress, in the area where the unmanned vehicle cannot reach, the UAV needs to fly independently, and the path planning method of returning to the unmanned vehicle needs to fully consider the above two scenarios, in addition, it is necessary to mark that the UAV and the unmanned vehicle keep communication in the flight process, and the UAV can obtain the positioning of the unmanned vehicle in real time. Specifically, the process of the autonomous navigation of the UAV returning to the unmanned vehicle for charging is as shown in Figure 5 If not, the real-time positioning of the inspection vehicle is performed, and the dynamic path planning based on the positioning is performed.

[0080] In summary, the application provides a dynamic planning method for UAV navigation based on an inspection vehicle, and the overall process of the dynamic planning method is as shown in Figure 6As shown, first, autonomous path planning considering energy consumption in global positioning mode is considered, then it is judged whether the remaining power of the unmanned aerial vehicle in global positioning mode can complete the task, if yes, path planning in global positioning mode is continued, if no, it is identified whether there is a continuous marker inside the tunnel, if yes, the continuous marker is tracked, if no, flight along the fixed axis is performed, at the same time, the navigation mode is switched to target tracking mode, then it is judged whether the current remaining power of the unmanned aerial vehicle in target tracking mode can complete the inspection mode, if no, the unmanned aerial vehicle is returned to the unmanned aerial vehicle box for charging.

[0081] Embodiment 2

[0082] An unmanned aerial vehicle navigation dynamic planning system based on an inspection vehicle, applying the unmanned aerial vehicle navigation dynamic planning method based on the inspection vehicle, comprising:

[0083] An inspection task amount acquisition module: obtaining the task amount of the current inspection vehicle for inspecting the inside of the tunnel;

[0084] An unmanned aerial vehicle global positioning module: matching the navigation state of the current unmanned aerial vehicle during the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current unmanned aerial vehicle is global positioning mode, the unmanned aerial vehicle obtains position information through multi-sensor fusion in global positioning mode;

[0085] An electric quantity detection module: detecting whether the remaining power of the current unmanned aerial vehicle decreases to a preset threshold;

[0086] An unmanned aerial vehicle navigation judgment module: obtaining a first flown distance and a first power consumption generated by the unmanned aerial vehicle during the process of the current inspection vehicle inspecting the tunnel, and judging whether the current unmanned aerial vehicle can complete the task amount in global positioning mode in real time according to the first flown distance and the first power consumption;

[0087] An unmanned aerial vehicle navigation switching module: obtaining a target line located inside the tunnel and extending along the tunnel inside the tunnel according to the tunnel, the inspection vehicle inspects the inside of the tunnel in the extension direction of the target line, then the navigation state of the current unmanned aerial vehicle is changed to target tracking mode, the unmanned aerial vehicle obtains position information through the inspection vehicle in target tracking mode.

[0088] The above is only a preferred embodiment of the present application, and does not limit the present application in any form, according to the technical essence of the present application, any simple modification, equivalent replacement and improvement of the above embodiment within the spirit and principles of the present application are still within the protection scope of the technical scheme of the present application.

Claims

1. A method for dynamic planning of UAV navigation based on a patrol vehicle, characterized in that, The inspection vehicle inspects the inside of the tunnel, and a drone case for charging the drone and the drone are arranged on the inspection vehicle, and the method comprises the following steps: S1, obtaining a task amount of the current inspection vehicle for inspecting the inside of the tunnel; S2, matching a navigation state of the current drone in the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current drone is a global positioning mode, the drone obtains position information through multi-sensor fusion in the global positioning mode, and then step S3 is performed; Wherein, the process that the drone obtains position information through multi-sensor fusion in the global positioning mode is: in the global positioning mode, when the drone inspects that there is a defect in the inside of the tunnel, the position information of the drone is obtained through the fusion positioning between the relative pose sensor carried by the drone itself and the inertial sensor, laser radar and wheel odometer carried on the inspection vehicle; S3, detecting whether the remaining power of the current drone decreases to a preset threshold, if yes, step S4 is performed; S4, obtaining a first flown distance and a first power consumption amount generated by the drone in the process of the current inspection vehicle inspecting the tunnel, and judging whether the current drone can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption amount, if not, step S5 is performed; S5, obtaining a target line located in the inside of the tunnel and extending along the tunnel according to the inside of the tunnel, the inspection vehicle inspects the inside of the tunnel in the extension direction of the target line, and then the navigation state of the current drone is changed to a target tracking mode, and the drone obtains position information through the inspection vehicle in the target tracking mode; Wherein, the process that the drone obtains position information through the inspection vehicle in the target tracking mode is: in the target tracking mode, the inspection vehicle inspects the inside of the tunnel in the extension direction of the target line, when the drone inspects that there is a defect in the inside of the tunnel, the forward distance of the inspection vehicle is obtained through the wheel odometer carried on the inspection vehicle, and the position information of the drone is obtained according to the forward distance of the inspection vehicle. 2.The method of claim 1, wherein, The task amount comprises a tunnel inspection range, in the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current drone is the global positioning mode, the drone will autonomously plan a path according to the tunnel inspection range to obtain a first target path of the drone, and the first target path is taken as navigation for flight. 3.The method of claim 2, wherein, The first flown distance is the flight distance generated when the drone takes the first target path as navigation for flight in the global positioning mode, and the first power consumption amount is the power drop amount generated when the drone takes the first target path as navigation for flight in the global positioning mode.

4. The method of claim 3, wherein, In S4, the process of judging whether the current drone can complete the task amount in the global positioning mode in real time according to the first flown distance and the first power consumption amount is specifically: The first target path corresponding to the first flown distance and the first power consumption is calculated to obtain the remaining first target path of the current UAV, the remaining first target path is taken as navigation to fly, the power drop amount generated when the UAV flies the remaining first target path as navigation in the global positioning mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the global positioning mode, and vice versa.

5. The method of claim 1, wherein, Further comprising a step S6, which is: S6, when the navigation state of the current UAV is the target tracking mode, the second flown distance and the second power consumption generated by the UAV in the process of the current inspection vehicle inspecting the tunnel are obtained, and whether the current UAV can complete the task amount in the target tracking mode is judged in real time according to the second flown distance and the second power consumption, if not, the UAV navigation return value is controlled to return to the UAV case.

6. The method of claim 5, wherein, The task amount includes a tunnel inspection range, when the navigation state of the current UAV is the target tracking mode in the process of the current inspection vehicle inspecting the tunnel, the UAV will plan a path according to the tunnel inspection range and the target line to obtain a second target path of the UAV, the second target path coincides with the target line, and the second target path is taken as navigation to fly.

7. The method of claim 6, wherein, In S6, the process of judging whether the current UAV can complete the task amount in the target tracking mode in real time according to the second flown distance and the second power consumption is specifically: The second target path corresponding to the second flown distance and the second power consumption is calculated to obtain the remaining second target path of the current UAV, the remaining second target path is taken as navigation to fly, the power drop amount generated when the UAV flies the remaining second target path as navigation in the target tracking mode is estimated, the power drop amount is compared with the remaining power of the current UAV, if the power drop amount is less than the remaining power of the current UAV, it is judged that the current UAV can complete the task amount in the target tracking mode, and vice versa. 8.A system for dynamic planning of UAV navigation based on a patrol vehicle, characterized in that, The application of the UAV navigation dynamic planning method based on the inspection vehicle according to any one of claims 1-7 comprises: An inspection task amount acquisition module: obtaining the task amount of the current inspection vehicle inspecting the inside of the tunnel; A UAV global positioning module: matching the navigation state of the current UAV in the process of the current inspection vehicle inspecting the tunnel, if the navigation state of the current UAV is the global positioning mode, the UAV obtains position information through multi-sensor fusion in the global positioning mode; A power detection module: detecting whether the remaining power of the current UAV drops to a preset threshold; A UAV navigation judgment module: obtaining the first flown distance and the first power consumption generated by the UAV in the process of the current inspection vehicle inspecting the tunnel, and judging in real time whether the current UAV can complete the task amount in the global positioning mode according to the first flown distance and the first power consumption. The unmanned aerial vehicle navigation switching module: according to the target line located in the tunnel and extending along the tunnel obtained in the tunnel, the inspection vehicle inspects the tunnel in the extension direction of the target line, and the navigation state of the current unmanned aerial vehicle is changed to a target tracking mode, and the unmanned aerial vehicle obtains position information through the inspection vehicle in the target tracking mode.

Images