Method for generating route of autonomous inspection channel of unmanned aerial vehicle

Abstract

The invention discloses a method for generating a route of an autonomous inspection channel of an unmanned aerial vehicle, and the method is characterized in that the method comprises the steps: S1, channel selection and vectorization; s2, elevation processing mode decision making: calculating an elevation standard deviation in a frame selection area according to the imported DEM elevation data; dynamically adjusting the terrain clearance of the unmanned aerial vehicle according to the calculated elevation standard deviation; s3, automatic route planning comprises the steps of generating an initial waypoint, self-adaptive waypoint density and multi-angle coverage in a channel vector range; and S4, generating and verifying an air route file, wherein the air route file comprises standardized packaging and three-dimensional visual verification. An unmanned aerial vehicle inspection channel route is quickly generated through a two-dimensional plane map, and efficient and safe autonomous flight is realized by combining intelligent elevation processing and route optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle intelligent inspection, and in particular to a method for generating an autonomous inspection channel route of an unmanned aerial vehicle. BACKGROUND

[0002] The development background of the current unmanned aerial vehicle autonomous inspection channel route generation technology mainly includes: The mature application of three-dimensional modeling technology, traditional unmanned aerial vehicle inspection highly depends on three-dimensional laser point cloud or oblique photography model, which although improves the detection accuracy, but requires professional equipment (such as laser radar) and complex modeling process, which becomes the bottleneck of technology popularization.

[0003] The simplification scheme of two-dimensional map and preset route attempts to reduce the dependence on three-dimensional modeling, although the cost is reduced, but the intelligent degree is insufficient, and it is difficult to adapt to dynamic scenes.

[0004] Dynamic environment response technology, although it improves the dynamic response capability, but the demand for computing power and hardware cost is still high.

[0005] The above background technologies show that the autonomous inspection of unmanned aerial vehicles is undergoing a transformation from three-dimensional modeling dependence to lightweight dynamic perception, and from static path planning to hierarchical intelligent decision-making. The existing technology accumulation provides key support for the hybrid height flight scheme that does not depend on three-dimensional models, including: two-dimensional map intelligent processing, target point generation algorithm, real-time sensor fusion and other directions.

[0006] In related technologies, there are problems such as the disconnection between two-dimensional artificial planning and three-dimensional complex environment, high operation threshold and time cost of unmanned aerial vehicle inspection, inability to realize cross-platform standardized route output, and balance between automation and flexibility of manual control.

[0007] Based on this, the present application provides a method for generating an autonomous inspection channel route of an unmanned aerial vehicle. SUMMARY

[0008] The present application provides a method for generating an autonomous inspection channel route of an unmanned aerial vehicle, which avoids strong dependence on three-dimensional models through two-dimensional maps, and realizes efficient and safe autonomous flight by combining intelligent elevation processing and route optimization.

[0009] According to an aspect of the present application, a method for generating an autonomous inspection channel route of an unmanned aerial vehicle is provided, characterized in that the method comprises: S1, channel selection and vectorization: the flight control software loads the two-dimensional plane map of the target area; determine the manually framed inspection channel, the inspection channel is framed by drawing a polygon through a touch screen or a mouse; S2, elevation processing mode decision: according to the imported DEM elevation data, the elevation standard deviation in the frame region is calculated; the height from the ground of the unmanned aerial vehicle is dynamically adjusted according to the calculated elevation standard deviation; S3, automatic flight path planning, including: generating initial waypoints in the channel vector range, adaptive waypoint density and multi-angle coverage; Adaptive waypoint density includes: dynamically adjusting the distance between waypoints according to the target accuracy (for example: 5cm / pixel) requirement: the distance between waypoints for regular inspection is 50m, and the distance between waypoints for defect re-inspection is reduced to 20m; the camera angle is automatically adjusted during the flight path shooting process, a 45° tilt angle is inserted, and a hovering shooting instruction is automatically inserted for key components; Multi-angle coverage includes: automatically generating a surrounding waypoint at the target coordinate to ensure blind area coverage; S4, flight path file generation and verification, including standardized packaging and three-dimensional visualization verification.

[0010] In a possible implementation, the method further includes: S5, task execution and dynamic adjustment, including: Unmanned aerial vehicle end loading: The channel flight path file planned in the unmanned aerial vehicle flight control APP software is uploaded to the flight control system on the unmanned aerial vehicle through the remote controller radio signal, and the flight control system automatically analyzes and verifies the integrity; Flight adaptation: in the event of sudden weather changes, automatically land or return nearby, and record the breakpoint position for subsequent flight.

[0011] In a possible implementation, step S1 further includes attribute configuration: Set the inspection channel width and resolution; Bind the unmanned aerial vehicle model and lens parameters.

[0012] In a possible implementation, dynamically adjusting the height from the ground of the unmanned aerial vehicle according to the calculated elevation standard deviation includes: For flat terrain with an elevation change of less than 2m: enable fixed height mode; For complex terrain with an elevation change of greater than or equal to 2m: switch to the ground-following flight mode, and dynamically adjust the height from the ground of the unmanned aerial vehicle according to the calculated elevation standard deviation.

[0013] In a possible implementation, S4 further includes: Standardized packaging includes: a standard file with a suffix of kmz, including: coordinate system, waypoint sequence, and obstacle avoidance rule; Three-dimensional visualization verification includes: previewing the three-dimensional path of the flight path in the software, the three-dimensional path of the flight path is superimposed with an elevation profile, and the three-dimensional path of the flight path is used for manually fine-tuning the height of a specific waypoint or obstacle avoidance parameter.

[0014] In a possible implementation, the coordinate system is automatically labeled WGS84 or GCJ-02 format, the sequence of waypoints includes the longitude, latitude, height, shooting angle, and hovering time of the waypoint, the obstacle avoidance rule includes a fly-around radius, an emergency action instruction, and import of a no-fly zone and high-voltage line data, and the horizontal avoidance distance is greater than or equal to 50 m.

[0015] In a possible implementation, the initial waypoints are generated in the channel vector range, including: The flight height of the unmanned aerial vehicle is calculated according to the set target ground resolution, the type of the unmanned aerial vehicle, and the camera parameters; The flight loop times of the unmanned aerial vehicle are calculated according to the selected channel region and the resolution parameters, to meet the resolution requirement; The actual flight height is adjusted according to DEM elevation data to keep the resolution unchanged when the terrain undulates.

[0016] Compared with the prior art, the present application has the following beneficial effects: The method for generating a channel route of an unmanned aerial vehicle for autonomous inspection according to the embodiments of the present disclosure quickly generates a channel route of an unmanned aerial vehicle for inspection through a two-dimensional plane map, combines intelligent elevation processing and route optimization, and realizes efficient and safe autonomous flight.

[0017] The method solves the problem of disconnection between two-dimensional manual planning and three-dimensional complex environment, reduces the operation threshold and time cost of unmanned aerial vehicle inspection, realizes standardized route output across platforms, and balances the flexibility of automation and manual control. The fundamental purpose of the present application is to bridge the technical gap between "low-threshold manual operation" and "high-precision autonomous flight", and through decoupling design of two-dimensional channel selection and intelligent elevation control, both the flexibility of manual decision (experience judgment for complex terrain) and the automation processing capability are retained.

[0018] The present application does not rely on a three-dimensional model. Traditional methods need to rely on laser radar or oblique photography to construct a high-precision three-dimensional model, which has problems such as high data acquisition cost and long modeling time. The present application avoids strong dependence on a three-dimensional model through a two-dimensional map.

[0019] The present application realizes a leapfrog upgrade in terrain adaptability. The elevation processing flexibly selects a fixed elevation and a terrain-following flight according to actual conditions.

[0020] The present application realizes an intelligent leap in route planning. The density of waypoints of the route is self-adaptive. The route is compatible across platforms. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 FIG. 1 shows a flow chart of a method for generating a channel route of an unmanned aerial vehicle for autonomous inspection according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in different drawings represent the same or similar elements. Although various aspects of embodiments are illustrated in the drawings, the drawings are not necessarily drawn to scale unless specifically noted.

[0023] The term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations.

[0024] In addition, for the purpose of convenience and brevity, detailed descriptions of well-known functions and structures incorporated in the present disclosure can be omitted. It will be appreciated that those skilled in the art will be able to devise various modes of implementing the advantageous aspects of the present disclosure without the exercise of inventive faculty and without the aid of further experimentation.

[0025] As Figure 1 shown, according to an aspect of the present disclosure, a method for generating an unmanned aerial vehicle (UAV) autonomous inspection channel route is provided, and the method comprises: S1, channel selection and vectorization: Map loading and labeling: a flight control APP software loads a two-dimensional plane map of a target area (satellite image superposition is supported); an inspection channel is determined by manual framing, and the inspection channel is framed by drawing a polygon through a touch screen or a mouse; Based on a satellite map or a UAV aerial photograph orthographic image, the map is loaded into a flight control software interface, and zooming to a centimeter-level precision operation is supported.

[0026] Through a GIS coordinate system (such as WGS84), the map is aligned with the real geographical position.

[0027] Manual framing: a user draws a polygon or a polyline on a map to frame an inspection area, and multi-point touch control is supported to adjust the boundary.

[0028] S2, elevation processing mode decision: according to imported DEM elevation data, the standard deviation of the elevation in the framed area is calculated; and the height of the UAV from the ground is dynamically adjusted according to the calculated standard deviation of the elevation; Fixed elevation mode: a preset global flight height (such as 90 m) is verified for global safety through a channel height database.

[0029] Terrain-following flight mode: offline elevation data fusion: import elevation DEM data, and obtain elevation information in real time when planning a route.

[0030] S3, automatic route planning, including: generating initial waypoints within the range of the channel vector, and adaptively adjusting the density of the waypoints and multi-angle coverage; Adaptive waypoint density includes: dynamically adjusting the distance between waypoints according to the target accuracy requirement: the distance between waypoints of the conventional inspection is 50m (20 points per kilometer), and the distance between waypoints of the defect re-inspection is reduced to 20m; the camera angle is automatically adjusted during the flight, and a 45° tilt angle is inserted, such as a lateral offset lens (±3m) to generate a 45° oblique shooting path (to improve the detection rate of fine targets); the gimbal pitch angle is automatically changed according to the terrain (error ≤2°), for example, the camera pitch angle is adjusted according to the terrain change. The key components automatically insert the hovering shooting instruction; Multi-angle coverage includes: automatically generating a surrounding waypoint at the target coordinate to ensure no blind area coverage; S4, flight path file generation and verification: including standardized packaging and three-dimensional visualization verification.

[0031] In a possible implementation, the method further includes: S5, task execution and dynamic adjustment, including: UAV-side loading: uploading the channel flight path file planned in the UAV flight control APP software to the flight control system on the UAV through the remote controller radio signal, and the flight control system automatically analyzes and verifies the integrity; Flight adaptation: in the event of sudden weather changes, automatically landing or returning nearby, and recording the breakpoint position for subsequent flight continuation.

[0032] In a possible implementation, step S1 further includes attribute configuration: Setting the inspection channel width and resolution; The inspection channel setting: supporting importing DEM data to automatically obtain the inspection area, and manually dragging the screen to draw the inspection channel area, supporting free setting of the polygon type.

[0033] Binding target device type, automatically binding UAV model and lens parameters, and supporting manual change.

[0034] In a possible implementation, dynamically adjusting the height of the UAV from the ground according to the calculated height standard deviation includes: For flat terrain with a height change of less than 2m: enable the fixed height mode (default height from the ground is 80m); For complex terrain with a height change of greater than or equal to 2m: switch to the terrain-following flight mode, and dynamically adjust the height of the UAV from the ground according to the calculated height standard deviation (50-120m).

[0035] In a possible implementation, the S4 further includes: Standardized packaging includes: a standard file with a kmz suffix, adapted to the DJI MSDK flight control protocol, including: coordinate system, waypoint sequence, obstacle avoidance rule; The three-dimensional visualization check includes previewing the route three-dimensional path (superimposed elevation profile) in the software, the route three-dimensional path is the superimposed elevation profile, and the route three-dimensional path is used for manually fine-tuning the height of a specific waypoint or obstacle avoidance parameter.

[0036] In a possible implementation, the coordinate system is automatically labeled WGS84 or GCJ-02 format, the waypoint sequence includes the longitude and latitude of the waypoint, the height, the shooting angle, the hovering time (2-5 seconds), the obstacle avoidance rule includes the fly-around radius, the emergency action instruction, and the import of the no-fly zone and high-voltage line data, and the horizontal avoidance distance is greater than or equal to 50 m.

[0037] In a possible implementation, the initial waypoints are generated within the channel vector range, including: According to the set target ground resolution, the type of the unmanned aerial vehicle, and the camera parameters, the flight height of the unmanned aerial vehicle is calculated; According to the selected channel area and the resolution parameter, the flight loop times of the unmanned aerial vehicle are calculated to meet the resolution requirement; According to the DEM elevation data, the actual flight height is adjusted to keep the resolution unchanged when the terrain undulates.

[0038] The above has described the embodiments of the present disclosure, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles, practical application, or technical improvement in the market of the embodiments, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs), characterized in that, The method includes: S1, Channel Selection and Vectorization: The flight control software loads a two-dimensional planar map of the target area; the manually selected inspection channel is determined, and the inspection channel is selected by drawing polygons using a touch screen or mouse. S2, Elevation Processing Mode Decision: Calculate the elevation standard deviation within the selected area based on the imported DEM elevation data; dynamically adjust the drone's altitude based on the calculated elevation standard deviation. S3, automatic route planning includes: generating initial waypoints within the channel vector range, adaptive waypoint density, and multi-angle coverage; Adaptive waypoint density includes: dynamically adjusting waypoint spacing according to target accuracy requirements: the waypoint spacing for routine inspections is 50m, while for defect re-inspection, the spacing is reduced to 20m; automatically adjusting the camera angle during flight path shooting, inserting a 45° tilt angle, and automatically inserting hovering photography commands for key components. Multi-angle coverage includes: automatically generating waypoints around the target coordinates to ensure coverage without blind spots; S4, Route document generation and verification: including standardized encapsulation and 3D visualization verification.

2. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The method further includes: S5, task execution and dynamic adjustment, including: Drone client loading: The flight path file planned in the drone flight control APP software is uploaded to the drone's flight control system via remote control radio signal. The flight control system automatically parses and verifies the integrity of the file. In-flight adaptation: In the event of sudden weather changes, it will automatically land at the nearest airport or return to base, and record the location of the breakpoint for subsequent flights.

3. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, Step S1 also includes: attribute configuration: Set the inspection channel width and resolution; Bind the target drone model and lens parameters.

4. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The drone's altitude is dynamically adjusted based on the calculated standard deviation of elevation, including: For flat terrain with elevation changes of less than 2 meters: Enable fixed height mode; For complex terrain with elevation changes of 2 meters or more: switch to terrain-following flight mode and dynamically adjust the drone's altitude based on the calculated elevation standard deviation.

5. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, S4 further includes: Standardized encapsulation includes: standard files with the suffix kmz, including: coordinate system, waypoint sequence, and obstacle avoidance rules; The 3D visualization verification includes: previewing the 3D route path in the software. The 3D route path is an overlaid elevation profile. The 3D route path is used to manually fine-tune the altitude of specific waypoints or obstacle avoidance parameters.

6. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The coordinate system is automatically labeled in WGS84 or GCJ-02 format. The waypoint sequence includes the latitude, longitude, altitude, shooting angle, and hovering time of the waypoints. The obstacle avoidance rules include: detour radius, emergency action instructions, and import of no-fly zone and high-voltage line data. The horizontal avoidance distance is ≥50m.

7. The method for generating autonomous inspection routes for unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, Generate initial waypoints within the channel vector range, including: Calculate the drone's flight altitude based on the set target ground resolution, drone type, and camera parameters; Calculate the number of UAV flight loops based on the selected channel area and resolution parameters to meet the resolution requirements; Adjust the actual flight altitude based on DEM elevation data to maintain constant resolution despite terrain undulations.

Images