Method, device and equipment for generating unmanned aerial vehicle inspection path in power transmission line, storage medium and computer program product

Abstract

The embodiment of the invention provides a method, device and equipment for generating an unmanned aerial vehicle inspection path in a power transmission line, a storage medium and a computer program product. The method comprises the following steps: constructing a three-dimensional scene according to position information of towers corresponding to multiple sections of power transmission lines and position information of obstacles; wherein the three-dimensional scene comprises mapping nodes of a plurality of towers and mapping nodes of obstacles; in the three-dimensional scene, according to position information of a first mapping node of a tower corresponding to the initial power transmission line, position information of a second mapping node corresponding to a tower corresponding to the termination power transmission line and an unmanned aerial vehicle consumption and flight time optimization rule, determining a plurality of discrete nodes distributed along the multiple sections of power transmission lines; generating a moving trajectory according to the plurality of discrete nodes based on the first obstacle avoidance constraint; and performing local optimization on the moving trajectory based on the second obstacle avoidance constraint to obtain an unmanned aerial vehicle inspection path. The method is used for improving the inspection efficiency of the power transmission line.

Description

Technical Field

[0001] The present application relates to the field of unmanned aerial vehicles (UAVs), and particularly to a method, apparatus, device, storage medium, and computer program product for generating an inspection path of a UAV in a transmission line. Background Art

[0002] Inspecting large-scale and complex transmission lines to discover problems in the transmission lines plays an important role in the safety and stability of the transmission lines.

[0003] Related technologies adopt the means of manually controlling the flight of a UAV to inspect the transmission line corridor. When an operator controls the UAV, they need to control the flight speed of the UAV, align the UAV with the inspection line, and also take into account the obstacles ahead at the same time. The operation is complex.

[0004] Therefore, there is a technical problem of low inspection efficiency in inspecting transmission lines using related technologies. Summary of the Invention

[0005] Embodiments of the present application provide a method, apparatus, device, storage medium, and computer program product for generating an inspection path of a UAV in a transmission line, so as to achieve the technical effect of improving the inspection efficiency of the UAV for inspecting the transmission line.

[0006] In a first aspect, an embodiment of the present application provides a method for generating an inspection path of a UAV in a transmission line, including:

[0007] Constructing a three-dimensional scene according to the position information of the poles corresponding to multiple sections of transmission lines and the position information of obstacles; wherein, each position information in the three-dimensional scene includes the distance information between the position and the nearest obstacle for the mapping nodes of the multiple poles and the mapping nodes of the obstacles.

[0008] In the three-dimensional scene, determining a plurality of discrete nodes distributed along the multiple sections of transmission lines according to the position information of the first mapping node corresponding to the pole of the starting transmission line, the position information of the second mapping node corresponding to the pole of the ending transmission line, and the UAV consumption and flight time optimization rule.

[0009] Generating a running trajectory based on a first obstacle avoidance constraint according to the plurality of discrete nodes.

[0010] Performing local optimization on the running trajectory based on a second obstacle avoidance constraint to obtain the UAV inspection path.

[0011] In a possible implementation manner, determining a plurality of discrete nodes distributed along the multi-segment transmission lines according to the position information of the first mapping node corresponding to the pole tower corresponding to the starting transmission line, the position information of the second mapping node corresponding to the pole tower corresponding to the ending transmission line, and the optimization rule of the drone consumption and flight time includes:

[0012] Determining a starting position according to the position information of the first mapping node of the starting transmission line;

[0013] Determining an ending position according to the position information of the second mapping node of the ending transmission line;

[0014] Determining the plurality of discrete nodes from the starting position to the ending position based on the node expansion algorithm according to the optimization rule of the drone consumption and flight time.

[0015] In a possible implementation manner, generating an operation trajectory based on the first obstacle avoidance constraint according to the plurality of discrete nodes includes:

[0016] Generating the operation trajectory based on the curve fitting algorithm according to the plurality of discrete nodes.

[0017] In a possible implementation manner, the curve fitting algorithm includes an objective function for smoothing the fitting curve, and the objective function includes the first obstacle avoidance constraint;

[0018] The generating the operation trajectory based on the curve fitting algorithm according to the plurality of discrete nodes includes:

[0019] Performing curve fitting on the plurality of discrete nodes based on the objective function to obtain the operation trajectory.

[0020] In a possible implementation manner, performing local optimization on the operation trajectory based on the second obstacle avoidance constraint to obtain a drone inspection path includes:

[0021] Dividing the operation trajectory into a plurality of local operation trajectories;

[0022] Performing local optimization on the plurality of local operation trajectories based on a local optimization algorithm to obtain a plurality of local spatial states; wherein, the local optimization algorithm includes the second obstacle avoidance constraint;

[0023] Determining the drone inspection path according to the plurality of local spatial states.

[0024] In a possible implementation manner, the local spatial state includes one or more of the following: the position of the drone, the speed of the drone, the attitude quaternion of the drone in the world coordinate system, and the thrust of the drone.

[0025] In a possible implementation, for any one of the multiple discrete nodes, the discrete node has one or more of the following attribute information: the position of the unmanned aerial vehicle, the speed of the unmanned aerial vehicle, and the acceleration of the unmanned aerial vehicle.

[0026] In a possible implementation, the first obstacle avoidance constraint includes: a first constraint determined by the distance between each of the discrete nodes and the mapping node of the nearest obstacle;

[0027] The second obstacle avoidance constraint includes: a second constraint determined by the distance between each of the discrete nodes and the mapping node of the nearest obstacle, and a third constraint determined by the safe distance between each of the discrete nodes and the power transmission line.

[0028] In a possible implementation, the safe distance between the discrete node and the power transmission line includes: the distance between the discrete node and the plane where the corresponding power transmission line is located.

[0029] In a second aspect, an embodiment of the present application provides a device for generating an inspection path of an unmanned aerial vehicle in a power transmission line, including:

[0030] A construction module, configured to construct a three-dimensional scene according to the position information of the towers corresponding to multiple sections of power transmission lines and the position information of obstacles; wherein, the three-dimensional scene includes mapping nodes of the multiple towers and mapping nodes of the obstacles;

[0031] A determination module, configured to determine, in the three-dimensional scene, multiple discrete nodes distributed along the multiple sections of power transmission lines according to the position information of the first mapping node corresponding to the tower corresponding to the starting power transmission line, the position information of the second mapping node corresponding to the tower corresponding to the ending power transmission line, and the optimization rule of the consumption and flight time of the unmanned aerial vehicle;

[0032] A generation module, configured to generate an operation trajectory based on the first obstacle avoidance constraint according to the multiple discrete nodes;

[0033] An optimization module, configured to perform local optimization on the operation trajectory based on the second obstacle avoidance constraint to obtain an inspection path of the unmanned aerial vehicle.

[0034] In a third aspect, an embodiment of the present application provides a device for generating an inspection path of an unmanned aerial vehicle in a power transmission line, including: a memory, a processor;

[0035] The memory stores computer execution instructions;

[0036] The processor executes the computer execution instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0037] Fourthly, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above first aspect and / or various possible implementation manners of the first aspect when executed by a processor.

[0038] Fifthly, an embodiment of the present application provides a computer program product including a computer program, which implements the above first aspect and / or various possible implementation manners of the first aspect when executed by a processor.

[0039] The method, device, equipment, storage medium, and computer program product for generating a drone inspection path in a power transmission line provided by the embodiments of the present application construct a three-dimensional scene based on the position information of the power transmission line and the corresponding towers and the information of obstacles in the power transmission line, determine multiple discrete nodes according to the optimization rules of drone consumption and flight time; generate a running trajectory based on the first obstacle avoidance rule; and perform local optimization on the motion trajectory according to the second obstacle avoidance rule. The obtained drone inspection path is used to guide the drone to inspect the power transmission line. The generated drone inspection path optimizes the drone consumption and flight time, and effectively avoids obstacles on the inspection path, thereby improving the inspection efficiency of the drone for inspecting the power transmission line. Description of the Drawings

[0040] The drawings here are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0041] Figure 1 It is a schematic flowchart of the method for generating a drone inspection path in a power transmission line provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic diagram of the scene of the power transmission line and the tower used for three-dimensional scene modeling provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the plane corresponding to the power transmission line provided by an embodiment of the present application;

[0044] Figure 4 It is a side view of the inspection path generated in the three-dimensional modeling scene provided by an embodiment of the present application;

[0045] Figure 5 It is a top view of the inspection path generated in the three-dimensional modeling scene provided by an embodiment of the present application;

[0046] Figure 6 It is a schematic structural diagram of the device for generating a drone inspection path in a power transmission line provided by an embodiment of the present application;

[0047] Figure 7 This is a schematic structural diagram of the device provided by the embodiment of the present application for generating the inspection path of the unmanned aerial vehicle (UAV) in the transmission line.

[0048] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be given later. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0049] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of the devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0050] Inspecting large-scale and complex transmission lines to discover problems in the transmission lines plays an important role in the safety and stability of the transmission lines. Inspecting large-scale and complex transmission lines requires a large amount of manpower and material resources. The traditional inspection method mainly based on manual work has low inspection accuracy and many blind spots, and cannot meet the inspection requirements. Therefore, the method of using UAVs to inspect transmission lines is developing faster and faster.

[0051] In the related art, when using UAVs to inspect transmission lines, the inspection is mainly carried out by the UAVs and supplemented by manual work. Specifically, when inspecting the transmission lines in the related art, the operator manually controls the flight of the UAV to inspect the transmission line corridor. This requires the operator to control both the flight speed of the UAV, align the UAV with the inspection line, and take into account the obstacles ahead when operating the UAV.

[0052] Based on the above analysis, it can be seen that when using the related art to inspect transmission lines, the control of the inspection path of the UAV and the avoidance of obstacles during the flight of the UAV both rely on manual operations, resulting in complex operations. Therefore, there is a technical problem of low inspection efficiency.

[0053] The method, device, equipment, storage medium and computer program product provided by the present application for generating the inspection path of the UAV in the transmission line are used to solve the above technical problems.

[0054] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0055] Figure 1 It is a schematic flowchart of a method provided by this application for generating an unmanned aerial vehicle (UAV) inspection path in a transmission line. As Figure 1 shown, the method includes:

[0056] S101. Construct a three-dimensional scene based on the position information of the poles corresponding to multiple sections of transmission lines and the position information of obstacles; wherein, the three-dimensional scene includes mapping nodes of multiple poles and mapping nodes of obstacles.

[0057] It should be noted that the data used for modeling can be real data about transmission lines, poles, and obstacles collected manually or by acquisition devices.

[0058] S102. In the three-dimensional scene, determine multiple discrete nodes distributed along multiple sections of transmission lines according to the position information of the first mapping node corresponding to the pole of the starting transmission line, the position information of the second mapping node corresponding to the pole of the ending transmission line, and the UAV consumption and flight time optimization rule.

[0059] It should be noted that the UAV realizes the inspection of the transmission line by flying along the transmission line from the starting point to the ending point above the transmission line. Therefore, in the three-dimensional scene, the starting transmission line and the ending transmission line of the multiple sections of transmission lines to be inspected can be determined. The starting and ending nodes of the inspection path are determined by the position information of the first mapping node of the pole corresponding to the starting transmission line and the position information of the second mapping node of the pole corresponding to the ending transmission line, and multiple discrete nodes distributed along the multiple sections of transmission lines to be inspected are initially determined, so as to generate an operation trajectory subsequently.

[0060] S103. Generate an operation trajectory based on the first obstacle avoidance constraint according to multiple discrete nodes.

[0061] S104. Based on the second obstacle avoidance constraint, locally optimize the operation trajectory to obtain the UAV inspection path.

[0062] It should be noted that since step S103 considers the obstacle avoidance constraint, the generated operation trajectory avoids the obstacles in the transmission line. However, more accurate parameters are needed to guide the UAV flight. Therefore, step S104 further considers the obstacle avoidance constraint and locally optimizes the operation trajectory, thereby obtaining the UAV inspection path including more accurate guiding parameters.

[0063] The method for generating a drone inspection path in a transmission line provided in an embodiment of the present application constructs a three-dimensional scene based on the position information of the transmission line and the tower corresponding to the transmission line, and the information of obstacles in the transmission line, and determines multiple discrete nodes according to the drone consumption and flight time optimization rule; based on the first obstacle avoidance rule, generates an operation trajectory according to the multiple discrete nodes; according to the second obstacle avoidance rule, locally optimizes the motion trajectory, and the obtained drone inspection path is used to guide the drone to inspect the transmission line. The generated drone inspection path optimizes the drone consumption and flight time, and effectively avoids obstacles on the inspection path, thereby improving the inspection efficiency of the drone for inspecting the transmission line.

[0064] Figure 2 A schematic diagram of a scene of transmission lines and towers used for three-dimensional scene modeling provided in an embodiment of the present application, such as Figure 2 As shown, towers P0', P1', and P2' are towers corresponding to three sections of the multi-section transmission line. In some specific embodiments, the three-dimensional scene modeling can be to model the multiple sections of transmission lines, the towers connected to each transmission line, and obstacles in the transmission line.

[0065] In a three-dimensional scene, we can use the set (P0, P1, ..., P s ) represents the mapping nodes of the towers in multiple transmission lines, which is recorded as set P. Where s is the total number of transmission line towers, P s Represents the mapping node of the terminating tower corresponding to the s-th transmission line segment.

[0066] In order to distinguish different sections of transmission lines, the area to which each section of transmission line belongs can be modeled as follows.

[0067] Let the i-th section of the transmission line be P i to P i+1 , i is any integer greater than or equal to 0 and less than s. Vector It can be expressed by the following formula (1):

[0068]

[0069] Where x i,1 ,y i,2 ,z i,3 They represent the three-dimensional coordinates in the three-dimensional scene respectively; T represents the transpose of the vector.

[0070] Figure 3 The schematic diagram of the plane corresponding to the transmission line provided in this application is as follows: Figure 3 As shown, let it be perpendicular to the vector Vector s on the horizontal plane i Denoted as s i =(s1,s2,0), then s iIt can be calculated by the following formula (2):

[0071]

[0072] The plane normal vector corresponding to this section of the transmission line can be expressed by the following formula (3):

[0073]

[0074] In the formula, z i is the plane normal vector; A i , B i , C i are the parameters of the equation of the plane where this section of the transmission line is located respectively.

[0075] Substitute P i into the plane A i x + B i y + C i z + D i = 0, then D i can be solved, and the equation of the plane corresponding to this section of the transmission line is obtained.

[0076] Suppose the planes corresponding to two adjacent sections of the transmission line are A i x + B i y + C i z + D i = 0 and A i+1 x + B i+1 y + C i+1 z + D i+1 = 0, then the plane perpendicular to the horizontal plane at the intersection of these two planes can be expressed by the following formula (4):

[0077]

[0078] In the formula, A i+1 , B i+1 , C i+1 are the parameters of the equation of the plane corresponding to the (i + 1)-th section of the transmission line respectively, and a i,i+1 , b i,i+1 , c i,i+1 are the parameters of the equation of the plane perpendicular to the horizontal plane at the intersection of the planes corresponding to the i-th section of the transmission line and the (i + 1)-th section of the transmission line respectively.

[0079] When the position of the drone satisfies the conditions of the following formulas (5)-(6), it can be considered that the drone is in the i-th to (i + 1)-th sections of the transmission line:

[0080] a i,i+1 x + b i,i+1 y + c i,i+1 ≤ 0 (5);

[0081] a i-1,i x + b i-1,i y + c i-1,i ≥ 0 (6);

[0082] The safe flight of the UAV can be ensured when it flies at a certain distance from the transmission line. Therefore, the safe distance between the position of the UAV and the transmission line can be set. The position of the UAV can be represented by discrete nodes in a three-dimensional scene. Therefore, the safe distance between the position of the UAV and the transmission line is represented as the safe distance between the discrete nodes and the transmission line in the three-dimensional scene; the safe distance between the discrete nodes and the transmission line includes: the distance between the discrete nodes and the plane where the corresponding transmission line is located. In the three-dimensional scene, the safe distance can be modeled by the following formula (7):

[0083]

[0084] In the formula, d max is the safe distance between the discrete node and the transmission line.

[0085] In these embodiments, by performing three-dimensional modeling on the transmission line and the tower, defining the plane of each section of the transmission line, and setting the safe distance between the position of the UAV and the transmission line, it is convenient to plan the inspection path of the UAV subsequently.

[0086] Next, taking the planning of the UAV inspection path in this three-dimensional modeling as an example, the technical solution of the present application will be further described.

[0087] In some embodiments of these embodiments, for any one of the multiple discrete nodes obtained in step S102, the discrete node has one or more of the following attribute information: the position of the UAV, the speed of the UAV, and the acceleration of the UAV.

[0088] Determining multiple discrete nodes distributed along multiple sections of the transmission line according to the position information of the first mapping node corresponding to the tower corresponding to the starting transmission line, the position information of the second mapping node corresponding to the tower corresponding to the ending transmission line, and the UAV consumption and flight time optimization rule in step S103 includes:

[0089] First, determine the starting position according to the position information of the first mapping node of the starting transmission line.

[0090] Second, determine the ending position according to the position information of the second mapping node of the ending transmission line.

[0091] Third, based on the UAV consumption and flight time optimization rule and the node expansion algorithm, determine multiple discrete nodes from the starting position to the ending position.

[0092] Exemplarily, if multiple sections of transmission lines are respectively arranged on both sides of a road, and the corresponding transmission lines on both sides of the road are arranged in parallel, then an initial node can be set according to the positions of the first mapping nodes of the initial poles of the respective initial transmission lines on both sides of the road, and the initial node can be located at the middle position between the two first mapping nodes; a termination node can be set according to the positions of the second mapping nodes of the termination poles of the respective termination transmission lines on both sides of the road, and the termination node can be located at the middle position between the two second mapping nodes.

[0093] As an example, the node expansion algorithm can be the hybrid A* algorithm. Specifically, the unmanned aerial vehicle is a quadrotor aircraft. Let the position, velocity, and acceleration of the unmanned aerial vehicle be p, v, and a respectively. Using the particle dynamics model, the rotational motion of the unmanned aerial vehicle is not considered, and it is assumed that the velocity and acceleration have upper and lower bounds respectively. The dynamic model of the unmanned aerial vehicle can be expressed by the following formula (8):

[0094]

[0095] In the formula, respectively represent the derivatives of p, v, and a; u ∈ [-u max , u max , a parameter used to control node expansion, and u max represents the maximum value of the node expansion parameter.

[0096] The range of u is discretized at equal intervals to obtain the discrete u values as the following formula (9):

[0097]

[0098] In the formula, ra represents the fractional ratio taken when discretizing u.

[0099] The cost function of the hybrid A* algorithm includes the actual cost g c and the heuristic cost h c , which respectively represent the cost of the unmanned aerial vehicle from the starting position to the current position and the cost from the current position to the target position. The cost function can be expressed by the following formula (10):

[0100] f c = g c + h c (10);

[0101] In the formula, f c represents the cost function value.

[0102] For a 3D modeling scenario, the cost function can be defined by the trajectory cost.

[0103] The trajectory cost of the unmanned aerial vehicle can be expressed by the following formula (11):

[0104]

[0105] In the formula, T represents the flight time of the entire trajectory of the UAV; J(T) represents the trajectory loss value; ρ is a parameter to measure the freedom of time; u(t) represents the value of u that changes with time t. The trajectory loss of the UAV describes the optimization rule of the consumption of the UAV and the flight time.

[0106] The actual loss of the hybrid A* algorithm can be expressed by the following formula (12):

[0107]

[0108] In the formula, τ is the time interval; j represents the number of segments into which the trajectory is divided according to the time interval τ; u j-1,j represents the value of u from the (j - 1)-th segment to the j-th segment.

[0109] Let the UAV state be [p T v T a T T , using the current state and the target state, the minimum value of the trajectory cost can be solved by using the principle of minimum value as:

[0110]

[0111] In the formula, J* is the minimum value of the trajectory cost;

[0112]

[0113] p μc , v μc , p μg , v μg respectively represent the current position, speed of the UAV and the target position, speed.

[0114] T* can be obtained by solving the following formula (15):

[0115]

[0116] Formula (15) can be solved by the Ferrari method, then h c can be expressed as the following formula (16):

[0117] h c = J * (T * ) (16);

[0118] Based on the cost function determined by formulas (10), (12), and (16), the A* algorithm can be used to determine multiple discrete nodes distributed along multiple transmission lines from the starting position to the ending position. ​

[0119] Multiple discrete nodes determined by the hybrid A-star algorithm roughly describe a feasible inspection path for the UAV. However, the calculation of the discrete node positions does not consider the influence of obstacles in the transmission line. In a three-dimensional scenario, the positions of the discrete nodes may be close to or overlap with the positions of the obstacles.

[0120] In order to obtain a complete inspection path that can avoid all obstacles, in some embodiments of these embodiments, generating a running trajectory based on the first obstacle avoidance constraint according to multiple discrete nodes in step S103 includes:

[0121] Generating a running trajectory based on the multiple discrete nodes using a curve fitting algorithm.

[0122] The curve fitting algorithm in step S103 includes an objective function for smoothing the fitted curve, and the objective function includes the first obstacle avoidance constraint.

[0123] Generating a running trajectory based on the multiple discrete nodes using a curve fitting algorithm includes:

[0124] Performing curve fitting on the multiple discrete nodes based on the objective function to obtain a running trajectory.

[0125] Among them, the first obstacle avoidance constraint includes: a first constraint determined by the distances between the discrete nodes and the mapped nodes of the nearest obstacles respectively.

[0126] Specifically, the cubic spline curve algorithm can be used as the curve fitting algorithm to fit the multiple discrete nodes.

[0127] The cubic spline curve is uniquely determined by a set of N + 1 control points: {Q0, Q1, …, Q N}, and a set of M + 1 time nodes: {t0, t1, …, t M}, where M = N + 3 + 1 = N + 4. For a uniform cubic spline curve, the time interval between any two adjacent nodes in the cubic spline curve is fixed, and the cubic spline curve can be defined by the following formula (17):

[0128]

[0129] In the formula, s(t) is the cubic spline curve, t is the time; t k is the time corresponding to the kth control point, Q k is the kth control point,

[0130]

[0131]

[0132] Δt is the time interval.

[0133] The optimization objectives of the cubic spline curve consist of smoothness, safety, speed, and acceleration constraints. To improve the success rate of the solution, these three objectives are added as soft constraints to the objective function. Then the objective function can be defined as the following formula (20):

[0134] f = λ1f s + λ2f c + λ3(f v + f a ) (20);

[0135] In the formula, f s is the smoothness term; f c is the safety term; f v is the speed term; f a is the acceleration term; λ1, λ2, and λ3 are the respective weights of f s , f c , (f v + f a ).

[0136] Taking a series of control points as decision variables, the optimization problem can be defined as the following formula (21):

[0137]

[0138] In the formula, argmin represents the variable value that makes the objective function reach the minimum value.

[0139] The smoothness term can be expressed by the following formula (22):

[0140]

[0141] The safety term can be expressed by the following formula (23):

[0142]

[0143] In the formula,

[0144]

[0145] d(Q i ) is the distance from Q i to the obstacle, that is, it represents the distance between the position of the UAV and the obstacle, and can be obtained by the positions of the discrete nodes in the three-dimensional scene and the positions of the mapped nodes of the nearest obstacle; d thr is the safety distance threshold from the obstacle; F c (d(Q i )) can be used to represent the first obstacle avoidance constraint.

[0146] The velocity term and the acceleration term can be expressed by the following formulas (25) and (26) respectively:

[0147]

[0148] where v iμ represents the velocity corresponding to the i-th control point with coordinates μ ; a iμ represents the acceleration corresponding to the i-th control point with coordinates μ .

[0149] For formulas (25) and (26), the following constraint of formula (27) is satisfied:

[0150]

[0151] where h is the velocity v iμ or the acceleration a iμ ; h max represents the maximum value of the velocity or the acceleration.

[0152] The velocity v in formula (25) i can be determined by formula (28):

[0153]

[0154] The acceleration a in formula (26) i can be determined by formula (29):

[0155]

[0156] Since the optimization problem of the objective function of the cubic spline curve is a non-linear optimization problem, in order to improve the solution efficiency, good initial values of discrete nodes are required. Therefore, multiple discrete nodes obtained by the A* algorithm can be used as the initial values of the cubic spline curve optimization problem, and a smooth fitting curve, that is, a motion path generated based on the curve fitting algorithm, can be obtained.

[0157] In these embodiments, the cubic spline curve algorithm is used to fit multiple discrete nodes obtained by the A* algorithm, and the constraint of the distance between the UAV position and the obstacle is added to the objective function of the cubic spline curve, so that the fitted cubic spline curve is smooth enough, and the motion path determined by the smooth curve effectively avoids the obstacle, so as to achieve the effect of smooth flight and obstacle avoidance of the UAV.

[0158] In some embodiments of these embodiments, based on the second obstacle avoidance constraint, the operation trajectory is locally optimized to obtain the UAV inspection path, including:

[0159] First, divide the operation trajectory into multiple local operation trajectories.

[0160] II. Based on the local optimization algorithm, perform local optimization on multiple local operation trajectories to obtain multiple local space states; among them, the local optimization algorithm includes the second obstacle avoidance constraint.

[0161] III. Determine the UAV inspection path according to multiple local space states.

[0162] Among them, the local space state includes one or more of the following: the position of the UAV, the speed of the UAV, the attitude quaternion of the UAV in the world coordinate system, and the thrust of the UAV.

[0163] Specifically, the local optimization algorithm can be a local trajectory planning algorithm based on the MPCC (Model Predictive Contouring Control) algorithm. The rigid body dynamics model of the UAV can be expressed as the following formula (30):

[0164]

[0165] In the formula, p, v, q, L are the position of the UAV, the speed of the UAV, the attitude quaternion of the UAV in the world coordinate system, and the thrust of the UAV, L = [0 0 L] T ; respectively represent the derivatives of p, v, q, L; ω is the angular velocity of the UAV in the body coordinate system; m is the mass of the UAV; R(q) is the rotation matrix corresponding to the quaternion; g is the gravitational acceleration of the UAV; η is the derivative of the thrust. Define u = [η ω T T , the space state of the UAV is sta = [p T v T q T L] T . Divide the operation trajectory into multiple local motion trajectories, and the state space of the UAV can be discretized as the following formula (31):

[0166] sta k+1 = sta k + f(sta k , u k )Δt (31);

[0167] In the formula, sta k represents the state space of the k-th local motion trajectory; f(sta k , u k ) is the function for solving the state space of the (k + 1)-th local motion trajectory.

[0168] MPCC can be defined as the following optimization problem:

[0169]

[0170] In the formula, e l is the tangential error; e c is the radial error; θ ∈ [0, 1] is the ratio of the arc length from the starting position to the target position to the arc length of the reference trajectory; θ k is the ratio of the arc length from the starting position to the target position corresponding to the k-th local motion trajectory to the arc length of the reference trajectory; u k represents the u value corresponding to the k-th local motion trajectory; u min and u max are the minimum and maximum values of u respectively; δ1, δ2, and δ3 are weight coefficients respectively; v θ,k represents the speed corresponding to the k-th local motion trajectory, and μ represents the weight parameter of the speed term; Δv θ represents the speed difference corresponding to the k-th local motion trajectory; represents the maximum value of the speed; represent the minimum and maximum values of the speed difference respectively; sta0 represents the initial state space; assume the reference trajectory is p r (θ), then e l , e c can be expressed as:

[0171]

[0172] e c (θ k ) = e(θ k ) - e l (θ k ) (3);

[0173] e(θ k ) = p k - p r (θ k ) (35);

[0174] In order to enable the UAV to accurately avoid obstacles and at the same time maintain a safe distance from the transmission line, a second obstacle avoidance constraint is established. The second obstacle avoidance constraint includes: a second constraint determined by the distance between each discrete node and the mapping node of the nearest obstacle, and a third constraint determined by the safe distance between each discrete node and the transmission line. Among them, the discrete node represents the discrete position corresponding to the local motion trajectory of the UAV in the three-dimensional scene. Specifically, the safety constraint can be established based on CBF (Control Barrier Function). Assume that the collision area of the UAV is simplified to a sphere with a radius of r, then the CBF function can be expressed as the following formulas (36) and (37):

[0175] h o(sta k )=d(p k )-rd s (36);

[0176]

[0177] Where h o (sta k ) represents the second constraint determined by the distance between the position of the UAV corresponding to the kth local motion trajectory and the obstacle; h l (sta k ) represents the third constraint determined by the safe distance between the position of the UAV corresponding to the kth local motion trajectory and the transmission line; d s For a safe distance.

[0178] For multiple local motion trajectories, the CBF function can be expressed as the following formulas (38) and (39):

[0179] h 0 (sta k )=h(sta k ) (38);

[0180] h i (sta k )=h i-1 (sta k+1 )+(c i -1)h i-1 (sta k ),i∈{1,2,3},c i ∈[0,1) (39);

[0181] Where c i represents a given parameter. Then the security set can be defined as follows:

[0182]

[0183] Where C s Represents a security collection.

[0184] For the system represented by formula (30), if there exists u k So that:

[0185]

[0186] Then the safety set C s is forward invariant. Then the MPCC optimization problem can be defined as the following formula (42):

[0187]

[0188] such that \(sta_0 = sta\)

[0189] sta k+1 = sta k + f(sta k , u k )\(\Delta t\)

[0190] \(\theta\) k+1 = \(\theta\) k + v θ,k dt + 0.5\(\Delta v\) θ,k \(\Delta t\) 2

[0191] v θ,k+1 = v θ,k + \(\Delta v\) θ,k \(\Delta t\)

[0192] u min \(u_{min}\leq u\leq u_{max}\) max

[0193]

[0194] In 3D modeling, the reference trajectory in the MPCC algorithm is the motion trajectory determined by the cubic spline curve algorithm. Therefore, the reference trajectory can be expressed by the following formula (43):

[0195] p r (\(\theta\)) = s(\(\theta(t\) M - t_3)+ t_3) (43);

[0196] By solving the optimization problem, multiple optimized local spatial states can be obtained, and based on this, the UAV inspection path is determined by the reference trajectory and the parameters of multiple local spatial states.

[0197] In these embodiments, the reference motion trajectory is used to locally optimize the motion trajectory by using the constraints of the safety distances of obstacles and transmission lines in the MPCC algorithm. The determined UAV inspection path optimizes the UAV consumption and flight time, and at the same time can fly at a safe distance and effectively avoid obstacles. Using the generated UAV inspection path to guide the UAV to inspect the transmission line can improve the inspection efficiency of the transmission line.

[0198] Figure 4 is the side view of the inspection path generated in the 3D modeling scenario provided by the embodiment of the present application, Figure 5 is the top view of the inspection path generated in the 3D modeling scenario provided by the embodiment of the present application, as Figure 4 、 Figure 5As shown, the grid represents the position coordinates in 3D modeling, 401 represents the power transmission line, 402 represents the generated inspection path, and 403 represents the obstacle. It can be seen that the drone can start from the starting point, follow the power transmission line, bypass the obstacles in the figure and reach the end point.

[0199] The embodiment of the present application also provides an embodiment in which the drone performs inspections with reference to the generated inspection path. Specifically, the drone starts from the starting position and passes through each power transmission line segment in sequence until the termination position. For each power transmission line segment, it is determined whether there is an obstacle in the current power transmission line. If there is no obstacle, the inspection is performed along the line segment path determined by the two poles of the power transmission line; if there is an obstacle, the inspection is performed according to the generated inspection path.

[0200] Figure 6 It is a schematic structural diagram of a device for generating an inspection path of a drone in a power transmission line provided by an embodiment of the present application. As Figure 6 shown, the device for generating an inspection path of a drone in a power transmission line provided in this embodiment includes:

[0201] A construction module 601 for constructing a 3D scene according to the position information of the poles corresponding to each power transmission line segment and the position information of the obstacles; wherein, the 3D scene includes mapping nodes of multiple poles and mapping nodes of obstacles;

[0202] A determination module 602 for determining a plurality of discrete nodes distributed along multiple power transmission line segments in the 3D scene according to the position information of the first mapping node corresponding to the pole of the starting power transmission line, the position information of the second mapping node corresponding to the pole of the terminating power transmission line, and the optimization rule of the drone consumption and flight time;

[0203] A generation module 603 for generating a running trajectory based on the first obstacle avoidance constraint according to a plurality of discrete nodes;

[0204] An optimization module 604 for locally optimizing the running trajectory based on the second obstacle avoidance constraint to obtain the inspection path of the drone.

[0205] In a possible implementation manner, the determination module 602 is further configured to:

[0206] Determine the starting position according to the position information of the first mapping node of the starting power transmission line;

[0207] Determine the termination position according to the position information of the second mapping node of the terminating power transmission line;

[0208] Determine a plurality of discrete nodes from the starting position to the termination position based on the node expansion algorithm according to the optimization rule of the drone consumption and flight time.

[0209] In a possible implementation, the generating module 603 is further configured to generate an operation trajectory based on a curve fitting algorithm according to a plurality of discrete nodes.

[0210] In a possible implementation, the curve fitting algorithm includes an objective function for smoothing the fitted curve, and the objective function includes a first obstacle avoidance constraint.

[0211] Perform curve fitting on the plurality of discrete nodes based on the objective function to obtain an operation trajectory.

[0212] In a possible implementation, the optimizing module 604 is further configured to divide the operation trajectory into a plurality of local operation trajectories; perform local optimization on the plurality of local operation trajectories based on a local optimization algorithm to obtain a plurality of local spatial states; wherein, the local optimization algorithm includes a second obstacle avoidance constraint; determine the UAV inspection path according to the plurality of local spatial states.

[0213] In a possible implementation, the local spatial state includes one or more of the following: the position of the UAV, the speed of the UAV, the attitude quaternion of the UAV in the world coordinate system, and the thrust of the UAV.

[0214] In a possible implementation, for any one of the plurality of discrete nodes, the discrete node has one or more of the following attribute information: the position of the UAV, the speed of the UAV, and the acceleration of the UAV.

[0215] In a possible implementation, the first obstacle avoidance constraint includes: a first constraint determined by the distance between each discrete node and the mapping node of the nearest obstacle;

[0216] The second obstacle avoidance constraint includes: a second constraint determined by the distance between each discrete node and the mapping node of the nearest obstacle, and a third constraint determined by the safety distance between each discrete node and the power transmission line.

[0217] In a possible implementation, the safety distance between the discrete node and the power transmission line includes: the distance between the discrete node and the plane where the corresponding power transmission line is located.

[0218] The device for generating the UAV inspection path in the power transmission line provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0219] Figure 7 This is a schematic structural diagram of the device for generating the UAV inspection path in the power transmission line provided in the embodiment of the present application. As Figure 7As shown in the figure, the device 70 for generating the UAV inspection path in the transmission line provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the device 70 for generating the UAV inspection path in the transmission line further includes a communication component 703. Among them, the processor 701, the memory 702, and the communication component 703 are connected through a bus 704.

[0220] In the specific implementation process, at least one processor 701 executes the computer execution instructions stored in the memory 702, so that at least one processor 701 executes the above method.

[0221] For the specific implementation process of the processor 701, reference can be made to the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0222] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application-specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or by a combination of hardware and software modules in the processor.

[0223] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0224] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0225] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0226] The present application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above method.

[0227] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0228] An exemplary readable storage medium is coupled to the processor so that the processor can read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0229] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0230] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0231] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0232] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0233] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0234] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will easily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field of the present invention that are not disclosed in the present invention. It is not limited to the exact structure described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for generating an inspection path of an unmanned aerial vehicle in a transmission line, characterized in that, Including: Construct a three-dimensional scene according to the position information of the towers corresponding to each section of the transmission line and the position information of the obstacles; wherein, the three-dimensional scene includes mapping nodes of multiple said towers and mapping nodes of the obstacles; In the three-dimensional scene, determine a plurality of discrete nodes distributed along the multiple sections of the transmission line according to the position information of the first mapping node corresponding to the tower corresponding to the starting transmission line, the position information of the second mapping node corresponding to the tower corresponding to the ending transmission line, and the optimization rules of drone consumption and flight time; Generate an operation trajectory based on the first obstacle avoidance constraint according to the plurality of discrete nodes; Based on the second obstacle avoidance constraint, locally optimize the operation trajectory to obtain a drone inspection path.

2. The method according to claim 1, wherein The determining a plurality of discrete nodes distributed along the multiple sections of the transmission line according to the position information of the first mapping node corresponding to the tower corresponding to the starting transmission line, the position information of the second mapping node corresponding to the tower corresponding to the ending transmission line, and the optimization rules of drone consumption and flight time includes: Determine a starting position according to the position information of the first mapping node of the starting transmission line; Determine an ending position according to the position information of the second mapping node of the ending transmission line; Based on the optimization rules of drone consumption and flight time and based on a node expansion algorithm, determine the plurality of discrete nodes from the starting position to the ending position.

3. The method according to claim 1, wherein The generating an operation trajectory based on the first obstacle avoidance constraint according to the plurality of discrete nodes includes: Generate the operation trajectory based on a curve fitting algorithm according to the plurality of discrete nodes.

4. The method according to claim 3, characterized in that, The curve fitting algorithm includes an objective function for smoothing and fitting a curve, and the objective function includes the first obstacle avoidance constraint; The generating the operation trajectory based on a curve fitting algorithm according to the plurality of discrete nodes includes: Perform curve fitting on the plurality of discrete nodes based on the objective function to obtain the operation trajectory.

5. The method according to claim 1, wherein The locally optimizing the operation trajectory based on the second obstacle avoidance constraint to obtain a drone inspection path includes: Divide the operation trajectory into a plurality of local operation trajectories; Based on a local optimization algorithm, locally optimize the plurality of local operation trajectories to obtain a plurality of local spatial states; wherein, the local optimization algorithm includes the second obstacle avoidance constraint; Determine the drone inspection path according to the plurality of local spatial states.

6. The method according to claim 5, wherein The local spatial state includes one or more of the following: the position of the drone, the speed of the drone, the attitude quaternion of the drone in the world coordinate system, and the thrust of the drone.

7. The method according to claim 1, wherein For any discrete node among the plurality of discrete nodes, the discrete node has one or more of the following attribute information: the position of the drone, the speed of the drone, and the acceleration of the drone.

8. The method according to claim 7, wherein The first obstacle avoidance constraint includes: a first constraint determined by the distance between each of the discrete nodes and the mapping node of the nearest obstacle; The second obstacle avoidance constraint includes: a second constraint determined by the distance between each of the discrete nodes and the mapping node of the nearest obstacle, and a third constraint determined by the safety distance between each of the discrete nodes and the transmission line.

9. The method according to claim 8, characterized in that The safety distance between the discrete node and the power transmission line includes: the distance between the discrete node and the plane where the corresponding power transmission line is located.

10. A device for generating an inspection path of an unmanned aerial vehicle in a transmission line, characterized in that, Including: A construction module for constructing a three-dimensional scene according to the position information of the poles corresponding to each of the multiple power transmission lines and the position information of the obstacles; wherein, the three-dimensional scene includes mapping nodes of the multiple poles and mapping nodes of the obstacles; A determination module for determining, in the three-dimensional scene, a plurality of discrete nodes distributed along the multiple power transmission lines according to the position information of the first mapping node corresponding to the pole corresponding to the starting power transmission line, the position information of the second mapping node corresponding to the pole corresponding to the terminating power transmission line, and the optimization rules for the consumption and flight time of the unmanned aerial vehicle; A generation module for generating an operation trajectory based on the first obstacle avoidance constraint according to the plurality of discrete nodes; An optimization module for locally optimizing the operation trajectory based on the second obstacle avoidance constraint to obtain an unmanned aerial vehicle inspection path.

11. An apparatus for generating an inspection path of an unmanned aerial vehicle in a power transmission line, characterized in that Including: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, Computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by the processor, they are used to implement the method according to any one of claims 1-9.

13. A computer program product, characterized in that, Including a computer program, which implements the method according to any one of claims 1-9 when executed by the processor.

Images