Unmanned aerial vehicle path planning method, device, equipment and storage medium

Abstract

The embodiment of the invention discloses an unmanned aerial vehicle path planning method, device and equipment and a storage medium, and the method comprises the steps: obtaining the position information of a plurality of associated objects and a target unmanned aerial vehicle in a target region, and constructing a preliminary patrol network based on the position information; wherein the associated object at least comprises a transmission tower and an unmanned aerial vehicle base; reconstructing branches in the preliminary patrol network to obtain a target patrol network; and based on the target patrol network and the reference flight parameters of the target unmanned aerial vehicle, determining a target patrol path corresponding to each target unmanned aerial vehicle. According to the technical scheme provided by the embodiment of the invention, the problem of poor path optimization effect during path planning of the power transmission line based on the unmanned aerial vehicle in the prior art is solved, the target patrol network can be firstly constructed, and then the optimal path of each unmanned aerial vehicle is determined based on the target patrol network and the reference flight parameters of each unmanned aerial vehicle, so that the path optimization efficiency is improved. The route planning quality can be improved, and the unmanned aerial vehicle inspection efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of power transmission line inspection, and in particular to a method, device, equipment and storage medium for unmanned aerial vehicle path planning. Background Art

[0002] Transmission lines are one of the most important infrastructures in my country. These lines are thousands of kilometers long. In order to ensure the reliability of power supply, power companies have invested a lot of money in line construction and maintenance. In recent years, drones have been widely used in line inspections, greatly improving the safety of operations and reducing costs.

[0003] 1. When it comes to the path planning problem of drones for precise inspection of power towers, the ant colony optimization algorithm usually requires multiple iterations to find a near-optimal solution, which results in large computational and time overheads and is prone to falling into a local optimal solution rather than a global optimal solution. When multiple constraints are involved, such as flight altitude restrictions and obstacle avoidance requirements, the algorithm is prone to slow convergence or poor results.

[0004] 2. In the problem of drone path planning for remote power grid inspection, the hybrid genetic algorithm needs to determine the appropriate parameters through a large number of experiments, because inappropriate parameter settings have a great impact on the search efficiency and result quality of the genetic algorithm. Since the hybrid genetic algorithm performs well in global search but may be insufficient in local search, it is usually combined with other local search techniques to improve the quality of the solution. The current technology cannot effectively balance global and local searches. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment and storage medium for UAV path planning, which can first construct a target patrol network, and then determine the optimal path for each UAV based on the target patrol network and the reference flight parameters of each UAV, thereby improving the quality of path planning and the efficiency of UAV inspection.

[0006] In a first aspect, an embodiment of the present invention provides a method for UAV path planning, the method comprising:

[0007] The location information of multiple associated objects and target UAVs in the target area is obtained, and a preliminary patrol network is constructed based on the location information; wherein the associated objects include at least: transmission towers and UAV bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and reference flight parameters of the target UAV, the target patrol paths corresponding to each target UAV are determined respectively.

[0008] In a second aspect, an embodiment of the present invention provides a drone path planning device, the device comprising:

[0009] A network construction module is used to obtain the location information of multiple associated objects and target drones in the target area, and to construct a preliminary patrol network based on the location information; wherein the associated objects include at least: transmission towers and drone bases; a network reconstruction module is used to reconstruct the branches in the preliminary patrol network to obtain a target patrol network; a path determination module is used to determine the target patrol path corresponding to each target drone based on the target patrol network and the reference flight parameters of the target drone.

[0010] In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising:

[0011] one or more processors;

[0012] A memory for storing one or more programs;

[0013] When the one or more programs are executed by the one or more processors, the one or more processors implement the drone path planning method described in any embodiment.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the drone path planning method described in any embodiment.

[0015] The technical solution provided by the embodiment of the present invention obtains the location information of multiple related objects and target drones in the target area, and constructs a preliminary patrol network based on the location information; wherein the related objects include at least: transmission towers and drone bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and the reference flight parameters of the target drone, the target patrol path corresponding to each target drone is determined respectively. The technical solution of the embodiment of the present invention solves the problem that the existing technology is prone to poor path optimization when planning the path of transmission lines based on drones. The target patrol network can be constructed first, and then the optimal path of each drone can be determined based on the target patrol network and the reference flight parameters of each drone, which can improve the quality of path planning and the efficiency of drone inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a UAV path planning method provided by an embodiment of the present invention;

[0017] Figure 2 This is another flow chart of a UAV path planning method provided by an embodiment of the present invention;

[0018] Figure 3 It is a schematic diagram of constructing a directed weighted network provided by an embodiment of the present invention;

[0019] Figure 4 It is a schematic diagram of reconstructing a patrol network provided by an embodiment of the present invention;

[0020] Figure 5 This is a workflow diagram for performing drone path planning provided by an embodiment of the present invention;

[0021] Figure 6 It is a structural schematic diagram of a UAV path planning device provided by an embodiment of the present invention;

[0022] Figure 7 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Figure 1 It is a flow chart of a UAV path planning method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of planning the path of a UAV patrolling a power transmission line. The method can be executed by a UAV path planning device, which can be implemented by software and / or hardware.

[0025] like Figure 1 As shown, the UAV path planning method includes the following steps:

[0026] S110, obtaining location information of multiple associated objects and a target drone in a target area, and constructing a preliminary patrol network based on the location information.

[0027] The target area may be an area where a transmission line inspection is required. The associated object may be an object associated with a line inspection task. Exemplarily, the associated objects include at least: a transmission tower and a drone base. In the embodiment of the present invention, the transmission lines formed between the transmission towers may be inspected, and the inspection path of each target drone may be determined with a shorter overall inspection time as the goal while ensuring that each transmission line in the target area is inspected by at least one drone. The drone base may serve as a charging station for the drone, as well as a starting point and an end point for executing the task. The specific number of drone bases is not limited here. The location information may include information such as geographic coordinates, and the specific content of the location information is not limited here. The target drone may be a drone used to perform line inspection tasks. Further, the preliminary inspection network may be a network composed of transmission lines in the target area. Exemplarily, each associated object in the target area may be used as a network node, and then each two network nodes may be connected to obtain a preliminary inspection network.

[0028] S120: Reconstruct the branches in the preliminary patrol network to obtain a target patrol network.

[0029] The target patrol network may be a network obtained by reconstructing the preliminary patrol network. Exemplarily, the network branches in the preliminary patrol network may be clustered based on the association relationship between the network branches in the preliminary patrol network to obtain the target patrol network.

[0030] S130: Based on the target patrol network and the reference flight parameters of the target UAV, determine the target patrol path corresponding to each target UAV.

[0031] The target patrol path may be a patrol path corresponding to the patrol mission of the target UAV. Exemplarily, a patrol function for the target UAV may be constructed based on the target patrol network and the reference flight parameters of the target UAV. The parameters in the patrol function may be optimized under preset constraints with the goal of reducing the patrol time, thereby obtaining the target patrol path corresponding to the target UAV.

[0032] The technical solution provided by the embodiment of the present invention obtains the location information of multiple related objects and target drones in the target area, and constructs a preliminary patrol network based on the location information; wherein the related objects include at least: transmission towers and drone bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and the reference flight parameters of the target drone, the target patrol path corresponding to each target drone is determined respectively. The technical solution of the embodiment of the present invention solves the problem that the existing technology is prone to poor path optimization when planning the path of transmission lines based on drones. The target patrol network can be constructed first, and then the optimal path of each drone can be determined based on the target patrol network and the reference flight parameters of each drone, which can improve the quality of path planning and the efficiency of drone inspections.

[0033] Figure 2 It is another flow chart of a UAV path planning method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of planning the path of a UAV patrolling a power transmission line. Based on the above embodiment, this embodiment further illustrates how to construct a preliminary patrol network based on the location information; how to reconstruct the branches in the preliminary patrol network to obtain a target patrol network; and how to determine the target patrol path corresponding to each target UAV based on the target patrol network and the reference flight parameters of the target UAV. The device can be implemented by software and / or hardware and integrated in a computer device with application development function.

[0034] like Figure 2 As shown, the UAV path planning method includes the following steps:

[0035] S210: Acquire location information of multiple associated objects and a target UAV in a target area, and construct a preliminary patrol network based on the location information.

[0036] Optionally, obtain location information of multiple associated objects and target drones in the target area, and construct a preliminary patrol network based on the location information, including: constructing multiple network nodes based on the location information of the associated objects; connecting the multiple network nodes to obtain a directed weighted network, and using the obtained directed weighted network as the initial patrol network; determining a network parameter set corresponding to the initial patrol network; and determining the preliminary patrol network based on the initial patrol network and the network parameter set.

[0037] Among them, the location point corresponding to each associated object can be taken as a network node, and then every two network nodes can be connected to obtain a directed weighted network. Among them, a weighted directed graph is a network data structure, in which each edge has a weight associated with it, and this weight can represent the length, cost or other measurement of the edge. Unlike undirected networks, the edges in weighted directed networks are directed, and the weights may be asymmetric, that is, the weight of the edge from vertex u to vertex v may be different from the weight of the edge from vertex v to vertex u. That is, when connecting two network nodes, two connecting lines in opposite directions will be formed. Exemplary, Figure 3 FIG. 1 is a schematic diagram of constructing a directed weighted network provided by an embodiment of the present invention. Figure 3 As shown, the left side of the figure is a position relationship diagram of associated objects and target drones in the target area, and the right side is a corresponding directed weighted network constructed based on the position relationship diagram on the left.

[0038] Further, the network parameter set may be a set of parameters associated with a directed weighted network. Specifically, the network parameter set includes: at least one of: node parameters, edge parameters, drone parameters and patrol cost parameters. Among them, the node parameters may be location parameters of transmission towers and drone bases in the target area. Edge parameters may be parameters related to network branches in a weighted directed network. Exemplarily, edge parameters may include parameters such as branch distances of network branches in a weighted directed network. Drone parameters may be parameters for the number of drones performing transmission line patrol tasks. Patrol cost parameters may be cost parameters corresponding to drone patrols of network branches. Exemplarily, patrol cost parameters may include flight time parameters and battery consumption parameters. Further, the initial patrol network and the network parameter set may be combined to obtain a preliminary patrol network.

[0039] Optionally, determining the patrol cost parameters includes: determining multiple directed branches from a directed weighted network; for each directed branch, determining the flight time parameter corresponding to the directed branch based on the length of the directed branch and the reference environmental parameters; determining the battery consumption parameter based on the length of the directed branch and the reference flight distance of the target UAV; determining the patrol cost parameter based on the flight time parameter and the battery consumption parameter.

[0040] Among them, a directed branch can be a branch that connects two network nodes and has a direction. Exemplarily, there can be two directed branches AB and BA between network node A and network node B. The reference environmental parameters can be environmental parameters in the target area. Exemplarily, the reference environmental parameters can include wind direction parameters and wind force parameters, etc. The flight time parameter can be a time parameter used by the drone to patrol the directed branch. Exemplarily, the final target patrol speed can be determined based on the reference flight speed of the target drone and the reference environmental parameters, and then the length of the directed branch is divided by the target patrol speed to obtain the flight time parameter.

[0041] Further, the reference flight distance may be the maximum flight distance of the target UAV. The battery consumption parameter may be a parameter of the power consumed by the target UAV patrolling the directed branch. Exemplarily, the length of the directed branch may be compared with the reference flight distance to obtain a parameter of the power percentage consumed by the target UAV patrolling the directed branch, and the power percentage parameter may be used as the battery consumption parameter.

[0042] Optionally, determining a reference flight distance of the target UAV includes: determining a maximum flight distance based on a reference flight speed and a maximum flight time of the target UAV; and determining a reference flight distance based on the maximum flight distance and a preset correction coefficient.

[0043] Among them, the reference flight speed can be a reference speed for the target UAV to fly. Exemplarily, the flight speed marked when the target UAV leaves the factory can be used as the reference flight speed. The maximum flight time can be the longest duration that the target UAV is in a flight working state. Exemplarily, the maximum flight time can also be based on the flight time marked when the target UAV leaves the factory. The preset correction coefficient can be a coefficient for correcting the flight distance of the target UAV. The preset correction coefficient can be set manually, and exemplarily, the preset correction coefficient can be taken from the range of (0,1]. Furthermore, the maximum flight distance and the preset correction coefficient can be multiplied, and the product obtained can be used as the reference flight distance.

[0044] S220: Identify network branches in the preliminary patrol network, and determine, for each network branch, a patrol cost parameter corresponding to the network branch.

[0045] The network branches may be branches formed by edges in the preliminary inspection network. Specifically, these edges are surrounded by network nodes that have a single connection to other edges (terminal network nodes) or network nodes that are connected to at least three other network nodes (forked network nodes). Figure 4 The network shown in (a) is a preliminary inspection network; Figure 4 (b) shows the identification result of the network branches in the preliminary patrol network, and there are 7 network branches in the preliminary patrol network.

[0046] The patrol cost parameter may be a parameter representing the cost of patrolling a network branch. Specifically, the patrol cost parameter may be a parameter representing the power consumed by patrolling a network branch. Exemplarily, the battery consumption parameters corresponding to all network edges in the network branch may be added together to obtain the patrol cost parameter corresponding to the network branch.

[0047] S230: Clustering the network branches based on the patrol cost parameters to obtain the target patrol network.

[0048] The target patrol network may be a network obtained by reconstructing the preliminary patrol network. Optionally, the maximum patrol cost parameter may be used as a reference cost parameter, and the number of clusters may be determined based on the reference cost parameter and a preset correction parameter; based on the number of clusters, the network nodes in the network branch may be clustered to obtain multiple target clusters, and the target patrol network may be determined based on the multiple target clusters; wherein the number of the multiple target clusters is equal to the number of clusters.

[0049] Among them, the number of clustered clusters can be the total number of clusters obtained by clustering network branches. The target cluster can be the cluster obtained by clustering network branches. Exemplarily, the number of clusters corresponding to each network branch can be determined based on the number of clustered clusters and the number of network nodes in the network branch. Exemplarily, if the number of network nodes in a network branch is large, a larger number of clusters can be allocated to the network branch. Furthermore, for each network branch, the network nodes in the network branch can be clustered to obtain the same number of target clusters as the number of clusters. Finally, each target cluster can be taken as a cluster node, and then all cluster nodes can be connected to obtain the target patrol network. Exemplarily, Figure 4 (c) shows the Figure 4 Clustering results obtained after clustering the network branches in (b). Figure 4 As shown in (c) in the figure, when the number of clusters is equal to 10, the network nodes in the network branch can be clustered to obtain 10 target clusters. Figure 4 (d) can be based on Figure 4 The target patrol network is determined by the clustering result of (c). It should be noted here that Figure 4 In (c), the target clusters corresponding to nodes 8 to 16 are connected to many other target clusters. In order to better restore the connection relationship between branches in the network, Figure 4 In (d), the target cluster can be regarded as two cluster nodes.

[0050] S240: For each target UAV, based on the target patrol network and the reference flight parameters of the target UAV, determine a target patrol function corresponding to the target UAV.

[0051] The reference flight parameters may be flight parameters of the target UAV performing patrol missions. For example, the reference flight parameters may include flight speed, maximum flight time, and maximum power parameters.

[0052] The target patrol function may be a function for optimizing the patrol path of the target UAV. For example, based on the target patrol network and the reference flight parameters of the target UAV, a corresponding path optimization function may be constructed with the goal of reducing the patrol time, and then the path optimization function may be used as the target patrol function.

[0053] S250, optimizing the parameters in the multiple target patrol functions based on the preset constraints, and obtaining the target patrol paths corresponding to each target UAV.

[0054] Among them, the preset constraint condition may be a condition constraining the execution mode of the patrol mission of the target UAV. For example, the preset constraint condition may include: each network branch has at least one target UAV passing through, and the flight time of the target UAV cannot exceed the maximum flight time and other constraints. The target patrol path may be the patrol path corresponding to the patrol mission performed by the target UAV. Specifically, under the preset constraint condition, the target patrol function may be optimized for parameters, thereby obtaining the target patrol path corresponding to each target UAV.

[0055] For illustrative purposes, in order to better understand the technical solution provided by the present invention, specific embodiments are introduced below. Figure 5 FIG. 1 is a workflow diagram for performing drone path planning provided by an embodiment of the present invention. Figure 5 As shown in the figure, the workflow for drone path planning includes the following steps: 1. Obtain grid information: Obtain the distribution of transmission towers in the inspection area, the accurate location of drones and their bases. 2. Construct a graph representation: Represent the power grid as a graph, where the power towers are represented as vertices of the graph and the drone bases are represented as another set of vertices of the graph. The edges between these vertices represent potential flight paths between drones. 3. Construct energy consumption models: Calculate flight time and battery consumption based on the flight speed of the drone and the location of the power towers and drone bases. These models are used to evaluate the energy consumption of drones during flight. 4. Construct a clustering strategy: In order to reduce the computational burden of the planning problem, a clustering strategy is proposed to group power lines into differentiated branches. This can reduce the number of vertices and edges of the graph without affecting the topological structure of the graph. 5. Construct an optimization problem: Convert the inspection task into an optimization problem on the graph, and find the best allocation and inspection order by minimizing the task time of the drone team. 6. Solve the optimization problem: The optimization problem can be solved using integer linear programming (MILP).

[0056] In step 1, by obtaining existing maps and databases of the power grid area, field surveys are conducted to confirm the actual location of transmission towers and the exact coordinates of drones and their bases, and these data are recorded using GPS equipment. Next, the collected data is entered into a geographic information system (GIS) to organize and verify the accuracy of the information. Finally, a detailed map or 3D model is generated to indicate the distribution of transmission towers and the location of drone bases to support subsequent inspection route planning.

[0057] In step 2, a directed weighted multigraph is constructed using the available drones and their base coordinates and the transmission tower locations and their connections given in step 1. The collection Represents the vertices of the graph, including represents the set of n electric towers and represents the set of drone bases, δ represents the number of available drones, and A collection to represent the set of available drones

[0058] The vertices in are connected by a set of edges ε that define potential drone flights between all vertices. Associated with the edges in ε is the cost set gather denote the cost of flight time and battery consumption between vertices, respectively. The flight time can be calculated by considering the flight speed of the drone during the inspection and the locations of the power tower and the drone base. In addition, when the drone returns to the base to recharge, the charging time is quantified as a part of the flight time.

[0059] Since the path planning problem considers heterogeneous drones, the cost of flying between two vertices is not independent of the drones used. Second, the cost of flying between two vertices may depend on the flight direction, for example, due to the presence of wind. Therefore, the number of edges connecting two vertices is 2×δ, except in the set An edge with one vertex in .

[0060] (It is believed that each drone should be operated from its own base.) Define e i，j|k ∈ε is the flight process of UAV k from vertex i to vertex j (i≠j), and the time spent in this process is defined as The amount of battery consumed is defined as b i，j|k ∈B, then according to the above discussion, it is believed that the round-trip time between two points is different from the amount of battery consumed, that is, t i，j|k ≠t j，i|k and b i，j|k ≠b j，i|k .

[0061] The edges in ε can be divided into two different sets, namely gather Included Collection The set is all the edges connecting two vertices in the grid, which represent the physically connected towers in the real grid. Contains not in the set The other edges in .

[0062] In step 3, the maximum flight time of the drone provided by the manufacturer And the reference flight speed during the flight It is easy to estimate the maximum distance that UAV k can fly in the inspection mission. However, there are some unpredictable events in the actual situation that can reduce the maximum flight time, so a safety margin parameter β should be applied. k ∈(0, 1], maximum safe distance Can be used Since the location of the tower and the location of the drone base are known, the flight distance d between each pair {i, j} i，j They can be approximated by their Euclidean distance. Assuming that there is a linear relationship between the flight distance and the battery consumption, the battery capacity in step 2 can be expressed by formula (1):

[0063]

[0064] In step 4, the power grid is constructed based on the known tower distribution given in step 1, such as Figure 4 As shown in (a), we first identify its different branches, which consist of a set of connected edges surrounded by vertices that have a single connection to other edges (terminal vertices) or vertices connected to at least three other vertices (forking vertices), such as Figure 4 As shown in (b), secondly, for each branch s, the battery consumption cost of each available drone crossing the entire branch is evaluated from two directions. Among the generated cost sets, the highest one is recorded as And as a reference value. At this time, the parameter α∈(0,1) is introduced as the battery threshold to determine the number of clusters that the branch is divided into. In this way, the number of clusters of branch s is determined as is the upper limit function, and then, the edges in branch s are distributed to In clusters, such as Figure 4 This process is repeated iteratively until all branches are clustered. Finally, the clustering branches are considered to reconstruct the original power grid, as shown in (c) in the figure. Figure 4 As shown in (d) in .

[0065] In step 5, by encoding the directed weighted multigraph ζ obtained in step 2, the inspection task can be transformed into an optimization problem on the graph, that is, finding the best allocation and inspection order for each drone. Drone from the collection Starting and ending at the base in In the minimum mission time given by the cost in the set, while satisfying the battery capacity constraint of the UAV, Fly between the vertices in until all edges are covered This can be done with a collection The latter means that if the target inspection is beyond the range that the drone can cover with a set of batteries, they must return to base to recharge the batteries before they can continue their mission.

[0066] The problem described above can be solved by using a preset optimization algorithm. In this case, it is necessary to define a binary decision variable x i，j|k , which has only two values ​​representing edge e i，j|k ∈ε is covered(x i，j|k =1) or not covered (x i，j|k =0), optimizing the mission time of a multi-UAV team means minimizing the inspection time of the UAVs, because the last UAV needs more time to complete the inspection when it returns to the base at the end of the mission. This objective is not linear and should be reformulated as encoding in a problem. Therefore, an equivalent objective could be to minimize the sum of the inspection times of all UAVs while keeping these times as balanced as possible. In order to include this balance in the optimization problem, we also define the set For each pair of drones r and q in , we define a variable real variable y that quantifies the difference in inspection time between the two drones. r，q ≥0, r,q is the index of the drone, and r <q。

[0067] In summary, the target patrol function can be expressed as follows:

[0068]

[0069]

[0070] In this formulation, the objective function in equation (2) is consistent with the optimization method described previously. Constraints (3) and (4) ensure that all drones start their missions from their associated base and complete their missions there. These constraints also allow a visit to a base if a drone needs to recharge. Constraint (5) enforces the continuity of each vertex for each drone. This means that if a drone reaches a vertex, the same drone must leave it. Constraint (6) ensures that the entire grid is covered, since in the set The set of edges connecting two towers contained in must select at least one edge, either in one direction or in the opposite direction. Constraints (7) and (8) aim to balance the inspection time between UAVs. r，q is included in the objective function, so the only way to minimize the sum is to minimize the value of the variable y r，q , thereby balancing the inspection times r and q of each pair of drones according to these constraints. Finally, constraint (9) prevents the formation of sub-circuits that are not connected to the base or that exceed the drone battery capacity. Therefore, the function h(S) determines the time at which the drone must enter and leave Each subset contained in The lower bound of the number of The number of constraints may be too large, and these constraints are usually omitted at the beginning of the optimization process and gradually added when they are not satisfied. Nevertheless, in order to speed up the search for the optimal solution, the following battery constraints can be included:

[0071]

[0072] These constraints require that the total battery consumed by each drone during the inspection period (the left side of Equation (10)) must be less than or equal to the time it spends at its base (the right side of Equation (10)), assuming that the drone always leaves the base with a full battery.

[0073] In step 6, when the problem in step 5 is solved, it will give a set of decision variables x with binary value 1 i，j|k As output, the set of graph edges covered by the multi-drone team is selected The set composed of * , then, the edge assigned to each UAV k are directly identifiable because they are already represented by index k. The inspection order that each drone k must follow can be determined from index i=0 k Edge Start calculating sequentially, calculating and connecting edges sequentially until index j=0 k side End. For the same drone k, when there are multiple edges Its index i = 0 k This means that there are several flight processes associated with this drone. They can all be viewed as a single integrated multi-circuit, computed according to the same connection strategy, where each circuit passes through vertex 0 k Connect to the previous tour. In this way, each drone k has an optimal route P associated with it. k , the route consists of an ordered set of vertices, inferred directly from the preceding edge sequence, and has the form:

[0074]

[0075] Among them, A, B, C, D, and E are the vertices (towers) that the drone k must follow when performing inspection tasks. Vertices B, C, and D can also be used as bases. k .

[0076] The technical solution provided by the embodiment of the present invention obtains the location information of multiple related objects and target drones in the target area, and constructs a preliminary patrol network based on the location information; identifies network branches in the preliminary patrol network, and determines the patrol cost parameters corresponding to the network branches for each network branch; clusters the network branches based on the patrol cost parameters to obtain the target patrol network; for each target drone, determines the target patrol function corresponding to the target drone based on the target patrol network and the reference flight parameters of the target drone; optimizes the parameters in the multiple target patrol functions based on preset constraints to obtain the target patrol paths corresponding to each target drone. The technical solution of the embodiment of the present invention solves the problem that the existing technology is prone to poor path optimization when planning the path of power transmission lines based on drones. The target patrol network can be constructed first, and then the optimal path of each drone can be determined based on the target patrol network and the reference flight parameters of each drone, which can improve the quality of path planning and the efficiency of drone inspection.

[0077] Figure 6 It is a structural schematic diagram of a UAV path planning device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of planning the path of a UAV patrolling a power transmission line. The device can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0078] like Figure 6 As shown, the UAV path planning device includes: a network construction module 310, a network reconstruction module 320 and a path determination module 330.

[0079] Among them, the network construction module 310 is used to obtain the location information of multiple related objects and target drones in the target area, and to construct a preliminary patrol network based on the location information; wherein the related objects include at least: transmission towers and drone bases; the network reconstruction module 320 is used to reconstruct the branches in the preliminary patrol network to obtain the target patrol network; the path determination module 330 is used to determine the target patrol path corresponding to each target drone based on the target patrol network and the reference flight parameters of the target drone.

[0080] The technical solution provided by the embodiment of the present invention obtains the location information of multiple related objects and target drones in the target area, and constructs a preliminary patrol network based on the location information; wherein the related objects include at least: transmission towers and drone bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and the reference flight parameters of the target drone, the target patrol path corresponding to each target drone is determined respectively. The technical solution of the embodiment of the present invention solves the problem that the existing technology is prone to poor path optimization when planning the path of transmission lines based on drones. The target patrol network can be constructed first, and then the optimal path of each drone can be determined based on the target patrol network and the reference flight parameters of each drone, which can improve the quality of path planning and the efficiency of drone inspections.

[0081] In an optional embodiment, the network reconstruction module 320 is specifically used to: identify network branches in the preliminary patrol network; wherein the network branches are branches connecting adjacent network nodes; for each network branch, determine the patrol cost parameter corresponding to the network branch; wherein the patrol cost parameter is used to represent the power consumption required for the target UAV to pass through the network branch; cluster the network branches based on the patrol cost parameter to obtain the target patrol network.

[0082] In an optional embodiment, the network reconstruction module 320 includes: a network branch clustering unit, used to: take the maximum patrol cost parameter as a reference cost parameter, and determine the number of clustering clusters based on the reference cost parameter and a preset correction parameter; based on the number of clustering clusters, cluster the network nodes in the network branch to obtain multiple target clusters, and determine the target patrol network based on the multiple target clusters; wherein the number of the multiple target clusters is equal to the number of clustering clusters.

[0083] In an optional embodiment, the network construction module 310 is specifically used to: construct multiple network nodes based on the location information of the associated objects; connect the multiple network nodes to obtain a directed weighted network, and use the obtained directed weighted network as an initial patrol network; determine a network parameter set corresponding to the initial patrol network; wherein the network parameter set includes: at least one of node parameters, edge parameters, drone parameters and patrol cost parameters; determine the preliminary patrol network based on the initial patrol network and the network parameter set.

[0084] In an optional embodiment, the network construction module 310 includes: a patrol cost parameter determination unit, used to: determine multiple directed branches from the directed weighted network; wherein the directed branch is a directional branch connecting two network nodes; for each directed branch, determine the flight time parameter corresponding to the directed branch according to the length of the directed branch and the reference environmental parameters; determine the battery consumption parameter according to the length of the directed branch and the reference flight distance of the target UAV; determine the patrol cost parameter according to the flight time parameter and the battery consumption parameter.

[0085] In an optional embodiment, the network construction module 310 includes: a network branch clustering unit, used to: determine the maximum flight distance based on the reference flight speed and maximum flight time of the target UAV; determine the reference flight distance according to the maximum flight distance and a preset correction coefficient.

[0086] In an optional embodiment, the path determination module 330 is specifically used to: for each target UAV, determine the target patrol function corresponding to the target UAV based on the target patrol network and the reference flight parameters of the target UAV; optimize the parameters in multiple target patrol functions based on preset constraints to obtain the target patrol paths corresponding to each target UAV.

[0087] The drone path planning device provided in the embodiment of the present invention can execute the drone path planning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0088] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 7 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 7 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be configured in the drone path planning device.

[0089] like Figure 7 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0090] The bus 18 may be one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0091] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0092] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0093] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0094] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 20. Figure 7 As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0095] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, such as implementing the drone path planning method provided in the embodiment of the present invention, which includes:

[0096] The location information of multiple associated objects and target UAVs in the target area is obtained, and a preliminary patrol network is constructed based on the location information; wherein the associated objects include at least: transmission towers and UAV bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and reference flight parameters of the target UAV, the target patrol paths corresponding to each target UAV are determined respectively.

[0097] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, a method for planning a path for a drone as provided in any embodiment of the present invention is implemented, including:

[0098] The location information of multiple associated objects and target UAVs in the target area is obtained, and a preliminary patrol network is constructed based on the location information; wherein the associated objects include at least: transmission towers and UAV bases; the branches in the preliminary patrol network are reconstructed to obtain a target patrol network; based on the target patrol network and reference flight parameters of the target UAV, the target patrol paths corresponding to each target UAV are determined respectively.

[0099] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0100] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0101] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0102] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0104] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for UAV path planning, characterized in that: include: Acquire location information of multiple associated objects and a target UAV in a target area, and construct a preliminary patrol network based on the location information; wherein the associated objects include at least: a transmission tower and a UAV base; Reconstructing the branches in the preliminary patrol network to obtain a target patrol network; Based on the target patrol network and the reference flight parameters of the target UAV, a target patrol path corresponding to each target UAV is determined respectively.

2. The method according to claim 1, characterized in that The reconstructing the branches in the preliminary patrol network to obtain the target patrol network includes: Identifying a network branch in the preliminary patrol network; wherein the network branch is a branch connecting adjacent network nodes; For each network branch, determining a patrol cost parameter corresponding to the network branch; wherein the patrol cost parameter is used to represent the power consumption required for the target UAV to pass through the network branch; The network branches are clustered based on the patrol cost parameters to obtain the target patrol network.

3. The method according to claim 2, characterized in that The clustering of the network branches based on the patrol cost parameter to obtain the target patrol network includes: Taking the maximum patrol cost parameter as a reference cost parameter, and determining the number of clusters based on the reference cost parameter and a preset correction parameter; Based on the number of clustering clusters, the network nodes in the network branch are clustered to obtain multiple target clusters, and the target patrol network is determined based on the multiple target clusters; wherein the number of the multiple target clusters is equal to the number of clustering clusters.

4. The method according to claim 1, characterized in that: The step of obtaining location information of a plurality of associated objects and a target UAV in a target area and constructing a preliminary patrol network based on the location information includes: constructing a plurality of network nodes based on the location information of the associated objects; Connecting the plurality of network nodes to obtain a directed weighted network, and using the obtained directed weighted network as an initial patrol network; Determine a network parameter set corresponding to the initial patrol network; wherein the network parameter set includes: at least one of a node parameter, an edge parameter, a drone parameter, and a patrol cost parameter; The preliminary patrol network is determined according to the initial patrol network and the network parameter set.

5. The method according to claim 4, characterized in that Determining the patrol cost parameter includes: Determining a plurality of directed branches from the directed weighted network; wherein the directed branches are branches connecting two network nodes and having directions; For each directional branch, determining a flight time parameter corresponding to the directional branch according to the length of the directional branch and a reference environment parameter; Determining a battery consumption parameter according to the length of the directed branch and the reference flight distance of the target UAV; The patrol cost parameter is determined according to the flight time parameter and the battery consumption parameter.

6. The method according to claim 5, characterized in that Determining a reference flight distance of the target UAV includes: Determining a maximum flight distance based on a reference flight speed and a maximum flight time of the target UAV; The reference flight distance is determined according to the maximum flight distance and a preset correction coefficient.

7. The method according to claim 1, characterized in that The step of determining the target patrol path corresponding to each target UAV based on the target patrol network and the reference flight parameters of the target UAV includes: For each target UAV, based on the target patrol network and the reference flight parameters of the target UAV, determine a target patrol function corresponding to the target UAV; Based on the preset constraints, the parameters in multiple target patrol functions are optimized to obtain the target patrol paths corresponding to each target UAV.

8. A drone path planning device, characterized in that: The device comprises: A network construction module is used to obtain the location information of multiple associated objects and target drones in the target area, and to construct a preliminary patrol network based on the location information; wherein the associated objects include at least: transmission towers and drone bases; A network reconstruction module, used to reconstruct the branches in the preliminary patrol network to obtain a target patrol network; The path determination module is used to determine the target patrol path corresponding to each target UAV based on the target patrol network and the reference flight parameters of the target UAV.

9. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the drone path planning method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the drone path planning method as described in any one of claims 1 to 7 is implemented.

Images