Substation joint patrol method and device, electronic equipment and storage medium

Abstract

The invention provides a combined patrol method and device for a transformer substation, electronic equipment and a storage medium, and the method comprises the steps: obtaining an initial patrol path of an unmanned plane and a patrol path of a ground robot through coverage path planning, and obtaining the patrol path of the ground robot based on an unmanned plane path point in the initial patrol path of the unmanned plane and a robot path point in the patrol path of the ground robot. After the first bipartite graph is constructed, robot path points matched with all the unmanned aerial vehicle path points are obtained through matching, and therefore the maximum battery replacement time is determined; and based on the maximum power conversion time, determining a power conversion path point in the initial patrol path of the unmanned aerial vehicle and a matched power conversion path point in the patrol path of the ground robot, and after the power conversion path point is added to the initial patrol path of the unmanned aerial vehicle, obtaining the patrol path of the unmanned aerial vehicle. The unmanned aerial vehicle and the ground robot can jointly complete an inspection task, and meanwhile, the ground robot provides a battery replacement service for the unmanned aerial vehicle, so that the defect that the endurance time of the unmanned aerial vehicle is short is overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a substation joint patrol method, device, electronic equipment and storage medium. Background Art

[0002] As an important infrastructure, the safety management of substations and their surrounding environment is of vital importance. Various factors such as weather, external intrusion and natural disasters may pose potential threats to the operation of substations. Traditional manual patrols have problems of low efficiency and blind spots, while automatic patrol solutions can complete monitoring tasks more efficiently and comprehensively, which is particularly necessary in the complex environment around substations.

[0003] In the automatic patrol mission, the joint patrol scheme of drones and ground robots has shown significant advantages. With its flexibility and wide field of view, drones can quickly cover large areas and monitor high-altitude equipment and the overall situation of the entire environment. Ground robots can conduct in-depth inspections on the ground, check blind spots such as the bottom of equipment and near fences, and obtain detailed data through sensors. The two complement each other. On the one hand, they can improve patrol efficiency, and on the other hand, they can make up for the limitations of a single device. In addition, the combination of drones and ground robots also allows for rapid response in emergencies. For example, the drone first discovers an abnormality and then guides the ground robot to the scene for further inspection, realizing efficient patrols with division of labor and cooperation.

[0004] However, drones have limited flight time and it is difficult to complete the entire patrol mission without interruption. At present, some work uses ground unmanned vehicles as battery replacement or charging points for drones to solve the problem of short drone flight time. However, in these works, ground robots are only used as battery replacement or charging points for drones and cannot complete ground patrol work at the same time. Therefore, it is necessary to provide a substation joint patrol solution to jointly plan paths for drones and ground robots, so that ground robots can simultaneously conduct ground patrols and provide battery replacement services for drones that perform patrol tasks simultaneously. Summary of the invention

[0005] The present invention provides a substation joint patrol method, device, electronic equipment and storage medium, which are used to solve the defect of short flight time of unmanned aerial vehicles in the prior art, so that a ground robot can simultaneously perform ground patrols and provide power replacement services for the unmanned aerial vehicles.

[0006] The present invention provides a substation joint patrol method, comprising:

[0007] Based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, coverage path planning is performed respectively to obtain the initial patrol path of the UAV and the patrol path of the ground robot;

[0008] Constructing a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot;

[0009] Matching the first bipartite graph to obtain robot path points that match each drone path point, and determining a maximum battery replacement time based on the distance between each drone path point and its matching robot path point;

[0010] Based on the maximum battery swap time, determining a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot;

[0011] After adding the battery swapping path points in the initial patrol path of the drone that match the battery swapping path points in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone, the patrol path of the drone is obtained;

[0012] A joint patrol is performed based on the patrol path of the UAV and the patrol path of the ground robot.

[0013] According to a substation joint patrol method provided by the present invention, based on the maximum power exchange time, determining the power exchange path point in the initial patrol path of the drone and the power exchange path point matched in the patrol path of the ground robot, including:

[0014] Based on the maximum battery-swap time, the initial patrol path of the UAV and the patrol path of the ground robot are clustered respectively to obtain a plurality of UAV path clusters and robot path clusters; wherein the sum of the flight time of all path points in any UAV path cluster is not greater than the difference between the preset maximum flight time and the maximum battery-swap time, and the sum of the travel time of all path points in any robot path cluster is not greater than the preset maximum flight time;

[0015] Determine the robot path clusters that match each drone path cluster;

[0016] Based on each UAV path cluster and its matching robot path cluster, the battery swap path points in the corresponding UAV path cluster and its matching robot path cluster are determined.

[0017] According to a substation joint patrol method provided by the present invention, the drone path cluster is constructed based on the following method:

[0018] The first cluster expansion step: determine the flight time from the current drone path point in the current drone path cluster to the next drone path point of the current drone path point in the initial patrol path of the drone; if the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is less than or equal to the difference between the preset maximum flight time and the maximum battery replacement time, then add the next drone path point to the current drone path cluster, update the current total flight time based on the flight time from the current drone path point to the next drone path point, and use the next drone path point as the current drone path point when the next drone path point is not the last drone path point, and jump to the first iterative step; if the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is greater than the difference between the preset maximum flight time and the maximum battery replacement time, then jump to the first cluster creation step;

[0019] The first iteration step: repeating the first cluster expansion step;

[0020] The first cluster creation step: create an empty drone path cluster as the current drone path cluster, add the next drone path point to the current drone path cluster, and when the next drone path point is not the last drone path point, use the next drone path point as the current drone path point and jump to the first cluster expansion step.

[0021] According to a substation joint patrol method provided by the present invention, the robot path cluster is constructed based on the following method:

[0022] The second cluster expansion step: determine the travel time from the current robot path point in the current robot path cluster to the next robot path point of the current robot path point in the patrol path of the ground robot; if the sum of the travel time from the current robot path point to the next robot path point and the current total travel time is less than or equal to the preset maximum flight time, then add the next robot path point to the current robot path cluster, update the current total travel time based on the travel time from the current robot path point to the next robot path point, and when the next robot path point is not the last robot path point, use the next robot path point as the current robot path point, and jump to the second iteration step; if the sum of the travel time from the current robot path point to the next robot path point and the current total travel time is greater than the preset maximum flight time, then jump to the second cluster creation step;

[0023] Second iterative step: repeating the second type cluster expansion step;

[0024] The second cluster creation step: create an empty robot path cluster as the current robot path cluster, add the next robot path point to the current robot path cluster, and when the next robot path point is not the last robot path point, use the next robot path point as the current robot path point and jump to the second cluster expansion step.

[0025] According to a substation joint patrol method provided by the present invention, based on each drone path cluster and its matching robot path cluster, a battery swapping path point in the corresponding drone path cluster and its matching robot path cluster are determined, including:

[0026] Based on any UAV path cluster and its matching robot path cluster, a second bipartite graph is constructed;

[0027] Matching the second bipartite graph to obtain robot path points that match each drone path point in any drone path cluster;

[0028] Determine the last drone path point of any drone path cluster and its matching robot path point as the battery replacement path point in any drone path cluster and its matching robot path cluster.

[0029] According to a substation joint patrol method provided by the present invention, determining a robot path cluster matching each drone path cluster includes:

[0030] For any UAV path cluster, determine the robot path cluster with the shortest distance between the first robot path point and the first UAV path point of any UAV path cluster as the robot path cluster that matches any UAV path cluster.

[0031] According to a substation joint patrol method provided by the present invention, the maximum power replacement time is determined based on the distance between each drone path point and its matching robot path point, including:

[0032] Determine the one-way battery replacement time based on the maximum value of the distance between each drone path point and its matching robot path point;

[0033] Determine twice the value of the one-way battery replacement time as the maximum battery replacement time.

[0034] The present invention also provides a substation joint patrol device, comprising:

[0035] A path initial planning unit, used to perform coverage path planning based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, respectively, to obtain the initial patrol path of the UAV and the patrol path of the ground robot;

[0036] A first bipartite graph construction unit, configured to construct a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot;

[0037] A battery replacement time determination unit, configured to match the first bipartite graph to obtain robot path points matched by each drone path point, and determine a maximum battery replacement time based on a distance between each drone path point and its matched robot path point;

[0038] A battery swap path point determination unit, configured to determine a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot based on the maximum battery swap time;

[0039] A path updating unit, configured to obtain a patrol path of the drone after adding a battery swapping path point in the initial patrol path of the drone that matches a battery swapping path point in the patrol path of the ground robot to a corresponding battery swapping path point in the initial patrol path of the drone;

[0040] A joint patrol unit is used to perform a joint patrol based on the patrol path of the UAV and the patrol path of the ground robot.

[0041] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned substation joint patrol methods is implemented.

[0042] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the substation joint patrol method as described in any one of the above is implemented.

[0043] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned substation joint patrol methods.

[0044] The substation joint patrol method, device, electronic device and storage medium provided by the present invention respectively perform coverage path planning based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot to obtain the initial patrol path of the drone and the patrol path of the ground robot; construct a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; match the first bipartite graph to obtain the robot path points matched by each drone path point, and determine the maximum battery replacement time based on the distance between each drone path point and the robot path point matched by it; determine the battery replacement path points in the initial patrol path of the drone and the battery replacement path points matched by it in the patrol path of the ground robot based on the maximum battery replacement time; add the battery replacement path points in the initial patrol path of the drone that match the battery replacement path points in the patrol path of the ground robot to the corresponding battery replacement path points in the initial patrol path of the drone to obtain the patrol path of the drone; perform joint patrol based on the patrol path of the drone and the patrol path of the ground robot, so that the drone and the ground robot can jointly complete the patrol task while the ground robot provides battery replacement service for the drone, thereby solving the defect of short drone endurance time. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a flow chart of the substation joint patrol method provided by the present invention;

[0047] Figure 2 It is one of the flow charts of the method for determining the battery replacement path point provided by the present invention;

[0048] Figure 3 This is the second flow chart of the method for determining the battery replacement path point provided by the present invention;

[0049] Figure 4 This is a schematic diagram of the structure of the substation joint patrol device provided by the present invention.

[0050] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0052] Figure 1 FIG. 1 is a flow chart of the substation joint patrol method provided by the present invention, such as Figure 1 As shown, the method includes:

[0053] Step 110, performing coverage path planning based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, respectively, to obtain an initial patrol path of the UAV and a patrol path of the ground robot;

[0054] Step 120, constructing a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot;

[0055] Step 130, matching the first bipartite graph to obtain robot path points matched by each drone path point, and determining a maximum battery replacement time based on the distance between each drone path point and its matched robot path point;

[0056] Step 140, based on the maximum battery swap time, determining a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot;

[0057] Step 150, after adding the battery swapping path points in the initial patrol path of the drone that match the battery swapping path points in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone, the patrol path of the drone is obtained;

[0058] Step 160: Perform a joint patrol based on the patrol path of the UAV and the patrol path of the ground robot.

[0059] Specifically, according to the patrol requirements of the substation and the surrounding environment, the patrol area for the UAV and the patrol area for the ground robot are pre-demarcated. According to the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, the initial patrol path of the UAV and the patrol path of the ground robot can be obtained by using the Coverage Path Planning (CCP), such as the Boustrophedon Cellular Decomposition algorithm and its derivative algorithms. It should be noted that, considering that the ground robot needs to be used as a power exchange point for the UAV in addition to completing its own patrol mission, it is necessary to update the patrol paths of the two and add the meeting point of the two. Considering that the ground robot moves slowly and has fewer moving directions, while the UAV can achieve linear motion between two points, when adding the meeting point, the patrol path of the ground robot will be kept unchanged, and the initial patrol path of the UAV will be modified so that the UAV will actively find the ground robot to meet when the battery is insufficient.

[0060] The basic goal of the rendezvous point determination task of the drone and the ground robot is that the drone reaches the rendezvous point for battery replacement before the battery is exhausted, and the optimization goal is to shorten the overall flight path of the drone and the waiting time during the battery replacement process as much as possible. To this end, the first bipartite graph can be constructed based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot. Among them, each left vertex in the first bipartite graph is a drone path point, and each right vertex is a robot path point. Subsequently, the edge weights of each drone path point to each robot path point are determined according to the distance between each drone path point and each robot path point, and the time when the drone arrives at any drone path point and the time when the ground robot arrives at any robot path point. In some embodiments, the one-way flight time can be determined based on the distance from any drone path point to any robot path point and the drone flight time, and the waiting time for battery replacement of the drone is determined based on the time when the drone arrives at the drone path point and the time when the ground robot arrives at the robot path point and the above-mentioned one-way flight time, so as to determine the sum of the one-way flight time and the waiting time for battery replacement as the edge weight from the drone path point to the robot path point.

[0061] Based on the edge weights from each drone path point to each robot path point, a graph matching algorithm (such as the Hungarian algorithm) is used to match the first bipartite graph to obtain the robot path points that match each drone path point, and based on the distance between each drone path point and the robot path point that matches it, the maximum battery swap time is determined. The maximum battery swap time represents the longest round-trip time from the current drone path point to the robot path point that serves as its battery swap point in the patrol path of the ground robot. In some embodiments, the one-way battery swap time can be determined based on the maximum value of the distance between each drone path point and the robot path point that matches it and the flight speed of the drone, and twice the value of the one-way battery swap time is determined as the maximum battery swap time.

[0062] Based on the maximum battery replacement time, the battery replacement path point in the initial patrol path of the UAV and its matching battery replacement path point in the patrol path of the ground robot can be determined, so that the power of the UAV can meet the requirements of the UAV to fully charge from the last battery replacement path point G in the patrol path of the ground robot. i-1 Fly to the battery swap path point A that matches it in the initial patrol path i-1 , from the battery swapping path point A i-1 Fly to the next battery replacement path point A i , from the battery swap path point A i Fly to the matching battery swap path point G in the patrol path of the ground robot i Replace the battery and fly back to the battery replacement path point A i , until the patrol mission is completed. Among them, the drone starts from the last battery replacement path point G i-1 Fly to the battery swap path point A that matches it in the initial patrol path i-1 The time spent and the time from the battery replacement path point A i Fly to the matching battery swap path point G in the patrol path of the ground robot i The total time spent shall not exceed the above-mentioned maximum battery replacement time.

[0063] In some embodiments, Figure 2 As shown, the battery swapping path points in the initial patrol path of the UAV and the matching battery swapping path points in the patrol path of the ground robot can be determined based on the following method:

[0064] Step 210: Based on the maximum battery swap time, the initial patrol path of the UAV and the patrol path of the ground robot are clustered to obtain a plurality of UAV path clusters and robot path clusters; wherein the sum of the flight time of all path points in any UAV path cluster is not greater than the difference between the preset maximum flight time and the maximum battery swap time, and the sum of the travel time of all path points in any robot path cluster is not greater than the preset maximum flight time;

[0065] Step 220, determining the robot path clusters that match each drone path cluster;

[0066] Step 230, based on each drone path cluster and its matching robot path cluster, determine the battery replacement path points in the corresponding drone path cluster and its matching robot path cluster.

[0067] Here, based on the maximum battery replacement time, the initial patrol path of the drone and the patrol path of the ground robot can be clustered respectively to obtain multiple drone path clusters and robot path clusters. Among them, each drone path cluster contains multiple continuous drone path points in the initial patrol path, and each robot path cluster contains multiple continuous robot path points in the patrol path. Each drone path cluster obtained after path clustering satisfies the condition that the sum of the flight time of all path points in any drone path cluster is not greater than the difference between the preset maximum flight time and the maximum battery replacement time, and each robot path cluster satisfies the condition that the sum of the travel time of all path points in any robot path cluster is not greater than the preset maximum flight time. Here, the maximum flight time is the flight time that the drone battery can support when it is fully charged when flying at a preset speed.

[0068] In some embodiments, clustering can be performed based on the following method to obtain drone path clusters:

[0069] The first cluster expansion step: determine the current drone path point A in the current drone path cluster j (Initially, it is the first UAV path point of the UAV's initial patrol path) to the next UAV path point A of the current UAV path point in the UAV's initial patrol path j+1 The flight time Ti; if the current drone path point A j To the next drone path point A j+1 If the sum of the flight time Ti and the current total flight time Tf (initial value is 0) is less than or equal to the difference between the preset maximum flight time T and the maximum battery replacement time C, the next drone path point A j+1 Add to the current drone path cluster, based on the current drone path point A j To the next drone path point A j+1 The flight time Ti updates the current total flight time Tf (Tf = Tf + Ti), and at the next drone path point A j+1 If it is not the last drone path point, the next drone path point A j+1 As the current drone path point, jump to the first iteration step to iteratively execute the first type of cluster expansion step; if the current drone path point A j To the next drone path point Aj+1 If the sum of the flight time Ti and the current total flight time Tf is greater than the difference between the preset maximum flight time T and the maximum battery replacement time C, jump to the first cluster creation step;

[0070] First iteration step: repeat the first cluster expansion step;

[0071] The first cluster creation step: create an empty drone path cluster as the current drone path cluster, and assign the next drone path point A j+1 Add to the current drone path cluster and at the next drone path point A j+1 If it is not the last drone path point, the next drone path point A j+1 As the current UAV path point, jump to the first cluster expansion step.

[0072] Similarly, the robot path clusters can be clustered based on the following method:

[0073] The second cluster expansion step: determine the current robot path point G in the current robot path cluster n (Initially, it is the first robot path point in the patrol path) to the current robot path point G in the patrol path of the ground robot n The next robot path point G n+1 Travel time tn; if the current robot path point G n To the next robot path point G n+1 If the sum of the travel time tn and the current travel time Tr (initial value is 0) is less than or equal to the preset maximum flight time T, the next robot path point G n+1 Add to the current robot path cluster, based on the current robot path point G n To the next robot path point G n+1 The current total driving time Tr (Tr = Tr + tn) is updated based on the driving time tn, and at the next robot path point G n+1 If it is not the last robot path point, the next robot path point G n+1 As the current robot path point, jump to the second iteration step and continue to iterate and execute this step; if the current robot path point G n To the next robot path point G n+1 If the sum of the driving time tn and the current total driving time Tr is greater than the preset maximum flight time T, jump to the second type cluster creation step;

[0074] Second iteration step: repeat the second cluster expansion step;

[0075] The second cluster creation step: create an empty robot path cluster as the current robot path cluster, and set the next robot path point Gn+1 Add to the current robot path cluster and at the next robot path point G n+1 If it is not the last robot path point, the next robot path point G n+1 As the current robot path point, jump to the second type of cluster expansion step.

[0076] After obtaining each drone path cluster and robot path cluster, determine the robot path cluster that matches each drone path cluster. In some embodiments, for any drone path cluster, the robot path cluster with the shortest distance between the first robot path point and the first drone path point of the drone path cluster can be determined as the robot path cluster that matches the drone path cluster. Based on each drone path cluster and its matching robot path cluster, the battery exchange path points in each drone path cluster and its matching robot path cluster can be determined one by one. Among them, there is one battery exchange path point in a drone path cluster. It should be noted that, through the maximum battery exchange time determination method and path clustering method given in the above embodiment, the battery exchange path points in each drone path cluster and its matching robot path cluster can be determined to meet the requirements of the drone reaching the meeting point for battery exchange before the battery is exhausted, the battery exchange waiting time is short and the overall flight path is short, thereby reducing the impact of drone battery exchange on the patrol mission of drones and ground robots.

[0077] In some embodiments, in order to further shorten the overall flight path length of the drone including the battery replacement path and the battery replacement waiting time, as shown in FIG. Figure 3 As shown, the following method can be used to determine the battery swapping path points in each drone path cluster and the battery swapping path points in the matching robot path cluster:

[0078] Step 310, constructing a second bipartite graph based on any drone path cluster and its matching robot path cluster;

[0079] Step 320, matching the second bipartite graph to obtain robot path points that match each drone path point in any drone path cluster;

[0080] Step 330, determine the last drone path point of any drone path cluster and its matching robot path point as the battery replacement path point in any drone path cluster and its matching robot path cluster.

[0081] Here, a second bipartite graph can be constructed based on any drone path cluster and its matching robot path cluster, so that each left vertex in the second bipartite graph is a drone path point in the drone path cluster, and each right vertex is a robot path point in the robot path cluster matched by the drone path cluster. Based on the distance between each drone path point and each robot path point, as well as the time when the drone arrives at any drone path point and the time when the ground robot arrives at any robot path point, the edge weights from each drone path point to each robot path point are determined. The edge weights from each drone path point to each robot path point can be directly obtained from the first bipartite graph, which will not be repeated here. Subsequently, the second bipartite graph is matched using a graph matching algorithm to obtain the robot path points matched by each drone path point in the drone path cluster. The last drone path point of the drone path cluster and its matching robot path point are determined as the battery exchange path point Ca in the drone path cluster and the battery exchange path point Cg in its matching robot path cluster, respectively.

[0082] In summary, the method provided by the embodiment of the present invention performs coverage path planning based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot respectively, so as to obtain the initial patrol path of the drone and the patrol path of the ground robot; constructs a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; matches the first bipartite graph to obtain the robot path points matched by each drone path point, and determines the maximum battery replacement time based on the distance between each drone path point and the robot path point matched by it; determines the battery replacement path points in the initial patrol path of the drone and the battery replacement path points matched by it in the patrol path of the ground robot based on the maximum battery replacement time; adds the battery replacement path points in the initial patrol path of the drone that match the battery replacement path points in the patrol path of the ground robot to the corresponding battery replacement path points in the initial patrol path of the drone, so as to obtain the patrol path of the drone; performs joint patrol based on the patrol path of the drone and the patrol path of the ground robot, so as to enable the drone and the ground robot to jointly complete the patrol task while the ground robot provides the drone with battery replacement service, so as to solve the defect of short flight time of the drone.

[0083] The substation joint patrol device provided by the present invention is described below. The substation joint patrol device described below and the substation joint patrol method described above can be referenced to each other.

[0084] Based on any of the above embodiments, Figure 4 Schematic diagram of the structure of the substation joint patrol device provided by the present invention. Figure 4 As shown, the device comprises:

[0085] The initial path planning unit 410 is used to perform coverage path planning based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, respectively, to obtain the initial patrol path of the UAV and the patrol path of the ground robot;

[0086] A first bipartite graph construction unit 420, configured to construct a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot;

[0087] A battery replacement time determination unit 430 is used to match the first bipartite graph to obtain robot path points matched by each drone path point, and determine the maximum battery replacement time based on the distance between each drone path point and the robot path point matched thereto;

[0088] A battery swap path point determination unit 440 is used to determine a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot based on the maximum battery swap time;

[0089] A path updating unit 450 is used to obtain a patrol path of the drone after adding the battery swapping path points in the initial patrol path of the drone that match the battery swapping path points in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone;

[0090] The joint patrol unit 460 is used to perform a joint patrol based on the patrol path of the UAV and the patrol path of the ground robot.

[0091] The device provided by the embodiment of the present invention performs coverage path planning based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot respectively, so as to obtain the initial patrol path of the drone and the patrol path of the ground robot; constructs a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; matches the first bipartite graph to obtain the robot path points matched by each drone path point, and determines the maximum battery replacement time based on the distance between each drone path point and the robot path point matched by it; determines the battery replacement path points in the initial patrol path of the drone and the battery replacement path points matched by it in the patrol path of the ground robot based on the maximum battery replacement time; obtains the patrol path of the drone after adding the battery replacement path points matched by the battery replacement path points in the initial patrol path of the drone in the patrol path of the ground robot to the corresponding battery replacement path points in the initial patrol path of the drone; performs joint patrol based on the patrol path of the drone and the patrol path of the ground robot, so as to enable the drone and the ground robot to jointly complete the patrol task while the ground robot provides the drone with a battery replacement service, thereby solving the defect of the drone's short battery life.

[0092] Based on any of the above embodiments, based on the maximum battery swap time, determining a battery swap path point in the initial patrol path of the drone and a battery swap path point matched by the drone in the patrol path of the ground robot includes:

[0093] Based on the maximum battery-swap time, the initial patrol path of the UAV and the patrol path of the ground robot are clustered respectively to obtain a plurality of UAV path clusters and robot path clusters; wherein the sum of the flight time of all path points in any UAV path cluster is not greater than the difference between the preset maximum flight time and the maximum battery-swap time, and the sum of the travel time of all path points in any robot path cluster is not greater than the preset maximum flight time;

[0094] Determine the robot path clusters that match each drone path cluster;

[0095] Based on each UAV path cluster and its matching robot path cluster, the battery swap path points in the corresponding UAV path cluster and its matching robot path cluster are determined.

[0096] Based on any of the above embodiments, the drone path cluster is constructed based on the following method:

[0097] The first cluster expansion step: determine the flight time from the current drone path point in the current drone path cluster to the next drone path point of the current drone path point in the initial patrol path of the drone; if the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is less than or equal to the difference between the preset maximum flight time and the maximum battery replacement time, then add the next drone path point to the current drone path cluster, update the current total flight time based on the flight time from the current drone path point to the next drone path point, and use the next drone path point as the current drone path point when the next drone path point is not the last drone path point, and jump to the first iterative step; if the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is greater than the difference between the preset maximum flight time and the maximum battery replacement time, then jump to the first cluster creation step;

[0098] The first iteration step: repeating the first cluster expansion step;

[0099] The first cluster creation step: create an empty drone path cluster as the current drone path cluster, add the next drone path point to the current drone path cluster, and when the next drone path point is not the last drone path point, use the next drone path point as the current drone path point and jump to the first cluster expansion step.

[0100] Based on any of the above embodiments, the robot path cluster is constructed in the following manner:

[0101] The second cluster expansion step: determine the travel time from the current robot path point in the current robot path cluster to the next robot path point of the current robot path point in the patrol path of the ground robot; if the sum of the travel time from the current robot path point to the next robot path point and the current total travel time is less than or equal to the preset maximum flight time, then add the next robot path point to the current robot path cluster, update the current total travel time based on the travel time from the current robot path point to the next robot path point, and when the next robot path point is not the last robot path point, use the next robot path point as the current robot path point, and jump to the second iteration step; if the sum of the travel time from the current robot path point to the next robot path point and the current total travel time is greater than the preset maximum flight time, then jump to the second cluster creation step;

[0102] Second iterative step: repeating the second type cluster expansion step;

[0103] The second cluster creation step: create an empty robot path cluster as the current robot path cluster, add the next robot path point to the current robot path cluster, and when the next robot path point is not the last robot path point, use the next robot path point as the current robot path point and jump to the second cluster expansion step.

[0104] Based on any of the above embodiments, based on each drone path cluster and its matching robot path cluster, determining a battery swapping path point in the corresponding drone path cluster and its matching robot path cluster includes:

[0105] Based on any UAV path cluster and its matching robot path cluster, a second bipartite graph is constructed;

[0106] Matching the second bipartite graph to obtain robot path points that match each drone path point in any drone path cluster;

[0107] Determine the last drone path point of any drone path cluster and its matching robot path point as the battery replacement path point in any drone path cluster and its matching robot path cluster.

[0108] Based on any of the above embodiments, determining the robot path clusters that match each drone path cluster includes:

[0109] For any UAV path cluster, determine the robot path cluster with the shortest distance between the first robot path point and the first UAV path point of any UAV path cluster as the robot path cluster that matches any UAV path cluster.

[0110] Based on any of the above embodiments, determining the maximum battery replacement time based on the distance between each drone path point and its matching robot path point includes:

[0111] Determine the one-way battery replacement time based on the maximum value of the distance between each drone path point and its matching robot path point;

[0112] Determine twice the value of the one-way battery replacement time as the maximum battery replacement time.

[0113] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5As shown, the electronic device may include: a processor (processor) 510, a memory (memory) 520, a communication interface (Communications Interface) 530 and a communication bus 540, wherein the processor 510, the memory 520, and the communication interface 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 520 to execute a joint patrol method for a substation, which includes: performing coverage path planning based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot to obtain the initial patrol path of the drone and the patrol path of the ground robot; constructing a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; matching the first bipartite graph to obtain the robot path points matched by each drone path point, and determining the maximum battery swapping time based on the distance between each drone path point and the robot path point matched by it; determining the battery swapping path points in the initial patrol path of the drone and the battery swapping path points matched by it in the patrol path of the ground robot based on the maximum battery swapping time; obtaining the patrol path of the drone after adding the battery swapping path points in the initial patrol path of the drone and the battery swapping path points matched by the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone; and performing a joint patrol based on the patrol path of the drone and the patrol path of the ground robot.

[0114] In addition, the logic instructions in the above-mentioned memory 520 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0115] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the substation joint patrol method provided by the above methods, and the method includes: based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot, respectively perform coverage path planning to obtain the initial patrol path of the drone and the patrol path of the ground robot; based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot, construct a first bipartite graph ; Match the first bipartite graph to obtain the robot path points that match each UAV path point, and determine the maximum battery swapping time based on the distance between each UAV path point and the robot path point that matches it; based on the maximum battery swapping time, determine the battery swapping path points in the initial patrol path of the UAV and the battery swapping path points that match them in the patrol path of the ground robot; add the battery swapping path points in the initial patrol path of the UAV and the battery swapping path points that match them in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the UAV to obtain the patrol path of the UAV; perform joint patrol based on the patrol path of the UAV and the patrol path of the ground robot.

[0116] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when executed by a processor to execute the above-mentioned substation joint patrol methods, the method comprising: performing coverage path planning based on the regional map of the patrol area of ​​the drone and the regional map of the patrol area of ​​the ground robot, respectively, to obtain the initial patrol path of the drone and the patrol path of the ground robot; constructing a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; matching the first bipartite graph to obtain the robot path points matched by each drone path point, and determining the maximum battery swapping time based on the distance between each drone path point and the robot path point matched by it; determining the battery swapping path points in the initial patrol path of the drone and the battery swapping path points matched by it in the patrol path of the ground robot based on the maximum battery swapping time; obtaining the patrol path of the drone after adding the battery swapping path points in the initial patrol path of the drone and the battery swapping path points matched by it in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone; and performing joint patrol based on the patrol path of the drone and the patrol path of the ground robot.

[0117] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A substation joint patrol method, characterized in that: include: Based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, coverage path planning is performed respectively to obtain the initial patrol path of the UAV and the patrol path of the ground robot; Constructing a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; Matching the first bipartite graph to obtain robot path points that match each drone path point, and determining a maximum battery replacement time based on the distance between each drone path point and its matching robot path point; Based on the maximum battery swap time, determining a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot; After adding the battery swapping path points in the initial patrol path of the drone that match the battery swapping path points in the patrol path of the ground robot to the corresponding battery swapping path points in the initial patrol path of the drone, the patrol path of the drone is obtained; A joint patrol is performed based on the patrol path of the UAV and the patrol path of the ground robot.

2. The substation joint patrol method according to claim 1, characterized in that: Based on the maximum battery swap time, determining a battery swap path point in the initial patrol path of the UAV and a battery swap path point matched by the UAV in the patrol path of the ground robot includes: Based on the maximum battery-swap time, the initial patrol path of the UAV and the patrol path of the ground robot are clustered respectively to obtain a plurality of UAV path clusters and robot path clusters; wherein the sum of the flight time of all path points in any UAV path cluster is not greater than the difference between the preset maximum flight time and the maximum battery-swap time, and the sum of the travel time of all path points in any robot path cluster is not greater than the preset maximum flight time; Determine the robot path clusters that match each drone path cluster; Based on each UAV path cluster and its matching robot path cluster, the battery swap path points in the corresponding UAV path cluster and its matching robot path cluster are determined.

3. The substation joint patrol method according to claim 2, characterized in that: The drone path cluster is constructed based on the following method: The first cluster expansion step: determining the flight time from the current drone path point in the current drone path cluster to the next drone path point of the current drone path point in the initial patrol path of the drone; If the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is less than or equal to the difference between the preset maximum flight time and the maximum battery replacement time, the next drone path point is added to the current drone path cluster, and the current total flight time is updated based on the flight time from the current drone path point to the next drone path point. When the next drone path point is not the last drone path point, the next drone path point is used as the current drone path point, and the process jumps to the first iteration step; if the sum of the flight time from the current drone path point to the next drone path point and the current total flight time is greater than the difference between the preset maximum flight time and the maximum battery replacement time, the process jumps to the first cluster creation step; The first iteration step: repeating the first cluster expansion step; The first cluster creation step: create an empty drone path cluster as the current drone path cluster, add the next drone path point to the current drone path cluster, and when the next drone path point is not the last drone path point, use the next drone path point as the current drone path point and jump to the first cluster expansion step.

4. The substation joint patrol method according to claim 2, characterized in that: The robot path cluster is constructed based on the following method: The second cluster expansion step: determining the travel time from the current robot path point in the current robot path cluster to the next robot path point of the current robot path point in the patrol path of the ground robot; If the sum of the driving time from the current robot path point to the next robot path point and the current total driving time is less than or equal to the preset maximum flight time, the next robot path point is added to the current robot path cluster, the current total driving time is updated based on the driving time from the current robot path point to the next robot path point, and when the next robot path point is not the last robot path point, the next robot path point is used as the current robot path point, and the process jumps to the second iteration step; if the sum of the driving time from the current robot path point to the next robot path point and the current total driving time is greater than the preset maximum flight time, the process jumps to the second cluster creation step; Second iterative step: repeating the second type cluster expansion step; The second cluster creation step: create an empty robot path cluster as the current robot path cluster, add the next robot path point to the current robot path cluster, and when the next robot path point is not the last robot path point, use the next robot path point as the current robot path point and jump to the second cluster expansion step.

5. The substation joint patrol method according to claim 2, characterized in that: Based on each UAV path cluster and its matching robot path cluster, determine the battery swap path point in the corresponding UAV path cluster and its matching robot path cluster, including: Based on any UAV path cluster and its matching robot path cluster, a second bipartite graph is constructed; Matching the second bipartite graph to obtain robot path points that match each drone path point in any drone path cluster; Determine the last drone path point of any drone path cluster and its matching robot path point as the battery replacement path point in any drone path cluster and its matching robot path cluster.

6. The substation joint patrol method according to claim 2, characterized in that: Determine the robot path clusters that match each drone path cluster, including: For any UAV path cluster, determine the robot path cluster with the shortest distance between the first robot path point and the first UAV path point of any UAV path cluster as the robot path cluster that matches any UAV path cluster.

7. The substation joint patrol method according to any one of claims 1 to 6, characterized in that: Based on the distance between each drone path point and its matching robot path point, the maximum battery replacement time is determined, including: Determine the one-way battery replacement time based on the maximum value of the distance between each drone path point and its matching robot path point; Determine twice the value of the one-way battery replacement time as the maximum battery replacement time.

8. A substation joint patrol device, characterized in that: include: A path initial planning unit, used to perform coverage path planning based on the regional map of the patrol area of ​​the UAV and the regional map of the patrol area of ​​the ground robot, respectively, to obtain the initial patrol path of the UAV and the patrol path of the ground robot; A first bipartite graph construction unit, configured to construct a first bipartite graph based on the drone path points in the initial patrol path of the drone and the robot path points in the patrol path of the ground robot; A battery replacement time determination unit, configured to match the first bipartite graph to obtain robot path points matched by each drone path point, and determine a maximum battery replacement time based on a distance between each drone path point and its matched robot path point; A battery swap path point determination unit, configured to determine a battery swap path point in the initial patrol path of the drone and a matching battery swap path point in the patrol path of the ground robot based on the maximum battery swap time; A path updating unit, configured to obtain a patrol path of the drone after adding a battery swapping path point in the initial patrol path of the drone that matches a battery swapping path point in the patrol path of the ground robot to a corresponding battery swapping path point in the initial patrol path of the drone; A joint patrol unit is used to perform a joint patrol based on the patrol path of the UAV and the patrol path of the ground robot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the substation joint patrol method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the substation joint patrol method according to any one of claims 1 to 7 is implemented.

Images