A route design method and system based on unmanned aerial vehicle obstacle avoidance and a terminal

Abstract

The application discloses a kind of route design method, system and terminal based on unmanned aerial vehicle obstacle avoidance, the method includes: obtaining inspection task information, obtain target unmanned aerial vehicle networking;And obtain the flight state information that target unmanned aerial vehicle in target unmanned aerial vehicle networking gathers, generate risk collision information by the risk prediction model that has been trained;According to target networking information, flight state information, risk collision information and the target networking information, obtain the route of each target unmanned aerial vehicle.The application obtains the information of each unmanned aerial vehicle and the distance information between unmanned aerial vehicles by analyzing the flight state information of unmanned aerial vehicle when patrolling surrounding environment building, and controls multiple unmanned aerial vehicles by the structure information of unmanned aerial vehicle networking, maintains the safety distance between unmanned aerial vehicles, reduces the dangerousness of multiple unmanned aerial vehicles when executing inspection task, improves the efficiency of management to multiple unmanned aerial vehicles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle control, and particularly relates to a flight path design method and system based on unmanned aerial vehicle obstacle avoidance, a terminal and a computer readable storage medium. BACKGROUND

[0002] The main purpose of unmanned aerial vehicle inspection operation is to improve inspection efficiency and accuracy, while reducing cost and risk. Unmanned aerial vehicle inspection can efficiently obtain information of an inspection object and timely discover and record abnormal conditions by optimizing a flight path and setting an inspection task.

[0003] However, in the existing field of unmanned aerial vehicle inspection, the perception and obstacle avoidance technology of the unmanned aerial vehicle is limited, and sometimes misjudgment or failure to avoid obstacles in time occurs, which threatens the safety of the unmanned aerial vehicle and power facilities, and the unmanned aerial vehicle may face collision and other safety risks during flight, and measures need to be taken to ensure its safety.

[0004] Therefore, the prior art still needs to be improved and developed. SUMMARY

[0005] The main purpose of the present application is to provide a flight path design method and system based on unmanned aerial vehicle obstacle avoidance, a terminal and a computer readable storage medium, which aims to solve the problem that multiple unmanned aerial vehicles jointly perform an inspection task in the prior art, which is easy to cause confusion, and the unmanned aerial vehicle and the surrounding environment buildings and unmanned aerial vehicles may collide, thereby causing a high risk of the task.

[0006] To achieve the above purpose, the present application provides a flight path design method based on unmanned aerial vehicle obstacle avoidance, which comprises the following steps:

[0007] Obtain multiple unmanned aerial vehicle information, construct a unmanned aerial vehicle network according to all the unmanned aerial vehicle information, obtain inspection task information, and construct a target unmanned aerial vehicle network in the unmanned aerial vehicle network according to the inspection task information;

[0008] Obtain first flight state information collected by multiple outer target unmanned aerial vehicles in the target unmanned aerial vehicle network and second flight state information collected by multiple inner target unmanned aerial vehicles;

[0009] Input multiple first flight state information and multiple second flight state information into a trained risk prediction model, and output risk collision information;

[0010] Obtain target networking information of the target unmanned aerial vehicle network, input multiple first flight state information, multiple second flight state information, risk collision information and target networking information into a trained flight path design model, and output a flight path of each outer target unmanned aerial vehicle and each inner target unmanned aerial vehicle.

[0011] Optionally, the route design method based on UAV obstacle avoidance, wherein the obtaining multiple UAV information, constructing a UAV network according to all the UAV information, obtaining inspection task information, and constructing a target UAV network according to the inspection task information, specifically comprises:

[0012] Obtaining multiple UAV information, establishing connections between all the UAVs according to all the UAV information, and obtaining a UAV network;

[0013] Obtaining and analyzing inspection task information to obtain multiple event information, changing the states of multiple UAVs in the UAV network according to the multiple event information, obtaining multiple target UAVs, and constructing a target UAV network according to all the target UAVs;

[0014] Among them, the UAVs in the UAV network are in a non-selected state, and the target UAVs in the target UAV network are in a selected state.

[0015] Optionally, the route design method based on UAV obstacle avoidance, wherein the multiple target UAVs include multiple peripheral target UAVs and multiple internal target UAVs;

[0016] The obtaining of first flight state information collected by the multiple peripheral target UAVs and second flight state information collected by the multiple internal target UAVs in the target UAV network specifically comprises:

[0017] Obtaining a query instruction of a user, and detecting the states of the multiple peripheral target UAVs and the multiple internal target UAVs according to the query instruction;

[0018] When it is determined that the states of the multiple peripheral target UAVs and the multiple internal target UAVs are all in a selected state, obtaining first flight state information of each of the peripheral target UAVs and second flight state information collected by each of the internal target UAVs.

[0019] Optionally, the route design method based on UAV obstacle avoidance, wherein when it is determined that the states of the multiple peripheral target UAVs and the multiple internal target UAVs are all in a selected state, displaying the first flight state information of each of the peripheral target UAVs and the second flight state information collected by each of the internal target UAVs, specifically comprises:

[0020] When it is determined that the states of the multiple peripheral target UAVs are all in a selected state, obtaining start point position information, end point position information, environment information, UAV distance information, path point information, flight direction information, and route state information collected by each of the peripheral target UAVs;

[0021] When it is determined that the states of the plurality of internal target drones are all selected states, obtain start point position information, end point position information, drone distance information, waypoint information, flight direction information and flight path state information collected by each of the peripheral target drones;

[0022] The environment information represents distance information of the peripheral target drone from surrounding buildings, and the drone distance information represents distance information between each target drone and a neighboring target drone.

[0023] Optionally, the route design method based on drone obstacle avoidance, wherein the inputting of the plurality of first flight state information and the plurality of second flight state information into the trained risk prediction model to output risk collision information specifically comprises:

[0024] An initial risk prediction model is constructed, historical inspection task information of historical inspection tasks is obtained, and the historical inspection task information is input into the initial risk prediction model for training to obtain the risk prediction model;

[0025] Each of the environment information and each of the drone distance information is input into the risk prediction model to output risk collision information.

[0026] Optionally, the route design method based on drone obstacle avoidance, wherein the target networking information comprises information transmission direction and mesh structure information.

[0027] The target networking information of the target drone networking is obtained, the plurality of first flight state information, the plurality of second flight state information, the risk collision information and the target networking information are input into a trained route design model to output a flight path of each peripheral target drone and each internal target drone, and the method specifically comprises:

[0028] An initial route design model is constructed, historical flight paths are obtained, and the historical flight paths are input into the initial route design model for training to obtain the route design model;

[0029] The information transmission direction and the mesh structure information of each target drone in the target drone networking are obtained.

[0030] Each of the start point position information, each of the end point position information, each of the waypoint information, each of the flight direction information, each of the flight path state information, the risk collision information, each of the information transmission direction and the mesh structure information are input into the route design model to output a flight path of each peripheral target drone and each internal target drone.

[0031] Optionally, the route design method based on UAV obstacle avoidance, wherein the route design model is input with each of the start point information, each of the end point information, each of the way point information, each of the flight direction information, each of the route state information, the risk collision information, each of the information transmission direction and the mesh structure information, and output with the route of each of the outer target UAV and each of the inner target UAV, and then further comprising:

[0032] According to each of the route, a plurality of control instructions are generated;

[0033] According to all of the control instructions, each of the outer target UAV and each of the inner target UAV adjusts the flight state;

[0034] According to the mesh structure information and the information transmission direction, the adjusted flight state of the plurality of target UAVs is sent to a plurality of adjacent target UAVs to control the plurality of adjacent target UAVs to update the UAV distance information according to all of the flight state.

[0035] In addition, to achieve the above-mentioned purpose, the application further provides a route design system based on UAV obstacle avoidance, wherein the route design system based on UAV obstacle avoidance comprises:

[0036] A UAV connection module is configured to acquire a plurality of UAV information, construct a UAV network according to all of the UAV information, acquire a patrol task information, and construct a target UAV network in the UAV network according to the patrol task information;

[0037] An information acquisition module is configured to acquire first flight state information collected by a plurality of outer target UAVs in the target UAV network and second flight state information collected by a plurality of inner target UAVs;

[0038] A risk prediction module is configured to input the plurality of first flight state information and the plurality of second flight state information into a trained risk prediction model, and output risk collision information;

[0039] A route design module is configured to acquire target network information of the target UAV network, input the plurality of first flight state information, the plurality of second flight state information, the risk collision information and the target network information into a trained route design model, and output the route of each of the outer target UAV and each of the inner target UAV.

[0040] In addition, to achieve the above object, the present application also provides a terminal, wherein the terminal comprises a memory, a processor, and a UAV obstacle avoidance based route design program stored in the memory and executable on the processor, and the UAV obstacle avoidance based route design program implements the steps of the UAV obstacle avoidance based route design method when executed by the processor.

[0041] In addition, to achieve the above object, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a UAV obstacle avoidance based route design program, and the UAV obstacle avoidance based route design program implements the steps of the UAV obstacle avoidance based route design method when executed by a processor.

[0042] In the present application, a plurality of UAV information is acquired, a UAV network is constructed according to all the UAV information, a patrol task information is acquired, and a target UAV network is constructed in the UAV network according to the patrol task information; a plurality of first flight state information collected by a plurality of peripheral target UAVs in the target UAV network and a plurality of second flight state information collected by a plurality of internal target UAVs are acquired; the plurality of first flight state information and the plurality of second flight state information are input into a trained risk prediction model, and risk collision information is output; target network information of the target UAV network is acquired, the plurality of first flight state information, the plurality of second flight state information, the risk collision information, and the target network information are input into a trained route design model, and a route of each peripheral target UAV and each internal target UAV is output. The present application obtains the information of each UAV and the distance information between the UAVs by analyzing the flight state information of the UAVs when patrolling the surrounding environment buildings, and controls a plurality of UAVs through the structure information of the UAV network, maintains a safe distance between the UAVs, effectively avoids the collision between the UAVs and the surrounding environment buildings, and reduces the danger of the plurality of UAVs when performing the patrol task, thereby improving the efficiency of managing the plurality of UAVs. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a flowchart of a preferred embodiment of the UAV obstacle avoidance based route design method of the present application;

[0044] Figure 2 is a first schematic diagram of UAV adjustment of a preferred embodiment of the UAV obstacle avoidance based route design method of the present application;

[0045] Figure 3 is a second schematic diagram of UAV adjustment of a preferred embodiment of the UAV obstacle avoidance based route design method of the present application;

[0046] Figure 4is a structural diagram of a preferred embodiment of a route design system based on unmanned aerial vehicle obstacle avoidance of the present application;

[0047] Figure 5 is a schematic diagram of an operating environment of a preferred embodiment of a terminal of the present application. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions and advantages of the present application clearer and more explicit, the present application is further described in detail below with reference to the drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0049] In the existing field of unmanned aerial vehicle inspection, the perception and obstacle avoidance technology of unmanned aerial vehicles are limited, sometimes leading to misjudgment or failure to avoid obstacles in time, which poses a threat to the safety of unmanned aerial vehicles and power facilities, and may face collision and other safety risks during flight, thus measures need to be taken to ensure the safety thereof.

[0050] The route design method based on unmanned aerial vehicle obstacle avoidance according to the preferred embodiment of the present application, as shown in Figure 1 includes the following steps:

[0051] Step S10, obtaining a plurality of unmanned aerial vehicle information, constructing a network of unmanned aerial vehicles according to all the unmanned aerial vehicle information, obtaining inspection task information, and constructing a target network of unmanned aerial vehicles in the network of unmanned aerial vehicles according to the inspection task information.

[0052] Among them, the unmanned aerial vehicles in the network of unmanned aerial vehicles are in a non-selected state, and the target unmanned aerial vehicles in the target network of unmanned aerial vehicles are in a selected state. When the unmanned aerial vehicle is in the selected state, detailed information is displayed, including the start point position, the end point position, the mark point along the way, the route state, the distance between the mark points, the flight direction of the unmanned aerial vehicle and the power information of the unmanned aerial vehicle, and other detailed unmanned aerial vehicle information. When the unmanned aerial vehicle is in the non-selected state, only the start point position, the mark point position, the route state and the driving direction of the unmanned aerial vehicle are displayed.

[0053] Specifically, a plurality of unmanned aerial vehicle information is obtained, a connection between all the unmanned aerial vehicles is established according to all the unmanned aerial vehicle information, a network of unmanned aerial vehicles is obtained, inspection task information is obtained and analyzed, a plurality of event information is obtained, the state of a plurality of unmanned aerial vehicles in the network of unmanned aerial vehicles is changed according to a plurality of the event information, a plurality of target unmanned aerial vehicles are obtained, and a target network of unmanned aerial vehicles is constructed according to all the target unmanned aerial vehicles.

[0054] Wherein, according to the relevant information of each unmanned aerial vehicle, Wi-Fi connection or Mesh connection between each unmanned aerial vehicle is established to form unmanned aerial vehicle networking; when the inspection task is acquired, the relevant information of the inspection task can be analyzed to obtain a plurality of event information, which mainly refers to the basic requirements of the current inspection task, so that a proper number of target unmanned aerial vehicles can be selected in the unmanned aerial vehicle networking according to the basic requirements, that is, part of the target unmanned aerial vehicles are screened out from the original unmanned aerial vehicle networking, and the connection between the target unmanned aerial vehicles does not need to be established again, so that the target unmanned aerial vehicle networking is directly obtained, the efficiency of the inspection task is improved, and the resource utilization rate is improved by selecting appropriate target unmanned aerial vehicles according to the inspection task.

[0055] Step S20, acquiring first flight state information collected by a plurality of peripheral target unmanned aerial vehicles in the target unmanned aerial vehicle networking and second flight state information collected by a plurality of internal target unmanned aerial vehicles.

[0056] Wherein, the plurality of target unmanned aerial vehicles include a plurality of peripheral target unmanned aerial vehicles and a plurality of internal target unmanned aerial vehicles. The peripheral target unmanned aerial vehicle refers to the unmanned aerial vehicle in the outer periphery of the target unmanned aerial vehicle networking, and the internal target unmanned aerial vehicle refers to the unmanned aerial vehicle surrounded by the peripheral target unmanned aerial vehicle in the target unmanned aerial vehicle networking. When selecting target unmanned aerial vehicles from the unmanned aerial vehicle networking, the state of the target unmanned aerial vehicle (such as the power information of the unmanned aerial vehicle) needs to be judged first, and if appropriate, it is changed to a selected state, and if not appropriate, the user needs to be prompted. For example, when a unmanned aerial vehicle is selected, the power of the unmanned aerial vehicle is insufficient, or the connection state is unstable, the user will be prompted that the state of the current unmanned aerial vehicle is unstable, and other unmanned aerial vehicles will be automatically selected as target unmanned aerial vehicles to avoid affecting the normal execution of the inspection task.

[0057] Specifically, the query instruction of the user is acquired, the states of the plurality of peripheral target unmanned aerial vehicles and the plurality of internal target unmanned aerial vehicles are detected according to the query instruction; when it is determined that the states of the plurality of peripheral target unmanned aerial vehicles and the plurality of internal target unmanned aerial vehicles are all selected states, the first flight state information of each peripheral target unmanned aerial vehicle and the second flight state information collected by each internal target unmanned aerial vehicle are acquired.

[0058] Before the target unmanned aerial vehicle networking is obtained and the inspection task is executed, it is queried whether the target unmanned aerial vehicles in the target unmanned aerial vehicle networking are in the selected state, and the target unmanned aerial vehicles can be detected again whether they are suitable for the current inspection task. After it is determined that all aspects of information are correct, the current inspection task can be started to be executed, and the flight state information collected by each target unmanned aerial vehicle is acquired, wherein the peripheral target unmanned aerial vehicle needs to collect the distance between the surrounding environment and the obstacles such as buildings and birds and other flying objects, so as to improve the safety of the inspection task.

[0059] Further, when it is determined that the states of the plurality of outer target unmanned aerial vehicles are all selected states, the start point position information, the end point position information, the environment information, the unmanned aerial vehicle distance information, the passing point information, the flight direction information and the flight path state information collected by each outer target unmanned aerial vehicle are obtained; when it is determined that the states of the plurality of inner target unmanned aerial vehicles are all selected states, the start point position information, the end point position information, the unmanned aerial vehicle distance information, the passing point information, the flight direction information and the flight path state information collected by each outer target unmanned aerial vehicle are obtained; wherein the environment information represents the distance information of the outer target unmanned aerial vehicle from the surrounding buildings, and the unmanned aerial vehicle distance information represents the distance information between each target unmanned aerial vehicle and the adjacent target unmanned aerial vehicle.

[0060] In the process of performing the inspection task, the flight state information collected by the target unmanned aerial vehicle includes the start point position information, the end point position information, the unmanned aerial vehicle distance information, the passing point information, the flight direction information and the flight path state information, and the outer target unmanned aerial vehicle needs to collect one more item of environment information to ensure the safety of the entire target unmanned aerial vehicle network in the process of performing the inspection task. In addition, the unmanned aerial vehicle distance information collected by each target unmanned aerial vehicle respectively represents the distance between the target unmanned aerial vehicle and the surrounding unmanned aerial vehicle, which further improves the safety of the entire target unmanned aerial vehicle network in the process of performing the inspection task. The start point position information, the end point position information, the passing point information, the flight direction information and the flight path state information can be used to prompt the user about the progress and status of the current target unmanned aerial vehicle network performing the inspection task, and provide real-time information for the user. The user can input control instructions in a timely manner to adjust the target unmanned aerial vehicle according to the real-time information, thereby improving the degree of freedom of performing the inspection task.

[0061] Step S30, inputting the plurality of first flight state information and the plurality of second flight state information into the trained risk prediction model to output risk collision information.

[0062] Specifically, an initial risk prediction model is constructed, historical inspection task information of historical inspection tasks is obtained, and the historical inspection task information is input into the initial risk prediction model for training to obtain a risk prediction model; each environment information and each unmanned aerial vehicle distance information are input into the risk prediction model to output risk collision information.

[0063] Wherein, the risk prediction model is first trained using the relevant information of the historical inspection tasks. When the current target unmanned aerial vehicle performs the inspection task, the environment information and the unmanned aerial vehicle distance information collected are input into the risk prediction model to predict the collision risk information of the outer target unmanned aerial vehicle with the buildings or other flying objects in the surrounding environment, and the collision risk information between each target unmanned aerial vehicle, thereby improving the accuracy of risk prediction in the process of performing the inspection task and avoiding delay in performing the inspection task due to false prediction.

[0064] Step S40, obtaining target networking information of the target unmanned aerial vehicle networking, inputting the plurality of first flight state information, the plurality of second flight state information, the risk collision information and the target networking information into the trained route design model, and outputting the route of each outer target unmanned aerial vehicle and each internal target unmanned aerial vehicle.

[0065] The target networking information includes information transmission direction and mesh structure information. The information transmission direction indicates the direction of information transmission between target unmanned aerial vehicles, for example, part of the outer target unmanned aerial vehicle transmits flight state information to the internal target unmanned aerial vehicle, or the internal target unmanned aerial vehicle transmits flight state information to the outer target unmanned aerial vehicle, thereby avoiding information confusion between target unmanned aerial vehicles and reducing the execution efficiency of the inspection task.

[0066] Specifically, an initial route design model is constructed, historical routes are obtained, and the historical routes are input into the initial route design model for training to obtain a route design model; the information transmission direction and the mesh structure information of each target unmanned aerial vehicle in the target unmanned aerial vehicle networking are obtained; each of the starting point position information, each of the ending point position information, each of the way point information, each of the flight direction information, each of the route state information, the risk collision information, each of the information transmission direction and the mesh structure information are input into the route design model, and the route of each outer target unmanned aerial vehicle and each internal target unmanned aerial vehicle is output.

[0067] The way point information and the flight direction information can be set according to the user's own needs. If the user has no special requirements, as shown in the figure, a plurality of options can be set according to the starting point position information and the ending point position information of each target unmanned aerial vehicle, so that the user can select the most suitable execution plan, or the user can select a suitable execution plan by himself / herself, and then input each starting point position information, each ending point position information, each way point information, each flight direction information, each route state information, risk collision information, each information transmission direction and mesh structure information into the route design model, to obtain the most efficient route on the basis of meeting the user's needs. Figure 2

[0068] Further, a plurality of control instructions are generated according to each of the routes; each of the outer target unmanned aerial vehicles and each of the internal target unmanned aerial vehicles are controlled to adjust the flight state according to all the control instructions; the adjusted flight state of the plurality of target unmanned aerial vehicles is sent to a plurality of adjacent target unmanned aerial vehicles according to the mesh structure information and the information transmission direction, so that the plurality of adjacent target unmanned aerial vehicles update the unmanned aerial vehicle distance information according to all the flight states.

[0069] ​The adjusted flight state is transmitted to other target drones through a preset mesh structure and a preset information transmission direction, as shown in the figure, and the flight speed and other information of the target drone is transmitted to other target drones. Figure 3 When there is a collision risk between the target drones, the lower target drone (i.e., the drone receiving the flight state information of other target drones) needs to be adjusted, which can reduce the number of target drone adjustments, reduce the burden of resource scheduling, and improve the efficiency of adjusting target drones during the execution of the inspection task.

[0070] The present application analyzes the flight state information of the drones, obtains the information of each drone during the inspection and the distance information between the drones, and controls multiple drones through the structure information of the drone network to maintain a safe distance between the drones, effectively avoiding collisions between the drones and the surrounding environment buildings and between the drones, reducing the danger of multiple drones during the execution of the inspection task, and improving the efficiency of managing multiple drones.

[0071] Further, as shown in the figure, Figure 4 Based on the above-mentioned route design method based on drone obstacle avoidance, the present application also correspondingly provides a route design system based on drone obstacle avoidance, wherein the route design system based on drone obstacle avoidance comprises:

[0072] The drone connection module 51 is used to obtain multiple drone information, construct a drone network according to all the drone information, obtain inspection task information, and construct a target drone network in the drone network according to the inspection task information.

[0073] The information acquisition module 52 is used to obtain first flight state information collected by multiple outer target drones in the target drone network and second flight state information collected by multiple inner target drones.

[0074] The risk prediction module 53 is used to input multiple first flight state information and multiple second flight state information into a trained risk prediction model and output risk collision information.

[0075] The route design module 54 is used to obtain target network information of the target drone network, input multiple first flight state information, multiple second flight state information, the risk collision information, and the target network information into a trained route design model, and output the route of each outer target drone and each inner target drone.

[0076] Further, as shown in the figure, Figure 5As shown, based on the above route design method and system based on UAV obstacle avoidance, the application also correspondingly provides a terminal, which comprises a processor 10, a memory 20 and a display 30. Figure 5 Only part of the components of the terminal is shown, but it should be understood that all the shown components are not required to be implemented, and more or less components can be alternatively implemented.

[0077] The memory 20 can be an internal storage unit of the terminal in some embodiments, such as a hard disk or a memory of the terminal. The memory 20 can also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Further, the memory 20 can include both the internal storage unit and the external storage device of the terminal. The memory 20 is used to store application software and various data installed on the terminal, such as program codes of the terminal, etc. The memory 20 can also be used to temporarily store data that has been output or will be output. In an embodiment, the memory 20 stores a route design program based on UAV obstacle avoidance 40, which can be executed by the processor 10 to implement the route design method based on UAV obstacle avoidance in the application.

[0078] The processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, which is used to run program codes or process data stored in the memory 20, such as to execute the route design method based on UAV obstacle avoidance, etc.

[0079] The display 30 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 30 is used to display information of the terminal and to display visualized user interfaces. The components 10-30 of the terminal communicate with each other through a system bus.

[0080] In an embodiment, the following steps are implemented when the processor 10 executes the route design program based on UAV obstacle avoidance 40 in the memory 20:

[0081] Obtaining a plurality of UAV information, constructing a UAV network according to all the UAV information, obtaining inspection task information, and constructing a target UAV network in the UAV network according to the inspection task information;

[0082] acquire first flight state information collected by a plurality of outer target UAVs in the target UAV network and second flight state information collected by a plurality of inner target UAVs;

[0083] input the plurality of first flight state information and the plurality of second flight state information into a trained risk prediction model, and output risk collision information;

[0084] acquire target networking information of the target UAV network, input the plurality of first flight state information, the plurality of second flight state information, the risk collision information and the target networking information into a trained route design model, and output a route of each outer target UAV and each inner target UAV.

[0085] wherein, the acquiring a plurality of UAV information, according to all the UAV information, constructing a UAV network, acquiring a patrol task information, according to the patrol task information, constructing a target UAV network in the UAV network, specifically comprising:

[0086] acquiring a plurality of UAV information, according to all the UAV information, establishing a connection between all the UAVs, obtaining a UAV network;

[0087] acquiring patrol task information and analyzing to obtain a plurality of event information, changing a state of a plurality of UAVs in the UAV network according to a plurality of the event information, obtaining a plurality of target UAVs, and constructing a target UAV network according to all the target UAVs;

[0088] wherein, the UAV in the UAV network is in a non-selected state, and the target UAV in the target UAV network is in a selected state.

[0089] wherein, the plurality of target UAVs comprises a plurality of outer target UAVs and a plurality of inner target UAVs;

[0090] the acquiring first flight state information collected by a plurality of outer target UAVs in the target UAV network and second flight state information collected by a plurality of inner target UAVs, specifically comprising:

[0091] acquiring a query instruction of a user, and detecting a state of a plurality of the outer target UAVs and a plurality of the inner target UAVs according to the query instruction;

[0092] when it is determined that the state of a plurality of the outer target UAVs and a plurality of the inner target UAVs is in a selected state, acquiring first flight state information of each of the outer target UAVs and second flight state information collected by each of the inner target UAVs.

[0093] The first flight state information of each of the plurality of outer target drones and the second flight state information collected by each of the plurality of inner target drones are displayed when it is determined that the states of the plurality of outer target drones and the plurality of inner target drones are all selected states, and the display specifically includes:

[0094] When it is determined that the states of the plurality of outer target drones are all selected states, the start point position information, the end point position information, the environment information, the drone distance information, the waypoint information, the flight direction information and the route state information collected by each of the plurality of outer target drones are obtained;

[0095] When it is determined that the states of the plurality of inner target drones are all selected states, the start point position information, the end point position information, the drone distance information, the waypoint information, the flight direction information and the route state information collected by each of the plurality of outer target drones are obtained;

[0096] The environment information represents the distance information of the outer target drone from the surrounding buildings when the outer target drone implements shooting, and the drone distance information represents the distance information between each of the target drones and the adjacent target drones.

[0097] The first flight state information and the second flight state information are input into the trained risk prediction model, and risk collision information is output, and the input specifically includes:

[0098] An initial risk prediction model is constructed, historical inspection task information of a historical inspection task is obtained, and the historical inspection task information is input into the initial risk prediction model for training to obtain a risk prediction model;

[0099] Each of the environment information and the drone distance information is input into the risk prediction model, and risk collision information is output.

[0100] The target networking information includes information transmission direction and mesh structure information.

[0101] The target networking information of the target drone networking is obtained, the first flight state information, the second flight state information, the risk collision information and the target networking information are input into the trained route design model, and the route of each outer target drone and each inner target drone is output, and the input specifically includes:

[0102] An initial route design model is constructed, a historical route is obtained, and the historical route is input into the initial route design model for training to obtain a route design model;

[0103] The information transmission direction and the mesh structure information of each target drone in the target drone networking are obtained.

[0104] Input each of the starting point location information, each of the ending point location information, each of the waypoint information, each of the flight direction information, each of the route status information, the risk collision information, each of the information transmission direction and the mesh structure information into the route design model, and output the route of each peripheral target UAV and each internal target UAV.

[0105] The process involves inputting each of the starting point location information, each of the ending point location information, each of the waypoint information, each of the flight direction information, each of the route status information, the risk collision information, each of the information transmission directions, and the mesh structure information into the route design model, and outputting the routes for each peripheral target UAV and each internal target UAV. This process further includes:

[0106] For each of the aforementioned flight paths, multiple control commands are generated;

[0107] According to all the control commands, control each of the peripheral target UAVs and each of the internal target UAVs to adjust their flight status;

[0108] Based on the mesh structure information and the information transmission direction, the adjusted flight status of multiple target drones is sent to multiple neighboring target drones, so as to control the multiple neighboring target drones to update the drone distance information according to all the flight statuses.

[0109] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a flight path design program based on UAV obstacle avoidance, and the flight path design program based on UAV obstacle avoidance implements the steps of the flight path design method based on UAV obstacle avoidance as described above when executed by a processor.

[0110] In summary, the application provides a flight path design method based on UAV obstacle avoidance and related equipment, the method comprising: obtaining a plurality of UAV information, constructing a UAV network according to all the UAV information, obtaining inspection task information, and constructing a target UAV network in the UAV network according to the inspection task information; obtaining first flight state information collected by a plurality of peripheral target UAVs in the target UAV network and second flight state information collected by a plurality of internal target UAVs; inputting a plurality of the first flight state information and a plurality of the second flight state information into a trained risk prediction model to output risk collision information; obtaining target network information of the target UAV network, inputting a plurality of the first flight state information, a plurality of the second flight state information, the risk collision information and the target network information into a trained flight path design model to output a flight path of each peripheral target UAV and each internal target UAV. The application obtains the information of each UAV and the distance information between UAVs when inspecting the surrounding environment by analyzing the flight state information of the UAV, controls a plurality of UAVs through the structure information of the UAV network, maintains a safe distance between the UAVs, effectively avoids the collision between the UAVs and the surrounding environment buildings, reduces the danger of a plurality of UAVs when performing the inspection task, and improves the efficiency of managing a plurality of UAVs.

[0111] It should be noted that in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or terminals including a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles or terminals. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another identical element in the process, method, article or terminal including the element.

[0112] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware (such as a processor, a controller, etc.) to complete, and the program can be stored in a computer-readable computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0113] It should be understood that the application is not limited to the above examples, and those skilled in the art can make improvements or changes according to the above description, and all these improvements and changes should be within the protection scope of the appended claims of the application.

Claims

1. A flight path design method based on obstacle avoidance by unmanned aerial vehicles (UAVs), characterized in that, The methods include: Acquiring information on multiple drones, constructing a drone network based on all the drone information, acquiring inspection task information, and constructing a target drone network within the drone network based on the inspection task information include: Acquire information on multiple drones, and establish connections between all drones based on all the drone information to obtain a drone network; The inspection task information is acquired and analyzed to obtain multiple event information. Based on the multiple event information, the status of multiple drones in the drone network is changed to obtain multiple target drones. A target drone network is constructed based on all the target drones. In the above, the drones in the drone network are in a non-selected state, while the target drones in the target drone network are in a selected state; The multiple target drones include: multiple peripheral target drones and multiple internal target drones; Acquiring first flight status information collected by multiple peripheral target drones and second flight status information collected by multiple internal target drones in the target drone network includes: Obtain the user's query command, and detect the status of multiple peripheral target drones and multiple internal target drones based on the query command; When multiple peripheral target drones are selected, acquire the starting point location information, ending point location information, environmental information, drone distance information, waypoint information, flight direction information, and flight path status information collected by each peripheral target drone; When it is determined that the status of multiple internal target drones is selected, the starting position information, ending position information, drone distance information, waypoint information, flight direction information and flight path status information collected by each peripheral target drone are obtained; The environmental information refers to the distance information between the peripheral target drone and the surrounding buildings, and the drone distance information refers to the distance information between each target drone and its neighboring target drones. Multiple first flight state information and multiple second flight state information are input into a trained risk prediction model to output risk collision information. Obtain the target network information of the target UAV network, input multiple first flight status information, multiple second flight status information, the risk collision information and the target network information into the trained flight path design model, and output the flight path of each peripheral target UAV and each internal target UAV.

2. The flight path design method based on UAV obstacle avoidance according to claim 1, characterized in that, The step of inputting multiple sets of first flight state information and multiple sets of second flight state information into a pre-trained risk prediction model and outputting risk collision information specifically includes: An initial risk prediction model is constructed by obtaining historical inspection task information and inputting the historical inspection task information into the initial risk prediction model for training, thereby obtaining the risk prediction model. Each piece of environmental information and each piece of UAV distance information is input into the risk prediction model, and risk collision information is output.

3. The route design method based on UAV obstacle avoidance according to claim 1, characterized in that, The target networking information includes: information transmission direction and mesh structure information; The step of obtaining the target network information of the target UAV network involves inputting multiple sets of first flight status information, multiple sets of second flight status information, the risk collision information, and the target network information into a pre-trained flight path design model, and outputting the flight paths for each peripheral target UAV and each internal target UAV, specifically including: Construct an initial route design model, obtain historical routes, and input the historical routes into the initial route design model for training to obtain the route design model; Obtain the information transmission direction and mesh structure information of each target UAV in the target UAV network; Input each of the starting point location information, each of the ending point location information, each of the waypoint information, each of the flight direction information, each of the route status information, the risk collision information, each of the information transmission direction and the mesh structure information into the route design model, and output the route of each peripheral target UAV and each internal target UAV.

4. The flight path design method based on UAV obstacle avoidance according to claim 3, characterized in that, The process involves inputting each of the starting point location information, each of the ending point location information, each of the waypoint information, each of the flight direction information, each of the route status information, the risk collision information, each of the information transmission directions, and the mesh structure information into the route design model, and outputting the routes for each peripheral target UAV and each internal target UAV. This process further includes: For each of the aforementioned flight paths, multiple control commands are generated; According to all the control commands, control each of the peripheral target UAVs and each of the internal target UAVs to adjust their flight status; Based on the mesh structure information and the information transmission direction, the adjusted flight status of multiple target drones is sent to multiple neighboring target drones, so as to control the multiple neighboring target drones to update the drone distance information according to all the flight statuses.

5. A flight path design system based on obstacle avoidance for unmanned aerial vehicles (UAVs), characterized in that, The UAV obstacle avoidance-based flight path design system is applied to the UAV obstacle avoidance-based flight path design method as described in any one of claims 1-4, wherein the UAV obstacle avoidance-based flight path design system comprises: The drone connection module is used to acquire information from multiple drones, construct a drone network based on all the drone information, acquire inspection task information, and construct a target drone network in the drone network based on the inspection task information. The information acquisition module is used to acquire first flight status information collected by multiple peripheral target drones and second flight status information collected by multiple internal target drones in the target drone network. The risk prediction module is used to input multiple first flight state information and multiple second flight state information into a trained risk prediction model and output risk collision information. The route design module is used to acquire the target network information of the target UAV network, input multiple first flight status information, multiple second flight status information, the risk collision information and the target network information into the trained route design model, and output the route of each peripheral target UAV and each internal target UAV.

6. A terminal, characterized in that, The terminal includes: a memory, a processor, and a flight path design program based on UAV obstacle avoidance stored in the memory and executable on the processor. When the UAV obstacle avoidance flight path design program is executed by the processor, it implements the steps of the flight path design method based on UAV obstacle avoidance as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a flight path design program based on UAV obstacle avoidance, which, when executed by a processor, implements the steps of the flight path design method based on UAV obstacle avoidance as described in any one of claims 1-5.

Images