Route design method and system based on obstacle avoidance of unmanned aerial vehicle, and terminal

Abstract

The invention discloses a route design method, system and terminal based on unmanned aerial vehicle obstacle avoidance, and the method comprises the steps: obtaining inspection task information, and obtaining a target unmanned aerial vehicle network; obtaining flight state information collected by a target unmanned aerial vehicle in the target unmanned aerial vehicle network, and generating risk collision information through a trained risk prediction model; and obtaining the route of each target unmanned aerial vehicle according to the target networking information, the flight state information, the risk collision information and the target networking information. According to the invention, by analyzing the flight state information of the unmanned aerial vehicles, the information of each unmanned aerial vehicle and the surrounding environment building and the distance information between the unmanned aerial vehicles during inspection are obtained, the plurality of unmanned aerial vehicles are controlled through the structure information of the unmanned aerial vehicle networking, and the safe distance between the unmanned aerial vehicles is maintained. The risk of the plurality of unmanned aerial vehicles when the plurality of unmanned aerial vehicles execute the inspection task is reduced, and the management efficiency of the plurality of unmanned aerial vehicles is improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control technology, and in particular to a route design method, system, terminal and computer-readable storage medium based on unmanned aerial vehicle obstacle avoidance. Background Art

[0002] The main purpose of drone inspection is to improve inspection efficiency and accuracy while reducing costs and risks. By optimizing flight paths and setting inspection tasks, drone inspections can efficiently obtain information about inspection objects and promptly detect and record abnormal situations.

[0003] However, in the existing drone inspection field, the drone's perception and obstacle avoidance technology is limited, and sometimes misjudgment or failure to avoid obstacles in time may occur, posing a threat to the safety of drones and power facilities. In addition, the drone may face safety risks such as collisions 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 of the invention

[0005] The main purpose of the present invention is to provide a route design method, system, terminal and computer-readable storage medium based on drone obstacle avoidance, aiming to solve the problems in the prior art that multiple drones are prone to confusion when performing inspection tasks together, and that drones may collide with surrounding buildings and drones, thereby causing the mission to be more dangerous.

[0006] To achieve the above object, the present invention provides a route design method based on unmanned aerial vehicle obstacle avoidance, and the route design method based on unmanned aerial vehicle obstacle avoidance comprises the following steps:

[0007] Acquire information of 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;

[0008] 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;

[0009] Inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information;

[0010] The target networking information of the target UAV network is obtained, a plurality of the first flight state information, a plurality of the second flight state information, the risk collision information and the target networking information are input into a trained route design model, and the routes of each peripheral target UAV and each internal target UAV are output.

[0011] Optionally, the route design method based on drone obstacle avoidance, wherein the acquiring of multiple drone information, building a drone network based on all the drone information, acquiring inspection task information, and building a target drone network in the drone network based on the inspection task information, specifically includes:

[0012] Acquire information of multiple drones, and establish connections between all the drones based on the information of all the drones to obtain a drone network;

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

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

[0015] Optionally, in the route design method based on drone obstacle avoidance, the multiple target drones include: multiple peripheral target drones and multiple internal target drones;

[0016] The obtaining of 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 specifically includes:

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

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

[0019] Optionally, the route design method based on drone obstacle avoidance, wherein when it is determined that the states of the plurality of peripheral target drones and the plurality of internal target drones are all in the selected state, the first flight state information of each peripheral target drone and the second flight state information collected by each internal target drone are displayed, specifically including:

[0020] When it is determined that the states of the plurality of peripheral target drones are all in the selected state, the starting point position information, the end point position information, the environmental information, the drone distance information, the waypoint information, the flight direction information and the route status information collected by each peripheral target drone are obtained;

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

[0022] The environmental information indicates the distance information between the peripheral target drone and surrounding buildings, and the drone distance information indicates the distance information between each target drone and adjacent target drones.

[0023] Optionally, the route design method based on unmanned aerial vehicle obstacle avoidance, wherein the step of inputting a plurality of the first flight state information and a plurality of the second flight state information into a trained risk prediction model and outputting risk collision information specifically includes:

[0024] Constructing an initial risk prediction model, obtaining historical inspection task information of historical inspection tasks, and inputting the historical inspection task information into the initial risk prediction model for training to obtain a risk prediction model;

[0025] Each piece of environmental information and each piece of UAV distance information are input into the risk prediction model, and risk collision information is output.

[0026] Optionally, in the route design method based on obstacle avoidance of unmanned aerial vehicles, the target networking information includes: information transmission direction and mesh structure information;

[0027] The step of obtaining target networking 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 networking information into a trained route design model, and outputting the routes of each peripheral target UAV and each internal target UAV specifically includes:

[0028] Constructing an initial route design model, obtaining historical routes, and inputting the historical routes into the initial route design model for training to obtain a route design model;

[0029] Obtaining information transmission direction and mesh structure information of each target drone in the target drone network;

[0030] The starting point position information, the end point position information, the waypoint information, the flight direction information, the route status information, the collision risk information, the information transmission direction and the mesh structure information are input into the route design model, and the route of each peripheral target UAV and each internal target UAV is output.

[0031] Optionally, the route design method based on obstacle avoidance of unmanned aerial vehicles, wherein each starting point position information, each end point position information, each waypoint information, each flight direction information, each route state information, the risk collision information, each information transmission direction and mesh structure information are input into the route design model, and the route of each peripheral target unmanned aerial vehicle and each internal target unmanned aerial vehicle is output, and then the route design method further includes:

[0032] generating a plurality of control instructions according to each of the routes;

[0033] According to all the control instructions, control each of the peripheral target UAVs and each of the internal target UAVs to adjust the flight state;

[0034] According to the mesh structure information and the information transmission direction, the adjusted flight states of the multiple target drones are sent to the multiple adjacent target drones, so as to control the multiple adjacent target drones to update the drone distance information according to all the flight states.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a route design system based on unmanned aerial vehicle obstacle avoidance, wherein the route design system based on unmanned aerial vehicle obstacle avoidance includes:

[0036] A drone connection module is used to obtain information of multiple drones, build a drone network based on all the drone information, obtain inspection task information, and build a target drone network in the drone network based on the inspection task information;

[0037] An information acquisition module, 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;

[0038] A risk prediction module, used for inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information;

[0039] The route design module is used to obtain the target networking information of the target UAV network, input the multiple first flight state information, the multiple second flight state information, the risk collision information and the target networking information into the trained route design model, and output the route of each peripheral target UAV and each internal target UAV.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a route design program based on drone obstacle avoidance stored in the memory and executable on the processor, wherein the route design program based on drone obstacle avoidance implements the steps of the route design method based on drone obstacle avoidance as described above when the route design program based on drone obstacle avoidance is executed by the processor.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a route design program based on drone obstacle avoidance, and when the route design program based on drone obstacle avoidance is executed by a processor, the steps of the route design method based on drone obstacle avoidance as described above are implemented.

[0042] In the present invention, multiple drone information is obtained, and a drone network is constructed according to all the drone information, and inspection task information is obtained. According to the inspection task information, a target drone network is constructed in the drone network; the first flight state information collected by multiple peripheral target drones and the second flight state information collected by multiple internal target drones in the target drone network are obtained; the multiple first flight state information and the multiple second flight state information are input into the trained risk prediction model, and the risk collision information is output; the target network information of the target drone network is obtained, and the multiple first flight state information, the multiple second flight state information, the risk collision information and the target network information are input into the trained route design model, and the route of each peripheral target drone and each internal target drone is output. The present invention obtains the information of each drone and the surrounding environment buildings during the inspection and the distance information between the drones by analyzing the flight state information of the drones, and controls the multiple drones through the structural information of the drone network, maintains a safe distance between the drones, effectively avoids the possible collision between the drones and the surrounding environment buildings and the drones, reduces the danger of multiple drones when performing inspection tasks, and improves the efficiency of managing multiple drones. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a preferred embodiment of the route design method based on obstacle avoidance of unmanned aerial vehicles of the present invention;

[0044] Figure 2 It is a first schematic diagram of adjustment of a drone according to a preferred embodiment of the route design method based on obstacle avoidance of a drone of the present invention;

[0045] Figure 3 It is a second schematic diagram of adjustment of a drone according to a preferred embodiment of the route design method based on drone obstacle avoidance of the present invention;

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

[0047] Figure 5 Schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0049] In the existing drone inspection field, the drone’s perception and obstacle avoidance technology is limited, and sometimes misjudgments or failure to avoid obstacles in time may occur, posing a threat to the safety of drones and power facilities. In addition, drones may face safety risks such as collisions during flight, and measures need to be taken to ensure their safety.

[0050] The route design method based on obstacle avoidance of unmanned aerial vehicle described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the route design method based on unmanned aerial vehicle obstacle avoidance includes the following steps:

[0051] Step S10: obtain information of multiple drones, build a drone network based on all the drone information, obtain inspection task information, and build a target drone network in the drone network based on the inspection task information.

[0052] Among them, the drones in the drone network are in a non-selected state, and the target drone in the target drone network is in a selected state. When the drone is in a selected state, detailed information will be displayed, including the starting point position, the end point position, the marking points along the way, the route status, the distance between the passing marking points, the flight direction of the drone and the power information of the drone, and when the drone is in a non-selected state, only the abbreviated contents such as the starting point position, the passing marking point position, the route status and the driving direction of the drone will be displayed.

[0053] Specifically, information of multiple drones is obtained, and connections between all drones are established based on the information of all the drones to obtain a drone network; inspection task information is obtained and analyzed to obtain multiple event information, and the states of multiple drones in the drone network are changed based on the multiple event information to obtain multiple target drones, and a target drone network is constructed based on all the target drones.

[0054] Among them, according to the relevant information of each drone, a Wi-Fi connection or Mesh connection is established between each drone to form a drone network; when the inspection task is obtained, the relevant information of the inspection task can be analyzed to obtain multiple event information. These event information mainly refer to the basic requirements of this inspection task, so that according to these basic requirements, a suitable number of target drones can be selected in the drone network, that is, some target drones are screened out from the original drone network, and there is no need to establish the connection between these target drones again, and the target drone network is directly obtained, which improves the efficiency of the inspection task, and selects the appropriate target drone according to the inspection task, thereby improving resource utilization.

[0055] Step S20: 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.

[0056] Among them, the multiple target drones include: multiple peripheral target drones and multiple internal target drones. Peripheral target drones refer to drones in the periphery of the target drone network, and internal target drones refer to drones surrounded by peripheral target drones in the target drone network. When selecting a target drone from the drone network, it is necessary to first determine the status of the target drone (such as the battery information of the drone, etc.), and change it to the selected state if it is appropriate. If it is not appropriate, it is necessary to prompt the user. For example, when a drone is selected, the drone has insufficient battery or the connection status is unstable, the user will be prompted that the status of the current drone is unstable, and other drones will be automatically selected as target drones to avoid affecting the normal execution of the inspection task.

[0057] Specifically, a query instruction of the user is obtained, and the status of the plurality of peripheral target UAVs and the plurality of internal target UAVs is detected according to the query instruction; when it is determined that the status of the plurality of peripheral target UAVs and the plurality of internal target UAVs are all selected, the first flight status information of each peripheral target UAV and the second flight status information collected by each internal target UAV are obtained.

[0058] After obtaining the target drone network and before executing the inspection task, first check whether the target drone in the target drone network is selected, and you can also check again whether the target drone is suitable for the current inspection task. After confirming that all aspects of information are correct, you can start the current inspection task and obtain the flight status information collected by each target drone. Among them, the peripheral target drone needs to collect more distances from obstacles in the surrounding environment than the internal target drone, such as buildings and flying objects such as birds, so as to improve the safety of the inspection task.

[0059] Furthermore, when it is determined that the states of multiple peripheral target drones are all in the selected state, the starting point position information, end point position information, environmental information, drone distance information, waypoint information, flight direction information and route status information collected by each of the peripheral target drones are obtained; when it is determined that the states of multiple internal target drones are all in the selected state, the starting point position information, end point position information, drone distance information, waypoint information, flight direction information and route status information collected by each of the peripheral target drones are obtained; wherein the environmental information represents the distance information between the peripheral target drone and the surrounding buildings taken, and the drone distance information represents the distance information between each of the target drones and the adjacent target drones.

[0060] Among them, during the inspection task, the flight status information collected by the target drone includes the starting position information, the end position information, the drone distance information, the waypoint information, the flight direction information and the route status information, while the peripheral target drone needs to collect one more environmental information to ensure the safety of the entire target drone network during the inspection task. Secondly, the drone distance information collected by each target drone represents the distance between the target drone and the surrounding drones, further improving the safety of the entire target drone network during the inspection task. The starting position information, the end position information, the waypoint information, the flight direction information and the route status information can be used to prompt the user the progress and status of the current target drone network in performing the inspection task, providing real-time information for the user. The user can input control instructions in time according to the real-time information to adjust the target drone, which improves the freedom of performing the inspection task.

[0061] Step S30: input multiple pieces of the first flight status information and multiple pieces of the second flight status information into a trained risk prediction model, and 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 of the environmental information and each of the UAV distance information is input into the risk prediction model, and risk collision information is output.

[0063] Among them, the risk prediction model is first trained using the relevant information of historical inspection tasks. When the current target UAV is performing an inspection task, the collected environmental information and UAV distance information are input into the risk prediction model. The risk prediction model is used to predict the collision risk information between peripheral target UAVs and buildings or other flying objects in the surrounding environment, as well as the collision risk information between each target UAV, thereby improving the accuracy of risk prediction during the inspection task and avoiding delays in the execution of the inspection task due to incorrect predictions.

[0064] Step S40, obtaining the target networking information of the target UAV network, inputting the plurality of the first flight state information, the plurality of the second flight state information, the risk collision information and the target networking information into the trained route design model, and outputting the routes of each peripheral target UAV and each internal target UAV.

[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 drones, such as some peripheral target drones transmitting flight status information to internal target drones, or internal target drones transmitting flight status information to peripheral target drones, thereby avoiding information confusion between target drones and reducing the execution efficiency of inspection tasks.

[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 mesh structure information of each target UAV in the target UAV network are obtained; each starting point position information, each end point position information, each waypoint information, each flight direction information, each route status information, the risk collision information, each information transmission direction and mesh structure information are input into the route design model, and the routes of each peripheral target UAV and each internal target UAV are output.

[0067] Among them, the waypoint information and flight direction information can be set according to the user's own needs. If the user has no special requirements, such as Figure 2 As shown, multiple options can be set according to the starting position information and the end position information of each target UAV so that the user can choose the most appropriate execution plan, or the user can choose a suitable execution plan by himself, and then input each starting position information, each end position information, each waypoint information, each flight direction information, each route status 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 user needs.

[0068] Furthermore, according to each of the routes, a plurality of control instructions are generated; according to all of the control instructions, each of the peripheral target UAVs and each of the internal target UAVs are controlled to adjust their flight status; according to the mesh structure information and the information transmission direction, the adjusted flight status of the plurality of target UAVs is sent to the plurality of adjacent target UAVs, so as to control the plurality of adjacent target UAVs to update the UAV distance information according to all of the flight statuses.

[0069] Through the preset mesh structure and the preset information transmission direction, the adjusted flight status is transmitted to other target drones, such as Figure 3 As shown, the flight speed and other information of the target UAV is transmitted to other target UAVs. When there is a risk of collision between target UAVs, it is necessary to adjust the lower-level target UAVs (i.e., the UAVs that receive the flight status information of other target UAVs). This can reduce the number of adjustments to the target UAVs, and at the same time reduce the burden of resource scheduling, thereby improving the efficiency of adjusting the target UAVs during the inspection mission.

[0070] The present invention obtains information about each drone and its surrounding buildings during inspection and distance information between drones by analyzing the flight status information of drones, and controls multiple drones through the structural information of drone networking to maintain a safe distance between drones, effectively avoiding possible collisions between drones and surrounding buildings and drones, reducing the danger of multiple drones when performing inspection tasks, and improving the efficiency of managing multiple drones.

[0071] Furthermore, if Figure 4 As shown, based on the above-mentioned route design method based on unmanned aerial vehicle obstacle avoidance, the present invention also provides a route design system based on unmanned aerial vehicle obstacle avoidance, wherein the route design system based on unmanned aerial vehicle obstacle avoidance includes:

[0072] The drone connection module 51 is used to obtain information of multiple drones, build a drone network based on all the drone information, obtain inspection task information, and build a target drone network in the drone network based on the inspection task information;

[0073] An information acquisition module 52 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;

[0074] A risk prediction module 53, used for inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information;

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

[0076] Furthermore, if Figure 5As shown, based on the above-mentioned route design method and system based on drone obstacle avoidance, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 5 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0077] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a route design program 40 based on drone obstacle avoidance is stored on the memory 20, and the route design program 40 based on drone obstacle avoidance can be executed by the processor 10, thereby realizing the route design method based on drone obstacle avoidance in the present application.

[0078] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the route design method based on drone obstacle avoidance.

[0079] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

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

[0081] Acquire information of 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;

[0082] 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;

[0083] Inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information;

[0084] The target networking information of the target UAV network is obtained, a plurality of the first flight state information, a plurality of the second flight state information, the risk collision information and the target networking information are input into a trained route design model, and the routes of each peripheral target UAV and each internal target UAV are output.

[0085] The acquiring of information of a plurality of drones, building a drone network according to the information of all the drones, acquiring inspection task information, and building a target drone network in the drone network according to the inspection task information specifically includes:

[0086] Acquire information of multiple drones, and establish connections between all the drones based on the information of all the drones to obtain a drone network;

[0087] Obtaining and analyzing inspection task information to obtain a plurality of event information, changing the states of a plurality of drones in the drone network according to the plurality of event information, obtaining a plurality of target drones, and constructing a target drone network according to all the target drones;

[0088] Among them, the drones in the drone network are in a non-selected state, and the target drones in the target drone network are in a selected state.

[0089] The plurality of target drones include: a plurality of peripheral target drones and a plurality of internal target drones;

[0090] The obtaining of 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 specifically includes:

[0091] Obtaining a query instruction from a user, and detecting the states of the plurality of peripheral target drones and the plurality of internal target drones according to the query instruction;

[0092] When it is determined that the states of the plurality of peripheral target UAVs and the plurality of internal target UAVs are all in the selected state, the first flight state information of each peripheral target UAV and the second flight state information collected by each internal target UAV are obtained.

[0093] Wherein, when it is determined that the states of the plurality of peripheral target drones and the plurality of internal target drones are all in the selected state, the first flight state information of each peripheral target drone and the second flight state information collected by each internal target drone are displayed, specifically including:

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

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

[0096] The environmental information indicates the distance information between the peripheral target drone and surrounding buildings, and the drone distance information indicates the distance information between each target drone and adjacent target drones.

[0097] The step of inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model and outputting risk collision information specifically includes:

[0098] Constructing an initial risk prediction model, obtaining historical inspection task information of historical inspection tasks, and inputting the historical inspection task information into the initial risk prediction model for training to obtain a risk prediction model;

[0099] Each piece of environmental information and each piece of UAV distance information are 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 step of obtaining target networking 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 networking information into a trained route design model, and outputting the routes of each peripheral target UAV and each internal target UAV specifically includes:

[0102] Constructing an initial route design model, obtaining historical routes, and inputting the historical routes into the initial route design model for training to obtain a route design model;

[0103] Obtaining information transmission direction and mesh structure information of each target drone in the target drone network;

[0104] The starting point position information, the end point position information, the waypoint information, the flight direction information, the route status information, the collision risk information, the information transmission direction and the mesh structure information are input into the route design model, and the route of each peripheral target UAV and each internal target UAV is output.

[0105] The method further comprises: inputting each starting point position information, each end point position information, each waypoint information, each flight direction information, each route status information, the risk collision information, each information transmission direction and mesh structure information into the route design model, outputting the route of each peripheral target UAV and each internal target UAV, and then:

[0106] generating a plurality of control instructions according to each of the routes;

[0107] According to all the control instructions, control each of the peripheral target UAVs and each of the internal target UAVs to adjust the flight state;

[0108] According to the mesh structure information and the information transmission direction, the adjusted flight states of the multiple target drones are sent to the multiple adjacent target drones, so as to control the multiple adjacent target drones to update the drone distance information according to all the flight states.

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

[0110] In summary, the present invention provides a route design method based on unmanned aerial vehicle obstacle avoidance and related equipment, the method comprising: obtaining information of multiple unmanned aerial vehicles, building a unmanned aerial vehicle network based on all the unmanned aerial vehicle information, obtaining inspection task information, and building a target unmanned aerial vehicle network in the unmanned aerial vehicle network based on the inspection task information; obtaining first flight state information collected by multiple peripheral target unmanned aerial vehicles and second flight state information collected by multiple internal target unmanned aerial vehicles in the target unmanned aerial vehicle network; inputting multiple first flight state information and multiple second flight state information into a trained risk prediction model, and outputting risk collision information; obtaining target networking information of the target unmanned aerial vehicle network, inputting multiple first flight state information, multiple second flight state information, the risk collision information and the target networking information into a trained route design model, and outputting the route of each peripheral target unmanned aerial vehicle and each internal target unmanned aerial vehicle. The present invention obtains information about each drone and its surrounding buildings during inspection and distance information between drones by analyzing the flight status information of drones, and controls multiple drones through the structural information of drone networking to maintain a safe distance between drones, effectively avoiding possible collisions between drones and surrounding buildings and drones, reducing the danger of multiple drones when performing inspection tasks, and improving the efficiency of managing multiple drones.

[0111] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements 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 embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, 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 of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A route design method based on unmanned aerial vehicle obstacle avoidance, characterized in that: The route design method based on unmanned aerial vehicle obstacle avoidance includes: Acquire information of 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; 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; Inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information; The target networking information of the target UAV network is obtained, a plurality of the first flight state information, a plurality of the second flight state information, the risk collision information and the target networking information are input into a trained route design model, and the routes of each peripheral target UAV and each internal target UAV are output.

2. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 1 is characterized in that: The acquiring of information of a plurality of drones, building a drone network according to the information of all the drones, acquiring inspection task information, and building a target drone network in the drone network according to the inspection task information specifically includes: Acquire information of multiple drones, and establish connections between all the drones based on the information of all the drones to obtain a drone network; Obtaining and analyzing inspection task information to obtain a plurality of event information, changing the states of a plurality of drones in the drone network according to the plurality of event information, obtaining a plurality of target drones, and constructing a target drone network according to all the target drones; Among them, the drones in the drone network are in a non-selected state, and the target drones in the target drone network are in a selected state.

3. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 2 is characterized in that: The plurality of target drones include: a plurality of peripheral target drones and a plurality of internal target drones; The obtaining of 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 specifically includes: Obtaining a query instruction from a user, and detecting the states of the plurality of peripheral target drones and the plurality of internal target drones according to the query instruction; When it is determined that the states of the plurality of peripheral target UAVs and the plurality of internal target UAVs are all in the selected state, the first flight state information of each peripheral target UAV and the second flight state information collected by each internal target UAV are obtained.

4. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 3 is characterized in that: When it is determined that the states of the plurality of peripheral target drones and the plurality of internal target drones are all in the selected state, the first flight state information of each peripheral target drone and the second flight state information collected by each internal target drone are displayed, specifically including: When it is determined that the states of the plurality of peripheral target drones are all in the selected state, the starting point position information, the end point position information, the environmental information, the drone distance information, the waypoint information, the flight direction information and the route status information collected by each peripheral target drone are obtained; When it is determined that the states of the plurality of internal target drones are all in the selected state, the starting point position information, the end point position information, the drone distance information, the waypoint information, the flight direction information and the route status information collected by each of the peripheral target drones are obtained; The environmental information indicates the distance information between the peripheral target drone and surrounding buildings, and the drone distance information indicates the distance information between each target drone and adjacent target drones.

5. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 4 is characterized in that: The step of inputting the plurality of first flight status information and the plurality of second flight status information into a trained risk prediction model and outputting risk collision information specifically includes: Constructing an initial risk prediction model, obtaining historical inspection task information of historical inspection tasks, and inputting the historical inspection task information into the initial risk prediction model for training to obtain a risk prediction model; Each piece of environmental information and each piece of UAV distance information are input into the risk prediction model, and risk collision information is output.

6. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 4 is characterized in that: The target networking information includes: information transmission direction and mesh structure information; The step of obtaining target networking 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 networking information into a trained route design model, and outputting the routes of each peripheral target UAV and each internal target UAV specifically includes: Constructing an initial route design model, obtaining historical routes, and inputting the historical routes into the initial route design model for training to obtain a route design model; Obtaining information transmission direction and mesh structure information of each target drone in the target drone network; The starting point position information, the end point position information, the waypoint information, the flight direction information, the route status information, the collision risk information, the information transmission direction and the mesh structure information are input into the route design model, and the route of each peripheral target UAV and each internal target UAV is output.

7. The route design method based on obstacle avoidance of unmanned aerial vehicle according to claim 6 is characterized in that: The step of inputting each starting point position information, each end point position information, each waypoint information, each flight direction information, each route status information, the risk collision information, each information transmission direction and mesh structure information into the route design model, and outputting the route of each peripheral target UAV and each internal target UAV, further comprising: generating a plurality of control instructions according to each of the routes; According to all the control instructions, control each of the peripheral target UAVs and each of the internal target UAVs to adjust the flight state; According to the mesh structure information and the information transmission direction, the adjusted flight states of the multiple target drones are sent to the multiple adjacent target drones, so as to control the multiple adjacent target drones to update the drone distance information according to all the flight states.

8. A route planning system based on obstacle avoidance for unmanned aerial vehicles, characterized in that: The route design system based on unmanned aerial vehicle obstacle avoidance includes: A drone connection module is used to obtain information of multiple drones, build a drone network based on all the drone information, obtain inspection task information, and build a target drone network in the drone network based on the inspection task information; An information acquisition module, 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; A risk prediction module, used for inputting a plurality of the first flight status information and a plurality of the second flight status information into a trained risk prediction model, and outputting risk collision information; The route design module is used to obtain the target networking information of the target UAV network, input the multiple first flight state information, the multiple second flight state information, the risk collision information and the target networking information into the trained route design model, and output the route of each peripheral target UAV and each internal target UAV.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a route design program based on drone obstacle avoidance stored in the memory and executable on the processor. When the route design program based on drone obstacle avoidance is executed by the processor, the steps of the route design method based on drone obstacle avoidance as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a route design program based on drone obstacle avoidance, and when the route design program based on drone obstacle avoidance is executed by a processor, the steps of the route design method based on drone obstacle avoidance as described in any one of claims 1-7 are implemented.

Images