An unmanned aerial vehicle-based low-altitude digital wisdom management platform

Abstract

The application discloses a low-altitude digital intelligent management platform based on a UAV, belongs to the technical field of UAV management, and comprises a flight route autonomous planning module, a flight speed regulation module, a safety protection module, a network switching module and a user interaction module.The flight route autonomous planning module plans an optimal flight route; the flight speed regulation module dynamically regulates flight speed according to environmental information and geographic information; the safety protection module protects the UAV management platform and reduces intrusion; the network switching module has two working modes, namely, a traditional wireless network mode and a Mesh self-organizing network mode; and the user interaction module realizes man-machine interaction functions.The application can automatically plan a flight route to improve flight efficiency, and dynamically and accurately adjusts the speed of the UAV according to geographic environment conditions, self-operation conditions and wind speed and other factors during UAV flight, so that the UAV can normally perform a task and flight quality is ensured.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of unmanned aerial vehicle management, and particularly relates to a low-altitude digital intelligent management platform based on an unmanned aerial vehicle. BACKGROUND

[0002] With the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicles have been widely applied in many fields such as surveying, inspection, logistics, agriculture and emergency rescue due to their advantages of high flexibility, low cost and rapid deployment.

[0003] However, unmanned aerial vehicles face many challenges in large-scale and complex scene applications. For example, when performing a flight task, an unmanned aerial vehicle generally flies at a fixed speed along a route. Since the route is generally set by humans, the unmanned aerial vehicle cannot autonomously set the optimal route, and the speed cannot be autonomously adjusted, thereby affecting the task execution efficiency. In addition, since the unmanned aerial vehicle performs tasks in a collaborative manner, the safety protection measures are not in place, the relevant information is easily stolen by intrusion, and the unmanned aerial vehicle is also prone to malfunction, causing losses. SUMMARY

[0004] The purpose of the present application is to provide a low-altitude digital intelligent management platform based on an unmanned aerial vehicle to solve the problems in the background art.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] A low-altitude digital intelligent management platform based on an unmanned aerial vehicle, the management platform comprising:

[0007] a flight route autonomous planning module for planning an optimal flight route according to information of a work area;

[0008] a flight speed regulation module for dynamically regulating the flight speed according to environmental information and geographic information of the work area;

[0009] a safety protection module for protecting the unmanned aerial vehicle management platform from intrusion;

[0010] a network switching module having two working modes, a traditional wireless network mode and a Mesh self-organizing network mode, and automatically switching to the Mesh self-organizing network mode when the signal of the traditional network mode is weak;

[0011] a user interaction module for realizing human-computer interaction function.

[0012] Further, the working method of the flight route autonomous planning module is:

[0013] Obtaining three-dimensional map information of the working area, and obtaining a plane profile of the working area after removing the no-fly area;

[0014] Determining an initial position and a reaching position of the UAV flight, and finding a position of a region with the shortest flight distance in the plane profile;

[0015] Based on the three-dimensional map information, proportionally dividing the region with the shortest flight distance into multiple small segments, and judging whether there is an obstacle or a disturbing building in each small segment based on the three-dimensional map information, if not, determining the small segment as a flight segment;

[0016] If yes, obtaining blank areas on both sides of the flight direction of the small segment, extending a straight line L from the center point of the small segment to both sides, obtaining center points of a previous segment and a next segment of the small segment, connecting the center points of the previous segment and the next segment to the straight line L, finding a shortest connection line without affecting the flight condition of the UAV, and determining the shortest connection line as a new flight segment of the UAV.

[0017] Further, the route autonomous planning module is further provided with an automatic obstacle avoidance unit, which captures a moving obstacle in front of the UAV in real time when the UAV flies on the planned path, and judges whether there is a collision possibility according to the moving speed and direction, and if yes, reduces the flight speed or adjusts the flight route to avoid the obstacle, and returns to the planned path automatically after the obstacle avoidance is completed.

[0018] Further, the flight speed regulation module has a working method as follows:

[0019] Real-time acquisition of the wind speed and direction of the UAV in flight, when it is a tailwind direction, the flight speed of the UAV is adjusted to V

[0020] V - ;

[0021] When it is a headwind direction, the flight speed of the UAV is adjusted to V

[0022] V + ;

[0023] In the formula, V0 is the current flight speed, WS is the current wind speed, θ is the included angle between the wind direction and the flight direction, FZ is the environmental complexity of the flight region, FZ0 is the comparison value of the environmental complexity, Tsf is the self-heating temperature of the UAV, Tsf0 is the comparison value of the heating temperature, ε v is a speed conversion coefficient, and a1 and a2 are weight coefficients.

[0024] Further, the network switching module has a working method as follows:

[0025] The UAV communicates in a traditional wireless network mode during work, and acquires network quality parameters of the communication network in real time during the communication, and compares the network quality parameters with respective switching trigger thresholds, and when the switching trigger thresholds are exceeded, the traditional wireless network mode is switched to a Mesh self-organizing network mode for communication;

[0026] Meanwhile, when all the network quality parameters do not exceed the respective switching trigger thresholds, the difference between each network quality parameter and the respective switching trigger threshold is acquired, the difference is normalized and weighted by giving respective weights, and an overall margin coefficient R is obtained, and the margin coefficient is compared with a set margin coefficient threshold R s of the switching trigger, and when R S , the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication.

[0027] Further, the working of the network switching module further includes:

[0028] When the network mode switching is not triggered, the margin coefficient is continuously acquired, a margin coefficient change function R(t) is constructed, and a network state quantitative index value K is calculated through a mathematical expression When K s , it is determined that the quality of the traditional wireless network is good, and when K s , the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication, and K s is a set network quality judgment threshold.

[0029] Further, the working method of the security protection module is:

[0030] A quantum random number fingerprint is generated for each UAV, identity verification is realized based on quantum key distribution technology, and the secret key is updated every five minutes;

[0031] After the system is logged in, according to daily login habits, the data download traffic change rate Pr d and the browsing volume change rate Pr l during login are acquired, and the network signal strength G during login is acquired, and a security quantitative index value B is calculated through a formula

[0032] When B s , it is determined that the platform has a security risk, B s is a set security risk judgment threshold, is a standard data download traffic change rate, for the rate of change of the pageview metric, maxG is the maximum signal strength, minG is the minimum signal strength, DeltaG is the signal strength ratio value, DeltaT is the time difference between the maximum signal strength and the minimum signal strength, sigma G for the standard deviation of the signal strength.

[0033] The beneficial effects of the present application are:

[0034] The present application can automatically plan the flight route to improve flight efficiency, and in the unmanned aerial vehicle flight, according to the geographical environment, the running condition and the wind speed and other factors are comprehensively analyzed, so as to dynamically and accurately adjust the speed of the unmanned aerial vehicle, ensure that the unmanned aerial vehicle can normally execute the task, and ensure the flight quality.

[0035] The present application verifies the identity of the logged-in personnel, monitors the operation of the logged-in personnel, judges whether the platform has a security risk according to the factors such as flow change, pageview change and signal strength change, and thus timely corresponding processing is performed, the safety performance is greatly improved, and the occurrence of data theft is reduced.

[0036] Of course, any product implementing the present application does not necessarily need to achieve all the advantages described above at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0038] Figure 1 for the module block diagram of the intelligent management platform of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0040] In one embodiment, a low-altitude digital intelligent management platform based on unmanned aerial vehicle is disclosed, as shown in Figure 1 The management platform comprises:

[0041] The flight route autonomous planning module is used for planning the best flight route according to the information of the working area;

[0042] The flight speed regulation module is used for dynamically regulating the flight speed according to the environmental information and the geographic information of the working area.

[0043] The security protection module is used for protecting the unmanned aerial vehicle management platform from being intruded.

[0044] The network switching module has two working modes, i.e., a traditional wireless network mode and a Mesh self-organizing network mode.

[0045] The user interaction module realizes the man-machine interaction function.

[0046] According to the above technical scheme, the flight route planning module plans the optimal flight route according to the relevant information of the working area of the unmanned aerial vehicle, including the geographic information and the environmental information, and can automatically avoid obstacles according to whether there is a moving obstacle in the planned route during flight, so that the flight efficiency is effectively improved, and the flight safety is ensured during flight. Meanwhile, the flight speed regulation module dynamically regulates the flight speed according to the environmental information and the geographic information of the working area, so that the unmanned aerial vehicle can always fly at a balanced speed, thereby ensuring the quality of the flight task. In addition, in order to ensure the safety performance of the unmanned aerial vehicle management platform, the security protection module is provided to verify the identity of the logged-in personnel, and to monitor the operation of the logged-in personnel. According to the factors such as the traffic variation, the browsing volume variation and the signal strength variation, it is judged whether the platform has a security risk, so that corresponding processing is performed in time to reduce the occurrence of data theft. The network switching module has two working modes, i.e., a traditional wireless network mode and a Mesh self-organizing network mode. The user interaction module realizes the man-machine interaction function, and facilitates the user to operate and manage the management platform.

[0047] The working method of the flight route planning module is as follows: obtaining the three-dimensional map information of the working area, obtaining the plane contour of the working area after removing the no-fly area;

[0048] Determining the initial position and the arrival position of the unmanned aerial vehicle flight, and finding the region position with the shortest flight distance in the plane contour;

[0049] Based on the three-dimensional map information, the region with the shortest flight distance is proportionally divided into multiple segments, based on the three-dimensional map information, it is judged whether there is an obstacle or a disturbing building in each segment, if not, the segment is determined as a flight segment;

[0050] If there is, the blank area on both sides of the flight direction of the segment is obtained, a straight line L is drawn from the center point of the segment to both sides, the center points of the previous and next segments are obtained, the center points of the previous and next segments are connected to the straight line L, the shortest connection is found without affecting the flight condition of the unmanned aerial vehicle, and a new flight segment of the unmanned aerial vehicle is determined;

[0051] The route autonomous planning module also has an automatic obstacle avoidance unit, which captures the moving obstacles in front of the unmanned aerial vehicle in real time when the unmanned aerial vehicle flies on the planned path, and judges whether there is a collision possibility according to the moving speed and direction, if there is, the flight speed is reduced or the flight route is adjusted to avoid obstacles, and after the obstacle avoidance is completed, the unmanned aerial vehicle returns to the planned path automatically.

[0052] The above technical solution provides a specific working method of the route autonomous planning module, first, the three-dimensional map information of the working area is obtained, after removing the no-fly area, the plane contour of the working area is obtained, the initial position and the arrival position of the unmanned aerial vehicle are determined, and the position of the region with the shortest flight distance is found in the plane contour, which can remove the no-fly area while reducing the flight path to ensure flight efficiency. At the same time, there may be obstacles in the shortest flight distance to block the flight of the unmanned aerial vehicle, therefore, based on the three-dimensional map information, the region with the shortest flight distance is proportionally divided into multiple segments, based on the three-dimensional map information, it is judged whether there is an obstacle or a disturbing building in each segment, if not, the segment is determined as a flight segment, if there is, the blank area on both sides of the flight direction of the segment is obtained, a straight line L is drawn from the center point of the segment to both sides, the center points of the previous and next segments are obtained, the center points of the previous and next segments are connected to the straight line L, the shortest connection is found without affecting the flight condition of the unmanned aerial vehicle, and a new flight segment of the unmanned aerial vehicle is determined, which can automatically avoid obstacles and areas affecting the flight of the unmanned aerial vehicle, while ensuring the shortest flight path, thereby ensuring the entire flight efficiency. The route autonomous planning module also has an automatic obstacle avoidance unit, which captures the moving obstacles in front of the unmanned aerial vehicle in real time when the unmanned aerial vehicle flies on the planned path, and judges whether there is a collision possibility according to the moving speed and direction, if there is, the flight speed is reduced or the flight route is adjusted to avoid obstacles, and after the obstacle avoidance is completed, the unmanned aerial vehicle returns to the planned path automatically, which can ensure the safety of the unmanned aerial vehicle during flight.

[0053] The working method of the flight speed control module is to obtain the wind speed and direction of the unmanned aerial vehicle in real time, when it is downwind, the flight speed is calculated by the formula

[0054] adjusting the flight speed of the unmanned aerial vehicle to V - ;

[0055] When it is a headwind direction, at this time, the flight speed of the unmanned aerial vehicle is adjusted to V

[0056] adjusting the flight speed of the unmanned aerial vehicle to V + ;

[0057] In the formula, V0 is the current flight speed, WS is the current wind speed, θ is the angle between the wind direction and the flight direction, FZ is the environmental complexity of the flight area, FZ0 is the comparison value of the environmental complexity, Tsf is the self-heating temperature of the unmanned aerial vehicle, Tsf0 is the comparison value of the heating temperature, ε v is a speed conversion coefficient, a1 and a2 are weight coefficients.

[0058] The above scheme provides a specific working method of the flight speed regulation module. Since the unmanned aerial vehicle generally needs to maintain a uniform speed during flight to ensure flight quality, but is affected by environmental factors, for example, under the condition of headwind, the actual flight speed will decrease if the original speed is used, and under the condition of tailwind, the actual flight speed will increase if the original speed is used, which is not conducive to flight quality. Therefore, the wind speed and the wind direction of the unmanned aerial vehicle during flight are obtained in real time, when it is a tailwind direction, at this time, the flight speed of the unmanned aerial vehicle is adjusted to V

[0059] adjusting the flight speed of the unmanned aerial vehicle to V - , when it is a headwind direction, at this time, the flight speed of the unmanned aerial vehicle is adjusted to V

[0060] adjusting the flight speed of the unmanned aerial vehicle to V + ; In the formula, V0 is the current flight speed, WS is the current wind speed, θ is the angle between the wind direction and the flight direction, FZ is the environmental complexity of the flight area, which is autonomously determined according to the geographical environment of the flight area, FZ0 is the comparison value of the environmental complexity, Tsf is the self-heating temperature of the unmanned aerial vehicle, Tsf0 is the comparison value of the heating temperature, ε v is a speed conversion coefficient, which is determined according to experimental data, a1 and a2 are weight coefficients. It can be seen from the formula V - that when it is a tailwind, the greater the wind speed, the more the corresponding speed is reduced. Similarly, the flight speed of the unmanned aerial vehicle is also related to the environmental complexity of the area and the self-heating temperature, for example, when the environment is more complex, the speed needs to be slower to ensure flight safety, and the higher the self-heating temperature, the greater the power consumption, so the speed also needs to be slower to ensure flight safety. Therefore, the environmental complexity of the flight area and the self-heating temperature of the unmanned aerial vehicle are obtained and brought into the formula V - , so as to automatically and accurately adjust the flight speed of the unmanned aerial vehicle. Similarly, when it is a headwind direction, at this time, the flight speed of the unmanned aerial vehicle is adjusted to V

[0061] Adjusting the unmanned aerial vehicle flight speed to V + In this way, the unmanned aerial vehicle speed can be dynamically adjusted according to the geographical environment, the self running condition and the wind speed and other factors during the unmanned aerial vehicle flight, so as to ensure that the unmanned aerial vehicle can normally perform the task and ensure the flight quality.

[0062] The network switching module working method is that the unmanned aerial vehicle communicates in the traditional wireless network mode during the work, and the network quality parameters of the communication network are obtained in real time during the period, and compared with the respective switching trigger threshold value, when the switching trigger threshold value is exceeded, the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication;

[0063] At the same time, when all the network quality parameters do not exceed the respective switching trigger threshold value, the difference between the respective network quality parameters and the respective switching trigger threshold value is obtained, and after the difference is normalized, the respective weight is given for weighting, the overall margin coefficient R is obtained, and the margin coefficient and the set switching trigger margin coefficient threshold R s are compared, when R s

[0064] The network switching module also includes that when the network mode switching is not triggered, the margin coefficient is continuously obtained at this time, the margin coefficient time-varying function R(t) is constructed, and the network state quantitative index value K is calculated through the mathematical expression When K s , it is judged that the quality of the traditional wireless network is good, and when K s , the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication, and K s is the set network quality judgment threshold value.

[0065] ​The technical solution provides a specific working method of the network switching module. The network switching module has two working modes, a traditional wireless network mode and a Mesh self-organizing network mode. The unmanned aerial vehicle communicates in the traditional wireless network mode during work, and real-time network quality parameters of the communication network are acquired and compared with respective switching trigger thresholds. When the switching trigger thresholds are exceeded, it indicates that the traditional network may be abnormal at this time. In order to ensure the continuity of communication, the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication. Meanwhile, when all the network quality parameters do not exceed the respective switching trigger thresholds, the difference between each network quality parameter and the respective switching trigger threshold is acquired. After normalization processing of the difference, respective weights are given for weighting to obtain an overall margin coefficient R. The smaller the margin coefficient R is, the closer the network quality parameters are to the threshold, and the greater the possibility of abnormality is. The margin coefficient is compared with the set switching trigger margin coefficient threshold R s . When R s , the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication. This way can further detect the quality of network communication, so as to switch in time. The working of the network switching module also includes: when the network mode switching is not triggered, the margin coefficient is continuously acquired, a margin coefficient change function R(t) with time is constructed, and a network state quantitative index value K is calculated through a mathematical expression . When K s , it is judged that the quality of the traditional wireless network is good. When K≤K s , the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication. K s is a set network quality judgment threshold. This way can monitor the network quality in real time when no abnormality occurs, analyze the potential abnormality of the network, and switch in time to ensure normal network communication. The greater the margin coefficient is, the better the network state is. The margin coefficient is continuously acquired, the margin coefficient change function R(t) with time is constructed, and a network state quantitative index value K is calculated through a mathematical expression . The greater the value of K is, the greater the overall margin in the detection period is, and the better the network quality is. On the contrary, the smaller the value of K is, the smaller the overall margin in the detection period is. At this time, although the network does not show abnormality, the possibility of potential abnormality is great. In order to ensure the continuity of communication quality, the traditional wireless network mode is switched to the Mesh self-organizing network mode for communication in advance.

[0066] The working method of the security protection module is: a quantum random number fingerprint is generated for each unmanned aerial vehicle, identity verification is realized based on quantum key distribution technology, and the secret key is updated every five minutes.

[0067] After the system is logged in, the data download flow rate Pr during login is obtained according to daily login habits d and the browsing volume rate Pr l Meanwhile, the network signal strength G during login is obtained, and the formula

[0068] The security quantitative index value B is calculated, and when B>B s , it is judged that the platform has a security risk, and B s is the set security risk judgment threshold value is the data download flow standard rate is the browsing volume standard rate, maxG is the maximum signal strength, minG is the minimum signal strength, ΔG is the signal strength comparison value, Δt is the time difference from the maximum signal strength to the minimum signal strength, and σ G is the standard deviation of the signal strength.

[0069] The technical solution provides a specific working method of the security protection module. First, a quantum random number fingerprint is generated for each unmanned aerial vehicle, identity verification is realized based on quantum key distribution technology, and the secret key is updated every five minutes. The secret key technology can greatly improve the accuracy of identity verification, thereby reducing the occurrence of platform intrusion. Meanwhile, after the system of the management platform is logged in, the data download flow rate Pr during login is obtained according to daily login habits d and the browsing volume rate Pr l Meanwhile, the network signal strength G during login is obtained, and the formula

[0070] The security quantitative index value B is calculated, and in the formula, B is the data download flow standard rate is the browsing volume standard rate, maxG is the maximum signal strength, minG is the minimum signal strength, ΔG is the signal strength comparison value, Δt is the time difference from the maximum signal strength to the minimum signal strength, and σ G is the standard deviation of the signal strength. As can be seen from the formula, when the data download flow rate during login and the browsing volume rate are obviously more than the standard value, the greater the security risk of the login user, which may be the login after the login information is invaded. Similarly, if the communication signal strength between the unmanned aerial vehicle and the ground station suddenly decreases or abnormally fluctuates, it may indicate that there is electromagnetic interference or signal hijacking, and the possibility of security risk is also greater. Therefore, the formula

[0071] The security quantitative index value B is calculated, and in the formula, B s is compared with the set security risk judgment threshold value B sIf the signal intensity is less than the threshold value, it is judged that the platform has a security risk. By verifying the identity of the logged-in personnel and monitoring the operation of the logged-in personnel, whether the platform has a security risk is judged according to factors such as flow change, browsing volume change and signal intensity change, so that corresponding processing is performed in time, the security performance is greatly improved, and the occurrence of data theft is reduced.

[0072] It should be noted that each parameter in the above calculation formula is a dimensionless calculation of the parameter after the unit is selected and the parameter is processed, and the processing method can be realized by existing technologies such as standardization processing, normalization processing and the like, which will not be described here.

[0073] The above is only an example and description of the concept of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or replace them with similar ways, as long as they do not deviate from the concept of the present application or exceed the scope defined by the present application.

Claims

1. A low-altitude digital intelligent management platform based on unmanned aerial vehicles (UAVs), characterized in that, The management platform includes: The autonomous flight route planning module is used to plan the optimal flight route based on information about the work area. A flight speed control module, which is used to dynamically control the flight speed based on environmental and geographical information of the work area; A security protection module is used to protect the drone management platform and prevent it from being hacked. The network switching module has two working modes: traditional wireless network mode and Mesh self-organizing network mode. When the signal is weak in traditional network mode, it automatically switches to Mesh self-organizing network mode. User interaction module, which implements human-computer interaction functions; The flight speed control module works by acquiring the wind speed and direction of the drone in real time during flight. When the wind is downwind, the speed is adjusted using a formula. Adjust the drone's flight speed to ; When the wind direction is against the wind, the formula is used. Adjust the drone's flight speed to ; In the formula, At the current flight speed, The current wind speed, The angle between the wind direction and the flight direction. Due to the environmental complexity of the flight area, This is a comparison value for environmental complexity. The temperature of the drone itself. This is a comparison value of heating temperature. The speed conversion coefficient, as well as These are the weighting coefficients; The security protection module works by generating a quantum random number fingerprint for each drone, using quantum key distribution technology to verify identity, and updating the key every five minutes. After the system is logged in, based on daily login habits, the data download traffic change rate during the login period is obtained. and the rate of change in page views Simultaneously, the network signal strength G during the login period is obtained, and the formula is used to obtain the signal strength G. Calculate the safety quantitative index value ,when If so, it is determined that the platform poses a security risk. To set a threshold for assessing security risks, The standard rate of change for data download traffic. The rate of change of pageviews. For maximum signal strength, For minimum signal strength, This is the signal strength comparison value. The time difference between the maximum and minimum signal strength. This represents the standard deviation of the signal strength.

2. The low-altitude digital intelligent management platform based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The working method of the autonomous route planning module is as follows: Obtain the 3D map information of the work area, and after removing the no-fly zone, obtain the planar outline of the work area; Determine the initial and final positions of the drone's flight, and locate the area with the shortest flight distance within the planar profile; Based on 3D map information, the area with the shortest flight distance is divided into multiple segments proportionally. Based on 3D map information, it is determined whether there are obstacles or interfering buildings that affect flight in each segment. If not, the segment is determined as a flight segment. If so, obtain the blank areas on both sides of the flight direction of the small segment, draw straight lines L extending from the center point of the small segment to both sides, and at the same time obtain the center points of the previous and next segments of the small segment. Connect the center points of the previous and next segments together to the straight line L. Without affecting the flight status of the drone, find the shortest connection line and determine it as the new flight segment of the drone.

3. The low-altitude digital intelligent management platform based on unmanned aerial vehicles (UAVs) according to claim 2, characterized in that, The autonomous route planning module is also equipped with an automatic obstacle avoidance unit. When the UAV is flying on the planned path, it can capture moving obstacles in front of it in real time and judge whether there is a possibility of collision based on the moving speed and direction. If there is, it will reduce the flight speed or adjust the flight route to avoid the obstacle. After the obstacle avoidance is completed, it will automatically return to the planned path.

4. The low-altitude digital intelligent management platform based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The network switching module operates as follows: When the drone is working, it communicates in the traditional wireless network mode. During this time, it acquires various network quality parameters of the communication network in real time and compares them with their respective switching trigger thresholds. When the switching trigger threshold is exceeded, the traditional wireless network mode is switched to Mesh self-organizing network mode for communication. Simultaneously, when all network quality parameters are within their respective handover trigger thresholds, the differences between each network quality parameter and its respective handover trigger threshold are obtained. These differences are normalized, assigned weights, and weighted to obtain the overall margin coefficient R. This margin coefficient is then compared with the set handover trigger margin threshold. When a comparison is performed, When switching from traditional wireless network mode to Mesh self-organizing network mode for communication.

5. A low-altitude digital intelligent management platform based on unmanned aerial vehicles (UAVs) according to claim 4, characterized in that, The operation of the network switching module also includes: When no network mode switch is triggered, the margin coefficient is continuously acquired, and a function of the margin coefficient changing over time is constructed. Through mathematical expressions Calculate the network state quantification index value ,when When the traditional wireless network is of good quality, it is judged to be of good quality. When necessary, the traditional wireless network mode will be switched to the Mesh self-organizing network mode for communication. The threshold for judging network quality is set.

Images