Method for Identifying Risks and Levels of Low-Altitude UAV Operations

Abstract

The present invention discloses a method for identifying the operation risks and levels of low-altitude unmanned aerial vehicles (UAVs), which relates to the technical field of UAV operation monitoring. The method includes collecting real-time UAV operation data, setting static alarm areas, and setting dynamic alarm areas according to the operation data; planning the UAV operation routes based on a three-dimensional grid method and predicting the future positions of UAVs according to the UAV operation data; monitoring the positions of UAVs in real time, performing static early warnings according to the static alarm areas, and synchronously calculating the relative distances between UAVs and performing dynamic early warnings according to the dynamic alarm areas; selecting and executing the optimal avoidance actions of UAVs. The present invention combines dynamic alarm areas to warn of UAV operation risks, realizes accurate analysis of UAV operation risks, calculates and executes the optimal avoidance actions, and improves the operation safety of UAVs in complex environments.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle operation monitoring, in particular to a method for identifying the operation risks and levels of low-altitude unmanned aerial vehicles. Background Art

[0002] In recent years, the technology of low-altitude unmanned aerial vehicles (UAVs) has developed rapidly in multiple fields, including logistics distribution, agricultural monitoring, environmental protection, security monitoring, and disaster relief. With the continuous progress of UAV technology and the expansion of its application scope, the operation safety problem of low-altitude UAVs has gradually attracted wide attention. The traditional methods for identifying and avoiding UAV operation risks mainly rely on the monitoring of ground stations and manual operations. Although this method ensures the operation safety of UAVs to a certain extent, due to the limitations of manual reaction speed and judgment ability, it cannot fully cope with complex low-altitude flight environments. In recent years, the technology of identifying and avoiding UAV operation risks based on automation and intelligence has gradually become a research hotspot. Although some achievements have been made, there are still many problems. The existing technologies have problems such as static warning lag, inaccurate path planning, and unreliable dynamic warning in UAV operation risk identification and avoidance, which affect the operation efficiency and safety of UAVs and are difficult to achieve precise obstacle avoidance. Summary of the Invention

[0003] In view of the problems existing in the above-mentioned existing methods for identifying the operation risks and levels of low-altitude UAVs, the present invention is proposed.

[0004] Therefore, the problems to be solved by the present invention are that the existing technologies have problems such as static warning lag, inaccurate path planning, and unreliable dynamic warning in UAV operation risk identification and avoidance, which affect the operation efficiency and safety of UAVs and are difficult to achieve precise obstacle avoidance.

[0005] To solve the above technical problems, the present invention provides the following technical solution: a method for identifying the operation risks and levels of low-altitude UAVs, which includes collecting UAV operation data in real time, setting static alarm areas, and setting dynamic alarm areas according to the operation data; planning the UAV operation route based on a three-dimensional grid method and predicting the future UAV position according to the UAV operation data; monitoring the UAV position in real time, performing static warning according to the static alarm areas, and synchronously calculating the relative distance between UAVs and performing dynamic warning according to the dynamic alarm areas; selecting and executing the optimal avoidance action of the UAV.

[0006] As a preferred solution of the method for identifying the operation risks and levels of low-altitude drones according to the present invention, the steps are as follows: collecting the operation data of the drone in real time, setting static alarm areas, and setting dynamic alarm areas according to the operation data, which means collecting the operation data of the drone in real time through sensors, generating a unique identifier for the drone according to the drone information, and setting the static alarm areas of the drone through the safe operation interval of the drone;

[0007] Define the update time interval of the dynamic alarm area as , and predict the position of the drone after the time interval based on the real-time drone operation data collected: where x(t), y(t), and z(t) are the coordinate positions of the drone at time t, V(t) is the speed of the drone at time t, and are the azimuth angle and pitch angle of the drone at time t respectively, , and are the coordinate positions of the drone after the time interval ;

[0008] Calculate the distance D between the coordinate position of the drone at time t and the coordinate position of the drone after the time interval as the radius of the dynamic alarm area to form a spherical area, and use the spherical area as the dynamic alarm area.

[0009] As a preferred solution of the method for identifying the operation risks and levels of low-altitude drones according to the present invention, the steps are as follows: the drone operation route planning based on the three-dimensional grid method means dividing the airspace into three-dimensional grids, and each grid cell represents a spatial unit;

[0010] Take the center point of the spatial unit as a jump point, the initial spatial unit of the drone as the initial jump point, and the target point spatial unit as the final jump point. Use the JPS algorithm for initial path planning, randomly select path jump points around the initial jump point, and calculate the movement cost g(v, c) from the initial jump point to the path jump point: where g(v) is the movement cost of jump point v. If jump point v is the initial jump point, the movement cost g(v) is 0, and d(v, c) is the distance from jump point v to jump point c;

[0011] Use the Manhattan distance to calculate the estimated cost h(c, z) from the path jump point c to the final jump point z: where x c , y c and z c are the coordinate positions of jump point c, x z , y z and z zIt is the coordinate position of the final jump point z;

[0012] When selecting a path jump point, calculate the comprehensive cost f of the path jump point: Select the path jump point with the minimum comprehensive cost f as the next jump point, and use the YOLO algorithm to identify the obstacles in the spatial unit of the next jump point. Connect the diagonal of the spatial unit to identify the obstacle position. If the obstacle is not on the diagonal of the spatial unit, the path of the UAV in this spatial unit is the diagonal. If the obstacle is on the diagonal of the spatial unit, reselect the jump point from the adjacent spatial units around this spatial unit;

[0013] Repeat selecting the path jump point until reaching the final jump point z, record the selected path jump points, determine the UAV path according to the spatial units of the path jump points, perform path smoothing processing through the Bezier curve, calculate the position of the UAV at each time point according to the UAV running speed, and record the time points and position coordinates.

[0014] As a preferred solution of the method for identifying the operation risks and levels of low-altitude UAVs according to the present invention, wherein: the predicting the future position of the UAV according to the UAV operation data includes,

[0015] Collect the historical operation data of the UAV, construct vectors for the operation data at each time point, and form an initial vector sequence P: Where p(n) is the operation data vector at the nth time point;

[0016] Perform an accumulation transformation on the initial vector sequence P to generate a new sequence P(1): Where p(i) is the operation data vector at the ith time point;

[0017] Perform smoothing processing on the sequence P(1) to generate a background value sequence Z(1): Where P(1) k Is the kth sequence vector in the sequence P(1), P(1) k-1 Is the (k - 1)th sequence vector in the sequence P(1);

[0018] Construct a grey prediction model formula: Where p(t + 1) is the operation data vector at time point t + 1, and a and b are model parameter vectors;

[0019] Establish a differential equation of the grey prediction model: Construct an observation value matrix Y based on the initial vector sequence P, construct a background value matrix Q based on the background value sequence Z(1), and solve the model parameter vector through the least squares method: Where T is the transpose operation;

[0020] The model parameter vector is obtained and substituted into the grey prediction model formula to obtain the operation data vector p(t + 1) at time point t + 1. The position coordinates of the UAV at time point t + 1 are extracted from the operation data vector p(t + 1).

[0021] Define the safety range of the operation data of each UAV according to the UAV design specifications, and calculate the fuzzy score S of the operation data of each UAV u : where o is the operation data of a single type of UAV, including the operation data of all types of UAVs, o max and o min are the upper and lower limits of the safety range of the operation data of a single type of UAV, o t+1 is the value of the operation data of a single type of UAV at time point t + 1, o cen is the middle value of the upper and lower limits of the safety range of the operation data of a single type of UAV;

[0022] Calculate the comprehensive evaluation value at time point t + 1 according to the fuzzy score of the operation data of each UAV: where L(t + 1) is the comprehensive evaluation value at time point t + 1, m is the type of UAV operation data, S u is the fuzzy score of the operation data of the u-th type of UAV;

[0023] Starting from the time point in the historical operation data of the UAV collected, calculate the comprehensive evaluation value of each time point in turn, and calculate the model parameter vector adjustment coefficient r according to the comprehensive evaluation values of t + 1 time points: where L(w) is the comprehensive evaluation value at the w-th time point;

[0024] Use the adjustment coefficient r to adjust the model parameter vectors a and b: where a new and b new are the adjusted model parameter vectors, a old and b old are the model parameter vectors before adjustment. Substitute the adjusted model parameter vectors into the grey prediction model formula to continuously predict the future operation data vector of the UAV, and continuously iterate and adjust the model parameter vectors.

[0025] As a preferred solution of the low-altitude UAV operation risk and level identification method described in the present invention, wherein: the real-time monitoring of the UAV position and the static early warning according to the static alarm area means that the UAV operation data is collected in real time to extract the UAV position coordinates. When it is detected that an intruding UAV enters the static alarm area of our UAV, a static early warning is automatically issued to remind the staff to fly carefully and display the unique identifier of the intruding UAV.

[0026] As a preferred solution of the method for identifying the operation risks and levels of low-altitude drones according to the present invention, wherein: the dynamic early warning of the relative distance between drones by synchronous calculation according to the dynamic alarm area means that when it is detected that an intruding drone invades the static alarm area of our drone, the position coordinates of the intruding drone and the position coordinates of our drone are obtained, and the distance between the intruding drone and our drone is calculated in real time. When the distance between the intruding drone and our drone is less than the radius of the dynamic alarm area, dynamic early warning is automatically carried out to remind the staff of the collision risk, and an avoidance command is generated synchronously.

[0027] As a preferred solution of the method for identifying the operation risks and levels of low-altitude drones according to the present invention, wherein: the selection and execution of the optimal avoidance action of the drone means that after generating the avoidance command, using the current operation data of our drone as the initial node, starting from the initial node, simulating all possible avoidance actions, simulating each avoidance action and using the grey prediction model formula to predict the future position coordinates of the intruding drone and our drone to detect the avoidance effect;

[0028] If there is no overlap in the future position coordinates of the intruding drone and our drone at the same time after the simulation of the avoidance action, it is recorded as a successful avoidance, and the time point and the drone position coordinates after the successful avoidance are obtained, and the distance between the drone position coordinates at this time point and the drone position coordinates at this time point in the planned drone path is calculated, and the avoidance action with the minimum distance is selected as the optimal avoidance action to execute.

[0029] As a preferred solution of the method for identifying the operation risks and levels of low-altitude drones according to the present invention, wherein: the drone operation data includes drone position coordinates, running speed, acceleration, direction angle, pitch angle, and running time series.

[0030] A computer device, comprising: a memory and a processor; the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for identifying the operation risks and levels of low-altitude drones are implemented.

[0031] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for identifying the operation risks and levels of low-altitude drones are implemented.

[0032] The beneficial effects of the present invention are as follows: By collecting drone operation data, setting static alarm areas and dynamic alarm areas, planning drone paths, and predicting the future position coordinates of drones in real time, the present invention realizes the monitoring of the future operation state of drones, combines the dynamic alarm area to warn of drone operation risks, realizes accurate analysis of drone operation risks, and calculates and executes the optimal avoidance action, thereby improving the operation safety of drones in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0034] Figure 1 It is a schematic flowchart of a method for identifying risks and levels of low-altitude UAV operations.

[0035] Figure 2 It is a schematic structural diagram of a method for identifying risks and levels of low-altitude UAV operations. Detailed implementation manners

[0036] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention in conjunction with the accompanying drawings of the specification.

[0037] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0038] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selectively exclusive embodiment from other embodiments. Embodiment

[0039] Referring to Figure 1 and Figure 2 , it is the first embodiment of the present invention. This embodiment provides a method for identifying risks and levels of low-altitude UAV operations. The method for identifying risks and levels of low-altitude UAV operations includes:

[0040] S1. Collect UAV operation data in real time, set a static alarm area, and set a dynamic alarm area according to the operation data;

[0041] Specifically, collecting UAV operation data in real time, setting a static alarm area, and setting a dynamic alarm area according to the operation data means collecting the operation data of the UAV in real time through sensors, generating a unique identifier for the UAV based on the UAV information, and setting the static alarm area of the UAV through the safe operation interval of the UAV.

[0042] Define the update time interval of the dynamic alarm area as Predict the time interval based on the collected real-time UAV operation data The UAV position after: where x(t), y(t), and z(t) are the UAV coordinate positions at time t, V(t) is the UAV speed at time t, and are the azimuth angle and pitch angle of the UAV at time t respectively, 、 and is the time interval The UAV coordinate position after;

[0043] Calculate the distance D between the UAV coordinate position at time t and the UAV coordinate position after the time interval as the radius of the dynamic alarm area to form a spherical area, and use the spherical area as the dynamic alarm area.

[0044] By collecting real-time UAV operation data, the system can always master the latest status information of the UAV, thereby improving the accuracy of early warning and path planning. Real-time data collection can timely reflect the changes in the speed, position, and attitude of the UAV, enabling the system to quickly respond to emergencies. The setting of the static alarm area is based on the safe operation interval of the UAV, which can effectively prevent the UAV from sounding an alarm before entering a dangerous area and taking preventive measures in advance. The fixity of this area ensures basic safety protection. The setting of the dynamic alarm area is based on real-time data to predict the future position of the UAV, which can adjust the early warning range in real time as the UAV moves. The dynamic alarm area is more flexible and accurate than the static alarm area and can more effectively prevent potential collision risks. Reasonably setting the time interval can ensure the prediction accuracy of the dynamic alarm area and avoid early warning errors caused by too long or too short time intervals. Through the unique identifier of the UAV, independent monitoring and management of multiple UAVs can be achieved, avoiding data confusion and improving the management efficiency and accuracy of the system. By calculating the distance D between the UAV position at time t and the UAV position after the time interval as the radius of the dynamic alarm area to form a spherical early warning area. This area can effectively cover the possible future flight range of the UAV and provide a wider range of early warning protection.

[0045] It should also be noted that the UAV operation data includes UAV position coordinates, operating speed, acceleration, direction angle, pitch angle, and operating time series.

[0046] S2. Plan the UAV operation route based on the three-dimensional grid method and predict the future UAV position according to the UAV operation data;

[0047] Specifically, the UAV flight path planning based on the three-dimensional grid method means dividing the airspace into three-dimensional grids, and each grid cell represents a spatial unit;

[0048] Taking the center point of the spatial unit as a jump point, the initial spatial unit of the UAV as the initial jump point, and the target point spatial unit as the final jump point, use the JPS algorithm to perform initial path planning. Randomly select path jump points around the initial jump point, and calculate the movement cost g(v, c) from the initial jump point to the path jump point: Where g(v) is the movement cost of jump point v. If jump point v is the initial jump point, the movement cost g(v) is 0, and d(v, c) is the distance from jump point v to jump point c;

[0049] Use the Manhattan distance to calculate the estimated cost h(c, z) from path jump point c to the final jump point z: Where x c 、y c and z c are the coordinate positions of jump point c, and x z 、y z and z z are the coordinate positions of the final jump point z;

[0050] When selecting a path jump point, calculate the comprehensive cost f of the path jump point: Select the path jump point with the minimum comprehensive cost f as the next jump point, and use the YOLO algorithm to identify the obstacles in the spatial unit of the next jump point. Connect the diagonals of the spatial unit to identify the obstacle positions. If the obstacle is not on the diagonal of the spatial unit, the path of the UAV in this spatial unit is the diagonal. If the obstacle is on the diagonal of the spatial unit, reselect jump points from the adjacent spatial units around this spatial unit;

[0051] Repeat selecting path jump points until reaching the final jump point z. Record the selected path jump points, determine the UAV path according to the spatial units of the path jump points, and perform path smoothing processing through B-spline curves. Calculate the position of the UAV at each time point according to the UAV flight speed, and record the time points and position coordinates.

[0052] The airspace is divided into three-dimensional grids, and each grid cell represents a spatial unit, which can effectively manage and simplify complex flight spaces. Through the grid method, the characteristics of each spatial region can be precisely defined, facilitating path planning and obstacle detection. The JPS algorithm optimizes the traditional A* algorithm through jump point search, reducing the inspection of redundant nodes and improving the efficiency and speed of path search. Using the JPS algorithm, the optimal path of the UAV from the initial jump point to the final jump point can be quickly found. By calculating the movement cost and estimated cost of the jump point, the actual movement cost and estimated cost of the path can be comprehensively considered to ensure that the selected path is both economical and efficient. The Manhattan distance is used for estimated cost calculation, which can quickly estimate the distance from the jump point to the final jump point. Obstacles in the spatial unit where the path jump point is located are identified in real time through the YOLO algorithm, potential flight risks can be accurately detected, and the flight path can be adjusted according to the position of the obstacles. If the obstacle is not on the diagonal of the spatial unit, the UAV can fly along the diagonal. If the obstacle is on the diagonal, a new jump point is reselected. The path is smoothed by a Bezier curve, which can make the flight path of the UAV more natural and smooth, reduce sharp turns and frequent speed changes, and optimize flight performance. The Bezier curve can generate a smooth curve according to the control points to adapt to the actual flight needs of the UAV.

[0053] Furthermore, predicting the future UAV position based on UAV operation data includes

[0054] Collecting the historical operation data of the UAV, constructing vectors for the operation data at each time point, and forming an initial vector sequence P: where p(n) is the operation data vector at the nth time point;

[0055] Performing an accumulation transformation on the initial vector sequence P to generate a new sequence P(1): where p(i) is the operation data vector at the ith time point;

[0056] Performing a smoothing process on the sequence P(1) to generate a background value sequence Z(1): where P(1) k is the kth sequence vector in the sequence P(1), and P(1) k-1 is the (k - 1)th sequence vector in the sequence P(1);

[0057] Constructing the grey prediction model formula: where p(t + 1) is the operation data vector at time point t + 1, and a and b are the model parameter vectors;

[0058] Establishing the differential equation of the grey prediction model: Constructing an observation value matrix Y based on the initial vector sequence P, constructing a background value matrix Q based on the background value sequence Z(1), and solving the model parameter vector by the least squares method where T is the transpose operation;

[0059] Substitute the obtained model parameter vector into the grey prediction model formula to obtain the operation data vector p(t + 1) at time point t + 1, and extract the position coordinates of the UAV at time point t + 1 from the operation data vector p(t + 1);

[0060] Define the safety range of each UAV's operation data according to the UAV design specifications, and calculate the fuzzy score S of each UAV's operation data u : where o is the operation data of a single type of UAV, including the operation data of all types of UAVs, o max and o min are the upper and lower limits of the safety range of the operation data of a single type of UAV, o t+1 is the value of the operation data of a single type of UAV at time point t + 1, o cen is the middle value of the upper and lower limits of the safety range of the operation data of a single type of UAV;

[0061] Calculate the comprehensive evaluation value at time point t + 1 according to the fuzzy score of each UAV's operation data: where L(t + 1) is the comprehensive evaluation value at time point t + 1, m is the type of UAV operation data, S u is the fuzzy score of the u-th type of UAV operation data;

[0062] Calculate the comprehensive evaluation value of each time point in sequence starting from the time point in the collected historical operation data of the UAV, and calculate the model parameter vector adjustment coefficient r according to the comprehensive evaluation values of t + 1 time points: where L(w) is the comprehensive evaluation value at the w-th time point;

[0063] Use the adjustment coefficient r to adjust the model parameter vectors a and b: where a new and b new are the adjusted model parameter vectors, a old and b old are the model parameter vectors before adjustment. Substitute the adjusted model parameter vectors into the grey prediction model formula to continuously predict the future operation data vector of the UAV, and continuously iterate to adjust the model parameter vectors.

[0064] By collecting and organizing the historical operation data of the drone, an initial vector sequence P can be constructed, which can systematically record and analyze the operation status of the drone at different time points, providing basic data for subsequent data processing and model construction. The cumulative transformation can smooth the data, reduce the random fluctuations of the data, highlight the trend of the data, and facilitate subsequent model construction and prediction. This step can enhance the smoothness and predictability of the data, improving the accuracy and reliability of the grey prediction model. The smoothing process can further reduce the fluctuations of the data, improve the stability and continuity of the data, facilitate subsequent model construction and parameter estimation, and can improve the quality of the background value sequence, providing more stable data support for the accurate modeling of the grey prediction model. By establishing the differential equation of the grey prediction model, the data after cumulative transformation can be associated with time to form a mathematical model that can be used to predict future states, providing a mathematical basis for the prediction of drone operation data and ensuring the scientificity and operability of the model. By constructing the observed value matrix and the background value matrix and using the least squares method to solve the model parameters, the parameters of the grey prediction model can be accurately determined, improving the fitting degree and prediction accuracy of the model. By performing fuzzy scoring on the drone operation data, the operation status of the drone can be quantitatively evaluated, facilitating comprehensive evaluation and risk warning, providing quantitative indicators for the evaluation and management of drone operation safety, and improving the scientificity and accuracy of safety evaluation. By calculating the comprehensive evaluation value, the operation status of the drone can be comprehensively evaluated, and the model parameters can be adjusted according to the evaluation results, improving the self-adaptability and prediction accuracy of the model, ensuring that the grey prediction model remains efficient and accurate in a changing environment, and providing technical support for the real-time evaluation and adjustment of the drone operation status. By continuously predicting and iteratively adjusting the model parameters, the operation prediction of the drone can be updated in real time, improving the accuracy and timeliness of the prediction, providing technical support for the real-time monitoring and dynamic adjustment of the drone, and improving the operation efficiency and safety of the drone.

[0065] S3. Real-time monitor the position of the drone, and conduct static early warning according to the static alarm area, and synchronously calculate the relative distance between drones and conduct dynamic early warning according to the dynamic alarm area;

[0066] Specifically, real-time monitoring the position of the drone and conducting static early warning according to the static alarm area means real-time collecting the drone operation data to extract the drone position coordinates. When it is detected that an intruding drone enters the static alarm area of our drone, static early warning is automatically carried out to remind the staff to fly carefully and display the unique identifier of the intruding drone.

[0067] The operation data of the UAV is collected in real time through sensors, and the current position coordinates of the UAV are extracted, which can accurately track the flight state of the UAV. Monitoring the UAV position in real time can ensure the accuracy and safety of the flight path, timely detect and handle abnormal situations. According to the flight environment and mission requirements of the UAV, static alarm areas are preset in advance. When the UAV enters this area, the system can trigger a warning in time to remind the operator or the automatic system to intervene. The setting of the static alarm area can effectively prevent the UAV from colliding with fixed obstacles or other UAVs, improving flight safety. When it is detected that an intruding UAV enters the static alarm area, the system will automatically trigger the static warning mechanism, reminding the staff to pay attention to flight safety and displaying the unique identifier of the intruding UAV. The static warning can issue an alarm at the first time when the UAV enters the dangerous area, preventing potential accidents. By displaying the unique identifier of the intruding UAV, the potential threat source can be clearly identified, facilitating the operator to monitor and handle. The unique identifier can help the operator quickly identify and locate the intruding UAV and take effective avoidance measures.

[0068] Furthermore, synchronously calculating the relative distance between UAVs and conducting dynamic warning according to the dynamic alarm area means that when it is detected that an intruding UAV invades the static alarm area of our UAV, the position coordinates of the intruding UAV and our UAV are obtained, and the distance between the intruding UAV and our UAV is calculated in real time. When the distance between the intruding UAV and our UAV is less than the radius of the dynamic alarm area, a dynamic warning is automatically issued to remind the staff of the collision risk, and an avoidance command is generated synchronously.

[0069] Through sensors and data links, the position coordinates of the intruding UAV and our UAV are obtained in real time, which can accurately track the flight state and relative position of the UAV, providing accurate data support for subsequent distance calculation and dynamic warning. By calculating the relative distance between the intruding UAV and our UAV in real time, the collision risk between the two can be judged in time. When the distance is less than the radius of the set dynamic alarm area, the system can quickly issue a warning. When the intruding UAV enters the static alarm area of our UAV and the relative distance between the two is less than the radius of the dynamic alarm area, the system will automatically conduct a dynamic warning. This warning mechanism can reflect the changes in the flight environment in real time, timely reminding the operator of the potential collision risk. While issuing the dynamic warning, the system will automatically generate an avoidance command to guide the UAV to change its flight path and avoid the potential collision risk. The automatic generation and execution of the avoidance command can reduce the delay of manual operation, improving the reaction speed and safety of the UAV.

[0070] S4. Select the optimal avoidance action of the UAV and execute it;

[0071] Specifically, selecting and executing the optimal avoidance action of the UAV means that after generating the avoidance command, using the current operation data of our UAV as the initial node, starting from the initial node, simulating all possible avoidance actions, simulating each avoidance action and using the grey prediction model formula to predict the future position coordinates of the intruding UAV and our UAV to detect the avoidance effect;

[0072] If there is no overlap in the future position coordinates of the intruding UAV and our UAV at the same time after the avoidance action simulation, it is recorded as a successful avoidance, and the time point and UAV position coordinates after the successful avoidance are obtained. Calculate the distance between the UAV position coordinates at this time point and the UAV position coordinates at this time point in the planned UAV path, and select the avoidance action with the smallest distance as the optimal avoidance action to execute.

[0073] After detecting the potential collision risk, the system automatically generates an avoidance command. The avoidance command includes a series of possible avoidance actions, such as changing speed, heading, and altitude, etc. These commands are generated based on the current flight state of the UAV and the surrounding environment data. Starting from the initial node, simulate all possible avoidance actions, test the effect of each avoidance action through simulation. During the simulation process, use the grey prediction model to predict the future position coordinates of the intruding UAV and our UAV, evaluate the effectiveness of the avoidance action. Through the grey prediction model, predict the future position coordinates of the intruding UAV and our UAV after the avoidance action. This model can make effective predictions under incomplete data and provide highly accurate future position data. During the simulation process, detect whether the position coordinates of the intruding UAV and our UAV overlap at the same future time point. If there is no overlap, it is recorded as a successful avoidance, and the time point and UAV position coordinates after the successful avoidance are obtained. Calculate the distance between the UAV position coordinates at the time point after the successful avoidance and the position coordinates at this time point in the planned path, and select the avoidance action with the smallest distance as the optimal avoidance action to execute. The optimal avoidance action can not only effectively avoid the collision risk, but also make the UAV as close as possible to the original planned path and reduce the flight deviation. Embodiment

[0074] When the above-described functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0075] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0076] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), fiber optic device, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as necessary, and then storing it in a computer memory.

[0077] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0078] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. Method for identifying operation risks and levels of low-altitude unmanned aerial vehicles, characterized in that: Including, Collecting real-time operation data of the UAV, setting static alarm areas, and setting dynamic alarm areas according to the operation data; Planning the UAV operation route based on the three-dimensional grid method and predicting the future UAV positions according to the UAV operation data; Monitoring the UAV positions in real time, giving static early warnings according to the static alarm areas, and synchronously calculating the relative distances between UAVs and giving dynamic early warnings according to the dynamic alarm areas; Selecting and executing the optimal avoidance actions of the UAV; The real-time collection of UAV operation data, setting static alarm areas, and setting dynamic alarm areas according to the operation data means that the operation data of the UAV is collected in real time through sensors, and the unique identifier of the UAV is generated according to the UAV information, and the static alarm area of the UAV is set through the safe operation interval of the UAV; Define the update time interval of the dynamic alarm area as , and predict the UAV position after the time interval based on the collected real-time UAV operation data: where x(t), y(t), and z(t) are the UAV coordinate positions at time t, and V(t) is the UAV speed at time t, and are the azimuth angle and pitch angle of the UAV at time t respectively, , and are the UAV coordinate positions after the time interval ; Calculate the time t and the time interval After that, use the distance D of the UAV coordinate position as the radius of the dynamic alert area to form a spherical area, and take the spherical area as the dynamic alert area; The prediction of the future UAV positions according to the UAV operation data includes, Collect the historical operation data of the drone, construct vectors from the operation data at each time point, and form an initial vector sequence P: where p(n) is the operation data vector at the nth time point; Accumulate and transform the initial vector sequence P to generate a new sequence P(1): where p(i) is the operation data vector at the i-th time point; Smoothing the sequence P(1) to generate the background value sequence Z(1): where P(1) k is the k-th sequence vector in the sequence P(1), and P(1) k-1 is the (k - 1)-th sequence vector in the sequence P(1); Build the grey prediction model formula: Where p(t + 1) is the operation data vector at time point t + 1, and a and b are the model parameter vectors; Establish the differential equation of the grey prediction model: Construct the observation value matrix Y based on the initial vector sequence P, construct the background value matrix Q based on the background value sequence Z(1), and solve the model parameter vector by the least squares method: where T is the transpose operation; Obtaining the model parameter vector and substituting it into the grey prediction model formula to get the operation data vector p(t + 1) at time point t + 1, and extracting the position coordinates of the UAV at time point t + 1 from the operation data vector p(t + 1); Define the safety range of each UAV operation data according to the UAV design specifications, and calculate the fuzzy score S of each UAV operation data u : where o is the operation data of a single type of UAV, including the operation data of all types of UAVs, o max and o min are the upper and lower limits of the safety range of the operation data of a single type of UAV, o t+1 is the value of the operation data of a single type of UAV at time point t + 1, o cen is the middle value of the upper and lower limits of the safety range of the operation data of a single type of UAV; Calculate the comprehensive evaluation value at time point t + 1 based on the fuzzy scores of each type of UAV operation data: where L(t + 1) is the comprehensive evaluation value at time point t + 1, m is the type of UAV operation data, and S u is the fuzzy score of the u-th type of UAV operation data; Starting from the time point in the historical operation data of the drone collection, calculate the comprehensive evaluation value of each time point in sequence, and calculate the model parameter vector adjustment coefficient r according to the comprehensive evaluation values of t + 1 time points: where L(w) is the comprehensive evaluation value at the w-th time point; Adjust the model parameter vectors a and b using the adjustment coefficient r: where a new and b new are the adjusted model parameter vectors, a old and b old are the model parameter vectors before adjustment. Substitute the adjusted model parameter vectors into the grey prediction model formula to continuously predict the future operation data vector of the UAV, and continuously iterate and adjust the model parameter vectors; The selection and execution of the optimal avoidance actions of the UAV means that after generating an avoidance command, using the current operation data of our UAV as the initial node, simulating all possible avoidance actions starting from the initial node, simulating each avoidance action and using the grey prediction model formula to predict the future position coordinates of the intruding UAV and our UAV to detect the avoidance effect; If there is no overlap in the future position coordinates of the intruding UAV and our UAV at the same time after the simulation of the avoidance actions, it is recorded as successful avoidance, and the time point and the UAV position coordinates after successful avoidance are obtained, calculating the distance between the UAV position coordinates at this time point and the UAV position coordinates at this time point in the planned UAV path, and selecting the avoidance action with the smallest distance as the optimal avoidance action to execute; The UAV operation data includes UAV position coordinates, operation speed, acceleration, direction angle, pitch angle, and operation time series.

2. The method for identifying the operation risks and levels of low-altitude unmanned aerial vehicles according to claim 1, characterized in that: The planning of the UAV operation route based on the three-dimensional grid method means dividing the airspace into three-dimensional grids, and each grid cell represents a spatial unit; Taking the center point of the spatial unit as the jump point, the initial spatial unit of the UAV as the initial jump point, and the target point spatial unit as the final jump point, the JPS algorithm is used for initial path planning. Randomly select path jump points around the initial jump point, and calculate the movement cost g(v, c) from the initial jump point to the path jump point: Where g(v) is the movement cost of jump point v. If jump point v is the initial jump point, the movement cost g(v) is 0, and d(v, c) is the distance from jump point v to jump point c; Use the Manhattan distance to calculate the estimated cost h(c, z) from path hop point c to the final hop point z: where x c , y c and z c are the coordinate positions of hop point c, and x z , y z and z z are the coordinate positions of the final hop point z; When selecting a path hop point, calculate the comprehensive cost f of the path hop point: Select the path hop point with the minimum comprehensive cost f as the next hop point, and use the YOLO algorithm to identify the obstacles in the spatial unit of the next hop point. Connect the diagonal of the spatial unit to identify the position of the obstacles. If the obstacle is not on the diagonal of the spatial unit, the path of the UAV in this spatial unit is the diagonal. If the obstacle is on the diagonal of the spatial unit, reselect the hop point from the adjacent spatial units around this spatial unit; Repeatedly selecting path jump points until the final jump point z is reached, recording the selected path jump points and determining the UAV path according to the spatial units of the path jump points, and performing path smoothing through a Bezier curve, calculating the position of the UAV at each time point according to the UAV operation speed, and recording the time point and the position coordinates.

3. The method for identifying the operation risks and levels of low-altitude unmanned aerial vehicles according to claim 2, characterized in that: The real-time monitoring of the UAV positions and giving static early warnings according to the static alarm areas means collecting the UAV operation data in real time to extract the UAV position coordinates, automatically giving a static early warning when it is detected that an intruding UAV enters the static alarm area of our UAV, reminding the staff to fly carefully, and displaying the unique identifier of the intruding UAV.

4. The method for identifying the operation risks and levels of low-altitude unmanned aerial vehicles as claimed in claim 3, wherein: The dynamic early warning of the relative distance between the synchronized computing UAVs according to the dynamic alert area means that when an intruding UAV is detected to invade the static alert area of our UAVs, the position coordinates of the intruding UAV and the position coordinates of our UAVs are obtained, and the distance between the intruding UAV and our UAVs is calculated in real time. When the distance between the intruding UAV and our UAVs is less than the radius of the dynamic alert area, dynamic early warning is automatically carried out to remind the staff of the collision risk, and an avoidance command is generated synchronously.

5. A computer device, comprising: A memory and a processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the low-altitude UAV operation risk and level identification method according to any one of claims 1 to 4 are realized.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the low-altitude UAV operation risk and level identification method according to any one of claims 1 to 4 are realized.

Images