Unmanned aerial vehicle low-altitude isolation area traffic management system

Abstract

The invention discloses an unmanned aerial vehicle low-altitude isolation area traffic management system, which relates to the technical field of monitoring analysis and comprises a monitoring module, an identification module, a control module and an early warning module. According to the unmanned aerial vehicle low-altitude isolation area traffic management system, whether the unmanned aerial vehicle violates the flight regulation of the isolation area is detected by analyzing the monitored flight path and behavior of the unmanned aerial vehicle through a violation detection algorithm, real-time monitoring and management of the unmanned aerial vehicle low-altitude isolation area can be realized, and the air traffic safety is improved; various advanced technologies, such as a multi-sensor fusion technology, a path planning algorithm, a violation detection algorithm and the like, are adopted, so that the unmanned aerial vehicle information can be quickly and accurately processed, and the management efficiency is improved; the method has good expansibility and adaptability, and can be adjusted and optimized according to different flight environments and task requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and analysis, and in particular to a low-altitude isolation area traffic management system for unmanned aerial vehicles. Background Art

[0002] At present, China has released a series of relevant standards such as Peking University GeoSOT grid division and Beidou grid location code, which are applicable to the spatial location identification of airspace management in the fields of aviation, aerospace, air-to-air launch, sounding, etc. in the national economy and defense. However, they are not completely applicable to the actual application of specific low-altitude services, and the grid division sizes vary. At present, my country is still in the exploratory stage in the field of low-altitude UAV operations, facing the mixed management of different levels of UAV operations and the problem of adaptive fine-grained digital modeling of airspace in complex low-altitude operation environments. With the diversification of UAV flight modes, the difficulty coefficient of low-altitude airspace management is high.

[0003] Low-altitude grid segmentation provides a spatiotemporal position reference benchmark for low-altitude airspace management. Based on the geographic longitude and latitude grid model, a unified low-altitude airspace grid position benchmark is established. Different levels of basic airspace grid units are divided according to the operating characteristics of drones. Based on the needs of low-altitude airspace management, the corresponding business applications are matched on grids at different levels. The size of the grid needs to consider the safety interval between drones of different levels. However, there is little research on the management methods and theoretical studies of drone safety risks with different operating characteristics at low altitudes at home and abroad. Drones are mainly operated in isolated airspaces. During flight, drones are mainly controlled by ground operators. There are no managers who monitor low-altitude flying objects in real time. Drones are relatively small in size, and it is impossible to carry out refined management of low-altitude airspace grids based on the operating characteristics of drones, and it is impossible to monitor drones in real time through low-altitude gridding. Summary of the invention

[0004] The purpose of the present invention is to provide a low-altitude isolation area traffic management system for unmanned aerial vehicles to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a low-altitude isolation area traffic management system for unmanned aerial vehicles, comprising a monitoring module, an identification module, a control module and an early warning module;

[0006] The monitoring module is used to monitor the low-altitude isolation area of ​​the drone in real time and obtain the location and flight speed information of the drone;

[0007] The identification module identifies and classifies the monitored drone information and distinguishes different types of drones;

[0008] The control module is used to obtain the optimal flight path by taking the current position of the drone, the target position and the boundary information of the isolation area as inputs and calculating the shortest flight path from the drone to the target position and a safe path that avoids collision with the boundary of the isolation area and other drones;

[0009] The control module also considers the shortest flight path, the real-time performance of the algorithm, and flight path planning under different flight environments and mission requirements when calculating the optimal flight path;

[0010] The early warning module sends out an early warning signal when it finds that the drone is flying illegally or there is a danger of collision.

[0011] Furthermore, the monitoring module adopts multi-sensor fusion technology, and the multi-sensors include radar sensors and optical sensors. At the same time, the monitoring module also has data processing and transmission functions, and transmits the monitored drone information to the identification module in real time. Through multi-sensor fusion technology, more comprehensive and accurate drone information can be obtained, providing strong support for subsequent identification and control.

[0012] Furthermore, the specific calculation formula of the control module when calculating the optimal flight path is:

[0013] Shortest flight path length = sqrt{(x2-x1)^2+(y2-y1)^2}

[0014] Where (x1, y1) is the current position coordinate, (x2, y2) is the target position coordinate; safety distance = d (preset safety distance constant), when the distance from the drone to the boundary of the isolation area is less than the safety distance, the path is adjusted to avoid the boundary; to avoid collisions with other drones, by establishing a location information database of other drones, the relative distance and relative speed with other drones are calculated in real time. When the relative distance is less than the safety distance and the relative speed may cause a collision, the path is adjusted to avoid it.

[0015] Furthermore, the control module uses a search algorithm to search when calculating the shortest flight path. The search algorithm is a heuristic search algorithm that estimates the cost from the current position to the target position through an evaluation function and selects the path with the minimum cost for search. The specific calculation formula is:

[0016] f(n)=g(n)+h(n)

[0017] Where f(n) is the evaluation function, g(n) is the actual cost from the starting point to the current node, and h(n) is the estimated cost from the current node to the target node;

[0018] When avoiding collision with the boundary of the isolation area, a distance field-based method is used to calculate the distance field value from the drone to the boundary of the isolation area. When the distance field value is less than the safe distance, it is determined that the path needs to be adjusted. The specific calculation formula is:

[0019] Distance field value = *vert boundary function (x, y) - drone position coordinates (x, y) *vert

[0020] The boundary function is determined according to the boundary shape of the isolation area. Through the distance field method, it can be determined whether the drone is close to the boundary of the isolation area and make corresponding path adjustments;

[0021] When avoiding collisions with other drones, a method based on the Voronoi diagram is used. By constructing the Voronoi diagram of the location information of other drones, when a drone enters the Voronoi area of ​​other drones, it is determined that a collision may occur and the path is adjusted. The specific calculation formula is:

[0022] Voronoi region boundary = {(x, y)*vertd((x, y), p_i)*leqd((x, y), p_j),*forallp_j*neqp_i}

[0023] Where (x, y) is the current drone position, p_i is the position of other drones, and d((x, y), p_i) is the distance between the two points.

[0024] Furthermore, the control module adopts parallel computing technology to improve the real-time performance of the algorithm, divides the calculation process of path planning into multiple subtasks, performs calculations simultaneously on different processors or computing units, and finally merges the results of each subtask. The specific calculation formula is:

[0025] Total computation time = Sum_{i=1}^{n}t_i

[0026] Where t_i is the computation time of the i-th subtask, and n is the number of subtasks.

[0027] Furthermore, in order to adapt to different flight environments and mission requirements, the control module introduces a dynamic weight adjustment mechanism, which dynamically adjusts the weight coefficient and safety distance parameter in the shortest flight path calculation according to the terrain and meteorological factors of the isolation area and the flight mission type of the drone. The specific calculation formula is:

[0028] Weight coefficient = alpha*times terrain factor + beta*times weather factor + gamma*times mission type factor

[0029] Among them, alpha, beta, and gamma are adjustment factors of the weight coefficients, and terrain factors, meteorological factors, and mission type factors are quantitatively evaluated based on actual conditions.

[0030] Furthermore, by analyzing the monitored drone flight trajectory and behavior, it is detected whether the drone violates the flight regulations of the isolation area. The specific working steps are as follows:

[0031] A1. The flight trajectory analysis of drones in the isolation area specifically includes the following steps:

[0032] A11, distance calculation algorithm, including the formula D = √((X 2 -X 1 ) 2 +(Y 2 -Y 1 ) 2 ), where D is the distance between two points, (X 1 ,Y 1 ) is the current position of the drone, (X 2 ,Y 2 ) is the boundary point of the isolation area;

[0033] A12, violation detection algorithm, uses the formula V = T / D, where V is the flight speed and T is the displacement of the drone per unit time;

[0034] A13, state assessment algorithm, through the formula S = AB, where S is the state assessment result, A is the current flight state, and B is the preset compliance state;

[0035] A14, behavior trend analysis algorithm, calculates the behavior trend of the drone over a period of time through the formula T_B=(ΣB_n) / n, where n is the calculation period;

[0036] A15, fast anomaly monitoring algorithm, whose formula is E = |CN|, where E is the anomaly value, C is the normal range threshold, and N is the real-time detection value; the above algorithm improves the system's detection capability and response speed to illegal behaviors through real-time data processing;

[0037] A2, the analysis of drone flight behavior in the isolated area specifically includes the following steps:

[0038] A21, KNN behavior classification algorithm, uses the formula f(x) = argmax(ΣI_k), where f(x) is the predicted behavior category and I_k is the category of the k nearest neighbors;

[0039] A22, support vector machine (SVM) algorithm, uses the optimization objective function L = 1 / 2||w|| 2 +C*Σξ_i, to maximize the margin and minimize the classification error;

[0040] A23, Hidden Markov Model (HMM), uses the formula P(O|λ)=ΣP(O|Q)P(Q|λ) to predict uncertain behavior;

[0041] A24, decision tree algorithm, uses information entropy for feature selection, through the formula:

[0042] H(D)=-Σp_i*log2(p_i) guides the growth of the tree;

[0043] A25, the deep learning network updates weights through the back-propagation algorithm to establish complex behavior patterns; the above algorithm can comprehensively evaluate the specific behavior of the drone and determine whether it is operating within the legal flight area, thereby ensuring the efficient and safe operation of the low-altitude management system.

[0044] Compared with the prior art, the present invention provides a low-altitude isolation area traffic management system for unmanned aerial vehicles, which calculates the shortest path from the unmanned aerial vehicle to the target location and the safe path that avoids collision with the isolation area boundary and other unmanned aerial vehicles through a path planning algorithm, and plans the optimal flight path for the unmanned aerial vehicle. The algorithm adopts a variety of advanced technologies, such as search algorithms, distance field-based methods, Voronoi diagram-based methods, etc., which can quickly and accurately plan a safe and efficient flight path. At the same time, the violation detection algorithm analyzes the monitored flight trajectory and behavior of the unmanned aerial vehicle to detect whether the unmanned aerial vehicle violates the flight regulations of the isolation area, and can realize real-time monitoring and management of the low-altitude isolation area of ​​unmanned aerial vehicles, thereby improving air traffic safety; adopts a variety of advanced technologies, such as multi-sensor fusion technology, path planning algorithms, violation detection algorithms, etc., which can quickly and accurately process unmanned aerial vehicle information and improve management efficiency; has good scalability and adaptability, and can be adjusted and optimized according to different flight environments and mission requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0046] Figure 1 A system structure block diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0048] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0049] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0051] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0052] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0053] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0054] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0055] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0056] See also Figure 1 , a UAV low-altitude isolation area traffic management system, including a monitoring module, an identification module, a control module and an early warning module;

[0057] The monitoring module is used to monitor the low-altitude isolation area of ​​the drone in real time and obtain the location and flight speed information of the drone. The monitoring module uses multi-sensor fusion technology to simultaneously obtain a variety of information about the drone, such as location, speed, attitude, etc. This information is transmitted to the recognition module in real time through the data processing and transmission module, providing an accurate data basis for subsequent recognition and control;

[0058] The identification module identifies and classifies the monitored drone information and distinguishes different types of drones. The identification module identifies and classifies the monitored drone information and can distinguish different types of drones, such as civil drones, military drones, etc. By identifying different types of drones, different management strategies can be adopted to improve the pertinence and effectiveness of management;

[0059] The control module is used to take the current position of the UAV, the target position and the boundary information of the isolation area as input, and obtain the optimal flight path by calculating the shortest flight path from the UAV to the target position and the safe path that avoids collision with the boundary of the isolation area and other UAVs;

[0060] When calculating the optimal flight path, the control module also considers the shortest flight path, the real-time performance of the algorithm, and flight path planning under different flight environments and mission requirements;

[0061] The control module controls and dispatches the drone based on the recognition results to ensure the drone's safe flight in the isolated area. The control module can control the drone's flight path, flight speed and other parameters by sending instructions to achieve precise control of the drone.

[0062] The early warning module sends out an early warning signal when it finds that the drone is flying illegally or there is a danger of collision. Through the collaborative work of various modules, the system realizes effective traffic management in the low-altitude isolation area of ​​drones and ensures air traffic safety. The early warning module sends out an early warning signal when it finds that the drone is flying illegally or there is a danger of collision. The early warning signal can remind air traffic management personnel and drone pilots through sound and light, so that timely measures can be taken to deal with it and avoid accidents.

[0063] The monitoring module uses multi-sensor fusion technology, including radar sensors and optical sensors, to improve the accuracy and reliability of monitoring. At the same time, the monitoring module also has data processing and transmission functions, transmitting the monitored drone information to the identification module in real time. Through multi-sensor fusion technology, more comprehensive and accurate drone information can be obtained, providing strong support for subsequent identification and control.

[0064] The specific calculation formula of the control module when calculating the optimal flight path is:

[0065] Shortest flight path length = sqrt{(x2-x1)^2+(y2-y1)^2}

[0066] Where (x1, y1) is the current position coordinate, (x2, y2) is the target position coordinate; safety distance = d (preset safety distance constant), when the distance from the drone to the boundary of the isolation area is less than the safety distance, the path is adjusted to avoid the boundary; for collision avoidance with other drones, by establishing a location information database of other drones, the relative distance and relative speed with other drones are calculated in real time. When the relative distance is less than the safety distance and the relative speed may cause a collision, the path is adjusted to avoid it. Through this path planning algorithm, a safe and efficient flight path can be planned for the drone in the low-altitude isolation area, effectively avoiding collisions and illegal flights.

[0067] When calculating the shortest flight path, the control module uses a search algorithm. The search algorithm is a heuristic search algorithm that estimates the cost from the current position to the target position through an evaluation function and selects the path with the minimum cost for search. The specific calculation formula is:

[0068] f(n)=g(n)+h(n)

[0069] Where f(n) is the evaluation function, g(n) is the actual cost from the starting point to the current node, and h(n) is the estimated cost from the current node to the target node. Through the search algorithm, the shortest flight path from the current position to the target position can be quickly found;

[0070] When avoiding collision with the boundary of the isolation area, a distance field-based method is used. The distance field is a method that represents the distance from each point in space to the boundary as a numerical value. By calculating the distance field value from the drone to the boundary of the isolation area, when the distance field value is less than the safe distance, it is determined that the path needs to be adjusted. The specific calculation formula is:

[0071] Distance field value = *vert boundary function (x, y) - drone position coordinates (x, y) *vert

[0072] The boundary function is determined according to the boundary shape of the isolation area. Through the distance field method, it can quickly and accurately determine whether the drone is close to the boundary of the isolation area and make corresponding path adjustments;

[0073] When avoiding collisions with other drones, a method based on the Voronoi diagram is used. The Voronoi diagram divides a plane into multiple regions. The distance between a point in each region and a specific point in the region is the shortest. By constructing the Voronoi diagram of the location information of other drones, when a drone enters the Voronoi region of other drones, it is determined that a collision may occur and the path is adjusted. The specific calculation formula is:

[0074] Voronoi region boundary = {(x, y)*vertd((x, y), p_i)*leqd((x, y), p_j),*forallp_j*neqp_i}

[0075] Where (x, y) is the current drone position, p_i is the position of other drones, and d((x, y), p_i) is the distance between the two points. The Voronoi diagram method can effectively avoid collisions between drones.

[0076] When improving the real-time performance of the algorithm, the control module uses parallel computing technology to divide the calculation process of path planning into multiple subtasks, which are calculated simultaneously on different processors or computing units, and finally the results of each subtask are merged. The specific calculation formula is:

[0077] Total computation time = Sum_{i=1}^{n}t_i

[0078] Where t_i is the calculation time of the ith subtask, and n is the number of subtasks. Through parallel computing technology, the calculation time of path planning can be greatly shortened to meet the needs of real-time flight of drones.

[0079] In order to adapt to different flight environments and mission requirements, the control module introduces a dynamic weight adjustment mechanism. According to the terrain and meteorological factors of the isolated area and the flight mission type of the drone, the weight coefficient and safety distance parameters in the shortest flight path calculation are dynamically adjusted. The specific calculation formula is: Weight coefficient = alpha*times terrain factor + beta*times meteorological factor + gamma*times mission type factor

[0080] Among them, alpha, beta, and gamma are adjustment factors of the weight coefficients, and terrain factors, meteorological factors, and task type factors are quantitatively evaluated according to actual conditions. Through the dynamic weight adjustment mechanism, path planning can be more adapted to different actual conditions and improve the rationality and effectiveness of path planning.

[0081] By analyzing the monitored drone flight trajectory and behavior, we can detect whether the drone violates the flight regulations of the isolation area, such as exceeding the isolation area or flying too fast. The specific work steps are as follows:

[0082] A1. The flight trajectory analysis of drones in the isolation area specifically includes the following steps:

[0083] A11, distance calculation algorithm, including the formula D = √((X 2 -X 1 ) 2 +(Y 2 -Y 1 ) 2 ), where D is the distance between two points, (X 1 ,Y 1 ) is the current position of the drone, (X 2 ,Y 2 ) is the boundary point of the isolation area;

[0084] A12, violation detection algorithm, uses the formula V = T / D, where V is the flight speed and T is the displacement of the drone per unit time;

[0085] A13, state assessment algorithm, through the formula S = AB, where S is the state assessment result, A is the current flight state, and B is the preset compliance state;

[0086] A14, behavior trend analysis algorithm, calculates the behavior trend of the drone over a period of time through the formula T_B=(ΣB_n) / n, where n is the calculation period;

[0087] A15, fast anomaly monitoring algorithm, whose formula is E = |CN|, where E is the anomaly value, C is the normal range threshold, and N is the real-time detection value; the above algorithm improves the system's detection capability and response speed to illegal behaviors through real-time data processing;

[0088] A2, the analysis of drone flight behavior in the isolated area specifically includes the following steps:

[0089] A21, KNN behavior classification algorithm, uses the formula f(x) = argmax(ΣI_k), where f(x) is the predicted behavior category and I_k is the category of the k nearest neighbors;

[0090] A22, support vector machine (SVM) algorithm, uses the optimization objective function L = 1 / 2||w|| 2 +C*Σξ_i, to maximize the margin and minimize the classification error;

[0091] A23, Hidden Markov Model (HMM), uses the formula P(O|λ)=ΣP(O|Q)P(Q|λ) to predict uncertain behavior;

[0092] A24, decision tree algorithm, uses information entropy for feature selection, through the formula:

[0093] H(D)=-Σp_i*log 2 (p_i) guides the growth of the tree;

[0094] A25, the deep learning network updates weights through the back-propagation algorithm to establish complex behavior patterns; the above algorithm can comprehensively evaluate the specific behavior of the drone and determine whether it is operating within the legal flight area, thereby ensuring the efficient and safe operation of the low-altitude management system.

[0095] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A UAV low-altitude isolation area traffic management system, characterized by: It includes monitoring module, identification module, control module and early warning module; The monitoring module is used to monitor the low-altitude isolation area of ​​the drone in real time and obtain the location and flight speed information of the drone; The identification module identifies and classifies the monitored drone information and distinguishes different types of drones; The control module is used to obtain the optimal flight path by taking the current position of the drone, the target position and the boundary information of the isolation area as inputs and calculating the shortest flight path from the drone to the target position and a safe path that avoids collision with the boundary of the isolation area and other drones; The control module also considers the shortest flight path, the real-time performance of the algorithm, and flight path planning under different flight environments and mission requirements when calculating the optimal flight path; The early warning module sends out an early warning signal when it finds that the drone is flying illegally or there is a danger of collision.

2. A UAV low-altitude isolation area traffic management system according to claim 1, characterized in that: The monitoring module adopts multi-sensor fusion technology, and the multi-sensors include radar sensors and optical sensors. At the same time, the monitoring module also has data processing and transmission functions, and transmits the monitored drone information to the identification module in real time. Through multi-sensor fusion technology, more comprehensive and accurate drone information can be obtained, providing strong support for subsequent identification and control.

3. A UAV low-altitude isolation area traffic management system according to claim 1, characterized in that: The specific calculation formula of the control module when calculating the optimal flight path is: Shortest flight path length = sqrt{(x2-x1)^2+(y2-y1)^2} Where (x1, y1) is the current position coordinate, (x2, y2) is the target position coordinate; safety distance = d (preset safety distance constant), when the distance from the drone to the boundary of the isolation area is less than the safety distance, the path is adjusted to avoid the boundary; to avoid collisions with other drones, by establishing a location information database of other drones, the relative distance and relative speed with other drones are calculated in real time. When the relative distance is less than the safety distance and the relative speed may cause a collision, the path is adjusted to avoid it.

4. The UAV low-altitude isolation area traffic management system according to claim 1 is characterized by: The control module uses a search algorithm to search when calculating the shortest flight path. The search algorithm is a heuristic search algorithm that estimates the cost from the current position to the target position through an evaluation function and selects the path with the minimum cost for search. The specific calculation formula is: f(n)=g(n)+h(n) Where f(n) is the evaluation function, g(n) is the actual cost from the starting point to the current node, and h(n) is the estimated cost from the current node to the target node; When avoiding collision with the boundary of the isolation area, a distance field-based method is used to calculate the distance field value from the drone to the boundary of the isolation area. When the distance field value is less than the safe distance, it is determined that the path needs to be adjusted. The specific calculation formula is: Distance field value = *vert boundary function (x, y) - drone position coordinates (x, y) *vert The boundary function is determined according to the boundary shape of the isolation area. Through the distance field method, it can be determined whether the drone is close to the boundary of the isolation area and make corresponding path adjustments; When avoiding collisions with other drones, a method based on the Voronoi diagram is used. By constructing the Voronoi diagram of the location information of other drones, when a drone enters the Voronoi area of ​​other drones, it is determined that a collision may occur and the path is adjusted. The specific calculation formula is: Voronoi region boundary = {(x, y)*vertd((x, y), p_i)*leqd((x, y), p_j),*forallp_j*neqp_i} Where (x, y) is the current drone position, p_i is the position of other drones, and d((x, y), p_i) is the distance between the two points.

5. A UAV low-altitude isolation area traffic management system according to claim 4, characterized in that: When improving the real-time performance of the algorithm, the control module adopts parallel computing technology to divide the calculation process of path planning into multiple subtasks, which are calculated simultaneously on different processors or computing units, and finally the results of each subtask are merged. The specific calculation formula is: Total computation time = sum_{i=1}^{n}t_i Where t_i is the computation time of the i-th subtask, and n is the number of subtasks.

6. A UAV low-altitude isolation area traffic management system according to claim 5, characterized in that: In order to adapt to different flight environments and mission requirements, the control module introduces a dynamic weight adjustment mechanism. According to the terrain and meteorological factors of the isolated area and the flight mission type of the UAV, the weight coefficient and safety distance parameter in the shortest flight path calculation are dynamically adjusted. The specific calculation formula is: Weight coefficient = alpha*times terrain factor + beta*times weather factor + gamma*times mission type factor Among them, alpha, beta, and gamma are adjustment factors of the weight coefficients, and terrain factors, meteorological factors, and mission type factors are quantitatively evaluated based on actual conditions.

7. A UAV low-altitude isolation area traffic management system according to claim 6, characterized in that: The control module also analyzes the monitored UAV flight trajectory and behavior to detect whether the UAV violates the flight regulations of the isolation area. The specific working steps are as follows: A1. The flight trajectory analysis of drones in the isolation area specifically includes the following steps: A11, distance calculation algorithm, including the formula D = √((X2-X1) 2 +(Y2-Y1) 2 ), where D is the distance between the two points, (X1, Y1) is the current position of the drone, and (X2, Y2) is the boundary point of the isolation area; A12, violation detection algorithm, uses the formula V = T / D, where V is the flight speed and T is the displacement of the drone per unit time; A13, state assessment algorithm, through the formula S = AB, where S is the state assessment result, A is the current flight state, and B is the preset compliance state; A14, behavior trend analysis algorithm, calculates the behavior trend of the drone over a period of time through the formula T_B=(ΣB_n) / n, where n is the calculation period; A15, fast anomaly monitoring algorithm, whose formula is E = |CN|, where E is the anomaly value, C is the normal range threshold, and N is the real-time detection value; A2, the analysis of drone flight behavior in the isolated area specifically includes the following steps: A21, KNN behavior classification algorithm, uses the formula f(x) = argmax(ΣI_k), where f(x) is the predicted behavior category and I_k is the category of the k nearest neighbors; A22, support vector machine (SVM) algorithm, uses the optimization objective function L = 1 / 2||w|| 2 +C*Σξ_i, to maximize the margin and minimize the classification error; A23, Hidden Markov Model (HMM), uses the formula P(O|λ)=ΣP(O|Q)P(Q|λ) to predict uncertain behavior; A24, decision tree algorithm, uses information entropy for feature selection, through the formula: H(D)=-Σp_i*log2(p_i) guides the growth of the tree; A25, deep learning networks update weights through back-propagation algorithms to establish complex behavior patterns.

Images