Unmanned aerial vehicle situation threat identification method and system

Abstract

The invention provides an unmanned aerial vehicle situation threat identification method and system, and belongs to the technical field of unmanned aerial vehicles, and the method comprises the steps: obtaining parameters: obtaining a situation threat parameter set of an unmanned aerial vehicle; function construction: constructing a distance measurement function; determining a core point: determining a data point set of each situation threat parameter in a neighborhood range in the situation threat parameter set according to a distance metric function, and determining the core point of the situation threat parameter based on the data point set; threat score determination: determining the threat score of each situation threat parameter according to the core points of the situation threat parameters; and repeating iteration: repeating iteration from the parameter acquisition step to the threat score determination step according to the sampling frequency until all the situation threat parameters are traversed, and completing unmanned aerial vehicle situation threat identification. According to the method, the core point of the situation threat parameter and the threat score of the situation threat parameter are updated based on the sampling frequency so as to adapt to situation threat identification in a dynamic change environment of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles, and relates to a situation assessment technology for unmanned aerial vehicles, and specifically to a method and system for identifying situation threats of unmanned aerial vehicles. Background Art

[0002] The situation of a drone refers to the state and form of a drone during flight, which can be used to assess whether there are unsafe factors in the drone during flight. There are also many related technologies for drone situation recognition in the prior art, which usually involve monitoring and analyzing security events in complex systems to identify potential threats and abnormal behaviors. For example, the patent document with application number CN202210170253.8 discloses a method and system for multi-drone collaborative situation awareness based on information fusion, which relates to the field of drone situation awareness technology. The method includes obtaining parameter values ​​at time zero and time t; determining multiple geodetic coordinates at time zero according to the parameter values ​​at time zero; obtaining the line of sight and viewing angle of the drone and the obstacle at time zero according to the attitude angle of the drone at time zero, the coordinates of the drone in the ground coordinate system, and the geodetic coordinates corresponding to the drone's body coordinate system; obtaining the fusion parameters at time t according to the line of sight, viewing angle, and parameter values ​​of each drone at time zero and the obstacle using DS evidence theory; obtaining the final fusion parameters at time t according to the fusion parameters at time t and the fusion parameters at time t-1. It can improve the perception results of the situation. It can be seen from this that the existing technology obtains the parameter value at a certain moment to calculate the drone situation, and the drone situation calculated in the end is static, not dynamic. However, in the actual flight process, the drone situation is dynamically changing, and the security threats to the drone are also dynamically changing. New attack methods and attack strategies continue to emerge. Therefore, the static drone situation recognition in the existing technology cannot adapt to the dynamically changing environment of drones. Summary of the invention

[0003] As described in the above background technology, the situational awareness or recognition of drones in the prior art is mostly static, and there is a technical problem that it cannot adapt to the dynamically changing environment of drones. To address this technical problem, the present invention proposes a drone situation threat recognition method and system.

[0004] The method for identifying situational threats of unmanned aerial vehicles of the present invention can perform situational threat identification of all situational threat parameters based on the sampling frequency by continuously repeating and iterating the parameter acquisition step, the function construction step, the core point determination step and the threat score determination step, match new threat features for each situational threat parameter, and timely update the core points of the situational threat parameters and the threat scores of the situational threat parameters to adapt to the situational threat identification in the dynamically changing environment of the unmanned aerial vehicle, better conform to the dynamic response of the unmanned aerial vehicle during flight, and also improve the accuracy of the situational threat identification of the unmanned aerial vehicle.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] The present invention provides a method for identifying a situational threat of an unmanned aerial vehicle, comprising the following steps:

[0007] Parameter acquisition: obtain the situation threat parameter set of the drone;

[0008] Function construction: construct distance measurement function;

[0009] Core point determination: Determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set;

[0010] Threat score determination: Determine the threat score of each situation threat parameter based on the core points of the situation threat parameter;

[0011] Repeated iteration: According to the sampling frequency, the iterative parameter acquisition step to the threat score determination step is repeated until all situation threat parameters are traversed and the drone situation threat identification is completed.

[0012] It is further defined that the situational threat identification parameter set of the UAV includes a longitude and latitude parameter set of ground mobile equipment, a longitude and latitude parameter set of ground fixed equipment, a longitude and latitude and altitude parameter set of aerial equipment, a longitude and latitude parameter set of water mobile equipment and / or a longitude and latitude parameter set of water fixed equipment.

[0013] It is further defined that the distance metric function d is:

[0014] d=q i +Nε(p i )

[0015] In the formula, q i is the i-th situation threat parameter, q i ∈Q, Q is the situation threat parameter set of the UAV; Nε(q i ) is q i 's neighborhood.

[0016] It is further defined that the core point determination specifically includes:

[0017] Determine a set of data points within a neighborhood range for each situation threat parameter in a situation threat parameter set according to a distance measurement function;

[0018] Based on the DBSCAN clustering algorithm, determine whether all data points in the data point set are greater than or equal to the threshold parameter. If so, the situation threat parameter q i is the core point; otherwise, the situation threat parameter q i Not the core point.

[0019] Further defined, the threat score determination specifically includes:

[0020] Construct threat score calculation model;

[0021] Determine the threat occurrence probability P, threat damage degree I and threat occurrence urgency U of each situation threat parameter according to the core point of each situation threat parameter;

[0022] Substitute the threat occurrence probability P, threat damage degree I and threat occurrence urgency U into the threat score calculation model to calculate the threat score of each situation threat parameter.

[0023] Further defined, the threat score calculation model text is:

[0024]

[0025] Where wP is the weight of the threat occurrence probability P; wI is the weight of the threat damage degree I; and wU is the weight of the threat occurrence urgency U.

[0026] The present invention provides a finite state automaton, which utilizes the above-mentioned unmanned aerial vehicle situation threat identification method to perform unmanned aerial vehicle situation threat identification.

[0027] The present invention provides a UAV situation threat identification system, which is applied to the above-mentioned UAV situation threat identification method, and comprises:

[0028] Parameter acquisition module: used to obtain the situation threat parameter set of the UAV;

[0029] Function building module: used to build distance measurement functions;

[0030] Core point determination module: used to determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set;

[0031] Threat score determination module: used to determine the threat score of each situation threat parameter according to the core point of the situation threat parameter;

[0032] Repeated iteration module: It is used to repeatedly iterate the parameter acquisition module to the threat score confirmation module according to the sampling frequency until all situation threat parameters are traversed to complete the drone situation threat identification.

[0033] The present invention provides a storage medium storing a program file, wherein the program file is executed to implement the above-mentioned drone situation threat identification method.

[0034] The present invention provides an electronic device, comprising a processor and a memory coupled to each other, wherein:

[0035] The memory is used to store the above-mentioned drone situation threat identification method;

[0036] The processor is used to execute program instructions stored in the memory.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The method for identifying situational threats of unmanned aerial vehicles of the present invention can perform situational threat identification of all situational threat parameters based on the sampling frequency by continuously repeating and iterating the parameter acquisition step, the function construction step, the core point determination step and the threat score determination step, match new threat features for each situational threat parameter, and dynamically update the core points of the situational threat parameters and the threat scores of the situational threat parameters to adapt to the situational threat identification in the dynamically changing environment of the unmanned aerial vehicle, which is more in line with the dynamic response of the unmanned aerial vehicle during flight, and also improves the accuracy of the situational threat identification of the unmanned aerial vehicle, so as to facilitate the accurate assessment of the safety of the unmanned aerial vehicle during flight.

[0039] 2. The situation threat identification parameter set of the UAV of the present invention includes the latitude and longitude parameter set of ground mobile equipment, the latitude and longitude parameter set of ground fixed equipment, the latitude and longitude and altitude parameter set of aerial equipment, the latitude and longitude parameter set of water mobile equipment and / or the latitude and longitude parameter set of water fixed equipment, so that the acquired situation threat identification parameters are very extensive and can almost cover all risk points, further improving the risk point identification of the UAV during flight.

[0040] 3. The UAV situation threat identification method of the present invention comprehensively considers the threat occurrence probability P, threat damage degree I and threat occurrence urgency U when calculating the threat score of each situation threat parameter, thereby realizing a multi-faceted evaluation of the threat degree to meet the situation threat identification requirements of different application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of a method for identifying a situational threat of a UAV according to the present invention;

[0042] Figure 2 Schematic diagram of the UAV situation threat identification system of the present invention. DETAILED DESCRIPTION

[0043] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings, but the present invention is not limited to the implementation modes described below.

[0044] See also Figure 1 The present invention provides a method for identifying a situational threat of an unmanned aerial vehicle, comprising the following steps:

[0045] Parameter acquisition: Get the UAV’s situation threat parameter set Q = q1 ,q 2 ,q 3 ,…,q I ,…,q n , n is the number of situation threat parameters; specifically, the situation threat parameter set includes the latitude and longitude parameter set of ground mobile equipment, the latitude and longitude parameter set of ground fixed equipment, the latitude and longitude and altitude parameter set of aerial equipment, the latitude and longitude parameter set of water mobile equipment and / or the latitude and longitude parameter set of water fixed equipment.

[0046] Function construction: Construct the distance metric function d:

[0047] d=q i +Nε(p i )

[0048] In the formula, q i is the i-th situation threat parameter, q i ∈Q, Q is the situation threat parameter set of the UAV; Nε(q i ) is q i 's neighborhood.

[0049] Core point determination: Determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set;

[0050] The core point determination steps specifically include:

[0051] Determine a set of data points within a neighborhood range for each situation threat parameter in a situation threat parameter set according to a distance measurement function;

[0052] Based on the DBSCAN clustering algorithm, determine whether all data points in the data point set are greater than or equal to the threshold parameter. If so, the situation threat parameter q i is the core point; otherwise, the situation threat parameter q i It is not a core point, but a boundary point or a noise point, which needs to be removed.

[0053] Furthermore, in the present invention, the core point determination step also includes:

[0054] Create clusters based on the determined core points and determine the data point q j Whether it is assigned to a cluster, where the data point q j Is a data point inside or outside the cluster. If so, the situation threat parameter q i is a core point; otherwise, the data point q j As the core point. This step is to find data points more comprehensively to avoid missing data points, so as to identify dangerous points more comprehensively.

[0055] Specifically, data point q j Whether the data point q is assigned to a cluster is determined by j Compared with the parameter threshold (MinPts) in the clustering algorithm, the specific value of the parameter threshold is well known to those skilled in the art. Preferably, in the present invention, the parameter threshold = 5; MinPts is the threshold parameter in the DBSCAN clustering algorithm, which represents the minimum number of points in the cluster. In the DBSCAN algorithm, if there are more than MinPts points in the neighborhood of a point, the point is considered to be a core point; otherwise, it may be a boundary point or a noise point and needs to be removed.

[0056] Threat score determination: Determine the threat score of each situation threat parameter based on the core points of the situation threat parameter;

[0057] The threat score determination specifically includes:

[0058] Constructing threat score calculation modeltext:

[0059]

[0060] Wherein, wP is the weight of the threat probability P; wI is the weight of the threat damage level I; wU is the weight of the threat urgency U; wherein wP, wI and wU are all arbitrary values ​​between 0 and 1, and wP+wI+wU=1. When wP=0, wI and wU can be combined arbitrarily and the sum of their values ​​equals 1, for example: wI=wU=0.5; wI=0.6, wU=0.4; wI=0.3, wU=0.7; when wP=0.1, wI and wU can be combined arbitrarily and the sum of their values ​​equals 0.9, for example: wI=wU=0.45; wI=0.5, wU=0.4; wI=0.3, wU=0.6; when wP=0.2, wI and wU can be combined arbitrarily and the sum of their values ​​equals 0.9, for example: wI=wU=0.45; wI=0.5, wU=0.4; wI=0.3, wU=0.6; when wP=0.2, wI and wU can be combined arbitrarily and the sum of their values ​​equals 0.9 Any combination of wI and wU and the sum of their values ​​can be equal to 0.8, for example: wI=wU=0.4; wI=0.4, wU=0.2; wI=0.1, wU=0.7; when wP=0.3, wI and wU can be combined arbitrarily, and the sum of their values ​​can be equal to 0.7, for example: wI=wU=0.35; wI=0.4, wU=0.3; wI=0.1, wU=0.6; when wP=0.4, wI and wU can be combined arbitrarily, and the sum of their values ​​can be equal to 0.6, for example: wI=wU=0.3; wI=0.4, wU=0.2; wI=0.1, wU=0.5; that is, for those skilled in the art, any form that can constitute wP+wI+wU=1 is acceptable. Preferably, the best combination in the present invention is: for aerial equipment, wP=0.5, wI=0.45, wU=0.05; for ground mobile equipment, wP=0.4, wI=0.4, wU=0.2; for ground fixed equipment, wP=0.3, wI=0.3, wU=0.4.

[0061] Determine the threat occurrence probability P, threat damage degree I and threat occurrence urgency U of each situation threat parameter according to the core point of each situation threat parameter;

[0062] Substitute the threat occurrence probability P, threat damage degree I and threat occurrence urgency U into the threat score calculation model to calculate the threat score of each situation threat parameter.

[0063] Repeated iteration: According to the sampling frequency, the parameter acquisition step to the threat score determination step is repeated until all situation threat parameters are traversed to complete the drone situation threat identification, where the situation threat parameter set is a set of multiple situation threat parameters. The sampling frequency can be 0.5 seconds, 1 second, 2 seconds, etc. The specific value is selected by the user according to the needs and the required calculation accuracy.

[0064] As a specific implementation of the present invention, the longitude and latitude parameters of ground mobile equipment are [vehicle 1, 110.248, 89.525], the longitude and latitude parameters of ground fixed equipment are [headquarters, 68.628, 107.527], the longitude and latitude and altitude parameters of aerial equipment are [aircraft 1, 121.639, 78.916, 218m], the longitude and latitude parameter set of water mobile equipment is selected with reference to the longitude and latitude parameter set of ground mobile equipment, and the longitude and latitude parameter set of water fixed equipment is selected with reference to the longitude and latitude parameter set of ground fixed equipment. The above situation threat parameter set of unmanned aerial vehicles is only a schematic example and does not limit the present invention. The specific values ​​can be the parameter values ​​of any mobile device, fixed device and aerial device.

[0065] As a specific implementation of the present invention, taking ground mobile equipment as an example, when creating a cluster based on the determined core points, all situation threat parameters must meet the following conditions:

[0066] C=\{(x,y)\midx^2+y^2\leq25\}

[0067] X and y represent the coordinate values ​​of the ground mobile equipment respectively. With the parameter threshold = 5, the cluster C formed is the set of all points within a circle (including the boundary) with a radius of 5 and the core point as the center.

[0068] For a UAV in flight, the situational threat environment is changing. Therefore, by repeatedly iterating the parameter acquisition step to the threat score determination step, the dynamic identification of the UAV situational threat can be ensured, which is more in line with the dynamic response of the UAV during flight, and also improves the accuracy of the UAV situational threat identification, which facilitates the accurate assessment of the safety of the UAV during flight.

[0069] The present invention provides a finite state automaton, which utilizes the above-mentioned UAV situation threat identification method to perform UAV situation threat identification. The specific technical scheme of the UAV situation threat identification method can be found in the above description.

[0070] See also Figure 2 , the present invention provides a UAV situation threat identification system, which is used for the above-mentioned UAV situation threat identification method, and includes a parameter acquisition module, a function construction module, a core point determination module, a threat score determination module and a repeated iteration module;

[0071] Parameter acquisition module: used to obtain the situation threat parameter set of the UAV;

[0072] Function building module: used to build distance measurement functions;

[0073] Core point determination module: used to determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set;

[0074] Threat score determination module: used to determine the threat score of each situation threat parameter according to the core point of the situation threat parameter;

[0075] Repeated iteration module: used to repeatedly iterate the parameter acquisition module to the threat score confirmation module according to the sampling frequency until all situation threat parameters are traversed to complete the drone situation threat identification, where the situation threat parameter set is a set composed of multiple situation threat parameters.

[0076] The unmanned aerial vehicle situation threat identification system of the present invention corresponds to the above-mentioned unmanned aerial vehicle situation threat identification method. The specific contents of the parameter acquisition module, the function construction module, the core point determination module, the threat score determination module and the repeated iteration module refer to the description of the above-mentioned unmanned aerial vehicle situation threat identification method, and the present invention will not be repeated here.

[0077] The present invention provides a storage medium, in which a program file is stored. The program file is executed to implement the above-mentioned drone situation threat identification method. The specific technical solution of the drone situation threat identification method is shown in the above description.

[0078] The storage medium in the present invention may specifically include random access memory (RAM), internal memory, read-only memory (ROM), programmable ROM, erasable programmable ROM, register, hard disk, removable disk or CD-ROM. It should be noted that those skilled in the art may specifically select the form and type of storage medium according to actual use requirements, and the present invention does not make further specific limitations.

[0079] The present invention discloses an electronic device, comprising a processor and a memory coupled to each other, wherein the memory is used to store the method for identifying the situation threat of a UAV; the processor is used to execute the program instructions stored in the memory. The specific technical solution of the method for identifying the situation threat of a UAV is described above.

[0080] The electronic device in the present invention includes any electronic device that can execute program instructions, such as a computer, a mobile terminal or a wearable device.

[0081] The above content is only used to illustrate the technical solution of the present invention, rather than to limit the present invention. Although the present invention has been described in detail with reference to the foregoing, a person skilled in the art should understand that the technical solution described above can still be modified, or part or all of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the present invention.

Claims

1. A method for identifying unmanned aerial vehicle situational threats, characterized in that: The following steps are involved: Parameter acquisition: obtain the situation threat parameter set of the drone; Function construction: construct distance measurement function; Core point determination: Determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set; Threat score determination: Determine the threat score of each situation threat parameter based on the core points of the situation threat parameter; Repeated iteration: According to the sampling frequency, the iterative parameter acquisition step to the threat score determination step is repeated until all situation threat parameters are traversed and the drone situation threat identification is completed.

2. The method for identifying drone situational threats according to claim 1, characterized in that: The situational threat identification parameter set of the UAV includes a latitude and longitude parameter set of ground mobile equipment, a latitude and longitude parameter set of ground fixed equipment, a latitude and longitude and altitude parameter set of aerial equipment, a latitude and longitude parameter set of water mobile equipment and / or a latitude and longitude parameter set of water fixed equipment.

3. The method for identifying drone situational threats according to claim 1, characterized in that: The distance metric function d is: d=q i +Nε(p i ) In the formula, q i is the i-th situation threat parameter, q i ∈Q, Q is the situation threat parameter set of the UAV; Nε(q i ) is q i 's neighborhood.

4. The method for identifying drone situational threats according to claim 3, characterized in that: The core point determination specifically includes: Determine a set of data points within a neighborhood range for each situation threat parameter in a situation threat parameter set according to a distance measurement function; Based on the DBSCAN clustering algorithm, determine whether all data points in the data point set are greater than or equal to the threshold parameter. If so, the situation threat parameter q i is the core point; otherwise, the situation threat parameter q i Not the core point.

5. The method for identifying drone situational threats according to claim 1, characterized in that: The threat score determination specifically includes: Construct threat score calculation model; Determine the threat occurrence probability P, threat damage degree I and threat occurrence urgency U of each situation threat parameter according to the core point of each situation threat parameter; Substitute the threat occurrence probability P, threat damage degree I and threat occurrence urgency U into the threat score calculation model to calculate the threat score of each situation threat parameter.

6. The method for identifying drone situational threats according to claim 5, characterized in that: The threat score calculation model text is: In the formula, wP is the weight of the threat occurrence probability P; wI is the weight of the threat damage level I; wU is the weight of the threat urgency U.

7. A finite state automaton, characterized in that: The finite state automaton performs drone situation threat identification using the drone situation threat identification method described in any one of claims 1 to 6.

8. A drone situation threat identification system, characterized in that: The method for identifying drone situational threats as described in claim 1 comprises: Parameter acquisition module: used to obtain the situation threat parameter set of the UAV; Function building module: used to build distance measurement functions; Core point determination module: used to determine the data point set of each situation threat parameter in the situation threat parameter set within the neighborhood range according to the distance measurement function, and determine the core point of the situation threat parameter based on the data point set; Threat score determination module: used to determine the threat score of each situation threat parameter according to the core point of the situation threat parameter; Repeated iteration module: It is used to repeatedly iterate the parameter acquisition module to the threat score confirmation module according to the sampling frequency until all situation threat parameters are traversed to complete the drone situation threat identification.

9. A storage medium, characterized in that: A program file is stored, and the program file is executed to implement the drone situation threat identification method as described in any one of claims 1-6.

10. An electronic device, characterized in that: The invention comprises a processor and a memory coupled to each other, wherein: The memory is used to store the method for identifying the situational threat of a drone according to any one of claims 1 to 6; The processor is used to execute program instructions stored in the memory.

Images