A situation analysis method and device for unmanned clusters

Abstract

The application discloses a situation analysis method and device for unmanned clusters, and the method comprises the following steps: collecting a spatial electromagnetic information set and a motion trajectory information set of the unmanned clusters; the spatial electromagnetic information set comprises electromagnetic information sets of motion spaces where the unmanned clusters are located; performing type identification processing on the motion trajectory information set of the unmanned clusters to obtain a category information set of the unmanned clusters; performing abnormality detection processing on the spatial electromagnetic information set to obtain an electromagnetic abnormal situation information set; and displaying the motion trajectory information set, the category information set and the electromagnetic abnormal situation information set of the unmanned clusters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned swarm and the field of information processing, and in particular to a situation analysis method and device for unmanned swarm. BACKGROUND

[0002] In the cooperative operation scene of unmanned swarm (such as emergency rescue, industrial inspection), accurate situation analysis is the core of task planning and risk avoidance. However, the existing technology has the problem of low efficiency of multi-dimensional data fusion. Unmanned swarm needs to process spatial electromagnetic information (such as radio frequency interference, spectrum occupation) and motion trajectory information (such as position, speed, formation shape) at the same time, but the traditional method only analyzes the two types of data independently, lacking cross-dimensional correlation ability. For example, the spatial overlap of electromagnetic anomaly area and swarm motion trajectory may indicate potential threats, but the existing technology cannot capture such correlation in real time. Existing electromagnetic monitoring mainly uses threshold triggering mechanism, and the response to gradual interference (such as slow rise of narrowband interference power) or hidden interference (such as frequency hopping interference) is delayed. At the same time, there is a lack of linkage analysis with swarm motion trajectory, which cannot predict the influence of electromagnetic environment on swarm task (such as communication unmanned aerial vehicle entering strong interference area may cause link interruption).

[0003] The roles of different devices in unmanned swarm (such as communication relay, computing node, task execution unit) need to be accurately distinguished through trajectory features. Traditional clustering methods based on geometric features (such as trajectory curvature, average speed) are difficult to describe complex motion patterns (such as dynamic formation transformation, cooperative obstacle avoidance), leading to misclassification. For example, communication unmanned aerial vehicles need to maintain fixed relay positions, and their trajectories fluctuate less, while computing unmanned aerial vehicles need to dynamically move to data aggregation points, and their trajectories are more complex, so the traditional method is easy to confuse the two types of roles. SUMMARY

[0004] The present application mainly solves the problem of how to accurately analyze and extract the electromagnetic situation and motion situation of unmanned swarm. The present application discloses a situation analysis method and device for unmanned swarm.

[0005] In a first aspect, the present application discloses a situation analysis method for unmanned swarm, comprising:

[0006] S1, a spatial electromagnetic information set and a motion trajectory information set of the unmanned swarm are collected; the spatial electromagnetic information set includes an electromagnetic information set of the motion space where the unmanned swarm is located; the electromagnetic information set includes the position coordinates and electromagnetic information of each location in the motion space where the unmanned swarm is located; the motion trajectory information set of the unmanned swarm includes the motion trajectory sequence of each unmanned device of the unmanned swarm;

[0007] S2, type identification processing is performed on the motion trajectory information set of the unmanned cluster to obtain a category information set of the unmanned cluster;

[0008] S3, anomaly detection processing is performed on the spatial electromagnetic information set to obtain an electromagnetic anomaly situation information set;

[0009] S4, the motion trajectory information set, the category information set, and the electromagnetic anomaly situation information set of the unmanned cluster are displayed.

[0010] The type identification processing on the motion trajectory information set of the unmanned cluster to obtain a category information set of the unmanned cluster comprises:

[0011] S21, intermediate quantity calculation is performed on the motion trajectory information set of the unmanned cluster to obtain intermediate trajectory information;

[0012] S22, clustering identification processing is performed on the intermediate trajectory information and the motion trajectory information set to obtain a category information set of the unmanned cluster.

[0013] The expression of the intermediate quantity calculation is:

[0014]

[0015] wherein a i,kj is the jth element of the kth trajectory point coordinate of the ith unmanned device motion trajectory sequence, ω1 and ω2 are respectively a preset first weighting factor and a second weighting factor, is the mean value of the jth element of the kth trajectory point coordinate of all unmanned device motion trajectory sequences, I is the total number of unmanned devices, J is the total number of trajectory point coordinates, β k is the kth element of the intermediate trajectory information.

[0016] The clustering identification processing on the intermediate trajectory information and the motion trajectory information set to obtain a category information set of the unmanned cluster comprises:

[0017] S221, the motion trajectory sequence of each unmanned device in the motion trajectory information set is respectively subjected to feature decomposition to obtain corresponding feature components;

[0018] S222, the feature component of each unmanned device is respectively subjected to difference feature calculation with the intermediate trajectory information to obtain corresponding difference feature values;

[0019] S223, the difference feature values are subjected to value interval statistical processing to obtain a value interval of the difference feature values;

[0020] S224, the value interval is uniformly divided into three subintervals; the value ranges of the three subintervals are arranged from small to large.

[0021] S225, determining the category of the unmanned device corresponding to the feature component of the difference feature value falling into the smallest sub-interval as the communication type, determining the category of the unmanned device corresponding to the feature component of the difference feature value falling into the largest sub-interval as the calculation type, and determining the category of the unmanned device corresponding to the feature component of the difference feature value falling into the middle sub-interval as the mixed type;

[0022] S226, constructing the category information set of the unmanned cluster by using the categories of all the unmanned devices.

[0023] The expression of the difference feature calculation is:

[0024]

[0025] Wherein, N is the number of elements contained in the feature component, ct i and β i are the i-th elements of the feature component and the intermediate trajectory information respectively, cy is the difference feature value, and are the average value of the feature component and the average value of the intermediate trajectory information respectively.

[0026] The abnormal detection processing on the spatial electromagnetic information set is performed to obtain an electromagnetic abnormal situation information set, comprising:

[0027] The position coordinates of each location in the spatial electromagnetic information set are uniformly distributed on a two-dimensional plane;

[0028] The electromagnetic information of the surrounding area of each location is calculated to obtain the electromagnetic curl vector of each location; and the modulus value of the electromagnetic curl vector is taken to obtain the curl modulus value of each location;

[0029] The electromagnetic information of the surrounding area of each location is calculated to obtain the electromagnetic divergence value of each location;

[0030] The mode value of the curl modulus value and the electromagnetic divergence value of each location is calculated to obtain the mode value;

[0031] It is judged whether the mode value is greater than a preset first discrimination threshold to obtain a first discrimination result, and if the first discrimination result is greater, it is discriminated that the position coordinates and the electromagnetic information of the location corresponding to the mode value are electromagnetic abnormal situation information;

[0032] The electromagnetic abnormal situation information set is constructed by using all the electromagnetic abnormal situation information.

[0033] The expression of the mode value calculation is:

[0034]

[0035] Wherein, M is the number of the calculated vorticity modulus of a place, s1 i and s2 i are the calculated i-th vorticity modulus and i-th electromagnetic divergence value of a place, respectively, F i denotes the i-th Laguerre function, and md denotes the mode value.

[0036] In a second aspect, the present application discloses a situation analysis device for unmanned clusters, which comprises:

[0037] a memory storing executable program codes;

[0038] a processor coupled with the memory;

[0039] the processor invokes the executable program codes stored in the memory to execute the situation analysis method for unmanned clusters.

[0040] In a third aspect, the present application discloses a computer storage medium storing computer instructions, which are invoked by a computer to execute the situation analysis method for unmanned clusters.

[0041] In a fourth aspect, the present application discloses an information data processing terminal for implementing the situation analysis method for unmanned clusters.

[0042] The present application has the following advantages:

[0043] The present application synchronously collects spatial electromagnetic information (including position coordinates and electromagnetic parameters) and cluster trajectory data, realizes spatial superposition visualization of the two types of information through a subsequent display module, assists an operator in quickly positioning the intersection area of electromagnetic anomalies and cluster movement, and for example, identifies the risk scenario of "unmanned aerial vehicle formation crossing the radio frequency interference hotspot".

[0044] The abnormality detection processing combines the spatial and temporal distribution characteristics of electromagnetic information, can identify transient interference (such as pulse noise) and trend anomalies (such as the continuous increase of electromagnetic power in a certain area), and through linkage with trajectory information, can predict the time window when the cluster enters a high-risk area, and trigger an avoidance strategy in advance. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The present application is a method for implementing the flowchart. DETAILED DESCRIPTION

[0046] In order to better understand the content of the present application, an embodiment is given as follows.

[0047] Figure 1 Flow chart for implementing the method of the present application.

[0048] In a first aspect of the embodiments of the present application, a situation analysis method for an unmanned cluster is disclosed, comprising:

[0049] S1, a spatial electromagnetic information set and a motion trajectory information set of the unmanned cluster are collected; the spatial electromagnetic information set comprises electromagnetic information sets of the motion space where the unmanned cluster is located; the electromagnetic information set comprises the position coordinates and electromagnetic information of each location; the motion trajectory information set of the unmanned cluster comprises the motion trajectory sequence of each unmanned device of the unmanned cluster;

[0050] S2, type identification processing is performed on the motion trajectory information set of the unmanned cluster to obtain a category information set of the unmanned cluster;

[0051] S3, abnormality detection processing is performed on the spatial electromagnetic information set to obtain an electromagnetic abnormal situation information set;

[0052] S4, the motion trajectory information set, the category information set and the electromagnetic abnormal situation information set of the unmanned cluster are displayed.

[0053] The type identification processing on the motion trajectory information set of the unmanned cluster to obtain the category information set of the unmanned cluster comprises:

[0054] S21, intermediate quantity calculation is performed on the motion trajectory information set of the unmanned cluster to obtain intermediate trajectory information;

[0055] S22, clustering identification processing is performed on the intermediate trajectory information and the motion trajectory information set to obtain the category information set of the unmanned cluster.

[0056] The expression of the intermediate quantity calculation is:

[0057]

[0058]

[0059] wherein, a i,kj is the jth element of the kth trajectory point coordinate of the motion trajectory sequence of the ith unmanned device, ω1 and ω2 are respectively a preset first weighting factor and a second weighting factor, is the mean value of the jth element of the kth trajectory point coordinate of the motion trajectory sequence of all unmanned devices, I is the total number of unmanned devices, J is the total number of elements of the trajectory point coordinate, and β k is the kth element of the intermediate trajectory information.

[0060] The first to third elements of the trajectory point coordinates are respectively an x-axis coordinate, a y-axis coordinate and a z-axis coordinate of the trajectory point coordinates.

[0061] The intermediate quantity calculation expression non-linearly quantifies the difference between the trajectory point and the cluster mean value through a combination of a sine function and an exponential function: the sine term is sensitive to small deviations, highlighting the local fluctuation characteristics of the trajectory point (such as the position fine adjustment of a communication-type unmanned aerial vehicle); the exponential term is sensitive to large deviations, capturing the global offset characteristics of the trajectory point (such as the long-distance movement of a computing-type unmanned aerial vehicle); and the weighting factors ω1 and ω2 dynamically balance the local and global characteristics, adapting to the trajectory mode differences in different task scenarios.

[0062] The adaptive feature decomposition and clustering uses an EMD series algorithm (such as TVF-EMD, EEMD) to perform multi-scale decomposition on the trajectory coordinate sequence (S221), extracts feature components reflecting different frequency components (such as low-frequency trend items and high-frequency fluctuation items), and effectively suppresses the interference of sensor noise on the trajectory features. The difference feature calculation expression (cy) quantifies the similarity between the single-device trajectory and the cluster average trajectory through the normalization processing of the covariance and the Euclidean distance: the numerator reflects the coordinated change trend of the trajectory component and the cluster mean value (positive correlation for synchronous motion and negative correlation for reverse motion); the denominator normalizes the root mean square of the trajectory point difference to eliminate the scale effect; and finally the difference feature value is divided into three intervals (S224-S225), realizing the precise classification of communication-type (low difference), computing-type (high difference) and hybrid-type (moderate difference) devices, and solving the problem that the traditional “hard clustering” cannot distinguish the intermediate state. The intermediate trajectory information is used as a compressed representation of the global feature of the cluster, reducing the difference calculation complexity of the single-device trajectory and the global feature from O(I×J×K) to O(J×K) (I is the number of devices), which is particularly suitable for large-scale cluster scenarios.

[0063] The clustering and identification processing on the intermediate trajectory information and the set of motion trajectory information obtains a set of category information of the unmanned cluster, and includes the following steps.

[0064] S221, for each motion trajectory sequence of each unmanned device in the set of motion trajectory information, feature decomposition is performed respectively to obtain corresponding feature components;

[0065] The feature decomposition can use EMD, TVF-EMD, EEMD, etc.

[0066] The feature decomposition obtains corresponding feature components by performing feature decomposition on the x-axis coordinate sequence, the y-axis coordinate sequence and the z-axis coordinate sequence in the motion trajectory sequence respectively, and obtaining the mean value of each coordinate axis feature component to obtain the corresponding feature component.

[0067] S222, For each feature component of the unmanned device, perform difference feature calculation with the intermediate trajectory information to obtain the corresponding difference feature value;

[0068] S223, Perform statistical processing on the value intervals of all differential characteristic values ​​to obtain the value intervals of the differential characteristic values;

[0069] S224, the value range is evenly divided into three sub-intervals; the value ranges of the three sub-intervals are arranged from smallest to largest;

[0070] S225, determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the smallest sub-interval, which is the communication type; determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the largest sub-interval, which is the calculation type; determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the middle sub-interval, which is the mixed type.

[0071] S226: Using the categories of all unmanned equipment, construct a set of category information for the unmanned cluster.

[0072] The expression for calculating the differential features is:

[0073]

[0074] Where N is the number of elements contained in the feature component, ct i and β i Let be the i-th element of the feature component and the intermediate trajectory information, respectively, and cy be the difference feature value. and These are the average values ​​of the feature components and the average values ​​of the intermediate trajectory information, respectively.

[0075] The anomaly detection processing of the spatial electromagnetic information set to obtain an electromagnetic anomaly situation information set includes:

[0076] The location coordinates of each point in the spatial electromagnetic information set are uniformly distributed on a two-dimensional plane;

[0077] For the electromagnetic information of the surrounding area of ​​each location, the curl is calculated to obtain the electromagnetic curl vector of each location; the modulus of the electromagnetic curl vector is taken to obtain the curl modulus of each location.

[0078] For the electromagnetic information of the surrounding area of ​​each location, divergence calculation is performed to obtain the electromagnetic divergence value of each location;

[0079] Model values ​​are calculated for the curl modulus and electromagnetic divergence values ​​at each location to obtain the model values;

[0080] Determine whether the pattern value is greater than a preset first discrimination threshold to obtain a first discrimination result. If the first discrimination result is greater than, determine the location coordinates and electromagnetic information of the location corresponding to the pattern value, which is electromagnetic anomaly situation information.

[0081] By utilizing all electromagnetic anomaly situation information, a set of electromagnetic anomaly situation information is constructed.

[0082] The anomaly detection process describes the spatial variation law of the electromagnetic environment from the perspective of vector field by performing curl and divergence calculations on electromagnetic information uniformly distributed in a two-dimensional plane: the curl modulus reflects the spatial circulation characteristics of electromagnetic energy and can identify ring interference sources (such as radio frequency coil radiation); the electromagnetic divergence value quantifies the divergence or convergence trend of electromagnetic energy and detects point source interference (such as local radio frequency transmitting devices); the mode value calculation integrates curl and divergence characteristics, and by comparing with a preset threshold, it achieves high-sensitivity detection of concealed interference and gradual interference, making up for the defects of single-point threshold detection.

[0083] The system links and visualizes electromagnetic anomaly information with the movement trajectory and equipment category information of unmanned swarms, enabling operators to quickly locate affected equipment using spatial heat maps and trajectory markings. For example, when communication equipment enters an electromagnetic anomaly area, the system can automatically trigger anti-interference strategies such as frequency switching and power adjustment to ensure communication link stability.

[0084] The expression for calculating the pattern value is:

[0085]

[0086] Where M is the number of curl modulus values ​​calculated for a given location, s1 i and s2 i Let F be the calculated curl modulus and electromagnetic divergence value for a given location. i Let represent the i-th Laguerre function, and md represent the pattern value.

[0087] The anomaly detection processing of the spatial electromagnetic information set to obtain an electromagnetic anomaly situation information set includes:

[0088] The location coordinates of each point in the spatial electromagnetic information set are uniformly distributed on a two-dimensional plane;

[0089] Obtain the set of standard electromagnetic field values ​​for the surrounding area of ​​the location;

[0090] For the electromagnetic information of the surrounding area of ​​each location, the difference between the electromagnetic information and the standard electromagnetic field value set is calculated to obtain the corresponding difference value;

[0091] Determine whether the difference value is greater than a preset second discrimination threshold to obtain a second discrimination result. If the second discrimination result is greater than, determine the location coordinates and electromagnetic information of the location corresponding to the difference value, which is electromagnetic anomaly situation information.

[0092] By utilizing all electromagnetic anomaly situation information, a set of electromagnetic anomaly situation information is constructed.

[0093] The expression for calculating the difference is:

[0094]

[0095] Where yc is the difference value, A ij Let B be the standard value of the electromagnetic field at the i-th horizontal and j-th vertical position in the surrounding area of ​​the location. ij Let N be the electromagnetic field strength value at the i-th horizontal position and the j-th vertical position in the surrounding area of ​​the location, where N and M are the number of vertical and horizontal positions in the surrounding area, respectively.

[0096] The surrounding area of ​​each location is a square area centered on that location.

[0097] The electromagnetic information refers to the electromagnetic field strength and direction values.

[0098] A second aspect of the present invention discloses a situational analysis device for an unmanned swarm, the device comprising:

[0099] Memory containing executable program code;

[0100] A processor coupled to the memory;

[0101] The processor calls the executable program code stored in the memory to execute the situation analysis method for the unmanned swarm.

[0102] In a third aspect of this invention, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions, which, when invoked by a computer, are used to execute the situation analysis method for the unmanned swarm.

[0103] In a fourth aspect of this invention, an information data processing terminal is disclosed, which is used to implement the situational analysis method for the unmanned swarm.

[0104] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A situational analysis method for unmanned swarms, characterized in that, include: S1, Collect a set of spatial electromagnetic information and a set of motion trajectory information of the unmanned swarm; the set of spatial electromagnetic information includes the set of electromagnetic information of the motion space in which the unmanned swarm is located; the set of electromagnetic information includes the position coordinates and electromagnetic information of each location in the motion space in which the unmanned swarm is located; the set of motion trajectory information of the unmanned swarm includes the motion trajectory sequence of each unmanned device in the unmanned swarm. S2, perform type identification processing on the motion trajectory information set of the unmanned swarm to obtain a category information set of the unmanned swarm, including: S21, perform intermediate quantity calculations on the motion trajectory information set of the unmanned swarm to obtain intermediate trajectory information; S22, perform clustering and identification processing on the intermediate trajectory information and motion trajectory information set to obtain the category information set of the unmanned cluster; The expression for calculating the intermediate quantity is: Among them, a i,kj Let ω1 and ω2 be the j-th element of the coordinates of the k-th trajectory point in the motion trajectory sequence of the i-th unmanned device, where ω1 and ω2 are the preset first and second weighting factors, respectively. Let be the mean of the j-th element of the coordinates of the k-th trajectory point in the motion trajectory sequence of all unmanned devices, I be the total number of unmanned devices, J be the total number of elements in the trajectory point coordinates, and β be the mean of the j-th element. k This is the k-th element of the intermediate trajectory information; S3, perform anomaly detection processing on the spatial electromagnetic information set to obtain an electromagnetic anomaly situation information set; S4 displays the set of motion trajectory information, category information, and electromagnetic anomaly situation information of the unmanned swarm.

2. The situational analysis method for unmanned swarms as described in claim 1, characterized in that, The clustering and identification processing of the intermediate trajectory information and motion trajectory information sets yields a set of category information for the unmanned swarm, including: S221, Perform feature decomposition on the motion trajectory sequence of each unmanned device in the motion trajectory information set to obtain the corresponding feature components; S222, For each feature component of the unmanned device, perform difference feature calculation with the intermediate trajectory information to obtain the corresponding difference feature value; S223, Perform statistical processing on the value intervals of all differential characteristic values ​​to obtain the value intervals of the differential characteristic values; S224, the value range is evenly divided into three sub-intervals; the value ranges of the three sub-intervals are arranged from smallest to largest; S225, determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the smallest sub-interval, which is the communication type; determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the largest sub-interval, which is the calculation type; determine the category of unmanned equipment whose feature components correspond to the difference feature values ​​that fall into the middle sub-interval, which is the mixed type. S226: Using the categories of all unmanned equipment, construct a set of category information for the unmanned cluster.

3. The situational analysis method for unmanned swarms as described in claim 2, characterized in that, The expression for calculating the differential features is: Where N is the number of elements contained in the feature component, ct i and β i Let be the i-th element of the feature component and the intermediate trajectory information, respectively, and cy be the difference feature value. and These are the average values ​​of the feature components and the average values ​​of the intermediate trajectory information, respectively.

4. The situational analysis method for unmanned swarms as described in claim 1, characterized in that, The anomaly detection processing of the spatial electromagnetic information set to obtain an electromagnetic anomaly situation information set includes: The location coordinates of each point in the spatial electromagnetic information set are uniformly distributed on a two-dimensional plane; For the electromagnetic information of the surrounding area of ​​each location, the curl is calculated to obtain the electromagnetic curl vector of each location; the modulus of the electromagnetic curl vector is taken to obtain the curl modulus of each location. For the electromagnetic information of the surrounding area of ​​each location, divergence calculation is performed to obtain the electromagnetic divergence value of each location; Model values ​​are calculated for the curl modulus and electromagnetic divergence values ​​at each location to obtain the model values; Determine whether the pattern value is greater than a preset first discrimination threshold to obtain a first discrimination result. If the first discrimination result is greater than, determine the location coordinates and electromagnetic information of the location corresponding to the pattern value, which is electromagnetic anomaly situation information. By utilizing all electromagnetic anomaly situation information, a set of electromagnetic anomaly situation information is constructed.

5. The situational analysis method for unmanned swarms as described in claim 4, characterized in that, The expression for calculating the pattern value is: Where M is the number of curl modulus values ​​calculated for a given location, s1 i and s2 i Let F be the calculated curl modulus and electromagnetic divergence value for a given location. i Let represent the i-th Laguerre function, and md represent the pattern value.

6. A situational analysis device for an unmanned swarm, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the situation analysis method for the unmanned swarm as described in any one of claims 1 to 5.

7. A computer-storable medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked by the computer, are used to execute the situation analysis method for the unmanned swarm as described in any one of claims 1 to 5.

Images