A data-driven unmanned system cluster communication frequency adaptive adjustment method, system and storage medium

Abstract

The present invention relates to the field of unmanned system clusters and is directed to a data-driven adaptive adjustment method, system, and storage medium for communication frequency. The method addresses the problem that existing methods use the selection of communication frequency as a default fixed value or take communication frequency restrictions as a prerequisite, thus failing to adaptively adjust the communication frequency. The method comprises the following steps: first, obtaining flight status data of a cluster of unmanned aerial vehicles (UAVs) at different flight speeds and communication frequencies; second, defining an evaluation index for the flight status of the cluster based on the deviation of the flight status data of each UAV in the cluster during a turning section; third, calculating the cluster flight index and performing dimensionality reduction processing; fourth, fitting typical functions between different frequencies and the cluster flight index to determine a quantitative relationship between the two; and fifth, determining a quantitative functional relationship between the communication frequency and the cluster flight index at different flight speeds, and inversely solving the functional relationship to obtain the optimal communication frequency under specific requirements and conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned system clusters, and in particular to a data-driven method, system, and storage medium for adaptively adjusting the communication frequency of an unmanned system cluster. Background Art

[0002] In the context of UAV swarm flight control, determining the relationship between the communication frequency between each UAV and the ground station and the control performance of the swarm is a key issue. Traditional research on the relationship between communication frequency and control performance of UAV swarms typically uses the selection of communication frequency as a default fixed value or as a premise for limiting the communication frequency. The main research focuses on optimizing the communication topology network, optimizing the structure and parameters of the control method, and improving the communication mechanism. Examples include reconstructing the communication topology network in the UAV swarm and identifying key nodes, applying reinforcement learning-based control methods or integrating different control algorithms to improve algorithm robustness, and designing communication conditions as event-triggered.

[0003] For drones, which demand high real-time and accurate command execution, allocating computational tasks to their onboard processors is crucial. Optimizing the communication frequency based on control precision requirements can reduce the processor's computational load and achieve higher computational efficiency. However, few studies have examined the communication frequency within a cluster as a primary influencing variable, quantitatively investigating its relationship with cluster control performance and providing methods for adaptively adjusting the cluster communication frequency. Summary of the Invention

[0004] The technical problems to be solved by the present invention are:

[0005] Existing methods use the selection of the communication frequency as a default fixed value or take the limitation of the communication frequency as a premise, and are unable to adaptively adjust the communication frequency.

[0006] The present invention is to solve the above technical problems using the following technical solutions:

[0007] In order to determine and apply the relationship between communication frequency and cluster control performance in the scenario of UAV cluster flight control, the present invention provides a data-driven unmanned system cluster communication frequency adaptive adjustment method, comprising the following steps:

[0008] Step 1: Obtain flight status data of the drone cluster at different flight speeds and communication frequencies;

[0009] Step 2: defining an evaluation index of the cluster flight status based on the deviation of the flight status data of each UAV in the UAV cluster during the turning section;

[0010] Step 3: Based on the evaluation indicators defined in step 2, the flight status data is converted into flight index data, the cluster flight indexes under different flight speeds and communication frequencies are obtained, and the cluster flight indexes are subjected to dimensionality reduction processing;

[0011] Step 4: Fit the different frequencies to the corresponding cluster flight indicators after dimensionality reduction using typical functions to determine the quantitative relationship between the two;

[0012] Step 5: Determine the quantitative functional relationship between the communication frequency and cluster flight indicators at different flight speeds, and inversely solve the functional relationship to obtain the optimal communication frequency under specific requirements and conditions.

[0013] Furthermore, step 2 includes the following process:

[0014] The evaluation index of the cluster flight status is defined based on the average deviation of the flight speed, yaw angle, horizontal position and height of each UAV in the turning section from the average value, namely:

[0015] Let V i is the flight speed of the UAV numbered i in the cluster, then the flight speed of the cluster center at this moment is for:

[0016]

[0017] Where n is the number of drones in the cluster, and the average deviation from the average speed is defined as As an evaluation index of cluster flight speed:

[0018]

[0019] With Ψ i is the yaw angle of the UAV numbered i in the cluster, and the yaw angle of the cluster center for:

[0020]

[0021] Define the average deviation from the mean yaw angle As an evaluation indicator of cluster yaw angle:

[0022]

[0023] P i is the horizontal position of the UAV numbered i in the cluster, and the expected horizontal position of the cluster is Define the average deviation of each drone from the expected horizontal position As an evaluation indicator of the cluster level position:

[0024]

[0025] Let Hi be the height of the UAV numbered i in the cluster, and the expected height of the cluster is Define the average deviation of each drone from the expected altitude As an evaluation indicator of cluster height:

[0026]

[0027] Furthermore, in step three, the cluster flight index is subjected to dimensionality reduction processing, specifically: the average value of the index within a time interval is used as the index result of the period.

[0028] Furthermore, the typical function fitting in step 4 includes fitting using a power function and an exponential function.

[0029] The present invention provides a data-driven unmanned system cluster communication frequency adaptive adjustment system, which has a program module corresponding to the steps of the method described in any one of the above technical solutions, and executes the steps in the above-mentioned data-driven unmanned system cluster communication frequency adaptive adjustment method during operation.

[0030] The present invention provides a computer-readable storage medium, which stores a computer program. The computer program is configured to implement the steps of the data-driven unmanned system cluster communication frequency adaptive adjustment method described in any one of the above technical solutions when called by a processor.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The method of the present invention has the following advantages: 1) The communication frequency in the flight of unmanned aerial vehicle clusters is actively used as the main factor affecting the cluster control effect. By defining the formation control index and quantitatively fitting different communication frequencies, the influence of the communication frequency on the cluster flight is accurately obtained; 2) Through the obtained function fitting relationship, the relationship between the communication frequency and the cluster flight index requirements is reversed, and the minimum acceptable communication frequency under the cluster flight index requirements is obtained, which saves computing resources and can be used to improve the robustness of other algorithms; 3) The communication frequency is crucial for unmanned system clusters. The present invention verifies the correlation between the communication frequency and cluster control performance in unmanned aerial vehicle clusters. Similar ideas can also be used in other types of unmanned system communications, thereby saving overall computing and communication costs and improving the overall operating efficiency and robustness of the unmanned system.

[0033] The present invention can ensure the control effect of drone clusters, fit the quantitative relationship between communication frequency and cluster control indicators, and provide an adaptive adjustment method for communication frequency. This idea can be easily deployed in various unmanned systems, reducing the communication load of the unmanned systems and improving the overall computing efficiency of the unmanned systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Flowchart of a data-driven method for adaptively adjusting the frequency of unmanned system cluster communication in an embodiment of the present invention;

[0035] Figure 2 Schematic diagram of definitions of various cluster flight indicators in an embodiment of the present invention;

[0036] Figure 3 This is a diagram showing the average values ​​of various types of cluster flight data when the communication frequency is 50 Hz and the flight speed is 50 m / s in an embodiment of the present invention;

[0037] Figure 4 This is a graph showing the average deviation of various types of cluster flight data from the average / expected value when the communication frequency is 50 Hz and the flight speed is 50 m / s in an embodiment of the present invention;

[0038] Figure 5 This is a diagram showing the relationship between flight speed deviation, position deviation, and communication frequency fitting when the flight speed is 50 m / s in an embodiment of the present invention;

[0039] Figure 6 This is a diagram showing the average values ​​of various types of cluster flight data when the communication frequency is 50 Hz and the flight speed is 80 m / s in an embodiment of the present invention;

[0040] Figure 7 This is a graph showing the average deviation of various types of cluster flight data from the average / expected value when the communication frequency is 50 Hz and the flight speed is 80 m / s in an embodiment of the present invention;

[0041] Figure 8 This is a diagram showing the relationship between flight speed deviation, position deviation, and communication frequency fitting when the flight speed is 80 m / s in an embodiment of the present invention;

[0042] Figure 9 4 is a flow chart of a communication frequency adaptation method in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the present invention, exemplary embodiments or examples of the present invention will be described below with reference to the accompanying drawings. Obviously, the described embodiments or examples are only some of the embodiments or examples of the present invention, and not all of them. Based on the embodiments or examples of the present invention, all other embodiments or examples obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0045] Specific implementation plan 1: Figure 1 and 2 As shown, the present invention provides a data-driven unmanned system cluster communication frequency adaptive adjustment method, comprising the following steps:

[0046] Step 1: Obtain flight status data of the drone cluster at different flight speeds and communication frequencies;

[0047] Step 2: defining an evaluation index of the cluster flight status based on the deviation of the flight status data of each UAV in the UAV cluster during the turning section;

[0048] Step 3: Based on the evaluation indicators defined in step 2, the flight status data is converted into flight index data, the cluster flight indexes under different flight speeds and communication frequencies are obtained, and the cluster flight indexes are subjected to dimensionality reduction processing;

[0049] Step 4: Fit the different frequencies to the corresponding cluster flight indicators after dimensionality reduction using typical functions to determine the quantitative relationship between the two;

[0050] Step 5: Determine the quantitative functional relationship between the communication frequency and cluster flight indicators at different flight speeds, and inversely solve the functional relationship to obtain the optimal communication frequency under specific requirements and conditions.

[0051] The present invention takes the communication frequency during UAV swarm flight as the main variable affecting the swarm control performance, constructs a quantitative relationship between various indicators during UAV swarm flight and the communication frequency, and obtains adaptive communication frequency selection under the swarm control performance requirements. By adjusting the communication frequency under certain flight conditions, the flight control's computing and communication resources are saved, and the computing efficiency of the UAV swarm in flight is improved while ensuring the cluster control effect.

[0052] Specific implementation plan 2: Step 2 includes the following process:

[0053] The evaluation index of the cluster flight status is defined based on the average deviation of the flight speed, yaw angle, horizontal position and height of each UAV in the turning section from the average value, namely:

[0054] Let V i is the flight speed of the UAV numbered i in the cluster, then the flight speed of the cluster center at this moment is for:

[0055]

[0056] Where n is the number of drones in the cluster, and the average deviation from the average speed is defined as As an evaluation index of cluster flight speed:

[0057]

[0058] With Ψ i is the yaw angle of the UAV numbered i in the cluster, and the yaw angle of the cluster center for:

[0059]

[0060] Define the average deviation from the mean yaw angle As an evaluation indicator of cluster yaw angle:

[0061]

[0062] P i is the horizontal position of the UAV numbered i in the cluster, and the expected horizontal position of the cluster is Define the average deviation of each drone from the expected horizontal position As an evaluation indicator of the cluster level position:

[0063]

[0064] H i is the height of the UAV numbered i in the cluster, and the expected height of the cluster is Define the average deviation of each drone from the expected altitude As an evaluation indicator of cluster height:

[0065]

[0066] The rest of this embodiment is the same as the first specific embodiment.

[0067] Specific Implementation Plan Three: In step three, flight speed is used as the primary classification criterion. Various indicators at different communication frequencies are then fitted against the communication frequencies. Because the indicators represent the performance of a particular indicator within a specific time period, the fitted data is the average value of that indicator within that time period. The average value of the indicator within a time interval is used as the indicator result for that period. Dimensionality reduction is performed on the cluster flight indicators, ultimately yielding a quantitative evaluation of cluster flight indicators at different flight speeds and communication frequencies. This implementation plan is otherwise identical to Specific Implementation Plan Two.

[0068] Specific Implementation Method 4: In step 4, typical functions are fitted to the different frequencies and the corresponding cluster flight indicators after dimensionality reduction, such as linear, quadratic, and cubic power functions and exponential functions. The quadratic and exponential functions with relatively reasonable fitting relationships are retained. In this implementation, the exponential relationship is the best fitting relationship. This implementation method is otherwise identical to Specific Implementation Method 3.

[0069] Specific implementation plan five: Figure 9 As shown, the inverse solution of the relationship in step 5 is to obtain the inverse function of the fitted function. After obtaining the inverse functions of multiple indicators and communication frequency, the accuracy requirements of multiple indicators can be integrated in a segmented manner to obtain a communication frequency that meets the requirements. This embodiment is otherwise the same as the specific embodiment 4.

[0070] Specific implementation plan six: A data-driven unmanned system cluster communication frequency adaptive adjustment system, comprising:

[0071] The data acquisition module is used to organize and output various real-time data of each drone in the cluster through the simulation program interface;

[0072] The data processing module is used to slice and organize the obtained data according to classification standards such as drone number, certain indicator sequence and flight period;

[0073] The flight index calculation module is used to convert the processed data into index data, obtain cluster flight indicators at different frequencies, and perform average dimensionality reduction processing;

[0074] The indicator fitting module is used to perform function fitting on the indicator with average dimension reduction and the sampling frequency to obtain the relationship between the frequency change and each indicator;

[0075] The frequency calculation and output module is used to inversely analyze the relationship between various indicators and frequency, and then provide a recommended adaptive communication frequency by comprehensively considering the error accuracy requirements and changes of multiple indicators. This module inversely analyzes the obtained function fitting relationship to obtain the relationship between frequency and indicator accuracy requirements, and then provides a frequency adaptive value table to meet the frequency adaptive law.

[0076] The present invention stores a computer program for the developed system (software) on a computer-readable storage medium. The computer program is configured to implement the steps of the aforementioned data-driven method for adaptively adjusting the frequency of clustered communications for unmanned systems when invoked by a processor. This materializes the present invention on a carrier, becoming a computer program product.

[0077] Various implementations of the systems and techniques described herein can be realized in digital electronic circuitry, integrated circuitry, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] The computer programs (also referred to as programs, software, software applications, or code) of the present invention include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0079] The following examples are used to verify the beneficial effects of the present invention.

[0080] Example 1

[0081] In order to verify the universality of cluster flight indicators and communication frequencies, this embodiment takes two groups of cluster flight data at different flight speeds for comparison, calculates the average deviation of each indicator from the standard, and then performs dimensionality reduction average processing to facilitate the relationship between the indicator and the communication frequency. The experiment selects flight speed conditions of 50m / s and 80m / s and communication frequencies of 1Hz, 2Hz, 5Hz, 10Hz, 25Hz, and 50Hz as the experimental background, and uses the results collected by the fixed-wing UAV formation flight simulation program as input data to test the performance of various indicators in cluster flight and the effect of fitting with the communication frequency. The simulation test software environment is Windows 11+python 3.7.10, and the hardware environment is Intel(R)Core(TMi7-10870H CPU+16.0GB RAM+NVDIA GeForce GTX 1650Ti.

[0082] The experiment first conducted a formation flight experiment under the conditions of a flight speed of 50m / s and a communication frequency of 50Hz, and collected various flight data during the flight. First, the data was processed to obtain the average value of each flight state to ensure the credibility of the data. The average value of various cluster flight data under this condition is as follows Figure 3 As shown in the figure, we can see that the cluster flight maintains a speed of 50m / s most of the time. The changes in various indicators are related to the status of cluster flight, such as assembly and turning, and change accordingly. It is precisely because the changes in various indicators are more obvious in the turning section of the flight, so the sampling period of each indicator is the same turning section.

[0083] The average deviation of each flight status data from the average / expected value is visualized, see Figure 4 As shown in the figure, the variation trend of the mean value with flight time is the same as that of the mean deviation, which is around 0 in straight flight and varies to varying degrees in the assembly and turning sections.

[0084] Figure 5 The figure shows the communication frequency fitting results of various cluster flight indicators at 50 m / s. The fitting results of relatively reasonable quadratic function and exponential function are retained. In the final back-calculation process, the exponential function is used as the relationship between the two.

[0085] Figure 6 、 Figure 7 and Figure 8 The data and fitting results from a formation flying experiment at a speed of 80 m / s and a communication frequency of 50 Hz are shown. By obtaining the inverse function of the fitted function and the inverse functions of multiple indicators and communication frequency, the requirements of these indicators can be integrated in a segmented manner to obtain adaptive communication frequencies for different flight speeds and flight indicators, as shown in Tables 1 and 2.

[0086] Table 1

[0087] 50m / s 1Hz 2Hz 5Hz 10Hz 25Hz 50Hz Flight speed deviation (m / s) 0.41< 0.11< 0.08< 0.075< 0.074< 0.074< Yaw angle deviation (°) 1.65< 1.5< 1.35< 1.21< 1.03< 1.01< Horizontal position deviation (m) 14< 6.5< 5.5< 4.7< 4.65< 4.64< Height deviation (m) 0.14< 0.06< 0.055< 0.055< 0.055< 0.054

[0088] Table 2

[0089] 80m / s 1Hz 2Hz 5Hz 10Hz 25Hz 50Hz Flight speed deviation (m / s) 1.75< 0.08< 0.07< 0.07< 0.065< 0.065< Yaw angle deviation (°) 5.89< 1.62< 1.55< 1.53< 1.52< 1.52< Horizontal position deviation (m) 44< 3.0< 2.8< 3.0< 2.7< 2.7< Height deviation (m) 0.75< 0.38< 0.375< 0.369< 0.365< 0.364<

[0090] Tables 1 and 2 show that: 1) the performance of each cluster flight indicator at different speeds is negatively correlated with the change in communication frequency. That is, the higher the communication frequency, the smaller the deviation of each flight status data. 2) The indicator requirements at 80 m / s are higher than those at 50 m / s. That is, the higher the speed, the higher the required communication frequency. 3) According to the exponential relationship between the fitted indicator and communication frequency, there is no significant improvement in the indicator control effect at 25 Hz and 50 Hz. Therefore, the communication frequency can be appropriately reduced, sacrificing certain indicator performance to reduce the cluster communication load.

[0091] Although the present invention is disclosed as above, the scope of protection disclosed by the present invention is not limited thereto. Those skilled in the art of the present invention may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A data-driven method for adaptively adjusting the frequency of unmanned system cluster communication, characterized in that: The following steps are involved: Step 1: Obtain flight status data of the drone cluster at different flight speeds and communication frequencies; Step 2: defining an evaluation index of the cluster flight status based on the deviation of the flight status data of each UAV in the UAV cluster during the turning section; Step 3: Based on the evaluation indicators defined in step 2, the flight status data is converted into flight index data, the cluster flight indexes under different flight speeds and communication frequencies are obtained, and the cluster flight indexes are subjected to dimensionality reduction processing; Step 4: Fit the different frequencies to the corresponding cluster flight indicators after dimensionality reduction using typical functions to determine the quantitative relationship between the two; Step 5: Determine the quantitative functional relationship between the communication frequency and cluster flight indicators at different flight speeds, and inversely solve the functional relationship to obtain the optimal communication frequency under specific requirements and conditions.

2. The data-driven unmanned system cluster communication frequency adaptive adjustment method according to claim 1 is characterized in that: Step 2 includes the following process: The evaluation index of the cluster flight status is defined based on the average deviation of the flight speed, yaw angle, horizontal position and height of each UAV in the turning section from the average value, namely: Let V i is the flight speed of the UAV numbered i in the cluster, then the flight speed of the cluster center at this moment is for: Where n is the number of drones in the cluster, and the average deviation from the average speed is defined as As an evaluation index of cluster flight speed: With Ψ i is the yaw angle of the UAV numbered i in the cluster, and the yaw angle of the cluster center for: Define the average deviation from the mean yaw angle As an evaluation indicator of cluster yaw angle: P i is the horizontal position of the UAV numbered i in the cluster, and the expected horizontal position of the cluster is Define the average deviation of each drone from the expected horizontal position As an evaluation indicator of the cluster level position: H i is the height of the UAV numbered i in the cluster, and the expected height of the cluster is Define the average deviation of each drone from the expected altitude As an evaluation indicator of cluster height:

3. The data-driven unmanned system cluster communication frequency adaptive adjustment method according to claim 2, characterized in that: In step three, the cluster flight indicators are subjected to dimensionality reduction processing, specifically: the average value of the indicator within a time interval is used as the indicator result of the period.

4. The data-driven unmanned system cluster communication frequency adaptive adjustment method according to claim 3 is characterized in that: The typical function fitting described in step 4 includes fitting using a power function and an exponential function.

5. A data-driven unmanned system cluster communication frequency adaptive adjustment system, characterized in that: The system has a program module corresponding to the steps of the method described in any one of claims 1 to 4 above, and executes the steps in the above data-driven unmanned system cluster communication frequency adaptive adjustment method during operation.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is configured to implement the steps of the data-driven unmanned system cluster communication frequency adaptive adjustment method according to any one of claims 1 to 4 when called by a processor.

Images