A threat degree prediction method and radar detection device of a UAV
By acquiring the relative position information of UAVs from radar detection equipment and dividing the position range, and setting adaptive factors to adjust the threat prediction model, the problem of inaccurate assessment of UAV threat level in existing technologies is solved, and adaptive assessment and timely early warning of UAV threat level are realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AUTEL INTELLIGENT AUTOMOBILE CORP LTD
- Filing Date
- 2023-06-05
- Publication Date
- 2026-06-26
AI Technical Summary
Existing methods for assessing the threat level of drones cannot accurately reflect the threat level posed by drones to defense points, resulting in the inability to provide timely and accurate early warnings.
By acquiring the relative position information of the UAV with respect to the radar detection equipment, dividing the position intervals, and adjusting the threat prediction model according to the different intervals, the threat level prediction value is determined, thereby achieving an adaptive assessment of the threat level of the UAV.
It improves the accuracy and timeliness of drone threat prediction, accurately reflects the threat level of drones to defense points, and ensures timely early warning.
Smart Images
Figure CN116774214B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of technology, specifically to a method for predicting the threat level of unmanned aerial vehicles (UAVs) and a radar detection device. Background Technology
[0002] With the rapid development of drone products, the density of drones appearing in low-altitude airspace is constantly increasing, posing a potential threat to the security of defense points located in low-altitude airspace. Therefore, it is necessary for defense points to assess the threat level of drones relative to the defense points in real time in order to provide timely warnings.
[0003] Current threat assessment methods often fail to accurately reflect the threat level of drones relative to defense points, hindering timely and accurate early warning. Summary of the Invention
[0004] One objective of this invention is to provide a method for predicting the threat level of unmanned aerial vehicles (UAVs) and a radar detection device, which can overcome the deficiencies existing in the prior art.
[0005] In a first aspect, embodiments of the present invention provide a method for predicting the threat level of a drone, comprising:
[0006] Acquire at least one type of relative position information of the UAV relative to the radar detection device, wherein each type of relative position information corresponds to multiple preset position intervals;
[0007] Among the multiple location intervals, the location interval corresponding to the at least one type of relative location information is determined as the target location interval. Different location intervals correspond to different preset adaptive factors. The preset adaptive factors are factors used to adaptively adjust the output of the preset threat prediction model.
[0008] A preset adaptive factor corresponding to the target location interval is determined as the target adaptive factor;
[0009] The threat prediction value is determined based on a preset threat prediction model, the at least one type of relative position information, and the target adaptive factor, wherein the threat prediction value is used to evaluate the degree of threat posed by the UAV to the radar detection equipment.
[0010] Optionally, the position interval has a first monotonic relationship with the preset adaptive factor.
[0011] Optionally, the target adaptive factor has a second monotonic relationship with the threat prediction value.
[0012] Optionally, when the predicted threat level is positively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the same as the first monotonic relationship;
[0013] When the predicted threat level is negatively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the opposite of the first monotonic relationship.
[0014] Optionally, the preset threat prediction model includes a prediction sub-model corresponding to each type of relative position information, and determining the threat prediction value based on the preset threat prediction model, the relative position information, and the target adaptive factor includes:
[0015] Based on the relative position information of each type and the target adaptive factor and preset sub-model corresponding to each type of relative position information, calculate the threat value corresponding to each type of relative position information;
[0016] The threat level prediction value is determined based on the threat values corresponding to at least two types of relative location information.
[0017] Optionally, the threat value corresponding to each type of relative location information is normalized, and determining the predicted threat level based on the threat values corresponding to at least two types of relative location information includes:
[0018] The threat values corresponding to at least two types of relative position information are fused to obtain a threat prediction value.
[0019] Optionally, the relative position information includes relative distance, the prediction sub-model includes a distance threat model, and the step of calculating the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model includes:
[0020] Based on the distance threat model and the target adaptive factor corresponding to the relative distance, the relative distance is normalized to obtain the threat value corresponding to the relative distance. The threat value corresponding to the relative distance is positively correlated with the relative distance.
[0021] Optionally, the relative position information includes relative altitude, the prediction sub-model includes a height threat model, and the step of calculating the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model includes:
[0022] Based on the height threat model and the target adaptive factor corresponding to the relative height, the relative height is normalized to obtain the threat value corresponding to the relative height, and the threat value corresponding to the relative height is positively correlated with the relative height.
[0023] In a second aspect, embodiments of the present invention provide a radar detection device, comprising:
[0024] At least one processor;
[0025] And, a memory communicatively connected to the at least one processor; wherein,
[0026] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described above.
[0027] In a third aspect, embodiments of the present invention provide a non-volatile computer storage medium storing computer-executable instructions for causing an electronic device to perform the method described above.
[0028] A threat prediction method for unmanned aerial vehicles (UAVs) provided in this embodiment of the invention includes: acquiring at least one type of relative position information of the UAV relative to a radar detection device, each type of relative position information corresponding to multiple preset position intervals; determining the position interval corresponding to the at least one type of relative position information as a target position interval among the multiple position intervals; different position intervals corresponding to different preset adaptive factors; the preset adaptive factors are factors that can adaptively adjust the output of a preset threat prediction model; determining the preset adaptive factor corresponding to the target position interval as a target adaptive factor; and determining a threat prediction value based on the preset threat prediction model, the at least one type of relative position information, and the target adaptive factor. Therefore, this embodiment can adjust the target adaptive factor of the preset threat prediction model according to the real-time position of the UAV, making the threat prediction value adaptive to the real-time position of the UAV. This is beneficial for predicting a more ideal threat level, making the threat prediction more realistically reflect the threat level of the UAV relative to the defense point, and thus facilitating timely and accurate early warning. Attached Figure Description
[0029] One or more embodiments are illustrated by way of example only, and these illustrative examples do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements, and unless otherwise stated, the figures in the drawings do not constitute a limitation on scale.
[0030] Figure 1 This is a schematic diagram of an application environment provided by an embodiment of the present invention;
[0031] Figure 2 This is a schematic diagram of the structure of a radar detection device provided in an embodiment of the present invention;
[0032] Figure 3 This is a flowchart illustrating a threat prediction method for unmanned aerial vehicles (UAVs) provided in an embodiment of the present invention.
[0033] Figure 4 This is a schematic diagram of a relative position provided in an embodiment of the present invention;
[0034] Figure 5 yes Figure 3 The flowchart of S304 is shown below;
[0035] Figure 6 This is a simulation diagram of a Sigmoid function curve provided in an embodiment of the present invention;
[0036] Figure 7 This is a schematic diagram of the structure of a threat prediction device for unmanned aerial vehicles provided in an embodiment of the present invention;
[0037] Figure 8 yes Figure 7 The diagram shows the structure of the third determining module;
[0038] Figure 9 This is a schematic diagram of the hardware structure of a controller provided in an embodiment of the present invention. Detailed Implementation
[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.
[0040] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.
[0041] Please see Figure 1 , Figure 1 This is a schematic diagram of an application environment provided by an embodiment of the present invention. For example... Figure 1 As shown, the application environment includes radar detection equipment 100 and unmanned aerial vehicle 200.
[0042] Radar detection device 100 is an electronic device that uses electromagnetic waves to detect targets such as drones. Radar detection device 100 can emit electromagnetic waves to scan one or more drones 200 and receive their echoes, thereby obtaining information such as the position (distance and altitude), speed, and azimuth of the drone 200 relative to the electromagnetic wave emission point. Based on the acquired information, radar detection device 100 can assess the threat level of each drone 200 relative to radar detection device 100, thus providing timely early warning for drones 200 posing a greater threat.
[0043] Radar detection equipment 100 can be any suitable type of radar detection equipment, such as mechanically scanned radar or phased array radar. Among them, mechanically scanned radar is a type of radar that achieves beam scanning by rotating the radar antenna. Phased array radar, also known as phased array radar, is a type of radar that changes the direction of the beam by changing the phase of the radar wave. Because it controls the beam electronically rather than by rotating the antenna surface mechanically, it is also called electronically scanned radar phased array technology.
[0044] In some embodiments, please refer to Figure 2 The radar detection device 100 includes a phased array antenna 101, a transmit / receive component 102, a data converter 103, and a controller 104.
[0045] The phased array antenna 101 can be used in scanning UAV 200. It is an antenna that changes its radiation pattern shape by controlling the feed phase of the radiating elements in the array antenna. The phased array antenna 101 can be a linear phased array antenna or a planar phased array antenna. Linear phased array antennas can be classified into vertical-fired arrays and end-fired arrays based on their basic array type. In a vertical-fired array, the maximum radiation direction is perpendicular to the array axis, and the antenna beam scans to the left and right sides of the linear array normal direction. In an end-fired array, the main lobe direction is along the array axis. A planar phased array antenna refers to an array antenna in which the antenna elements are distributed on a plane, and the antenna beam can be phase-controlled scanned in both azimuth and elevation directions.
[0046] The phased array antenna 101 can be composed of multiple radiating elements. A radiating element is a unit that constitutes the basic structure of the antenna and can effectively radiate or receive radio frequency signals.
[0047] The transmit / receive component 102 is electrically connected to the phased array antenna 101 and is responsible for transmitting and receiving radio frequency signals, controlling the amplitude and phase of the signals to complete beamforming and beam scanning.
[0048] The transmitting / receiving component 102 may include multiple transmitting / receiving units, each of which may be paired with a radiating unit. Each transmitting / receiving component is capable of transmitting radio frequency signals to the corresponding radiating unit and receiving radio frequency signals transmitted by the corresponding radiating unit.
[0049] The data converter 103 is electrically connected to the transmitter / receiver component 102. The data converter 103 is used to receive the radio frequency signals transmitted by the transmitter / receiver component 102, convert the radio frequency signals into digital signals, or transmit radio frequency signals to the transmitter / receiver component 102.
[0050] The controller 104 is electrically connected to the data converter 103 and is used to receive and process the digital signals transmitted by the data converter 103 to obtain information such as the position and speed of the UAV 200 relative to the radar detection device 100, or to transmit digital signals to the data converter 103 so that the data converter 103 can convert the digital signals into radio frequency signals and transmit them to the transmitter / receiver component 102.
[0051] Controller 104 can be any general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), microcontroller, ARM (Acorn RISC Machine) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. Furthermore, controller 104 can also be any conventional processor, controller, microcontroller, or state machine. Controller 104 can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP, and / or any other such configuration.
[0052] The controller 104, as the control core of the radar detection device 100, is used to execute the threat prediction method for UAVs as described below.
[0053] Drone 200 refers to unmanned aerial vehicles that can fly in any airspace, such as low altitude, medium altitude, and high altitude, including fixed-wing drones, rotary-wing drones, unmanned airships, paragliding drones, flapping-wing drones, and so on.
[0054] This invention provides a threat prediction method for unmanned aerial vehicles (UAVs), which is applied to radar detection equipment. Please refer to... Figure 3 Threat prediction methods include:
[0055] S301. Obtain at least one type of relative position information of the UAV relative to the radar detection equipment, and each type of relative position information corresponds to multiple preset position intervals;
[0056] In this step, the relative position information refers to the current position of the UAV in space relative to the radar detection equipment. This relative position information can include any type of positional information such as relative distance, relative altitude, and straight-line distance. Please refer to [link / reference]. Figure 4The plane where the radar detection equipment is located and is parallel to the horizontal plane is defined as plane P1, and the plane where the UAV is located and is perpendicular to plane P1 is defined as plane P2. Based on this definition, the relative distance is the vertical distance between the radar detection equipment and plane P2, the relative height is the vertical distance between the UAV and plane P1, and the straight-line distance is the shortest distance between the UAV and the radar detection equipment.
[0057] The location interval is a pre-defined interval obtained by dividing the location type corresponding to each type of relative location information within a preset location range according to a preset division method. Each type of relative location information can correspond to multiple location intervals, and different types of relative location information correspond to different location intervals.
[0058] The location range can be either a distance range or an altitude range. When the relative location information includes relative distance, the relative distance can correspond to multiple distance ranges, for example, multiple distance ranges can be (0, 800 meters), (800 meters, 1400 meters), and (1400 meters, 2000 meters). When the relative location information includes relative altitude, the relative altitude can correspond to multiple altitude ranges, for example, multiple altitude ranges can be (0, 200 meters), (200 meters, 400 meters), and (400 meters, 600 meters).
[0059] S302. Among multiple location intervals, the location interval corresponding to at least one type of relative location information is determined as the target location interval. Different location intervals correspond to different preset adaptive factors. The preset adaptive factors are factors used to adaptively adjust the output of the preset threat prediction model.
[0060] In this step, the target location interval is the location interval into which each type of relative location information falls within its corresponding multiple location intervals. The target location interval can be a target distance interval or a target height interval. When the relative location information includes relative distance, the target distance interval is the distance interval into which the relative distance falls within its corresponding multiple distance intervals. When the relative location information includes relative height, the target height interval is the height interval into which the relative height falls within its corresponding multiple height intervals.
[0061] For example, as mentioned earlier, when the relative position information includes relative distance: when the relative distance is 500 meters, 500 meters falls within the distance interval (0, 800 meters), then the radar detection device will determine the distance interval (0, 800 meters) corresponding to 500 meters as the target distance interval. When the relative distance is 1000 meters, 1000 meters falls within the distance interval (800 meters, 1400 meters), then the radar detection device will determine the distance interval (800 meters, 1000 meters) corresponding to 1000 meters as the target distance interval. When the relative distance is 1500 meters, 1500 meters falls within the distance interval (1400 meters, 2000 meters), then the radar detection device will determine the distance interval (1400 meters, 2000 meters) corresponding to 1500 meters as the target distance interval.
[0062] For example, as mentioned earlier, when the relative position information includes relative height: when the relative height is 100 meters, 100 meters falls within the height range (0, 200 meters), then the radar detection equipment will determine the height range (0, 200 meters) corresponding to 100 meters as the target height range. When the relative height is 300 meters, 300 meters falls within the height range (200 meters, 400 meters), then the radar detection equipment will determine the height range (200 meters, 400 meters) corresponding to 300 meters as the target height range. When the relative height is 500 meters, 500 meters falls within the height range (400 meters, 600 meters), then the radar detection equipment will determine the height range (400 meters, 600 meters) corresponding to 500 meters as the target height range.
[0063] In some embodiments, as described above, the distance intervals (0, 800 meters), (800 meters, 1400 meters), and (1400 meters, 2000 meters) can be configured with preset adaptive factors, wherein the preset adaptive factors corresponding to each distance interval are different from each other. The altitude intervals (0, 200 meters), (200 meters, 400 meters), and (400 meters, 600 meters) can also be configured with preset adaptive factors, wherein the preset adaptive factors corresponding to each altitude interval are different from each other.
[0064] The preset adaptive factor is a factor used to adaptively adjust the output of the preset threat prediction model. The preset threat prediction model is a model used to predict the threat level of the UAV to the radar detection equipment at different relative positions. The output of the preset threat prediction model is used to indicate the current threat level of the UAV to the radar detection equipment. Therefore, when different preset adaptive factors are used, the output of the preset threat prediction model will change accordingly, that is, the threat level of the current UAV to the radar detection equipment indicated by the output will also change accordingly.
[0065] In some embodiments, the position interval and the preset adaptive factor exhibit a first monotonic relationship. The first monotonic relationship is the relationship in which the preset adaptive factor changes monotonically with the position interval. This monotonic change can be monotonically increasing, in which case the first monotonic relationship is monotonically increasing; or it can be monotonically decreasing, in which case the first monotonic relationship is monotonically decreasing. When the first monotonic relationship is monotonically increasing, the larger the position interval, the larger the preset adaptive factor; conversely, when the first monotonic relationship is monotonically decreasing, the larger the position interval, the smaller the preset adaptive factor.
[0066] For example, as mentioned above, when the relative position information includes relative distance: when the first monotonic relationship is a monotonically increasing relationship, the distance interval (0, 800 meters) can correspond to a preset adaptive factor of 400, the distance interval (800 meters, 1400 meters) can correspond to a preset adaptive factor of 700, and the distance interval (1400 meters, 2000 meters) can correspond to a preset adaptive factor of 1000.
[0067] When the first monotonic relationship is a monotonically decreasing relationship, the distance interval (0, 800 meters) can correspond to a preset adaptive factor of 1000, the distance interval (800 meters, 1400 meters) can correspond to a preset adaptive factor of 700, and the distance interval (1400 meters, 2000 meters) can correspond to a preset adaptive factor of 400.
[0068] For another example, as mentioned earlier, when the relative position information includes relative height: when the first monotonic relationship is a monotonically increasing relationship, the height interval (0, 200 meters) can correspond to a preset adaptive factor of 200, the height interval (200 meters, 400 meters) can correspond to a preset adaptive factor of 400, and the height interval (400 meters, 600 meters) can correspond to a preset adaptive factor of 600.
[0069] When the first monotonic relationship is a monotonically decreasing relationship, the height interval (0, 200 meters) can correspond to a preset adaptive factor of 600, the height interval (200 meters, 400 meters) can correspond to a preset adaptive factor of 400, and the height interval (400 meters, 600 meters) can correspond to a preset adaptive factor of 200.
[0070] Therefore, this embodiment sets the relationship between the location interval and the preset adaptive factor to be monotonically increasing or monotonically decreasing, which is beneficial for adjusting the output of the preset threat prediction model in a positive or negative direction, and can reduce the difficulty of adjusting the output of the preset threat prediction model.
[0071] S303. Determine the preset adaptive factor corresponding to the target location interval as the target adaptive factor;
[0072] In this step, the target adaptive factor is the preset adaptive factor that corresponds to the target position interval among multiple preset adaptive factors.
[0073] For example, as mentioned earlier, when the relative position information includes relative distance: if the distance interval (800 meters, 1400 meters) is the target position interval, then the preset adaptive factor 700 corresponding to the distance interval (800 meters, 1400 meters) is the target adaptive factor.
[0074] For another example, as mentioned earlier, when the relative position information includes relative height: if the height range (200 meters, 400 meters) is the target position range, then the preset adaptive factor 400 corresponding to the height range (200 meters, 400 meters) is the target adaptive factor.
[0075] In some embodiments, the target adaptation factor has a second monotonic relationship with the threat prediction value, wherein the threat prediction value is used to evaluate the degree of threat posed by the UAV to the radar detection equipment.
[0076] The second monotonic relationship is the relationship between the predicted threat level and the target adaptive factor, which changes monotonically. This monotonic change can be monotonically increasing, in which case the second monotonic relationship is monotonically increasing; conversely, it can be monotonically decreasing, in which case the second monotonic relationship is monotonically decreasing. When the second monotonic relationship is monotonically increasing, the larger the target adaptive factor, the larger the predicted threat level; conversely, when the second monotonic relationship is monotonically decreasing, the larger the target adaptive factor, the smaller the predicted threat level.
[0077] Therefore, this embodiment sets the relationship between the target adaptive factor and the threat prediction value to be monotonically increasing or monotonically decreasing, which is beneficial for adjusting the threat prediction value in a positive or negative direction. This helps to adjust the threat level of the UAV relative to the radar detection equipment to an ideal state and reduces the difficulty of adjusting the threat level.
[0078] S304. Determine the threat level prediction value based on the preset threat prediction model, at least one type of relative position information, and target adaptive factor. The threat level prediction value is used to evaluate the degree of threat posed by the UAV to the radar detection equipment.
[0079] Therefore, this embodiment can adjust the target adaptive factor of the preset threat prediction model according to the real-time position of the UAV, so that the threat prediction value adapts to the real-time position of the UAV, which is conducive to predicting a more ideal threat level and making the threat level prediction more realistically reflect the threat level of the UAV relative to the defense point, thereby facilitating timely and accurate early warning.
[0080] In some embodiments, when the threat prediction value is positively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the same as the first monotonic relationship.
[0081] For example, the threat level prediction value is a value between 0 and 1. The closer the value is to 1, the higher the threat level of the drone relative to the radar detection equipment. The closer the value is to 0, the lower the threat level of the drone relative to the radar detection equipment. In this case, if the second monotonic relationship is monotonically increasing, the first monotonic relationship is also monotonically increasing. If the second monotonic relationship is monotonically decreasing, the first monotonic relationship is also monotonically decreasing.
[0082] The second monotonic relationship, being monotonically increasing, means that the larger the target adaptive factor, the greater the predicted threat level, and the higher the threat level of the UAV relative to the radar detection equipment. The first monotonic relationship, also monotonically increasing, means that the larger the position interval, the larger the preset adaptive factor. The target adaptive factor is a preset adaptive factor corresponding to the relative position information. Therefore, when the position interval corresponding to the relative position information is larger, the target adaptive factor is also larger, the predicted threat level is also larger, and the threat level of the UAV relative to the radar detection equipment is also higher. This allows the threat level to be adjusted upwards when the UAV is far from the radar detection equipment, avoiding a rapid decrease in threat level when the UAV is far from the radar detection equipment. The further the UAV is from the radar detection equipment, the more gradual the decrease in threat level, which is conducive to predicting a more ideal threat level.
[0083] The second monotonic relationship, being a monotonically decreasing relationship, means that the larger the target adaptive factor, the smaller the predicted threat level, and the lower the threat level of the UAV relative to the radar detection equipment. The first monotonic relationship, being a monotonically increasing relationship, means that the larger the position interval, the smaller the preset adaptive factor. The target adaptive factor is a preset adaptive factor corresponding to the relative position information. Therefore, when the position interval corresponding to the relative position information is larger, the target adaptive factor is smaller, the predicted threat level is larger, and the threat level of the UAV relative to the radar detection equipment is higher. This allows the threat level to be adjusted higher when the UAV is far from the radar detection equipment, avoiding the threat level decreasing too quickly when the UAV is far from the radar detection equipment. The further the UAV is from the radar detection equipment, the more gradually the threat level decreases, which is conducive to predicting a more ideal threat level.
[0084] In some embodiments, when the threat prediction value is negatively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the opposite of the first monotonic relationship.
[0085] For example, the threat level prediction value is a value between 0 and 1. The closer the value is to 1, the lower the threat level of the drone relative to the radar detection equipment. The closer the value is to 0, the higher the threat level of the drone relative to the radar detection equipment. In this case, if the second monotonic relationship is monotonically increasing, then the first monotonic relationship is monotonically decreasing. If the second monotonic relationship is monotonically decreasing, then the first monotonic relationship is monotonically increasing.
[0086] The second monotonic relationship, being monotonically increasing, means that the larger the target adaptive factor, the greater the predicted threat level, and the lower the threat level of the UAV relative to the radar detection equipment. The first monotonic relationship, being monotonically decreasing, means that the larger the position interval, the smaller the preset adaptive factor. The target adaptive factor is a preset adaptive factor corresponding to the relative position information. Therefore, when the position interval corresponding to the relative position information is larger, the target adaptive factor is smaller, the predicted threat level is smaller, and the threat level of the UAV relative to the radar detection equipment is higher. This allows the threat level to be adjusted higher when the UAV is far from the radar detection equipment, avoiding a rapid decrease in threat level when the UAV is far from the radar detection equipment. The further away the UAV is from the radar detection equipment, the more gradual the decrease in threat level, which is conducive to predicting a more ideal threat level.
[0087] The second monotonic relationship, being a monotonically decreasing relationship, means that the larger the target adaptive factor, the smaller the predicted threat level, and the higher the threat level of the UAV relative to the radar detection equipment. The first monotonic relationship, being a monotonically increasing relationship, means that the larger the position interval, the larger the preset adaptive factor. The target adaptive factor is a preset adaptive factor corresponding to the relative position information. Therefore, when the relative position information falls into a larger position interval, the target adaptive factor is larger, the predicted threat level is smaller, and the threat level of the UAV relative to the radar detection equipment is higher. This allows the threat level to be adjusted upwards when the UAV is far from the radar detection equipment, avoiding a rapid decrease in threat level when the UAV is far from the radar detection equipment. The further the UAV is from the radar detection equipment, the more gradual the decrease in threat level, which is conducive to predicting a more ideal threat level.
[0088] In some embodiments, the preset threat prediction model includes a prediction sub-model corresponding to each type of relative location information.
[0089] In some embodiments, the prediction sub-model includes a distance threat model and an altitude threat model. As mentioned above, when the relative position information includes relative distance, the prediction sub-model corresponding to the relative distance is the distance threat model; when the relative position information includes relative altitude, the prediction sub-model corresponding to the relative altitude is the altitude threat model. The distance threat model is used to predict the threat level of a drone to radar detection equipment at different relative distances, and the altitude threat model is used to predict the threat level of a drone to radar detection equipment at different relative altitudes.
[0090] In some embodiments, please refer to Figure 5 S304 includes:
[0091] S3041. Calculate the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model.
[0092] For example, as mentioned above, the relative position information includes relative distance and relative height. The controller calculates the threat value corresponding to the relative distance based on the relative distance, the target adaptive factor corresponding to the relative distance, and the distance threat model, and calculates the threat value corresponding to the relative height based on the relative height, the target adaptive factor corresponding to the relative height, and the height threat model.
[0093] In some embodiments, the controller normalizes the relative distance according to the distance threat model and the target adaptive factor corresponding to the relative distance to obtain the threat value corresponding to the relative distance, and the threat value corresponding to the relative distance is positively correlated with the relative distance.
[0094] Normalizing the relative distance is beneficial for predicting the threat level of UAVs relative to radar detection equipment in the dimension of distance threat. Standardizing the distance prediction index eliminates the differences between different prediction indices, which is conducive to combining multiple different prediction indices for comprehensive evaluation, and thus improves the prediction of threat level.
[0095] The fact that the threat value corresponding to relative distance is positively correlated with the relative distance means that the greater the relative distance, the greater the threat value corresponding to the relative distance, and the smaller the relative distance, the smaller the threat value corresponding to the relative distance.
[0096] In some embodiments, the distance threat model can be based on any suitable type of normalization model that can normalize relative distances, such as the Sigmoid normalization model, the Min-MaX normalization model, the Z-Score normalization model, the Log normalization model, and so on.
[0097] In some embodiments, the distance threat model is based on a Sigmoid normalized model.
[0098] The Sigmoid normalization model is a normalization model based on the Sigmoid function. The output range of the Sigmoid function is (0, 1), that is, the value range of the Sigmoid function is between 0 and 1. The expression of the Sigmoid function is as follows:
[0099]
[0100] Figure 6 This is a simulation diagram of the Sigmoid function curve. Figure 6 As shown, the Sigmoid function approaches a smooth state when x approaches positive or negative infinity, and σ(x) approaches 0 when x approaches negative infinity and approaches 1 when x approaches positive infinity.
[0101] In some embodiments, the distance threat model is expressed by the following formula:
[0102]
[0103] Among them, Th d denoted as the threat value corresponding to the relative distance, where d is the relative distance and D is the target adaptive factor corresponding to the relative distance.
[0104] As mentioned earlier, taking the first monotonic relationship as a monotonically increasing relationship as an example, when the relative distance d is 500 meters, the target adaptation factor D corresponding to 500 meters is 400. Then, the threat value Th corresponding to the relative distance is... d The value is 0.223. When the relative distance d is 1000 meters, the target adaptation factor D corresponding to 1000 meters is 700. Then the threat value Th corresponding to the relative distance is... d The value is 0.105. When the relative distance d is 1500 meters, the target adaptation factor D corresponding to 1500 meters is 1000. Then the threat value Th corresponding to the relative distance is... d It is 0.076.
[0105] It is understandable that if D is a fixed value of 400, then when the relative distance d is 500 meters, the threat value Th corresponding to that relative distance is... d The threat value Th is 0.223 when the relative distance d is 1000 meters. d The threat value Th is 0.0005 when the relative distance d is 1500 meters. d It is 0.000001.
[0106] Therefore, this embodiment can adjust the target adaptive factor of the distance threat model according to the relative distance between the UAV and the radar detection device, so that the threat value corresponding to the relative distance adapts to the relative distance, avoiding the threat value corresponding to the relative distance from decreasing too quickly when the relative distance is far, which is conducive to predicting a more ideal threat level.
[0107] In some embodiments, the controller normalizes the relative height according to the height threat model and the target adaptive factor corresponding to the relative height to obtain the threat value corresponding to the relative height, and the threat value corresponding to the relative height is positively correlated with the relative height.
[0108] Normalizing relative altitude is beneficial for predicting the threat level of UAVs relative to radar detection equipment in the dimension of altitude threat. Standardizing altitude prediction indicators eliminates differences between different prediction indicators (such as altitude prediction indicators and distance prediction indicators), which is conducive to combining multiple different prediction indicators for comprehensive evaluation, and thus facilitates the prediction of threat level.
[0109] The positive correlation between the threat value and relative altitude means that the higher the relative altitude, the greater the threat value, and the lower the relative altitude, the smaller the threat value.
[0110] In some embodiments, the high threat model can be based on any suitable type of normalization model that can normalize the relative height, such as the Sigmoid normalization model, the Min-MaX normalization model, the Z-Score normalization model, the Log normalization model, and so on.
[0111] In some embodiments, the high-threat model is based on a Sigmoid normalized model.
[0112] In some embodiments, the high-threat model is expressed by the following formula:
[0113]
[0114] Among them, Th h Let h be the threat level corresponding to the relative height, and H be the target adaptive factor corresponding to the relative height.
[0115] As mentioned earlier, taking the first monotonic relationship as a monotonically increasing relationship as an example, when the relative height h is 100 meters, the target adaptive factor H corresponding to 100 meters is 200. Then, the threat value Th corresponding to the relative height is... h The value is 0.5. When the relative height h is 300 meters, the target adaptation factor H corresponding to 300 meters is 400. Then the threat value Th corresponding to the relative height is... hThe value is 0.223. When the relative height h is 500 meters, the target adaptation factor H corresponding to 500 meters is 600. Then the threat value Th corresponding to the relative height is... h It is 0.159.
[0116] It is understandable that if H is a fixed value of 200, when the relative height h is 100 meters, the threat value Th corresponding to the relative distance is... d The threat value Th is 0.5 when the relative height h is 300 meters, corresponding to the relative distance. d The threat value Th is 0.0067 when the relative height h is 500 meters, corresponding to the relative distance. d It is 0.000045.
[0117] Therefore, this embodiment can adjust the target adaptation factor of the altitude threat model according to the relative altitude of the UAV relative to the radar detection device, so that the threat value corresponding to the relative altitude adapts to the relative altitude, avoiding the threat value corresponding to the relative altitude from dropping too quickly when the relative altitude is high, which is conducive to predicting a more ideal threat level.
[0118] S3042. Determine the threat level prediction value based on the threat values corresponding to at least two types of relative location information.
[0119] As mentioned earlier, since the threat values corresponding to relative distance and relative height are both normalized, the threat values corresponding to relative distance and relative height can be used to predict the degree of threat based on the same standard. Therefore, in some embodiments, the controller can fuse the threat values corresponding to at least two types of relative position information to obtain a predicted threat value.
[0120] Therefore, this embodiment, by normalizing both the threat values corresponding to relative distance and the threat values corresponding to relative height, fuses the threat values corresponding to relative distance and the threat values corresponding to relative height, which is beneficial to obtaining a better threat prediction value.
[0121] The controller can employ any suitable fusion algorithm to fuse the threat values corresponding to relative distance and relative height to obtain a threat level prediction. In some embodiments, the controller multiplies the threat value corresponding to relative distance by the threat value corresponding to relative height and uses the product as the threat level prediction.
[0122] As mentioned earlier, both the distance threat model and the altitude threat model are based on the Sigmoid normalization model. Thus, the threat values corresponding to relative distance and relative altitude are limited to the range of 0 to 1. Therefore, the product obtained by multiplying the threat value corresponding to relative distance by the threat value corresponding to relative altitude is also limited to the range of 0 to 1. Using this product as a threat prediction value can be conveniently used to analyze the threat level of UAVs relative to radar detection equipment.
[0123] Figure 7 This is a schematic diagram of the structure of a threat prediction device for unmanned aerial vehicles (UAVs) provided in an embodiment of the present invention. Figure 7 As shown, the threat prediction device 700 includes an acquisition module 701, a first determination module 702, a second determination module 703, and a third determination module 704.
[0124] The acquisition module 701 is used to acquire at least one type of relative position information of the UAV relative to the radar detection device. Each type of relative position information corresponds to multiple preset position intervals. The first determination module 702 is used to determine the position interval corresponding to the at least one type of relative position information as the target position interval among the multiple position intervals. Different position intervals correspond to different preset adaptive factors. The preset adaptive factors are factors used to adaptively adjust the output of the preset threat prediction model. The second determination module 703 is used to determine the preset adaptive factor corresponding to the target position interval as the target adaptive factor. The third determination module 704 is used to determine the threat prediction value based on the preset threat prediction model, the at least one type of relative position information and the target adaptive factor. The threat prediction value is used to evaluate the degree of threat posed by the UAV to the radar detection device.
[0125] In some embodiments, the preset threat prediction model includes a prediction sub-model corresponding to each type of relative location information. See [link to relevant documentation]. Figure 8 The third determining module 704 includes a calculation unit 7041 and a determining unit 7042.
[0126] The calculation unit 7041 is used to calculate the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model. The determination unit 7042 is used to determine the threat level prediction value based on the threat values corresponding to at least two types of relative position information.
[0127] It should be noted that the aforementioned drone threat prediction device can execute the drone threat prediction method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in the embodiments of the drone threat prediction device can be found in the drone threat prediction method provided in the embodiments of the present invention.
[0128] Figure 9This is a schematic diagram of the hardware structure of a controller provided in an embodiment of the present invention. Figure 9 As shown, the controller 104 includes one or more processors 1041 and a memory 1042. Figure 9 Take the 1041 processor as an example.
[0129] Processor 1041 and memory 1042 can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.
[0130] The memory 1042, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the UAV threat prediction method in the embodiments of the present invention. The processor 1041 executes various functional applications and data processing of the UAV threat prediction device by running the non-volatile software programs, instructions, and modules stored in the memory 1042, thereby realizing the functions of the UAV threat prediction method provided in the above method embodiments and the various modules or units in the above device embodiments.
[0131] Memory 1042 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 1042 may optionally include memory remotely located relative to processor 1041, and such remote memory may be connected to processor 1041 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0132] The program instructions / modules are stored in the memory 1042 and, when executed by one or more processors 1041, execute the UAV threat prediction method in any of the above method embodiments.
[0133] This invention also provides a non-volatile computer storage medium storing computer-executable instructions, which are executed by one or more processors, for example... Figure 9 One of the processors 1041 enables the one or more processors to execute the threat prediction method for the drone in any of the above method embodiments.
[0134] This invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions that, when executed by an electronic device, cause the electronic device to perform any of the aforementioned drone threat prediction methods.
[0135] The device or equipment embodiments described above are merely illustrative. The unit modules described as separate components may or may not be physically separate. The components shown as module units may or may not be physical units; that is, they may be located in one place or distributed across multiple network module units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0137] Finally, it should be noted that the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments are not intended to impose additional limitations on the content of the present invention; their purpose is to provide a more thorough and comprehensive understanding of the disclosure of the present invention. Furthermore, within the framework of the present invention, the above-mentioned technical features can be combined with each other, and many other variations of different aspects of the present invention as described above exist, all of which are considered to be within the scope of the present invention specification. Moreover, those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.
Claims
1. A threat prediction method for unmanned aerial vehicles (UAVs), applied to radar detection equipment, characterized in that, include: The UAV is acquired relative to the radar detection device in at least one type of relative position information. Each type of relative position information corresponds to multiple preset position intervals. The relative position information includes relative distance, and the relative distance corresponds to multiple preset distance intervals. Among the multiple location intervals, the location interval corresponding to the at least one type of relative location information is determined as the target location interval. Different location intervals correspond to different preset adaptive factors. The preset adaptive factors are factors used to adaptively adjust the output of the preset threat prediction model. The target location interval includes a target distance interval. The preset adaptive factors include a target adaptive factor corresponding to the relative distance. A preset adaptive factor corresponding to the target location interval is determined as the target adaptive factor; The threat prediction value is determined based on a preset threat prediction model, the at least one type of relative position information, and the target adaptive factor, wherein the threat prediction value is used to evaluate the degree of threat posed by the UAV to the radar detection equipment; The preset threat prediction model includes a prediction sub-model corresponding to each type of relative position information. Determining the threat prediction value based on the preset threat prediction model, the relative position information, and the target adaptive factor includes: Based on the relative position information of each type and the target adaptive factor and preset sub-model corresponding to each type of relative position information, calculate the threat value corresponding to each type of relative position information; The threat level prediction value is determined based on the threat values corresponding to at least two types of relative location information; The prediction sub-model includes a distance threat model, which is expressed by the following formula: Among them, T hd Let d be the threat value corresponding to the relative distance, and D be the target adaptive factor corresponding to the relative distance. When the relative distance d falls into different target distance intervals, the target adaptive factor D will also be different.
2. The method according to claim 1, characterized in that, The location interval has a first monotonic relationship with the preset adaptive factor.
3. The method according to claim 2, characterized in that, The target adaptive factor has a second monotonic relationship with the threat level prediction value.
4. The method according to claim 3, characterized in that, When the predicted threat level is positively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the same as the first monotonic relationship. When the predicted threat level is negatively correlated with the threat level of the UAV relative to the radar detection device, the second monotonic relationship is the opposite of the first monotonic relationship.
5. The method according to claim 1, characterized in that, The threat value corresponding to each type of relative location information is normalized, and the step of determining the threat level prediction value based on the threat values corresponding to at least two types of relative location information includes: The threat values corresponding to at least two types of relative position information are fused to obtain a threat prediction value.
6. The method according to claim 1, characterized in that, The step of calculating the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model includes: Based on the distance threat model and the target adaptive factor corresponding to the relative distance, the relative distance is normalized to obtain the threat value corresponding to the relative distance. The threat value corresponding to the relative distance is positively correlated with the relative distance.
7. The method according to claim 1, characterized in that, The relative position information also includes relative altitude, and the prediction sub-model also includes a height threat model. The step of calculating the threat value corresponding to each type of relative position information based on each type of relative position information, the target adaptive factor corresponding to each type of relative position information, and the preset sub-model includes: Based on the height threat model and the target adaptive factor corresponding to the relative height, the relative height is normalized to obtain the threat value corresponding to the relative height, and the threat value corresponding to the relative height is positively correlated with the relative height.
8. A radar detection device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1 to 7.
9. A non-volatile computer storage medium, characterized in that, The non-volatile computer storage medium stores computer-executable instructions for causing an electronic device to perform the method as described in any one of claims 1 to 7.