CN116540225B - Anti-interference radar networking decentralization wave beam and power distribution method - Google Patents
Anti-interference radar networking decentralization wave beam and power distribution method Download PDFInfo
- Publication number
- CN116540225B CN116540225B CN202310769206.XA CN202310769206A CN116540225B CN 116540225 B CN116540225 B CN 116540225B CN 202310769206 A CN202310769206 A CN 202310769206A CN 116540225 B CN116540225 B CN 116540225B
- Authority
- CN
- China
- Prior art keywords
- radar
- network
- value
- target
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006855 networking Effects 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims abstract description 36
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 55
- 230000006870 function Effects 0.000 claims description 49
- 230000006399 behavior Effects 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 238000011160 research Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 15
- 238000007726 management method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 230000001419 dependent effect Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
- G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
- G01S13/726—Multiple target tracking
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/36—Means for anti-jamming, e.g. ECCM, i.e. electronic counter-counter measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application relates to an anti-interference radar networking de-centralization wave beam and power distribution method, which comprises the following steps: constructing a first strategy network of each radar in the radar networking, determining observation of the target radar when judging that the target radar completes track initialization, mapping a behavior vector of the radar calculated according to the first strategy network and the observation to a beam distribution result and a power distribution result, acquiring a first measured value of a target radar processing target beam based on the power distribution result, determining a covariance matrix of a combined measured value, a combined measured value function and the combined measured value based on a correlation result obtained by correlating the first measured value and second measured values sent by other radars, and performing track management and direction prediction based on a tracking filtering result obtained by the correlation result so as to perform decentration beam and power distribution. Therefore, the problems that the beam and power distribution of the radar networking in related research excessively depend on a central node, cannot adapt to interference-free situations, and the constraint condition is not strong in practical significance are solved.
Description
Technical Field
The application relates to the technical field of radar networking and electronic countermeasure, in particular to an anti-interference-oriented radar networking decentralization wave beam and power distribution method.
Background
Radar networking is a great trend of radar development in various countries in the world today, in the situation of modern technological warfare, the form of warfare has been transited from platform center warfare to network center warfare, and along with the development of electronic technology, radar fight is more vigorous, and the development of a control fight networking system marked by an early warning network, a communication network, a command network and an interception network is a necessary precondition for winning future high-technology warfare. Compared with single-station radars, the radar networking has the advantages of waveform diversity, space diversity, multiplexing gain and the like, and the multi-target tracking is an important application of the radar networking, can bring great military benefits, attracts wide attention of countries around the world, is greatly developed, and has very wide application at home and abroad. To improve multi-target tracking performance, radar networking requires reasonable allocation of two types of limited resources, namely beams and power of each beam.
In the related art, the researches on the beam and power distribution problem of the radar networking mainly include: (1) Considering a centralized allocation mode, a central radar node is arranged, each radar transmits a detection result to the central node, the central node performs uniform allocation and transmits the detection result back to each radar for execution; (2) Only considering the interference-free condition, and taking the lower bound of tracking precision, namely the Bayesian Cramerro bound as an optimization target; (3) Assuming that the sum of the power of all radars is constant, a study is made based on this constraint.
However, the limitations of this study are mainly reflected in: (1) Setting a central node, which has high requirements on communication and is severely dependent on the central node; (2) In a military scene, the interference becomes a normal state gradually, and under the interference condition, the situation that the track is interrupted often exists, and compared with the tracking precision, the method is more concerned about whether the target can be kept up, namely the track integrity; (3) The constraint condition is not significant in practice, and in many radar networking, each radar is in fact only constrained by its own hardware condition.
Disclosure of Invention
The application provides an anti-interference radar networking de-centering wave beam and power distribution method, which aims to solve the problems that the wave beam and power distribution of the radar networking in related research is excessively dependent on a center node, cannot adapt to interference-free situations, has weak practical significance of constraint conditions and the like, does not need the center node, reduces communication requirements, enhances system robustness and anti-interference capability of the radar networking, and accords with practical constraint conditions of the power of the radar networking, so that each radar can be constrained by the maximum transmitting power of the radar.
In order to achieve the above objective, an embodiment of a first aspect of the present application provides an anti-interference-oriented method for decentralizing beams and power distribution in a radar networking, including the following steps:
Constructing a first strategy network of each radar in the radar networking, and judging whether the target radar completes track initialization;
if the target radar completes track initialization, determining the observation of the target radar, calculating a behavior vector of the radar according to the first strategy network and the observation, mapping the behavior vector to a beam distribution result and a power distribution result, acquiring a first measured value of a target beam processed by the target radar based on the power distribution result, and correlating the first measured value with a second measured value sent by other radars to obtain a correlation result; and
and determining a joint measurement value, a joint measurement function and a covariance matrix of the joint measurement value based on the association result, obtaining a tracking filtering result according to the joint measurement value, the joint measurement function and the covariance matrix of the joint measurement value, and performing track management and direction prediction according to the tracking filtering result so as to perform decentralization beam and power distribution according to the track management result and the direction prediction result.
According to an embodiment of the present application, the above anti-interference radar networking de-centering beam and power distribution method further includes:
Determining rewards of each radar in the radar networking, and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking;
updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network;
and if the updating times are greater than a preset threshold value, updating the target value network and the target strategy network according to the updated parameters of the first value network and the updated parameters of the first strategy network.
According to one embodiment of the application, the first policy network is:
；
wherein ,in the first place for radarnBeam and power allocation behavior for each time step; />For the first policy network;is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
According to one embodiment of the application, the first value network is:
；
wherein ,is radar iIn the first placenObtaining estimated values of returns in time steps; />For the first value network; />Is the firstnObserving all radars in each time step; />Is the firstnThe behavior of all radars for each time step; />Is a parameter of the first value network.
According to one embodiment of the application, the observations are:
；
wherein ,a new row vector is formed by arranging all row vectors end to end; />For tracker->An observation provided; />Is radariIs the first of (2)bObservation provided by the detection result of the individual beams, wherein +.>。
According to the anti-interference radar networking decentralization beam and power distribution method provided by the embodiment of the application, when track initialization is completed through judging a target radar, observation of the target radar is determined, a first strategy network and a behavior vector of the radar calculated according to the observation of each radar in the radar networking are mapped to a beam distribution result and a power distribution result, a first measured value of the target radar for processing the target beam is obtained based on the power distribution result, a correlation result obtained by correlating the first measured value with a second measured value sent by other radars is determined, a covariance matrix of a joint measured value, a joint measurement function and the joint measured value is determined, track management and direction prediction are performed based on the obtained tracking filtering result, and decentralization beam and power distribution are performed. Therefore, the problems that the beam and power distribution of the radar networking in the related research are excessively dependent on a central node, the interference-free situation cannot be adapted, the practical significance of constraint conditions is not strong and the like are solved, the central node is not needed, the communication requirements are reduced, the robustness of the system and the interference resistance of the radar networking are enhanced, the power constraint conditions of the radar networking are more practical, and each radar can be constrained by the maximum transmitting power of the radar.
To achieve the above objective, a second embodiment of the present application provides an anti-interference radar networking de-centering beam and power distribution device, including:
the first construction module is used for constructing a first strategy network of each radar in the radar networking and judging whether the target radar completes track initialization;
the processing module is used for determining the observation of the target radar when the target radar completes track initialization, calculating the behavior vector of the radar according to the first strategy network and the observation, mapping the behavior vector to a beam distribution result and a power distribution result, acquiring a first measured value of the target radar for processing a target beam based on the power distribution result, and correlating the first measured value with a second measured value sent by other radars to obtain a correlation result; and
the distribution module is used for determining a joint measurement value, a joint measurement function and a covariance matrix of the joint measurement value based on the association result, obtaining a tracking filtering result according to the joint measurement value, the joint measurement function and the covariance matrix of the joint measurement value, and carrying out track management and direction prediction according to the tracking filtering result so as to carry out decentralization wave beam and power distribution according to the track management result and the direction prediction result.
According to an embodiment of the present application, the anti-interference radar networking de-centering beam and power distribution device further includes:
the second construction module is used for determining rewards of each radar in the radar networking and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking;
the first updating module is used for updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network;
and the second updating module is used for updating the target value network and the target strategy network according to the updated parameters of the first value network and the updated parameters of the first strategy network when the updating times are larger than a preset threshold value.
According to one embodiment of the application, the first policy network is:
；
wherein ,in the first place for radarnBeam and power allocation behavior for each time step; / >For the first policy network;is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
According to one embodiment of the application, the first value network is:
；
wherein ,is radariIn the first placenObtaining estimated values of returns in time steps; />For the first value network; />Is the firstnObserving all radars in each time step; />Is the firstnThe behavior of all radars for each time step; />The first is a parameter of the value network.
According to one embodiment of the application, the observations are:
；
wherein ,a new row vector is formed by arranging all row vectors end to end; />For tracker->An observation provided; />Is radariIs the first of (2)bObservation provided by the detection result of the individual beams, wherein +.>。
According to the anti-interference radar networking de-centering beam and power distribution device provided by the embodiment of the application, when track initialization is completed through judging a target radar, observation of the target radar is determined, a first strategy network and a behavior vector of the radar calculated according to the observation of each radar in the radar networking are mapped to a beam distribution result and a power distribution result, a first measured value of the target radar for processing the target beam is obtained based on the power distribution result, a correlation result obtained by correlating the first measured value with a second measured value sent by other radars is determined, a covariance matrix of a joint measured value, a joint measurement function and the joint measured value is determined, track management and direction prediction are performed based on the obtained tracking filtering result, and thus de-centering beam and power distribution are performed. Therefore, the problems that the beam and power distribution of the radar networking in the related research are excessively dependent on a central node, the interference-free situation cannot be adapted, the practical significance of constraint conditions is not strong and the like are solved, the central node is not needed, the communication requirements are reduced, the robustness of the system and the interference resistance of the radar networking are enhanced, the power constraint conditions of the radar networking are more practical, and each radar can be constrained by the maximum transmitting power of the radar.
To achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the anti-interference radar networking de-centralization beam and power distribution method according to the embodiment.
To achieve the above object, a fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the anti-interference radar networking de-centering beam and power allocation method according to the above embodiment.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a method for anti-interference-oriented radar networking de-centering beam and power distribution according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a suitable scenario in accordance with one embodiment of the present application;
FIG. 3 is a schematic diagram of the architecture of a policy network according to one embodiment of the application;
FIG. 4 is a schematic diagram of the architecture of a value network according to one embodiment of the application;
FIG. 5 is a flow chart of a method for anti-interference oriented radar networking de-centering beam and power allocation in accordance with one embodiment of the present application;
FIG. 6 is a block diagram of an anti-interference-oriented radar networking de-centralized beam and power distribution apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The following describes a anti-interference radar networking de-centering beam and power distribution method according to an embodiment of the present application.
Fig. 1 is a flow chart of a method for anti-interference-oriented radar networking de-centering beam and power allocation in accordance with an embodiment of the present application.
Before specifically describing the anti-interference radar networking de-centering beam and power distribution method provided by the embodiment of the application, the principle of the method is briefly described below.
Because the method for decentralizing the beams and distributing the power by the radar networking is difficult to realize joint optimization, the application learns how to decentralize the beams and distributing the power by each radar so as to realize the cooperation effect, namely, the multi-target joint tracking performance under interference is improved, and the cooperation reinforcement learning is realized by the method of 'decentralizing training and decentralizing execution'. Specifically, each radar uses a policy network, the policy network inputs are self-observations, and the outputs are self-behaviors. Thus, with a strategic network, each radar can execute the strategy de-centralised, while each radar uses a centralised value network whose inputs contain observations of all radars and behaviors of all radars, the output being a predicted return value. The value network introduces the information of other radars, characterizes the efficacy of the joint behaviors of each radar, is only used in training and is used for better learning the cooperation strategy, and after the training is finished, each radar uses the own strategy network to realize the decentralized execution.
Figure 2 illustrates a suitable scenario for an embodiment of the present application,the radars are distributed in different locations, each operating independently in a single-base radar, each using the index +.>And (3) representing. As shown in FIG. 2, there is shown +.>Each radar tracks a plurality of targets through resource allocation, namely beam and power allocation, each target carries an jammer, radar emission signals can be intercepted and detected, interference signals are generated aiming at the direction of the radar, and each radar can transmit respective detection results through communication, and besides, each radar works independently: each radar only receives and processes own emission signals; each radar removes the middle partThe self beam and power allocation results are determined cardiously.
Specifically, as shown in fig. 1, the anti-interference radar networking de-centering beam and power distribution method comprises the following steps:
in step S101, a first policy network of each radar in the radar networking is constructed, and it is determined whether the target radar completes track initialization.
Wherein, in some embodiments, the first policy network is:
；（1）
wherein ,in the first place for radarnThe beam and power allocation behavior of a time step is a +. >A dimension vector;is a first policy network; />Is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
Parameters of the productThe initial value of (2) is randomly generated and is not particularly limited herein.
Specifically, the embodiment of the application constructs the radar in the radar networking based on the pair of the formula (1)iThe first policy network is constructed, as shown in fig. 3, and fig. 3 is a schematic structural diagram of the first policy network. The radar finds the target in the searching stage and carries out track initialization, judges whether the target radar completes track initialization, and establishes the radarDada (Chinese character)iHas the following componentsThe trackers, i.e. the radars can track +.>Target, assume at the firstnTime step, th->The corresponding target motion state of each filter is +.>The covariance matrix of the target motion state is +.>. wherein ,/>Is->A dimension vector, wherein each element sequentially represents the x-direction position, the x-direction speed, the y-direction position and the y-direction speed of the target; />Is->Matrix (S)> and />The initial effective value of (2) is determined by the search algorithm, the search algorithm is not particularly limited in the embodiment of the present application, if +.>If the track initialization of each filter is not completed, then，/>. It should be noted that, the radar generally needs several time steps to find the target and perform track initialization, if at least one tracker completes initialization, it indicates that the target radar completes track initialization, and the next operation can be performed, otherwise, track initialization is continuously performed in the search stage.
In step S102, if the target radar completes track initialization, determining an observation of the target radar, calculating a behavior vector of the radar according to the first policy network and the observation, mapping the behavior vector to a beam allocation result and a power allocation result, acquiring a first measurement value of a target radar processing target beam based on the power allocation result, and associating the first measurement value with a second measurement value transmitted by other radars to obtain an association result.
Wherein, in some embodiments, the observations are:
；
wherein ,a new row vector is formed by arranging all row vectors end to end; />For tracker->An observation provided; />Is radariIs the first of (2)bObservation provided by the detection result of the individual beams, wherein +.>。
Specifically, an observation, radar, is constructediPart of the observations of (a) are provided by the respective tracker and the other part by the respective beamDetection result providing, radariIn the first placenThe observations of the individual time steps can be represented by the above equation.
wherein ,is +.>A dimension vector, each element as follows:
i. first, thenBefore the time steps are started, the state value of the tracker is 0 or 1,0 is in a track interruption state, and 1 is in a tracking keeping state;
ii. FirstnBefore starting each time step, the tracker counts up the obtained effective detection result after initializing the track, and the element can reflect the quality of the whole track to a certain extent;
iii. firstnBefore the beginning of the time steps, the tracker has not been associated with the number of valid detection results in succession;
iv. FirstnBefore starting a time step, the tracker generates track interruption times;
v. firstnBefore starting the time steps, the radial distance corresponding to the latest track point in the tracker is represented by 0 if the tracker is in track interruption;
vi. The firstnBefore starting the time steps, the radial speed corresponding to the latest track point in the tracker is represented by 0 if the tracker is in track interruption;
vii. FirstnBefore the start of the time step, the azimuth corresponding to the latest track point in the tracker is indicated by 0 if the tracker is in track interruption.
Is +.>A dimension vector, each element as follows:
i. first, then-1 time step, pointing information of the beam, for the embodiment of the applicationProviding a tracker-indexed representation of azimuth predictions for the beam;
ii. Firstn-1 time step, the power level allocated by the beam;
iii. firstn-1 time step, the signal-to-interference-and-noise ratio of the beam received signal.
Further, computing a behavior vector of the radar from the first strategic network and the observations, and observingInputting a first policy network- >Obtaining the radariIn the first placenBehavior vector for each time step:
；
wherein ,indicating radar at->The beam and power allocation behavior of a time step is a +.>A dimension vector, expressed as:
；
wherein ,representing beam allocation results, +.>Represents the power allocation result, and。
further, the methodMapping the behavior vector to the beam allocation result and the power allocation result, first the beam allocation result, the radar pass functionWill->Mapping to discrete beam allocation results, the beam allocation is actually from +.>Selecting +.>The beam is emitted in the direction of +.>Seed allocation result, the embodiment of the application will +.>The 0-1 interval is divided into +.>And each section of the section corresponds to different distribution results. The function +.>At the position ofIs formed by the following steps:
；
wherein the direction isKRepresent the firstThe azimuth angles provided by the trackers and the rest of the cases adopt similar segmented mapping modes.
It should be noted that, the azimuth provided by the tracker in the track interruption state is invalid, and if the mapping result includes an invalid azimuth, the beam is not transmitted for the azimuth.
Next is the power allocation result, i.e. for the above selectionThe transmission direction of each beam, the transmission power is allocated to each beam, and the action vector is +. >In (I)>Indicating the power distribution result, the firstbThe transmitting power of each wave beam is, wherein ,/>，/>Is radariIs provided.
Further, a first measured value of a target radar processing target beam is obtained based on the power distribution result, and the radarBy treating->The received signals of the individual beams, obtaining measured values:
；
wherein ,the radial distance, the radial speed and the azimuth angle obtained by processing are respectively obtained, and meanwhile, the measurement variances of the radial distance, the radial speed and the azimuth angle can be obtained, which are respectively +.>、/>、/>And signal-to-interference-and-noise ratio estimator +.>。
It should be noted that if the signal-to-noise ratio is too low to obtain a valid measurement value, then，。
Further, correlating the first measured value with the second measured value sent by other radars to obtain a correlation result, and the radarsiThe detection results sent by other radars can be received, and the measured value set of all radars is recorded asIn the data association, for each radar +.>The measured values are respectively->Assigned to radarsiIs->And a tracker.
Further, the allocation cost calculation is carried out to makeRepresenting the measured value +.>Assigned to radarsiIs>Cost of the individual filters:
；
wherein ,，/>is->The filter is at the firstn-1. Time step prediction nTarget motion state of individual time steps, function->To transform target motion states into radariIs a function of the radial distance, radial velocity and azimuth angle +.>Is defined as follows:
；
wherein ,、/>、/>the weighting coefficients for the radial distance, radial velocity, and azimuth angle are shown, respectively.
If it isI.e. the measured value is invalid, or the filter is in a track-interrupting state, then, wherein />Is a very large positive number.
Furthermore, the data-dependent problem can be expressed as a solution optimization problem as follows:
；
；
wherein ,represents the firstbWhether or not the measured value is assigned to the->A value of 1 indicates an allocation.
Each tracker is assigned at most toIs assigned to the radariIs>Measurement value of individual tracker->If no effective measurement value is assigned to +.>The tracker is expressed as +>The method comprises the steps of carrying out a first treatment on the surface of the In addition, the variance of each measurement is assigned to each tracker as well. The variance of each measured value is used as a diagonal element to form a diagonal array, which is marked as +.>If->Then->。
Each radar is provided withjIs assigned to radariA kind of electronic devicePersonal tracker, i.e. p->Repeating the allocation cost calculation and solution optimization operation, wherein the combination measured value set obtained by each tracker allocation is +. >The covariance matrix set of the joint measurement values is +.>。
In step S103, based on the correlation result, a joint measurement value, a joint measurement function, and a covariance matrix of the joint measurement value are determined, a tracking filtering result is obtained according to the joint measurement value, the joint measurement function, and the covariance matrix of the joint measurement value, and track management and direction prediction are performed according to the tracking filtering result, so as to perform decentralization beam and power allocation according to the track management result and the direction prediction result.
Specifically, each tracker may be assigned to observations from different radars, and based on the correlation results, determine the joint measurement values, the joint measurement function, and the covariance matrix of the joint measurement values as:
；
；
；
at the same time, at、/>、/>In (1), elements corresponding to invalid measured values are deleted, e.g. if->Then
；
；
；
Tracking is realized by extended Kalman filtering, and the method comprises the following steps:
；
；
；
；
；
wherein the matrix and />Respectively is
；
For a step length of one time step, +.>，/>For acceleration variance +.>Is->Unit matrix->Is a function->At->Jacobian matrix at.
Further, track management and direction prediction are performed according to the tracking filtering result, if the tracker is continuousThe time steps are not allocated to validity Observing, determining that the track is interrupted in the tracker, and initializing the filter of the track interruption by the radar in the searching stage.
In the first placenTime step, if trackerThe track in (3) is still kept, and one-step prediction is performed:
；
based on this, the azimuth of the next time step of the target can be predictedIf the track in the filter is interrupted +.>Representing invalid azimuth angles, the tracker can provide an effective azimuth angle set of。
In addition, in some embodiments, the above anti-interference radar networking de-centering beam and power distribution method further includes: determining rewards of each radar in the radar networking, and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking; updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network; if the number of updates is greater than the preset threshold, updating the target value network and the target policy network according to the updated parameters of the first value network and the updated parameters of the first policy network.
Wherein, in some embodiments, the first value network is:
；（2）
wherein ,is radariIn the first placenObtaining estimated values of returns in time steps; />Is a first value network; />Is the firstnObserving all radars in each time step; />Is the firstnBehavior of all radars for each time step, +.>The total number of the radars; />Is a parameter of the first value network.
Parameters of the productThe initial value of (2) is randomly generated and is not particularly limited herein.
Specifically, determining rewards for each radar in a radar network, radariIn the first placenThe rewards for the individual time steps are defined as:
；
wherein the variables are indicatedMeaning of (1)
。
Further, the radar in the radar networkingiBuilding a target policy networkThe input, output and network structure of the target policy network are all equal to those of the first policy network +.>The same, the parameters of the target policy network are +.>The method comprises the steps of carrying out a first treatment on the surface of the Radar in radar networking based on (2)iConstructing a first value network, as shown in fig. 4, and fig. 4 is a schematic structural diagram of the first value network; radar in networking of radariConstructing a target value network->The input, output and network structure of the target value network are all equal to those of the first value network>The same, the parameters of the target value network are +.>。
Wherein the cost function of the first cost value network is defined as:
；
As the target value, defined as:
；
it is desirable that for each experienceGet and get->And->The updating of the first value network can be completed through gradient descent based on the cost function for the target value network and the target policy network respectively:
；
wherein ,the calculation of the gradient may be performed by a deep learning framework of the related art, and for avoiding redundancy, it is not described here.
The purpose of the first policy network is to maximize the output of the value network, the cost function of which is defined as:
；
wherein the desired representation is for each experienceInstead, the updating of the first policy network may be accomplished by gradient descent:
；/>
wherein ,the calculation of the gradient may be performed by a deep learning framework of the related art, and for avoiding redundancy, it is not described here.
Further, updating the first value network according to the cost function of the first value network, updating the first policy network according to the cost function of the first policy network, and updating the first policy network between the first value network and the first policy networkWhen the number of times is greater than a preset threshold, i.e. each update of the first value network and the first policy networkSecondly, respectively assigning the updated parameters of the first value network and the updated parameters of the first strategy network to the target value network and the target strategy network:
，/>。
In order to facilitate a person skilled in the art to further understand the anti-interference radar networking de-centering beam and power distribution method according to the embodiment of the present application, the following description is further provided with reference to fig. 5.
As shown in fig. 5, steps (1) - (8) represent training processes of the anti-interference radar networking de-centering beam and power distribution method, and steps (1) - (6) represent execution processes of the method after training is completed, and mainly comprise the following steps:
(1) Initializing a first strategy network, a target strategy network, a first value network, a target value network and a track;
(2) Beam and power allocation, including constructing observations, computing behavior vectors, and behavior maps;
(3) Obtaining a detection result;
(4) Data association, including allocation cost calculation and solution optimization;
(5) Tracking and filtering;
(6) Track management and direction prediction;
(7) Evaluation of rewards;
(8) Network training, including first value network training, first policy network training, updating of a target value network, and updating of a target policy network.
According to the anti-interference radar networking decentralization beam and power distribution method provided by the embodiment of the application, when track initialization is completed through judging a target radar, observation of the target radar is determined, a first strategy network and a behavior vector of the radar calculated according to the observation of each radar in the radar networking are mapped to a beam distribution result and a power distribution result, a first measured value of the target radar for processing the target beam is obtained based on the power distribution result, a correlation result obtained by correlating the first measured value with a second measured value sent by other radars is determined, a covariance matrix of a joint measured value, a joint measurement function and the joint measured value is determined, track management and direction prediction are performed based on the obtained tracking filtering result, and decentralization beam and power distribution are performed. Therefore, the problems that the beam and power distribution of the radar networking in the related research are excessively dependent on a central node, the interference-free situation cannot be adapted, the practical significance of constraint conditions is not strong and the like are solved, the central node is not needed, the communication requirements are reduced, the robustness of the system and the interference resistance of the radar networking are enhanced, the power constraint conditions of the radar networking are more practical, and each radar can be constrained by the maximum transmitting power of the radar.
Next, a description is given of an anti-interference radar networking de-centering beam and power distribution device according to an embodiment of the present application with reference to the accompanying drawings.
Fig. 6 is a block diagram of an anti-interference-oriented radar networking de-centering beam and power distribution device according to an embodiment of the present application.
As shown in fig. 6, the anti-interference radar networking de-centering beam and power distribution device 10 includes: a first build module 100, a process module 200, and an allocation module 300.
The first construction module 100 is configured to construct a first policy network of each radar in the radar networking, and determine whether the target radar completes track initialization;
the processing module 200 is configured to determine an observation of the target radar when the target radar completes track initialization, calculate a behavior vector of the radar according to the first policy network and the observation, map the behavior vector to a beam allocation result and a power allocation result, acquire a first measurement value of a target beam processed by the target radar based on the power allocation result, and correlate the first measurement value with a second measurement value sent by other radars to obtain a correlation result; and
the allocation module 300 is configured to determine a joint measurement value, a joint measurement function, and a covariance matrix of the joint measurement value based on the correlation result, obtain a tracking filtering result according to the joint measurement value, the joint measurement function, and the covariance matrix of the joint measurement value, and perform track management and direction prediction according to the tracking filtering result, so as to perform decentralization beam and power allocation according to the track management result and the direction prediction result.
Further, in some embodiments, the above-mentioned anti-interference-oriented radar networking de-centering beam and power distribution device 10 further includes:
the second construction module is used for determining rewards of each radar in the radar networking and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking;
the first updating module is used for updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network;
and the second updating module is used for updating the target value network and the target strategy network according to the updated parameters of the first value network and the updated parameters of the first strategy network when the updating times are larger than a preset threshold value.
Further, in some embodiments, the first policy network is:
；
wherein ,in the first place for radarnBeam and power allocation behavior for each time step; />Is a first policy network; />Is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
Further, in some embodiments, the first value network is:
；
wherein ,is radariIn the first placenObtaining estimated values of returns in time steps; />Is a first value network; />Is the firstnObserving all radars in each time step; />Is the firstnThe behavior of all radars for each time step; />Is a parameter of the first value network.
Further, in some embodiments, the observations are:
；
wherein ,a new row direction formed by arranging the row vectors end to endAn amount of; />For tracker->An observation provided; />Is radariIs the first of (2)bObservation provided by the detection result of the individual beams, wherein +.>。
It should be noted that, the explanation of the foregoing embodiment of the anti-interference radar networking de-centering beam and power distribution method is also applicable to the anti-interference radar networking de-centering beam and power distribution device of this embodiment, which is not described herein again.
According to the anti-interference radar networking de-centering beam and power distribution device provided by the embodiment of the application, when track initialization is completed through judging a target radar, observation of the target radar is determined, a first strategy network and a behavior vector of the radar calculated according to the observation of each radar in the radar networking are mapped to a beam distribution result and a power distribution result, a first measured value of the target radar for processing the target beam is obtained based on the power distribution result, a correlation result obtained by correlating the first measured value with a second measured value sent by other radars is determined, a covariance matrix of a joint measured value, a joint measurement function and the joint measured value is determined, track management and direction prediction are performed based on the obtained tracking filtering result, and thus de-centering beam and power distribution are performed. Therefore, the problems that the beam and power distribution of the radar networking in the related research are excessively dependent on a central node, the interference-free situation cannot be adapted, the practical significance of constraint conditions is not strong and the like are solved, the central node is not needed, the communication requirements are reduced, the robustness of the system and the interference resistance of the radar networking are enhanced, the power constraint conditions of the radar networking are more practical, and each radar can be constrained by the maximum transmitting power of the radar.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
memory 701, processor 702, and computer programs stored on memory 701 and executable on processor 702.
The processor 702 implements the anti-interference-oriented radar networking de-centering beam and power allocation method provided in the above embodiment when executing the program.
Further, the electronic device further includes:
a communication interface 703 for communication between the memory 701 and the processor 702.
Memory 701 for storing a computer program executable on processor 702.
The memory 701 may include high-speed RAM (Random Access Memory ) memory, and may also include non-volatile memory, such as at least one disk memory.
If the memory 701, the processor 702, and the communication interface 703 are implemented independently, the communication interface 703, the memory 701, and the processor 702 may be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component, external device interconnect) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a chip, the memory 701, the processor 702, and the communication interface 703 may communicate with each other through internal interfaces.
The processor 702 may be a CPU (Central Processing Unit ) or ASIC (Application Specific Integrated Circuit, application specific integrated circuit) or one or more integrated circuits configured to implement embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the anti-interference radar networking de-centralization wave beam and power distribution method.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (6)
1. An anti-interference radar networking de-centralization wave beam and power distribution method is characterized by comprising the following steps:
Constructing a first strategy network of each radar in the radar networking, and judging whether the target radar completes track initialization;
if the target radar completes track initialization, determining the observation of the target radar, calculating a behavior vector of the radar according to the first strategy network and the observation, mapping the behavior vector to a beam distribution result and a power distribution result, acquiring a first measured value of a target beam processed by the target radar based on the power distribution result, and correlating the first measured value with a second measured value sent by other radars to obtain a correlation result; and
based on the association result, determining a joint measurement value, a joint measurement function and a covariance matrix of the joint measurement value, obtaining a tracking filtering result according to the joint measurement value, the joint measurement function and the covariance matrix of the joint measurement value, and performing track management and direction prediction according to the tracking filtering result so as to perform decentralization wave beam and power distribution according to the track management result and the direction prediction result;
determining rewards of each radar in the radar networking, and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking;
Updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network;
if the updating times are larger than a preset threshold value, updating the target value network and the target strategy network according to the updated parameters of the first value network and the updated parameters of the first strategy network;
wherein the first policy network is:
；
wherein ,in the first place for radarnBeam and power allocation behavior for each time step; />For the first policy network; />Is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
2. The method of claim 1, wherein the first value network is:
；
wherein ,is radariIn the first placenObtaining estimated values of returns in time steps; />For the first value network; />Is the firstnObserving all radars in each time step; />Is the firstnThe behavior of all radars for each time step; />For the first value netParameters of the network.
3. The method of claim 1, wherein the observation is:
；
wherein ,a new row vector is formed by arranging all row vectors end to end; />For tracker->An observation provided; />Is radariIs the first of (2)bObservation provided by the detection result of the individual beams, wherein +.>。
4. An anti-interference radar networking de-centralization wave beam and power distribution device, which is characterized by comprising:
the first construction module is used for constructing a first strategy network of each radar in the radar networking and judging whether the target radar completes track initialization;
the processing module is used for determining the observation of the target radar when the target radar completes track initialization, calculating the behavior vector of the radar according to the first strategy network and the observation, mapping the behavior vector to a beam distribution result and a power distribution result, acquiring a first measured value of the target radar for processing a target beam based on the power distribution result, and correlating the first measured value with a second measured value sent by other radars to obtain a correlation result; and
the distribution module is used for determining a joint measurement value, a joint measurement function and a covariance matrix of the joint measurement value based on the association result, obtaining a tracking filtering result according to the joint measurement value, the joint measurement function and the covariance matrix of the joint measurement value, and carrying out track management and direction prediction according to the tracking filtering result so as to carry out decentralization wave beam and power distribution according to the track management result and the direction prediction result;
The second construction module is used for determining rewards of each radar in the radar networking and constructing a target strategy network, a first value network, a target value network, a cost function of the first value network and a cost function of the first strategy network of each radar in the radar networking;
the first updating module is used for updating the first value network according to the cost function of the first value network, updating the first strategy network according to the cost function of the first strategy network, and judging the updating times of the first value network and the first strategy network;
the second updating module is used for updating the target value network and the target strategy network according to the updated parameters of the first value network and the updated parameters of the first strategy network when the updating times are larger than a preset threshold value;
wherein the first policy network is:
；
wherein ,in the first place for radarnBeam and power allocation behavior for each time step; />For the first policy network; />Is radariIn the first placenObserving the time steps; />Is a parameter of the first policy network.
5. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the tamper-resistant radar networking de-centralization beam and power allocation method according to any one of claims 1-3.
6. A computer readable storage medium having stored thereon a computer program, the program being executable by a processor for implementing the interference-free oriented radar networking de-centering beam and power allocation method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310769206.XA CN116540225B (en) | 2023-06-28 | 2023-06-28 | Anti-interference radar networking decentralization wave beam and power distribution method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310769206.XA CN116540225B (en) | 2023-06-28 | 2023-06-28 | Anti-interference radar networking decentralization wave beam and power distribution method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116540225A CN116540225A (en) | 2023-08-04 |
| CN116540225B true CN116540225B (en) | 2023-09-19 |
Family
ID=87452761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310769206.XA Active CN116540225B (en) | 2023-06-28 | 2023-06-28 | Anti-interference radar networking decentralization wave beam and power distribution method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116540225B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8314733B1 (en) * | 2009-10-13 | 2012-11-20 | Lockheed Martin Corporation | Adjustment of radar parameters to maintain accelerating target in track |
| CN113203993A (en) * | 2021-04-30 | 2021-08-03 | 电子科技大学 | Self-adaptive multi-jammer cooperative interference suppression method for networking radar |
| KR20210096948A (en) * | 2020-01-29 | 2021-08-06 | 포항공과대학교 산학협력단 | Signal Generation Method of Radar-Communication Combination System |
| CN113466825A (en) * | 2021-06-17 | 2021-10-01 | 西安电子科技大学 | Networking radar resource allocation method based on mutual information maximization |
| CN114662271A (en) * | 2021-12-22 | 2022-06-24 | 中国人民解放军空军工程大学 | Wave beam-power-bandwidth joint allocation method in centralized MIMO radar multi-target tracking |
| CN114706045A (en) * | 2022-03-10 | 2022-07-05 | 南京航空航天大学 | Networking radar power time joint optimization method for multi-target tracking under space frequency perception |
| CN115236611A (en) * | 2022-08-04 | 2022-10-25 | 电子科技大学 | Multi-jammer cooperative suppression resource scheduling method for radar system |
| CN115567353A (en) * | 2022-09-30 | 2023-01-03 | 电子科技大学 | Radar networking system-oriented interference multi-beam scheduling and interference power joint optimization method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261848B (en) * | 2019-07-25 | 2021-04-30 | 北京邮电大学 | Radar communication integrated cooperative detection method and device based on beam power distribution |
| US20220120845A1 (en) * | 2020-10-15 | 2022-04-21 | Qualcomm Incorporated | Methods and system for predictive coordination of ego and interferer radar parameters |
-
2023
- 2023-06-28 CN CN202310769206.XA patent/CN116540225B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8314733B1 (en) * | 2009-10-13 | 2012-11-20 | Lockheed Martin Corporation | Adjustment of radar parameters to maintain accelerating target in track |
| KR20210096948A (en) * | 2020-01-29 | 2021-08-06 | 포항공과대학교 산학협력단 | Signal Generation Method of Radar-Communication Combination System |
| CN113203993A (en) * | 2021-04-30 | 2021-08-03 | 电子科技大学 | Self-adaptive multi-jammer cooperative interference suppression method for networking radar |
| CN113466825A (en) * | 2021-06-17 | 2021-10-01 | 西安电子科技大学 | Networking radar resource allocation method based on mutual information maximization |
| CN114662271A (en) * | 2021-12-22 | 2022-06-24 | 中国人民解放军空军工程大学 | Wave beam-power-bandwidth joint allocation method in centralized MIMO radar multi-target tracking |
| CN114706045A (en) * | 2022-03-10 | 2022-07-05 | 南京航空航天大学 | Networking radar power time joint optimization method for multi-target tracking under space frequency perception |
| CN115236611A (en) * | 2022-08-04 | 2022-10-25 | 电子科技大学 | Multi-jammer cooperative suppression resource scheduling method for radar system |
| CN115567353A (en) * | 2022-09-30 | 2023-01-03 | 电子科技大学 | Radar networking system-oriented interference multi-beam scheduling and interference power joint optimization method |
Non-Patent Citations (3)
| Title |
|---|
| SOJ干扰条件下雷达网目标跟踪条件CRLB;徐海全;王国宏;白晶;;火力与指挥控制(第09期);全文 * |
| 基于认知跟踪的集中式MIMO雷达功率分配算法;李正杰;谢军伟;张浩为;;探测与控制学报(第06期);全文 * |
| 对空情报雷达网密集假目标干扰机理分析;赵源;熊英;唐斌;;电讯技术(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116540225A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kreucher et al. | Sensor management using an active sensing approach | |
| EP1610152B1 (en) | Tracking of a moving object for a self-defence system | |
| McIntyre et al. | Information theoretic approach to sensor scheduling | |
| Kreucher et al. | Information-based sensor management for multitarget tracking | |
| CN113673565B (en) | Multi-sensor GM-PHD self-adaptive sequential fusion multi-target tracking method | |
| CN104021519B (en) | Multiple-moving target tracking method under the conditions of dense clutter based on GPU architecture | |
| Kreucher et al. | Multi-target sensor management using alpha-divergence measures | |
| CN114261400B (en) | Automatic driving decision method, device, equipment and storage medium | |
| CN116299287A (en) | Amplitude information-assisted cognitive radar tracking waveform selection method and system | |
| Zhang et al. | Performance analysis of deep reinforcement learning-based intelligent cooperative jamming method confronting multi-functional networked radar | |
| CN115618166A (en) | Time resource scheduling method and device based on multi-task radar | |
| Xia et al. | Extended object tracking with automotive radar using learned structural measurement model | |
| CN115236611A (en) | Multi-jammer cooperative suppression resource scheduling method for radar system | |
| CN116540225B (en) | Anti-interference radar networking decentralization wave beam and power distribution method | |
| CN113114399B (en) | Three-dimensional spectrum situation complementing method and device based on generation countermeasure network | |
| CN111198366B (en) | Method for quickly selecting finite array elements under distributed MIMO radar multitasking | |
| CN108490429A (en) | TWS Radar Multi Targets tracking and system | |
| CN115561748A (en) | Networked radar target search tracking resource allocation method based on radio frequency stealth | |
| Pulkkinen et al. | Time budget management in multifunction radars using reinforcement learning | |
| CN115220002B (en) | Multi-target data association tracking method and related device for fixed single station | |
| CN114722710B (en) | Range gate dragging interference method based on random simulation optimization | |
| CN110213094A (en) | It is a kind of to threaten the method for building up of active topology figure, device and storage equipment | |
| CN110031807A (en) | A kind of multistage smart noise jamming realization method based on model-free intensified learning | |
| CN116879863B (en) | Multi-target measuring method and system for continuous wave 4D millimeter wave radar | |
| Hintz et al. | Instantiation of dynamic goals based on situation information in sensor management systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |