CN113095504A - Target track prediction system and prediction method - Google Patents
Target track prediction system and prediction method Download PDFInfo
- Publication number
- CN113095504A CN113095504A CN202110394691.8A CN202110394691A CN113095504A CN 113095504 A CN113095504 A CN 113095504A CN 202110394691 A CN202110394691 A CN 202110394691A CN 113095504 A CN113095504 A CN 113095504A
- Authority
- CN
- China
- Prior art keywords
- target
- model
- maneuvering
- track
- prediction
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000012937 correction Methods 0.000 claims abstract description 20
- 230000010354 integration Effects 0.000 claims abstract description 13
- 238000013499 data model Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 16
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003446 memory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001308 synthesis method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Feedback Control In General (AREA)
Abstract
A target trajectory prediction system comprises a target maneuvering characteristic model set module, wherein a target maneuvering characteristic set comprises typical maneuvering local models of a plurality of targets; the forward trajectory prediction module defines a performance index function and establishes a target trajectory prediction model, parameters of the target trajectory prediction model are determined according to the matching degree of each typical maneuvering local model and the target actual flight trajectory, and a numerical integration method is adopted for forward trajectory prediction; and the backward feedback correction module is used for establishing a global importance map model, establishing an incidence relation between a forward prediction track and a flight important node according to the global importance map model, determining target maneuver intention information, correcting parameters of the target track prediction model by adopting a posterior conditional probability method, and then predicting the track again. The method breaks through the open-loop prediction limitation of the traditional track prediction method, integrates the feedback correction of the predicted track based on game countermeasure into the track prediction process, realizes the closed-loop prediction of the track, and improves the track prediction precision.
Description
Technical Field
The invention belongs to the technical field of target trajectory prediction, and particularly relates to a trajectory prediction system and a prediction method of a flying target.
Background
The target track prediction is a process of estimating a future motion state or an reachable range of a target according to target motion state parameters acquired by a detection system, and the actual process is to estimate future information according to a certain method and rule based on known historical information. Through effective track prediction, the knowledge of the target subsequent state can be improved, a basis is provided for planning and managing related tasks, and the method has wide application prospects in the fields of aviation control, aerospace target interception and the like.
The current trajectory prediction methods mainly include two major categories, namely analytical methods and numerical integration methods. The analytic method is a more intuitive track prediction method, and the main principle of the analytic method is to simplify the method by taking a specific motion mode or a motion relation as a condition, but when the motion mode of a target is complex and changeable, an analytic solution is often difficult to obtain, and if the target is predicted by aiming at an unknown non-cooperative target with the motion mode, the method is more difficult to adapt. The numerical integration method is to obtain a target predicted track by forward integration of a dynamic model, and similarly, when a target motion mode changes, especially when the track prediction is performed on a non-cooperative target with an unknown maneuvering mode, because the prediction process of the numerical integration method is an open loop process and no external information corrects the predicted track, errors in the prediction process are continuously accumulated and quickly dispersed, and the prediction requirement of the actual track of the non-cooperative target is difficult to meet.
Disclosure of Invention
The invention aims to provide a target track prediction system and a target track prediction method based on game countermeasure, which can improve the track prediction precision.
In order to achieve the purpose, the invention adopts the following technical solutions:
a target trajectory prediction system comprising: the system comprises a target maneuvering characteristic model set module used for establishing a target maneuvering characteristic model set, wherein the target maneuvering characteristic set comprises typical maneuvering local models of a plurality of targets; the forward track prediction module is used for performing forward track prediction on the target, defining a performance index function and establishing a target track prediction model, calculating the matching degree of each typical maneuvering local model in a target maneuvering characteristic model set and the target actual flight track through the performance index function, determining parameters of the target track prediction model according to the matching degree of each typical maneuvering local model and the target actual flight track, substituting the obtained parameters into the target track prediction model, and performing forward track prediction on the target by adopting a numerical integration method;
the backward feedback correction module is used for correcting the target track, a global importance map model is established according to flight important nodes, then an incidence relation between a forward prediction track and the flight important nodes is established according to the global importance map model, target maneuver intention information is determined, parameters of the target track prediction model are corrected by the target maneuver intention information through a posterior conditional probability method, track prediction is carried out according to the target track prediction model after the parameters are corrected, and a corrected track prediction result is obtained.
Further, when the target maneuvering characteristic model set module establishes a target maneuvering characteristic set, firstly, a maneuvering characteristic model for representing a target maneuvering mode is determined, then, the target maneuvering state is decomposed, and typical maneuvering local models of the target are established, wherein the typical maneuvering local models form a target maneuvering characteristic model set.
Further, the maneuvering characteristic model comprises a CA model, a CV model, a typical track data model and a dynamic model.
The invention also provides a target track prediction method, which comprises the following steps:
s1, establishing a target maneuvering characteristic model set, firstly determining a maneuvering characteristic model of the target, then decomposing the maneuvering state of the target, establishing a typical maneuvering local model of the target based on the maneuvering characteristic model, and forming the target maneuvering characteristic model set by the typical maneuvering local model;
s2, predicting a target forward track, defining a performance index function, establishing a target track prediction model, evaluating the matching degree of each typical maneuvering local model in the target maneuvering characteristic model set and the target actual flight track through the performance index function, determining parameters of the target track prediction model according to the matching degree of each typical maneuvering local model and the target actual flight track, and predicting the forward track of the target based on the target track prediction model by adopting a numerical integration method;
s3, correcting the target track, namely firstly determining flight important nodes, then establishing a global importance map model according to the flight important nodes, then establishing an incidence relation between a forward predicted track and the flight important nodes according to the global importance map model, determining target maneuver intention information, correcting parameters of the target track prediction model by using the target maneuver intention information and adopting a posterior conditional probability method, and predicting the target track according to the target track prediction model after parameter correction to obtain a corrected track prediction result.
Further, in step S2, a weighted least squares method is used to solve the parameters of the target trajectory prediction model.
Further, in step S2, a tracking error weighting method is used to define a performance index function, and the matching degree between the typical maneuver local model and the target actual flight trajectory is equal to the weight of the typical maneuver local model
Wherein J isi(k) And the performance index value of the ith typical maneuvering local model in the target maneuvering characteristic model set is represented, and M is the number of the typical maneuvering local models in the target maneuvering characteristic model set.
Further, in step S3, a bayesian inference method is used to determine the target maneuver intention information, where the target maneuver intention information is
In the formula, p (x)k-1J) is the prior probability of the j-th typical mobile local model at time k-1, p (x)k＝i,xk-1J) is the predicted trajectory posterior probability corresponding to a typical maneuver local model.
Further, the method for correcting the parameters of the target trajectory prediction model in step S3 is as follows: utilizing target maneuver intention information p (x)k＝i|xk-1J) correcting the target predicted state, there are: p (x)k|x1:k-1)＝∫p(xk|xk-1)p(xk-1|x1:k-1)dxk-1Root of another generationAccording to the corrected result p (x)k|x1:k-1) Parameters of the target track prediction model are corrected, and the parameters comprise:
wherein,
parameters of a typical maneuvering local model in the target maneuvering characteristic model set.
According to the technical scheme, a target maneuvering characteristic model set formed by typical maneuvering local models is established, a forward track prediction module introduces target maneuvering intention evaluation based on game countermeasure through a backward feedback correction module on the basis of target movement characteristic constraint track prediction, and backward correction is carried out on the predicted track, so that a track closed-loop prediction system combining the forward prediction under the constraint of movement characteristics and the predicted track feedback correction under the evaluation of game maneuvering intention is formed, the open-loop prediction limitation of the traditional track prediction method is broken through, the predicted track feedback correction based on the game countermeasure is integrated into the track prediction process, the track closed-loop prediction is realized, and the track prediction precision is improved. In addition, in the closed-loop prediction process, the target maneuvering characteristics and game confrontation intentions are adopted to restrict the track prediction range, and the cooperative target has richer maneuvering intention information, so that the method has a better prediction effect. The method is suitable for the prediction of the cooperative target track and the non-cooperative target track, the prediction system has better compatibility, and different types of data filtering and processing algorithms can be compatible in each module.
Drawings
FIG. 1 is a block diagram of an embodiment of the present invention;
FIG. 2 is a schematic view showing the relationship between the flight path of the reentry glide target and the local model representation thereof;
FIG. 3 is a schematic diagram of the trajectory space coverage of the maneuver feature model set of the reentry gliding target;
FIG. 4 is a schematic diagram of an importance map;
FIG. 5 is an association diagram of predicted trajectory and flight important nodes;
FIG. 6 is a graph of error variation predicted using the method of the present invention;
FIG. 7 is a graph of a change in model membership relationship;
FIG. 8 is a graph comparing the change in model roll angle β;
FIG. 9 shows a model KLComparing the change of (c) with the graph;
FIG. 10 shows a model KDVersus a graph.
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Detailed Description
The invention will be described in detail below with reference to the accompanying drawings, wherein for the purpose of illustrating embodiments of the invention, the drawings showing the structure of the device are not to scale but are partly enlarged, and the schematic drawings are only examples, and should not be construed as limiting the scope of the invention. It is to be noted, however, that the drawings are designed in a simplified form and are not to scale, but rather are to be construed in an attempt to more clearly and concisely illustrate embodiments of the present invention.
FIG. 1 is a block diagram of the system of the present invention, which includes a target maneuver feature model set module, a forward trajectory prediction module based on maneuver feature constraints, and a backward feedback modification module based on game play countermeasure.
The target maneuvering characteristic model set module is used for establishing a target maneuvering characteristic model set for describing a typical maneuvering pattern of a target, covering a target maneuvering space through the construction of the target maneuvering characteristic model set, and constraining a target trajectory prediction process as prior information of the target trajectory prediction process, and improving the target trajectory prediction precision through the introduction of the target prior information.
The working process of the target maneuvering characteristic model set module is as follows: firstly, a maneuvering characteristic model for representing a maneuvering mode of the target is determined, the more common maneuvering characteristic models comprise a CA model (constant velocity model), a CV model (constant acceleration model), a typical trajectory data model, a dynamic model and the like, and in practical application, what maneuvering characteristic model is adopted to represent the maneuvering mode of the target can be selected correspondingly according to the movement characteristics of the target.
After a maneuvering characteristic model for representing a maneuvering mode of the target is determined, maneuvering state decomposition such as the maneuvering mode, the flight state, the maneuvering capability and the like is carried out on the target, a typical maneuvering local model of the target is established, and a target maneuvering characteristic model set is formed by the obtained typical maneuvering local models. For example, if a CA model and a CV model are used for representing the maneuvering mode of the target, the maneuvering state of the target can be decomposed according to the target capability range, different local characteristic model parameters in the model are determined, and a plurality of typical maneuvering local models of the target are established, wherein the typical maneuvering local models form a target maneuvering characteristic model set. For another example, a typical trajectory data model is used as a maneuvering characteristic model to represent a maneuvering mode of the target, a maneuvering state decomposition can be performed on the target by combining typical maneuvering patterns of the target under different conditions and different states, a target sample trajectory is generated by using a dynamics principle, a typical maneuvering local model of the target is established, and a target maneuvering characteristic model set is further formed.
The forward track prediction module is used for establishing a target track prediction model, performing forward track prediction on a target based on the target track prediction model, taking track tracking data of the target as input, simultaneously determining probability distribution of a typical maneuvering local model of the target by adopting a data fusion method by combining a target maneuvering characteristic model set, and performing forward track prediction by adopting a numerical integration method based on the target track prediction model. The trajectory tracking data of the target is data obtained after detection, tracking and processing by a target trajectory tracking system.
The forward trajectory prediction module works as follows: defining a performance index function and establishing a target track prediction model, wherein the performance index function is used for evaluating the matching degree (incidence relation) of each typical maneuvering local model in a target maneuvering characteristic model set and the target actual flight track and establishing a motion characteristic incidence constraint mechanism for track prediction; and establishing a kinematic or dynamic model for predicting the track by combining the motion characteristics of the target, wherein the kinematic or dynamic model is used for predicting the track of the target. The performance index function can be defined in various forms, and the common methods include a tracking error weighting method, a tracking data interactive multi-model filtering method and the like.
And then, calculating the matching degree of each typical maneuvering local model in the target maneuvering characteristic model set and the target actual flight trajectory by using a performance index function based on a similarity principle, refining a target maneuvering characteristic change rule by taking the matching degree as a basis, namely determining parameters of a target trajectory prediction model, substituting the obtained parameters into the target trajectory prediction model, and then performing forward trajectory prediction on the target by adopting a numerical integration method. A weighted least squares approach may be employed to solve the parameters of the target trajectory prediction model.
And the backward feedback correction module is used for correcting the target track predicted by the forward track prediction module. And the backward feedback correction module evaluates the target game maneuver intention by constructing a game maneuver intention evaluation importance map model by utilizing the trajectory prediction result of the forward trajectory prediction module, extracts the predicted trajectory correction information with the target game maneuver intention evaluation, introduces the predicted trajectory correction information into the target trajectory prediction model established by the target trajectory forward prediction module, and corrects the predicted trajectory.
The working process of the backward feedback correction module is as follows: firstly, a global importance map model is established according to flight important nodes, a multi-model decomposition-synthesis method can be adopted to establish the global importance map model, namely, the importance degree of each node of an airspace where a target flies is determined, a local model taking the flight important nodes as the center is established, and a global description relation is established through topological mapping to obtain the global importance map model. The flight important node is set according to an application scenario, and for example, important political, military or economic places, facilities and the like having a large influence on a target flight mission can be set as the flight important node.
And then, according to the global importance map model, establishing an incidence relation between the forward prediction track and the flight important node, and determining target maneuvering intention information, and more specifically, establishing an incidence relation between the forward prediction track and the flight important node by using a coverage matching criterion between the global importance map model and a forward track prediction area (target track prediction spatial distribution) to determine the target maneuvering intention information. And assuming that the target threat degree is larger when the association degree is larger, determining the target maneuver intention information by adopting a Bayesian inference method. The forward trajectory prediction region is determined by the trajectory predicted by the target trajectory prediction model.
And correcting parameters of the target track prediction model by using the target maneuver intention information and adopting a posterior conditional probability method, and then performing track prediction according to the target track prediction model after parameter correction to obtain a corrected track prediction result.
The trajectory prediction process of the target trajectory prediction system of the present invention will be further described with reference to an embodiment, which performs trajectory prediction on a reentry glide target.
Firstly, establishing a target maneuvering characteristic model set of the reentry gliding target, and obtaining a target typical motion track by a target maneuvering characteristic model set module according to the motion characteristics of the reentry gliding target by adopting a kinematics principle, so that a typical track data model is adopted as a maneuvering characteristic model of the reentry gliding target, state variables with N LGR nodes are selected, local models of different stages and different states are represented by discrete points by adopting a Radau pseudo-spectrum method, and T is { K { (K) }1,K2,...,KNAnd (c) the step of (c) in which,
Xlis the state quantity, U, of the target ith LGR nodelThe flight control quantity of the target ith LGR node. The representative trajectory data model is used to realize the trajectory characterization of the target under specific conditions, as shown in fig. 2.
Then, aiming at different maneuvering modes and different flight states of the target, a dynamics principle is adopted to obtain a plurality of characteristic track sample data, a multi-model modeling method is adopted to carry out maneuvering state decomposition on the target, a typical maneuvering local model of the target is obtained, and the typical maneuvering local model forms a target maneuvering characteristic model set. In this embodiment, the state of each dimension in the d-dimensional constraint space is defined as pjJ-1, 2, …, d, the state of each dimension may takeThe set of values being a subset of the real space, i.e.
And further establishing a target maneuvering characteristic model set Pc as follows:
and solving the elements covering the constraint space to obtain a maneuvering characteristic model set covering the target track space. According to the embodiment, the reentry altitude is 72km, the reentry speed is 4000m/s, the terminal altitude constraint is 10km, when the longitudinal flight distance changes, offline trajectory optimization is performed on different longitudinal flight distance constraints to form a trajectory set covering a flight range, as shown in fig. 3, a maneuvering characteristic model set formed by typical maneuvering local models can cover a flight airspace of a target in different maneuvering modes.
And after the target maneuvering characteristic model set is established, the forward track prediction module carries out forward track prediction. The forward trajectory prediction module defines a performance index function and establishes a target trajectory prediction model, in this embodiment, a tracking error weighting method is used to define the performance index function, and the obtained performance index function is as follows:
in the formula ei(k) Representing the track deviation of the ith typical maneuvering local model in the target maneuvering characteristic model set at the time k, M is the number of the typical maneuvering local models in the target maneuvering characteristic model set, exp represents exponential operation, a0And a1Respectively a current error weight factor and a historical error weight factor, a0And a1The weights of the current error and the historical error in the performance index are determined when the weights are both larger than 0, the weights are used for determining the relative importance degree of the combination of the current time error and the past time error on the performance index, tau is a forgetting factor and represents the memory effect of the performance index, h is the selected limited time domain length,
is the trajectory state of the ith typical local model of maneuver at time k, y (k) is the actual flight trajectory state of the target at time k, rdlRepresenting a calculation of Euclidean distance; the track tracking data of the current target and the historical information of the flight process are utilized to form a performance index, the matching degree of each typical maneuvering local model in the maneuvering characteristic model set and the actual flight track (the current movement state of the target) of the target is evaluated through a performance index function, and the performance index value Ji(k) The larger the model is, the lower the matching degree of the ith typical maneuvering local model and the actual target state is, and the performance index value J is basedi(k) Using weights of a typical maneuver local model
To represent the degree of matching, w, of the typical maneuver local model with the target actual flight trajectoryi(k) The matching degree of the ith typical maneuvering local model and the target actual flight track is shown.
In this embodiment, the motion model under the reentry gliding target half-speed coordinate system is simplified, and the target trajectory prediction model established is as follows:
wherein v is the local velocity, gamma is the local track inclination, chi is the local track drift angle, r is the target geocentric distance, theta is the latitude,
longitude, ρ is the air density in the atmosphere of the target, g is the gravitational acceleration of the target, β is the roll angle,
s is the reference area of force, CDAnd CLRespectively, a resistance coefficient and a lift coefficient of the target, and m is the target mass.
Finally, calculating the matching degree w of the typical maneuvering local model and the target actual flight track by using the performance index functioni(k) According to wi(k) Fitting parameters (K) of a target trajectory prediction model using a weighted least squares methodD，KLAnd beta), substituting the parameters obtained by fitting into a target track prediction model, and integrating by adopting a fourth-order 'Runge-Kutta' numerical integration method to obtain a forward prediction track of the target.
And the backward feedback correction module is used for correcting the track predicted by the forward track prediction module. Firstly, a multi-model 'decomposition-synthesis' method is adopted to establish a global importance map model, and the multi-model 'decomposition-synthesis' method is a known method and is not an innovation part of the invention, and is not described herein again. In this embodiment, assuming that there are 4 important regions (flight important nodes) and the local distribution of each flight important node is calculated according to the gaussian distribution, a joint distribution probability function f can be usedmA global importance map model is formed as shown in fig. 4.
Secondly, mapping the forward track predicted by the target track prediction model to the global importance map model, and determining target maneuvering intention information through the incidence relation between the target forward track prediction area and the global importance map model area under the characteristic constraint, as shown in fig. 5. The target maneuver intention is evaluated by using a global importance map model, the important region (flight important node) of the embodiment follows Gaussian distribution, and a joint distribution probability function is used
Form a global importance map model, where xm0For the position of the m flight important node central point in the importance map, sigmamFor the mth flight importance node coverage, x represents the location of other points in the global importance map model.
In this embodiment, the spatial distribution of the target forward trajectory prediction region obtained according to the target trajectory prediction model is: f. ofp1(x) And fp2(x) Corresponding to the posterior probability w of the predicted trajectoryaComprises the following steps:
w in the formulap1And wp2Two spatially distributed posterior probabilities, x, for the target forward trajectory prediction region, respectively1、x2、x3、x4The distribution range of the flight important nodes (see figure 5); then, according to the posterior probability of the predicted track, determining the conditional probability of each typical maneuvering local model by using a Bayesian inference method, namely the target maneuvering intention information described by each typical maneuvering local model is as follows:
in the formula, p (x)k-1J) is the prior probability of the jth typical maneuver local model (j is 1,2, …, M) at the time point k-1, the prior probability of the typical maneuver local model is the matching degree of the typical maneuver local model and the target actual flight trajectory, and in the embodiment, the prior probability of the typical maneuver local model is the weight w of the typical maneuver local modeli(k)，p(xk＝i,xk-1J) is the posterior probability of the predicted trajectory corresponding to the typical local model of maneuver, i.e., the posterior probability w of the predicted trajectorya(ii) a Based on Bayesian prediction principle, target maneuver intention information p (x) is utilizedk＝i|xk-1J) correcting the target predicted state, there are: p (x)k|x1:k-1)＝∫p(xk|xk-1)p(xk-1|x1:k-1)dxk-1Wherein p (x)k-1|x1:k-1) The conditional probability of the moment k-1, namely the target maneuvering intention information of the typical maneuvering local model at the moment k-1, is obtained according to the correction result p (x)k|x1:k-1) The parameters of the target track prediction model established by the forward track prediction module are corrected, and the parameters comprise:
wherein,
for the parameters of the typical maneuver local model in the target maneuver characteristic model set (the parameters of the typical maneuver local model in the embodiment include K)D，KLBeta), M is a targetAnd concentrating the number of typical maneuvering local models by the maneuvering characteristic model, and on the basis, performing track prediction by using the target track prediction model after parameter correction to obtain a corrected track prediction result.
Fig. 6 to 10 are diagrams showing the effect of predicting the trajectory of the reentry gliding target by using the corrected target trajectory prediction model, and the prediction error change curve in fig. 6 shows that the method of the present invention has better prediction accuracy in the target 200 seconds prediction. The model membership relationship variation curve in fig. 7 shows that the correlation of the local feature model is converged in the prediction process. The model parameter variation comparison curves of fig. 8 to 10 show that the model parameters are converged when predicted in the prediction process, and have better prediction performance.
The invention also provides a target track prediction method, which comprises the following steps:
s1, establishing a target maneuvering characteristic model set;
firstly, determining a maneuvering characteristic model of a target, then carrying out maneuvering state decomposition on the target, establishing a typical maneuvering local model of the target based on the maneuvering characteristic model, and forming a target maneuvering characteristic model set by the typical maneuvering local model;
s2, predicting a target forward track;
defining a performance index function, establishing a target trajectory prediction model, wherein the performance index function is used for evaluating the matching degree of each typical maneuvering local model in the target maneuvering characteristic model set and the target actual flight trajectory, determining parameters of the target trajectory prediction model according to the matching degree of each typical maneuvering local model and the target actual flight trajectory, substituting the obtained parameters into the target trajectory prediction model, and predicting the forward trajectory of the target by using the target trajectory prediction model by adopting a numerical integration method;
s3, correcting the target track;
firstly, establishing a global importance map model of a flight important node, establishing an incidence relation between a forward prediction track and the flight important node in the global importance map model according to the global importance map model, and determining target maneuvering intention information; and correcting parameters of the target track prediction model by using the target maneuver intention information and adopting a posterior conditional probability method, and predicting the track of the target track according to the target track prediction model after parameter correction to obtain a corrected track prediction result.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A target trajectory prediction system, comprising:
the system comprises a target maneuvering characteristic model set module used for establishing a target maneuvering characteristic model set, wherein the target maneuvering characteristic set comprises typical maneuvering local models of a plurality of targets;
the forward track prediction module is used for performing forward track prediction on the target, defining a performance index function and establishing a target track prediction model, calculating the matching degree of each typical maneuvering local model in a target maneuvering characteristic model set and the target actual flight track through the performance index function, determining parameters of the target track prediction model according to the matching degree of each typical maneuvering local model and the target actual flight track, substituting the obtained parameters into the target track prediction model, and performing forward track prediction on the target by adopting a numerical integration method;
the backward feedback correction module is used for correcting the target track, a global importance map model is established according to flight important nodes, then an incidence relation between a forward prediction track and the flight important nodes is established according to the global importance map model, target maneuver intention information is determined, parameters of the target track prediction model are corrected by the target maneuver intention information through a posterior conditional probability method, track prediction is carried out according to the target track prediction model after the parameters are corrected, and a corrected track prediction result is obtained.
2. The target trajectory prediction system of claim 1, wherein: when the target maneuvering characteristic model set module establishes a target maneuvering characteristic set, firstly, a maneuvering characteristic model for representing a target maneuvering mode is determined, then, maneuvering state decomposition is carried out on a target, a typical maneuvering local model of the target is established, and the obtained typical maneuvering local model forms a target maneuvering characteristic model set.
3. The target trajectory prediction system of claim 2, wherein: the maneuvering characteristic model comprises a CA model, a CV model, a typical track data model and a dynamic model.
4. A target trajectory prediction method is characterized by comprising the following steps:
s1, establishing a target maneuvering characteristic model set, firstly determining a maneuvering characteristic model of a target, then carrying out maneuvering state decomposition on the target, establishing a typical maneuvering local model of the target based on the maneuvering characteristic model, and forming the target maneuvering characteristic model set by the typical maneuvering local model;
s2, predicting a target forward track, defining a performance index function, establishing a target track prediction model, evaluating the matching degree of each typical maneuvering local model in the target maneuvering characteristic model set and the target actual flight track through the performance index function, determining parameters of the target track prediction model according to the matching degree of each typical maneuvering local model and the target actual flight track, and predicting the forward track of the target based on the target track prediction model by adopting a numerical integration method;
s3, correcting the target track, namely firstly determining flight important nodes, then establishing a global importance map model according to the flight important nodes, then establishing an incidence relation between a forward predicted track and the flight important nodes according to the global importance map model, determining target maneuver intention information, correcting parameters of the target track prediction model by using the target maneuver intention information and adopting a posterior conditional probability method, and predicting the target track according to the target track prediction model after parameter correction to obtain a corrected track prediction result.
5. The target trajectory prediction method according to claim 4, characterized in that: in step S2, parameters of the target trajectory prediction model are solved by a weighted least squares method.
6. The target trajectory prediction method according to claim 4, characterized in that: in step S2, a tracking error weighting method is adopted to define a performance index function, and the matching degree of the typical maneuvering local model and the target actual flight path is the weight of the typical maneuvering local model
Wherein J isi(k) And the performance index value of the ith typical maneuvering local model in the target maneuvering characteristic model set is represented, and M is the number of the typical maneuvering local models in the target maneuvering characteristic model set.
7. The target trajectory prediction method according to claim 6, characterized in that: in step S3, a Bayesian inference method is adopted to determine target maneuver intention information
In the formula, p (x)k-1J) is the prior probability of the j-th typical mobile local model at time k-1, p (x)k＝i,xk-1J) is the predicted trajectory posterior probability corresponding to a typical maneuver local model.
8. The target trajectory prediction method according to claim 7, characterized in that: the method for correcting the parameters of the target trajectory prediction model in step S3 is as follows: eyes of userTarget movement intention information p (x)k＝i|xk-1J) correcting the target predicted state, there are: p (x)k|x1:k-1)＝∫p(xk|xk-1)p(xk-1|x1:k-1)dxk-1Then based on the corrected result p (x)k|x1:k-1) Parameters of the target track prediction model are corrected, and the parameters comprise:
wherein,
parameters of a typical maneuvering local model in the target maneuvering characteristic model set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110394691.8A CN113095504B (en) | 2021-04-13 | 2021-04-13 | Target track prediction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110394691.8A CN113095504B (en) | 2021-04-13 | 2021-04-13 | Target track prediction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113095504A true CN113095504A (en) | 2021-07-09 |
| CN113095504B CN113095504B (en) | 2022-10-21 |
Family
ID=76676733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110394691.8A Expired - Fee Related CN113095504B (en) | 2021-04-13 | 2021-04-13 | Target track prediction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095504B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761662A (en) * | 2021-09-10 | 2021-12-07 | 中国人民解放军空军工程大学 | Generation method of trajectory prediction pipeline of gliding target |
| CN114926795A (en) * | 2022-07-19 | 2022-08-19 | 深圳前海中电慧安科技有限公司 | Method, device, equipment and medium for determining information relevance |
| CN114998761A (en) * | 2022-06-15 | 2022-09-02 | 北京庚图科技有限公司 | Airplane target detection method and device, electronic equipment and medium |
| CN118466556A (en) * | 2024-07-09 | 2024-08-09 | 四川汉科计算机信息技术有限公司 | Aiming point control method and system based on track prejudgement, unmanned aerial vehicle and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336863A (en) * | 2013-06-24 | 2013-10-02 | 北京航空航天大学 | Radar flight path observation data-based flight intention recognition method |
| CN111783358A (en) * | 2020-07-02 | 2020-10-16 | 哈尔滨工业大学 | Bayesian estimation-based long-term trajectory prediction method for hypersonic aircraft |
-
2021
- 2021-04-13 CN CN202110394691.8A patent/CN113095504B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336863A (en) * | 2013-06-24 | 2013-10-02 | 北京航空航天大学 | Radar flight path observation data-based flight intention recognition method |
| CN111783358A (en) * | 2020-07-02 | 2020-10-16 | 哈尔滨工业大学 | Bayesian estimation-based long-term trajectory prediction method for hypersonic aircraft |
Non-Patent Citations (1)
| Title |
|---|
| 张凯等: "基于意图推断的高超声速滑翔目标贝叶斯轨迹预测", 《宇航学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761662A (en) * | 2021-09-10 | 2021-12-07 | 中国人民解放军空军工程大学 | Generation method of trajectory prediction pipeline of gliding target |
| CN113761662B (en) * | 2021-09-10 | 2022-10-21 | 中国人民解放军空军工程大学 | Generation method of trajectory prediction pipeline of gliding target |
| CN114998761A (en) * | 2022-06-15 | 2022-09-02 | 北京庚图科技有限公司 | Airplane target detection method and device, electronic equipment and medium |
| CN114926795A (en) * | 2022-07-19 | 2022-08-19 | 深圳前海中电慧安科技有限公司 | Method, device, equipment and medium for determining information relevance |
| CN114926795B (en) * | 2022-07-19 | 2022-11-15 | 深圳前海中电慧安科技有限公司 | Method, device, equipment and medium for determining information relevance |
| CN118466556A (en) * | 2024-07-09 | 2024-08-09 | 四川汉科计算机信息技术有限公司 | Aiming point control method and system based on track prejudgement, unmanned aerial vehicle and medium |
| CN118466556B (en) * | 2024-07-09 | 2024-09-17 | 四川汉科计算机信息技术有限公司 | Aiming point control method and system based on track prejudgement, unmanned aerial vehicle and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113095504B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113095504B (en) | Target track prediction system and method | |
| Zhang et al. | A novel real-time penetration path planning algorithm for stealth UAV in 3D complex dynamic environment | |
| Meera et al. | Obstacle-aware adaptive informative path planning for uav-based target search | |
| CN114048889B (en) | Aircraft trajectory prediction method based on long-term and short-term memory network | |
| Tisdale et al. | Autonomous UAV path planning and estimation | |
| CN112148008B (en) | Real-time unmanned aerial vehicle path prediction method based on deep reinforcement learning | |
| CN106814737B (en) | A kind of SLAM methods based on rodent models and RTAB Map closed loop detection algorithms | |
| CN113268074B (en) | Unmanned aerial vehicle flight path planning method based on joint optimization | |
| Zhang et al. | Probabilistic planning and risk evaluation based on ensemble weather forecasting | |
| Park et al. | A distributed ADMM approach to non-myopic path planning for multi-target tracking | |
| Zhang et al. | Enhancing Multi-UAV Reconnaissance and Search Through Double Critic DDPG With Belief Probability Maps | |
| Or et al. | Adaptive step size learning with applications to velocity aided inertial navigation system | |
| Koch et al. | Sensor scheduling strategies for 1-to-n multi-object tracking | |
| Ferrari et al. | Cooperative navigation for heterogeneous autonomous vehicles via approximate dynamic programming | |
| CN117369507B (en) | Unmanned aerial vehicle dynamic path planning method of self-adaptive particle swarm algorithm | |
| Ryan | Information-theoretic tracking control based on particle filter estimate | |
| Mirzaei et al. | Optimal path planning for two Uavs in a pursuit-evasion game | |
| Moon et al. | Learned search parameters for cooperating vehicles using gaussian process regressions | |
| Li et al. | Sma-nbo: A sequential multi-agent planning with nominal belief-state optimization in target tracking | |
| Mousavi et al. | A new predictive motion control of a planar vehicle under uncertainty via convex optimization | |
| Zhu et al. | UAV trajectory tracking via RNN-enhanced IMM-KF with ADS-B data | |
| Zhang et al. | An adaptive artificial potential function approach for geometric sensing | |
| Pouya et al. | Performing active search to locate indication of ancient water on mars: An online, probabilistic approach | |
| Zhou et al. | Design of UAV flight state recognition and trajectory prediction system based on trajectory feature construction | |
| CN117136343A (en) | System for balancing energy detection and observation times for auto-induction vehicles |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20221021 |