CN109460065A - Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function - Google Patents
Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function Download PDFInfo
- Publication number
- CN109460065A CN109460065A CN201910025290.8A CN201910025290A CN109460065A CN 109460065 A CN109460065 A CN 109460065A CN 201910025290 A CN201910025290 A CN 201910025290A CN 109460065 A CN109460065 A CN 109460065A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- formation
- potential function
- cluster
- potential
- 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
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000033001 locomotion Effects 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 230000008878 coupling Effects 0.000 claims description 12
- 238000010168 coupling process Methods 0.000 claims description 12
- 238000005859 coupling reaction Methods 0.000 claims description 12
- 230000007423 decrease Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 239000002245 particle Substances 0.000 claims 1
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010181 polygamy Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Abstract
The invention discloses a potential function-based unmanned aerial vehicle cluster formation characteristic identification method and system, which comprises the following steps of 1: pre-establishing a potential function model base corresponding to the formation characteristics of the unmanned aerial vehicle cluster according to the formation characteristics of the unmanned aerial vehicle cluster; step 2: acquiring a motion track of the unmanned aerial vehicle cluster through radar detection; and step 3: reversely solving the posterior probability of each potential function and parameters thereof in the potential function library according to the motion trail of the unmanned aerial vehicle cluster; and 4, step 4: and according to the obtained posterior probabilities of all potential functions and parameters thereof, taking the formation corresponding to the potential function with the maximum posterior probability as the unmanned aerial vehicle cluster formation according to decision requirements and outputting the formation. According to the method, the formation mode which can be adopted by the unmanned aerial vehicle can be conjectured through inversion of the formation characteristics of the unmanned aerial vehicle cluster, namely through observed cluster data.
Description
Technical field
The invention belongs to unmanned plane cluster confrontation field more particularly to a kind of unmanned plane cluster formation based on potential function are special
Levy discrimination method.
Background technique
In recent years, explosive growth is integrally presented in the research for autonomous system and artificial intelligence field.In this context,
Small-sized, inexpensive unmanned plane cluster, as excellent with task diversity, reliability etc. not available for single unmanned aerial vehicle platform
Gesture receives significant attention.With the fast development of unmanned plane Clustering, the demand to anti-unmanned plane Clustering is also increasingly
Urgently, especially under the threat of terrorism, inexpensive small drone cluster is easy to be used for since its is ready availability
Implement the attack of terrorism.Therefore, how to identify and effectively destroy the emphasis that the structure and function of unmanned plane cluster is research.Instead nobody
The committed step of machine Clustering is exactly its formation feature of accurate recognition.The technology of current anti-unmanned plane cluster rests on a large scale
Control plane is injured and monitored to signal interference, high energy weapon, these countermoves are at high cost, sustainability is low, to cluster network
Accurate damage effectiveness it is limited, at present to unmanned plane cluster be intended to accurately identify and Intelligent unattended machine cluster confrontation research still
It does not make a breakthrough, basic reason is cannot to accurately identify the formation feature of unmanned plane cluster to accomplish to have
Put arrow.
Summary of the invention
The technical problem to be solved by the present invention is to how accurate recognition unmanned plane cluster formation feature, provide one kind and be based on
The unmanned plane cluster formation feature identification method and system of potential function.
To solve this problem, the technical scheme adopted by the invention is that:
A kind of unmanned plane cluster formation feature identification method based on potential function, comprising the following steps:
Step 1: gesture corresponding with unmanned plane cluster formation feature is pre-established according to the formation feature of unmanned plane cluster
Function model library;
Step 2: the motion profile of unmanned plane cluster is obtained by radar detection;
Step 3: all kinds of potential functions in potential function library and its parameter are inversely found out according to the motion profile of unmanned plane cluster
Posterior probability;
Step 4: according to the posterior probability of calculated all kinds of potential functions and its parameter, being needed to take posterior probability according to decision
Formation corresponding to maximum potential function is unmanned plane cluster formation and exports.
To advanced optimize scheme, following improvement has been done:
Further, in step 1 potential function corresponding with unmanned plane cluster formation feature library construction method specifically:
Step 1.1: assuming that cluster has N frame unmanned plane, to the i-th frame unmanned plane, the citation form of potential function are as follows:
Wherein x=(x1,x2...xN) be N frame unmanned plane t moment location matrix, xiFor the absolute position of the i-th frame unmanned plane
It sets, v=(v1,v2...vN) be N frame unmanned plane t moment rate matrices,For speed coupling terms,For formation control item,For anticollision item, α is speed coupling strength parameter, and α ∈ (0 ,+∞), β are shape coupling strength parameter, β ∈ (0 ,+∞),
γ is the coupling strength parameter for preventing collision, γ ∈ (0 ,+∞).
Step 1.2: according to the relative position d=(d of N frame unmanned plane formation1,d2,…,dN) determined by formation, then this refers to
Determine the potential function of formation are as follows:
Wherein:For the convergent preference of speed, have with the position of unmanned plane individual each in cluster
It closing, s is the affecting parameters of distance between cluster individual, s > 1 is generally taken,It is the mean place of t moment unmanned plane cluster, c is
Anticollision spacing, cijIt indicates the anticollision spacing of i-th and jth frame unmanned plane, limits anticollision spacing c and be not less than specified formation
Minimum spacing
Further, as the relative position d=(d of N frame unmanned plane formation1,d2,…,dN) determined by formation be circle
When, then potential function is
Wherein, R is the radius of specified formation.
Further, in step 2 motion profile of unmanned plane cluster mainly include unmanned plane number of clusters N, one section it is discrete
The speed v of every frame unmanned plane in time Ti,obs(0),vi,obs(1),…,vi,obs(T) and position vector xi,obs(0),xi,obs
(1),…,xi,obs(T), wherein t=0 is initial time, and t=T is observation finish time.
Further, according to the motion profile x of unmanned plane cluster in step 3obsInversely find out all kinds of gesture letters in potential function library
Several and its parameter posterior probability method particularly includes:
Step 3.1: according to the motion profile x observedobsThe priori of all kinds of potential functions is general in preliminary given potential function library
Rate π (Mk) and its parameter prior probability π (θ | Mk);
Step 3.2: the posterior probability π (M of every class potential function is solved using adaptive ABC SMC model selection algorithmk|
xobs) and its parameter posterior probability π (θ | xobs)。
Further, ABC SMC model selection algorithm adaptive in step 3.2 specifically:
The population P in every wheel iteration is given, for the threshold for the gradient decline for needing to give in advance in former ABC SMC algorithm
Value ε0> ε1> ... > εT, given using adaptive method, i.e., given initial threshold ε0If t takes turns each grain in iteration
Sub- i passes through power of a test function modelThe unmanned plane cluster position x being calculatediData x is observed with originalobsDifference be εi
=d (xi,xobs), in εi, i=1,2 ..., take q quantile as the threshold epsilon of next round iteration in Pt+1, by above-mentioned given data
It brings into the adaptive ABC SMC model selection algorithm set, obtains every class potential function MkPosterior probability and its parameter
Posterior probability.
A kind of unmanned plane cluster formation feature identification system based on potential function, comprises the following modules:
Potential function library module: for storing gesture composed by potential function corresponding with all kinds of formation modes of unmanned plane cluster
Function library;
Motion profile obtains module: for obtaining the motion profile of unmanned plane cluster by radar detection;
It calculates posterior probability module and calculates posterior probability module: for passing through algorithm according to the motion profile of unmanned plane cluster
Find out the posterior probability of all kinds of potential functions and its parameter in potential function library;
It is counter to push away module: according to the posterior probability for calculating all kinds of potential functions calculated by posterior probability module and its parameter, root
It needs that formation corresponding to the maximum potential function of posterior probability is taken to be unmanned plane cluster formation and export according to decision.
Compared with prior art, beneficial effect obtained by the present invention is
The present invention is based on the unmanned plane cluster formation feature identification methods of potential function, by previously according to unmanned plane cluster
Formation feature establishes corresponding Potential Function Models library, then finds out all kinds of gesture letters in potential function library according to the motion profile of unmanned plane
Several posterior probability, and then taking unmanned plane cluster formation corresponding to the maximum potential function of posterior probability is estimated cluster team
Shape.The present invention is directed to the inverting of unmanned plane cluster formation feature, passes through the company-data observed, thus it is speculated that its collection that may be taken
Group's mode and formation.
Detailed description of the invention
Fig. 1 is flow chart of the invention;
Fig. 2 is the variation tendency of threshold value;
Fig. 3 is prediction formation (left side) compared with observing formation (right side).
Specific embodiment
Fig. 1 to Fig. 3 gives a kind of implementation of the unmanned plane cluster formation feature identification method the present invention is based on potential function
, the cluster for observing a 19 frame unmanned planes is first assumed in the present embodiment, and radar can track the track of each frame, see
Before measuring the formation of cluster formation, the potential function of cluster is judged according to its motion profile using method of the invention, and accordingly
Predict cluster formation.
A kind of unmanned plane cluster formation feature identification method based on potential function, comprising the following steps:
Step 1: being pre-established according to the formation feature of unmanned plane cluster corresponding with each formation feature of unmanned plane cluster
All kinds of Potential Function ModelsLibrary;The formation feature of unmanned plane cluster has: big airplane-shaped, linear, round, triangle
Deng;
Step 1.1: assuming that cluster has N frame unmanned plane, to the i-th frame unmanned plane, the citation form of potential function are as follows:
Wherein x=(x1,x2...xN) be N frame unmanned plane t moment location matrix, xiFor the absolute position of the i-th frame unmanned plane
It sets, v=(v1,v2...vN) be N frame unmanned plane t moment rate matrices,For speed coupling terms,For formation control item,For anticollision item, α is speed coupling strength parameter, and α ∈ (0 ,+∞), β are shape coupling strength parameter, β ∈ (0 ,+∞),
γ is the coupling strength parameter for preventing collision, γ ∈ (0 ,+∞).
Step 1.2: according to the relative position d=(d of N frame unmanned plane formation1,d2,…,dN) determined by formation, then this refers to
Determine the potential function of formation are as follows:
WhereinRelated with the position of each cluster individual for the convergent preference of speed, s is collection
The affecting parameters of distance, generally take s > 1 between group's individual,It is the mean place of t moment unmanned plane cluster, c is between anticollision
Away from cijIt indicates the anticollision spacing of i-th and jth frame unmanned plane, limits the minimum spacing that anticollision spacing c is not less than specified formationThen unmanned plane cluster will be stablized and form the formation over time, otherwise will will appear concussion.The present invention makes
With the relative position d=(d of unmanned plane formation1,d2,…,dN) description unmanned plane cluster various formation features.
Particularly, as the relative position d=(d of N frame unmanned plane formation1,d2,…,dN) determined by formation when being round,
Then
Wherein, R is the radius of specified formation.
Step 2: the motion profile of unmanned plane cluster is obtained by radar detection;The movement of unmanned plane cluster in the present embodiment
Track mainly includes the speed v of every frame unmanned plane in unmanned plane number of clusters N, one section of discrete time Ti,obs(0),vi,obs
(1),…,vi,obs(T) and position vector xi,obs(0),xi,obs(1),…,xi,obs(T), wherein t=0 is initial time, and t=T is
Observe finish time.
In order to verify the validity of method provided by the present invention, in the present embodiment, for the built-in algorithm of unmanned plane cluster
Using round potential function, i.e., a circular unmanned plane cluster formation is first given, forming naked eyes in 20-50 step-length or so can area
The formation divided now takes the position and speed information of preceding 5 step-lengths as observation data, verifies whether energy by means of the present invention
Predict circle.
Step 3: all kinds of potential functions in potential function library and its parameter are inversely found out according to the motion profile of unmanned plane cluster
Posterior probability;
Step 3.1: according to the motion profile x observedobThe priori of all kinds of potential functions is general in the tentatively given potential function library s
Rate π (Mk) and its parameter prior probability π (θ | Mk);Two class potential functions composition potential function library is chosen in the present embodiment, respectively
Round potential function:
With the potential function of big aircraft formation, wherein d is big aircraft shape:
The prior probability that two class potential functions in potential function library are enabled in the present embodiment is 1/2, the parameter in round potential function
The prior probability of α, beta, gamma, s and R are respectively 1,1,1,2,1, the parameter alpha in big aircraft potential function, beta, gamma, the prior probability of s
Respectively 1,1,1,2.
Step 3.2: the posterior probability π (M of every class potential function is solved using adaptive ABC SMC model selection algorithmk|
xobs) and its parameter posterior probability π (θ | xobs), adaptive ABC SMC model selection algorithm is from paper " Marin J
M,Pudlo P,Robert C P,et al.Approximate Bayesian computational methods[J]
.Statistics&Computing, 2012,22 (6): algorithm described in 1167-1180 ".
In the present embodiment, the input of adaptive ABC SMC model selection algorithm is the potential function shape in known models library
FormulaWith quantity m, m=2, i.e., have 2 class potential functions here in potential function library, the position that unmanned plane cluster is demarcated in a period of time T
Set xobs=(xobs(0),xobs(1),xobs(2),…,xobsAnd initial velocity v (T))obs(0).Ginseng required for the algorithm itself
Number specifically:
The population P in every wheel iteration is given, for the threshold for the gradient decline for needing to give in advance in former ABC SMC algorithm
Value ε0> ε1> ... > εT, given using adaptive method, i.e., given initial threshold ε0If t takes turns each grain in iteration
Sub- i passes through power of a test function modelObtained new data xi, i.e., the unmanned plane that is calculated by Potential Function Models
Cluster position xiDifference with former observation data is Euclidean distance quadratic sum εi=d (xi,xobs), in εi, i=1,2 ..., it is taken in P
Threshold epsilon of the q quantile as next round iterationt+1, above-mentioned given data is brought into the adaptive ABC SMC model set
In selection algorithm, every class potential function M is obtainedkPosterior probability, i.e., the posterior probability of round potential function is 1, big aircraft formation gesture
The posterior probability of function is 0, then according to principle of ordering, choosing round potential function is most probable model, calculates the posteriority of its parameter
Probability expectation, i.e. α, beta, gamma, s and R are respectively 1.42,0.28,3.72,3.87 and 0.68.
It is iterated using the method for ABC SMC, setting initial threshold is 0.1, and the population of each iteration is 5, warp
10 wheel iteration are crossed, obtain result as shown in Fig. 2, threshold value progressively decreases to show that Potential Function Models are posterior close to 0 in Fig. 2
Effect is become better and better.
The present embodiment takes ABC algorithm to carry out model solution.It on the one hand is because the potential function algorithm of unmanned plane cluster is multiple
Polygamy is very high, when general classical way is for example, by using maximum-likelihood method, is unable to get the expression formula of its likelihood function, and pattra leaves
ABC algorithm in this method can cope with such complex model reverse temperature intensity using the method that forward model brings Verification into
Difficult problem;On the other hand, bayes method can guarantee inverse problem without pathosis.On the basis of ABC algorithm, using SMC
Algorithm accelerates sampling, improves precision.
Step 4: according to the posterior probability of calculated all kinds of potential functions and its parameter, taking the posterior error of parameter is parameter
Estimation needs that formation corresponding to the maximum potential function of posterior probability is taken to be unmanned plane cluster formation and export according to decision.
Round potential function and parameter are obtained by the way that initial observation data are brought into above-mentioned steps or module, prediction the 30th
The formation of cluster and position when step-length, as shown in figure 3, the left side is prediction cluster, the right is observation cluster, it can be seen that the two
Formation is similar, illustrates that the method for the present invention has prediction effect.
The present invention gives a kind of unmanned plane cluster formation feature identification system based on potential function, including with lower die
Block:
Potential function library module: for storing gesture composed by potential function corresponding with all kinds of formation modes of unmanned plane cluster
Function library;
Motion profile obtains module: for obtaining the motion profile of unmanned plane cluster by radar detection;
It calculates posterior probability module and calculates posterior probability module: for passing through algorithm according to the motion profile of unmanned plane cluster
Find out the posterior probability of all kinds of potential functions and its parameter in potential function library;
It is counter to push away module: according to the posterior probability for calculating all kinds of potential functions calculated by posterior probability module and its parameter, root
It needs that formation corresponding to the maximum potential function of posterior probability is taken to be unmanned plane cluster formation and export according to decision.
The above is only the preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-described embodiment,
All technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
For those of ordinary skill, several improvements and modifications without departing from the principles of the present invention should be regarded as protection of the invention
Range.
Claims (7)
1. a kind of unmanned plane cluster formation feature identification method based on potential function, it is characterised in that: the following steps are included:
Step 1: being pre-established according to the formation feature of unmanned plane cluster corresponding all kinds of with each formation feature of unmanned plane cluster
Potential Function Models library;
Step 2: the motion profile of unmanned plane cluster is obtained by radar detection;
Step 3: the posteriority of all kinds of potential functions and its parameter in potential function library is inversely found out according to the motion profile of unmanned plane cluster
Probability;
Step 4: according to the posterior probability of calculated all kinds of potential functions and its parameter, being needed to take posterior probability maximum according to decision
Potential function corresponding to formation be unmanned plane cluster formation and to export.
2. the unmanned plane cluster formation feature identification method according to claim 1 based on potential function, it is characterised in that: step
The construction method in potential function corresponding with unmanned plane cluster formation feature library in rapid 1 specifically:
Step 1.1: assuming that cluster has N frame unmanned plane, to the i-th frame unmanned plane, the citation form of potential function are as follows:
Wherein x=(x1,x2,...,xN) be N frame unmanned plane t moment location matrix, xiFor the absolute position of the i-th frame unmanned plane, v
=(v1,v2...vN) be N frame unmanned plane t moment rate matrices,For speed coupling terms,For formation control item,For
Anticollision item, α are speed coupling strength parameter, and α ∈ (0 ,+∞), β are shape coupling strength parameter, and β ∈ (0 ,+∞), γ are anti-
The coupling strength parameter only collided, γ ∈ (0 ,+∞);
Step: 1.2: according to the relative position d=(d of N frame unmanned plane formation1,d2,…,dN) determined by formation, then this is specified
The potential function of formation are as follows:
WhereinRelated with the position of each cluster individual for the convergent preference of speed, s is cluster
The affecting parameters of distance, generally take s > 1 between body,It is the mean place of t moment unmanned plane cluster, c is anticollision spacing, cij
It indicates the anticollision spacing of i-th and jth frame unmanned plane, limits the minimum spacing that anticollision spacing c is not less than specified formation
3. the unmanned plane cluster formation feature identification method according to claim 2 based on potential function, it is characterised in that: when
Relative position d=(the d of N frame unmanned plane formation1,d2,…,dN) determined by formation when being round, then potential function is
Wherein, R is the radius of specified formation.
4. the unmanned plane cluster formation feature identification method according to claim 1 based on potential function, it is characterised in that: step
The motion profile of unmanned plane cluster mainly includes every frame unmanned plane in unmanned plane number of clusters N, one section of discrete time T in rapid 2
Speed vi,obs(0),vi,obs(1),…,vi,obs(T) and position vector xi,obs(0),xi,obs(1),…,xi,obs(T), wherein t=0
For initial time, t=T is observation finish time.
5. the unmanned plane cluster formation feature identification method according to claim 1 based on potential function, it is characterised in that: step
According to the motion profile x of unmanned plane cluster in rapid 3obsIt is general inversely to find out the posteriority of all kinds of potential functions and its parameter in potential function library
Rate method particularly includes:
Step 3.1: according to the motion profile x observedobsThe prior probability π of all kinds of potential functions in preliminary given potential function library
(Mk) and its parameter prior probability π (θ | Mk);
Step 3.2: the posterior probability π (M of every class potential function is solved using adaptive ABC SMC model selection algorithmk|xobs),
And its parameter posterior probability π (θ | xobs)。
6. the unmanned plane cluster formation feature identification method according to claim 1 based on potential function, it is characterised in that: step
Adaptive ABC SMC model selection algorithm in rapid 3.2 specifically:
The population P in every wheel iteration is given, for the threshold epsilon for the gradient decline for needing to give in advance in former ABC SMC algorithm0
> ε1> ... > εT, given using adaptive method, i.e., given initial threshold ε0If t takes turns each particle i in iteration
Pass through power of a test function modelThe unmanned plane cluster position data x being calculatediDifference with former observation data is Euclidean
Square distance and εi=d (xi,xobs), in εi, i=1,2 ..., take q quantile as the threshold epsilon of next round iteration in Pt+1, will
Above-mentioned given data is brought into the adaptive ABC SMC model selection algorithm set, and every class potential function M is obtainedkPosteriority
The posterior probability of probability and its parameter.
7. a kind of unmanned plane cluster formation feature identification system based on potential function according to any one of claim 1 to 6
System, it is characterised in that: comprise the following modules:
Potential function library module: for storing potential function composed by potential function corresponding with all kinds of formation modes of unmanned plane cluster
Library;
Motion profile obtains module: for obtaining the motion profile of unmanned plane cluster by radar detection;
Calculate posterior probability module: for finding out all kinds of gesture in potential function library by algorithm according to the motion profile of unmanned plane cluster
The posterior probability of function and its parameter;
It is counter to push away module: according to the posterior probability for calculating all kinds of potential functions calculated by posterior probability module and its parameter, according to certainly
Plan needs that formation corresponding to the maximum potential function of posterior probability is taken to be unmanned plane cluster formation and export.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025290.8A CN109460065B (en) | 2019-01-12 | 2019-01-12 | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025290.8A CN109460065B (en) | 2019-01-12 | 2019-01-12 | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109460065A true CN109460065A (en) | 2019-03-12 |
CN109460065B CN109460065B (en) | 2021-07-16 |
Family
ID=65616389
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910025290.8A Active CN109460065B (en) | 2019-01-12 | 2019-01-12 | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109460065B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110312306A (en) * | 2019-06-20 | 2019-10-08 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster cooperative positioning method and device based on asynchronous information |
CN111368971A (en) * | 2020-02-19 | 2020-07-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
CN112327887A (en) * | 2021-01-05 | 2021-02-05 | 成都信息工程大学 | Unmanned vehicle collision avoidance path planning method and system based on iteration improved APF |
CN114237292A (en) * | 2021-12-16 | 2022-03-25 | 中国人民解放军国防科技大学 | Distributed decision-making method for unmanned aerial vehicle cluster control and related equipment |
CN114911269A (en) * | 2022-06-17 | 2022-08-16 | 电子科技大学 | Networking radar interference strategy generation method based on unmanned aerial vehicle cluster |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20150059365A (en) * | 2013-11-22 | 2015-06-01 | 인하공업전문대학산학협력단 | Control apparatus for unmanned aerial vehicle and method thereof |
US20170131726A1 (en) * | 2015-11-06 | 2017-05-11 | SySense Incorporated | Automated operation of aircraft systems in inverted-v formations |
CN107065859A (en) * | 2017-02-14 | 2017-08-18 | 浙江工业大学 | The trajectory predictions method of multiple mobile robot |
CN108594853A (en) * | 2018-04-27 | 2018-09-28 | 中国人民解放军陆军工程大学 | Unmanned plane approach to formation control |
CN108873936A (en) * | 2018-07-09 | 2018-11-23 | 北京电子工程总体研究所 | A kind of aircraft autonomous formation method based on gesture game |
CN109062252A (en) * | 2018-08-27 | 2018-12-21 | 中国人民解放军战略支援部队航天工程大学 | Quadrotor drone cluster control method and its device based on Artificial Potential Field Method |
-
2019
- 2019-01-12 CN CN201910025290.8A patent/CN109460065B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20150059365A (en) * | 2013-11-22 | 2015-06-01 | 인하공업전문대학산학협력단 | Control apparatus for unmanned aerial vehicle and method thereof |
US20170131726A1 (en) * | 2015-11-06 | 2017-05-11 | SySense Incorporated | Automated operation of aircraft systems in inverted-v formations |
CN107065859A (en) * | 2017-02-14 | 2017-08-18 | 浙江工业大学 | The trajectory predictions method of multiple mobile robot |
CN108594853A (en) * | 2018-04-27 | 2018-09-28 | 中国人民解放军陆军工程大学 | Unmanned plane approach to formation control |
CN108873936A (en) * | 2018-07-09 | 2018-11-23 | 北京电子工程总体研究所 | A kind of aircraft autonomous formation method based on gesture game |
CN109062252A (en) * | 2018-08-27 | 2018-12-21 | 中国人民解放军战略支援部队航天工程大学 | Quadrotor drone cluster control method and its device based on Artificial Potential Field Method |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110312306A (en) * | 2019-06-20 | 2019-10-08 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster cooperative positioning method and device based on asynchronous information |
CN110312306B (en) * | 2019-06-20 | 2020-10-30 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster cooperative positioning method and device based on asynchronous information |
CN111368971A (en) * | 2020-02-19 | 2020-07-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
CN111368971B (en) * | 2020-02-19 | 2021-01-08 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
CN112327887A (en) * | 2021-01-05 | 2021-02-05 | 成都信息工程大学 | Unmanned vehicle collision avoidance path planning method and system based on iteration improved APF |
CN112327887B (en) * | 2021-01-05 | 2021-04-30 | 成都信息工程大学 | Unmanned vehicle collision avoidance path planning method and system based on iteration improved APF |
CN114237292A (en) * | 2021-12-16 | 2022-03-25 | 中国人民解放军国防科技大学 | Distributed decision-making method for unmanned aerial vehicle cluster control and related equipment |
CN114911269A (en) * | 2022-06-17 | 2022-08-16 | 电子科技大学 | Networking radar interference strategy generation method based on unmanned aerial vehicle cluster |
Also Published As
Publication number | Publication date |
---|---|
CN109460065B (en) | 2021-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109460065A (en) | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function | |
CN114048889B (en) | Aircraft trajectory prediction method based on long-term and short-term memory network | |
Milan et al. | Online multi-target tracking using recurrent neural networks | |
CN109191922B (en) | Large-scale four-dimensional track dynamic prediction method and device | |
Meyer et al. | Learning an uncertainty-aware object detector for autonomous driving | |
Mafeni Mase et al. | Benchmarking deep learning models for driver distraction detection | |
CN106934324A (en) | Based on the radar data correlating methods for simplifying many hypothesis algorithms | |
EP1734463A1 (en) | Methods and apparatus for target discrimination using observation vector weighting | |
Yazdian-Dehkordi et al. | Penalized Gaussian mixture probability hypothesis density filter for multiple target tracking | |
CN109657928B (en) | Cooperative scheduling method of closed-loop cooperative scheduling framework of vehicle-mounted sensor system | |
CN104268567A (en) | Extended target tracking method using observation data clustering and dividing | |
Shi et al. | Dynamic barycenter averaging kernel in RBF networks for time series classification | |
CN111445498A (en) | Target tracking method adopting Bi-L STM neural network | |
CN115051864B (en) | PCA-MF-WNN-based network security situation element extraction method and system | |
CN107871156B (en) | Ant colony multi-cell tracking system based on pheromone prediction | |
Martinsson et al. | Clustering vehicle maneuver trajectories using mixtures of hidden markov models | |
CN113589272A (en) | Automatic generation method for target tracking equipment on-duty log | |
CN116580322A (en) | Unmanned aerial vehicle infrared small target detection method under ground background | |
Tran Quang et al. | A hybrid deep convolutional neural network approach for predicting the traffic congestion index | |
CN110471768A (en) | A kind of load predicting method based on fastPCA-ARIMA | |
CN114137526A (en) | Label-based vehicle-mounted millimeter wave radar multi-target detection method and system | |
CN109447182A (en) | Driving behavior classification method and device based on HMM algorithm | |
CN111259604A (en) | High orbit satellite light pressure model identification method and system based on machine learning | |
CN115631628B (en) | Lane variable speed limit control method, device, computer equipment and storage medium | |
WO2021061951A1 (en) | Distance-based learning confidence model |
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 |