CN108334998B - Multi-target cooperative tracking method for multi-ground unmanned vehicle - Google Patents

Multi-target cooperative tracking method for multi-ground unmanned vehicle Download PDF

Info

Publication number
CN108334998B
CN108334998B CN201810375883.2A CN201810375883A CN108334998B CN 108334998 B CN108334998 B CN 108334998B CN 201810375883 A CN201810375883 A CN 201810375883A CN 108334998 B CN108334998 B CN 108334998B
Authority
CN
China
Prior art keywords
target
probability vector
ugv
matrix
tracking
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
Application number
CN201810375883.2A
Other languages
Chinese (zh)
Other versions
CN108334998A (en
Inventor
史彦军
韩俏梅
林娜
王柯飞
张文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dalian University of Technology
Original Assignee
Dalian University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dalian University of Technology filed Critical Dalian University of Technology
Priority to CN201810375883.2A priority Critical patent/CN108334998B/en
Publication of CN108334998A publication Critical patent/CN108334998A/en
Application granted granted Critical
Publication of CN108334998B publication Critical patent/CN108334998B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G05D1/02—Control of position or course in two dimensions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations

Abstract

The invention belongs to the field of multi-target cooperative controlAnd particularly relates to a multi-target cooperative tracking method for a multi-ground unmanned vehicle. The first step is as follows: constructing a mathematical model; the second step is that: improving a calculation tracking model of the algorithm; 2.1 determining the population scale and the number of genes; 2.2 initializing a probability vector; 2.3 generating two individuals; 2.4 two individuals compete; 2.5 updating the probability vector mode; 2.6 if the probability vector converges, ending; if the probability vector PtWithout convergence go to step 2.3. According to the invention, the ground unmanned vehicles are distributed to each tracking task according to the operational information, so that the total operational effect is optimal, and the problem is solved by using an improved compact genetic algorithm, thereby increasing the optimization capability of the algorithm.

Description

Multi-target cooperative tracking method for multi-ground unmanned vehicle
Technical Field
The invention belongs to the field of multi-target cooperative control, and particularly relates to a multi-target cooperative tracking method for a multi-ground unmanned vehicle.
Background
An Unmanned Ground Vehicle (UGV) is a Ground mobile platform that can be driven or operated remotely, used one or more times, and can carry a certain amount of load. Because the ground unmanned vehicle has the characteristics of automatic control and high intelligence, the ground unmanned vehicle can often reach areas which are difficult to reach by driving people or are very dangerous to human beings, and can complete the work which is difficult to be directly completed by the human beings.
The ground unmanned vehicle plays an important role in many tactical operation fields such as unexplosive explosive treatment, early warning reconnaissance, safety patrol, battlefield rescue, simple explosive device detection, mine detection and sweeping, urban area auxiliary operation, logistics guarantee and the like, so that manpower is greatly saved, and casualties are reduced. In future ground battles, the ground unmanned vehicle becomes an important component of an information equipment system, an important means for reducing casualties and a powerful guarantee for improving the accurate shooting capability of tactics, and particularly in the aspect of tactics early warning reconnaissance, the ground unmanned vehicle is flexible and mobile, can go deep into dangerous regions and reconnaissance blind areas to perform reconnaissance, and gradually becomes important equipment for acquiring and releasing tactics information of a ground battlefield. Although the aerospace early warning reconnaissance can provide support for the military to make a combat plan at a strategic level, the aerospace early warning reconnaissance cannot meet the tactical requirements of ground combat, and the ground unmanned vehicle can provide more detailed battlefield information for ground combat troops at a tactical level, so that the aerospace early warning reconnaissance becomes an important means for improving the situation awareness capability of the battlefield. The complexity of the modern war, namely the confrontation of the enemy and the my party requires that the command center can quickly and reasonably assign unmanned ground vehicles to cooperatively track a plurality of targets according to the battlefield environment, and the advantages of cooperative tracking are brought into play to the maximum extent.
The multi-target cooperative tracking problem of the multi-ground unmanned vehicles has the characteristic of large scale, and in order to reduce motion energy consumption as much as possible and improve the performance of a multi-target tracking system, the multi-ground unmanned vehicles need to be reasonably assigned so that the multi-ground unmanned vehicles can cooperate with one another and cooperatively track each target. For this purpose, a mathematical model is constructed, the problem is converted into a constrained combinatorial optimization problem, and then an optimization algorithm is adopted to solve the assignment problem. The more ground unmanned vehicles assigned to a tracked target, the more reliable the data about the target available to the vehicle, and thus the better the tracking performance for the tracked target, in the case of multiple tracked targets, the need for the command center to reasonably assign the ground unmanned vehicles to track the target.
The task allocation is regarded as a generalized assignment problem, namely the number m of the ground unmanned vehicles and the number n of the targets, the command center assigns tracking tasks to the multi-ground unmanned vehicles according to a certain assignment principle and constraint conditions, and assigns a plurality of ground unmanned vehicles to track a plurality of targets, so that the total combat effect of the multi-ground unmanned vehicles is optimal.
Disclosure of Invention
The technical problem to be solved by the invention is that a tracking task is assigned to a plurality of ground unmanned vehicles by a command center according to a certain constraint condition and an assignment principle, so that the total combat effect is optimal, an improved compact genetic algorithm is used for solving the problem, and the optimization capability of the algorithm is improved.
The technical scheme of the invention is as follows:
a multi-target cooperative tracking method for a multi-ground unmanned vehicle comprises the following steps:
the first step is as follows: construction of mathematical models
The command control center assigns the m UGVs to cooperatively track each target, each UGV is required to be responsible for one tracking task, each tracking task can be completed by a plurality of UGVs in a cooperative manner, and each UGV is guaranteed to uniformly track each target.
Let the distance between the ith UGV and the jth target be dijWherein i is 1,2, …, m; j is 1,2, …, n;
target assignment matrix Am×nThe element is aijWherein i is 1,2, …, m; j is 1,2, …, n; a isijA value of 0 or 1, aij1 denotes assigning the ith UGV to track the jth target, otherwise aij＝0；
The sum of the distances of the minimized UGV from the target is minJ:
Figure BDA0001639751930000031
target assignment matrix Am×nThe columns in (1) sum:
Figure BDA0001639751930000032
target assignment matrix Am×nRow summation in (2):
Figure BDA0001639751930000033
target assignment matrix Am×nThe overall summation in (1):
Figure BDA0001639751930000034
formula (1) represents that the optimal assignment scheme is solved to minimize the distance sum, namely, the total benefit is optimal;
equation (2) indicates that each UGV can track only one target;
formula (3) shows that the command center uniformly assigns UGVs to track each target, each platform tracks at least one target, wherein [ ] shows rounding operation;
formula (4) is represented by dijComposed matrix Dm×n＝(dij)m×nFor multiple UGVs, the multi-target tracking assigns a target distance matrix of the problem.
The second step is that: computing tracking models using improved algorithms
2.1 determining population size n and Gene number m
Corresponding to the mathematical model in the first step, the population scale n is the number of tracking targets, and the number m of genes is the number of UGVs.
2.2 initializing probability vectors
A population is represented by a probability vector, the value of each element of the probability vector representing the probability that the chromosome of the population takes a "1" or a "0" at each locus, the value of each element of the initial probability vector being 0.5, i.e. the value of each element of the initial probability vector is 0.5
Figure BDA0001639751930000041
2.3 Generation of two individuals
From the object distance matrix Dm×n＝(dij)m×nGenerating corresponding initial assignment matrix
Figure BDA0001639751930000042
The element in (A) isijWherein i is 1,2, …, m; j is 1,2, …, n.
At object distance matrix Dm×n＝(dij)m×nIn, if there is dijSatisfy dpqThen a ispq1, otherwise aij0; wherein d ispqIs a target distance matrix Dm×nThe minimum value of each row, p is more than or equal to 1 and less than or equal to m; q is more than or equal to 1 and less than or equal to n.
Provision for
Figure BDA0001639751930000043
The rows of the matrix are in domain relation with each other,interleaving different values of the exchange Domain positions to obtain another individual A'm×n。
2.4 two individuals compete
In the two individuals generated
Figure BDA0001639751930000044
And A'm×nIn the method, a good individual is found out from the two individuals through competition, winner (i) is a winning individual, loser (i) is a failed individual, and the competition mode is based on
Figure BDA0001639751930000045
Calculating;
updating the initial probability vector according to the condition that the value of each gene position in the winner (i) is ' 1 ' or ' 0
Figure BDA0001639751930000046
Each bit value of (a).
2.5 updating probability vector mode
Entropy and joint entropy were introduced to measure the diversity of each gene and the diversity of each generation.
Individuals in the population with the generation t
Figure BDA0001639751930000047
Consists of m genes, and is:
Figure BDA0001639751930000048
Figure BDA0001639751930000049
is 0 or 1(5)
Let the entropy of the kth (k ═ 1, 2.., m) gene of the t-th generation population be
Figure BDA00016397519300000414
Figure BDA00016397519300000410
When in use
Figure BDA00016397519300000411
When the temperature of the water is higher than the set temperature,
Figure BDA00016397519300000412
taking the maximum value
Figure BDA00016397519300000413
Let the joint entropy of the t generation population be Ht:
Figure BDA0001639751930000051
When in use
Figure BDA0001639751930000052
When H is presenttGet the maximum value
Figure BDA0001639751930000053
The probability vector PtEach item in (1) update
Figure BDA0001639751930000057
Comprises the following steps:
Figure BDA0001639751930000054
Figure BDA0001639751930000056
the probability vector PtComprises the following steps:
Figure BDA0001639751930000055
2.6 judgment
If the probability vector PtConverging, and ending; if it isProbability vector PtWithout convergence go to step 2.3.
The invention has the beneficial effects that: and distributing the ground unmanned vehicles to each tracking task according to the operational information to enable the total operational effect to be optimal, solving the problem by using an improved compact genetic algorithm and increasing the optimization capability of the algorithm.
Drawings
FIG. 1 is a flow chart of an improved compact genetic algorithm
FIG. 2 is a multiple UGV multiple target distribution plot.
Detailed Description
The following detailed description of the embodiments of the invention refers to the accompanying drawings.
A multi-target cooperative tracking method for a multi-ground unmanned vehicle comprises the following steps:
the first step is as follows: construction of mathematical models
The command control center assigns the m UGVs to cooperatively track each target, each UGV is required to be responsible for one tracking task, each tracking task can be completed by a plurality of UGVs in a cooperative manner, and each UGV is guaranteed to uniformly track each target.
Let the distance between the ith UGV and the jth target be dijWherein i is 1,2, …, m; j is 1,2, …, n;
target assignment matrix Am×nThe element is aijWherein i is 1,2, …, m; j is 1,2, …, n; a isijA value of 0 or 1, aij1 denotes assigning the ith UGV to track the jth target, otherwise aij＝0；
The sum of the distances of the minimized UGV from the target is minJ:
Figure BDA0001639751930000061
target assignment matrix Am×nThe columns in (1) sum:
Figure BDA0001639751930000062
target assignment matrix Am×nRow summation in (2):
Figure BDA0001639751930000063
target assignment matrix Am×nThe overall summation in (1):
Figure BDA0001639751930000064
formula (1) represents that the optimal assignment scheme is solved to minimize the distance sum, namely, the total benefit is optimal;
equation (2) indicates that each UGV can track only one target;
formula (3) shows that the command center uniformly assigns UGVs to track each target, each platform tracks at least one target, wherein [ ] shows rounding operation;
formula (4) is represented by dijComposed matrix Dm×n＝(dij)m×nFor multiple UGVs, the multi-target tracking assigns a target distance matrix of the problem.
The second step is that: improved algorithm computation tracking model
2.1 determining population size n and Gene number m
Corresponding to the mathematical model in the first step, the population scale n is the number of tracking targets, and the number m of genes is the number of UGVs.
2.2 initializing probability vectors
A population is represented by a probability vector, the value of each element of the probability vector representing the probability that the chromosome of the population takes a "1" or a "0" at each locus, the value of each element of the initial probability vector being 0.5, i.e. the value of each element of the initial probability vector is 0.5
Figure BDA0001639751930000071
2.3 Generation of two individuals
From the object distance matrix Dm×n＝(dij)m×nGenerating corresponding initial assignment matrix
Figure BDA0001639751930000072
The element in (A) isijWherein i is 1,2, …, m; j is 1,2, …, n.
At object distance matrix Dm×n＝(dij)m×nIn, if there is dijSatisfy dpqThen a ispq1, otherwise aij0; wherein d ispqIs a target distance matrix Dm×nThe minimum value of each row, p is more than or equal to 1 and less than or equal to m; q is more than or equal to 1 and less than or equal to n.
Provision for
Figure BDA0001639751930000073
The rows of the matrix are mutually in a domain relationship, and different values of the positions of the switching domains are interleaved to obtain another individual A'm×n。
2.4 two individuals compete
In the two individuals generated
Figure BDA0001639751930000074
And A'm×nIn the method, a good individual is found out from the two individuals through competition, winner (i) is a winning individual, loser (i) is a failed individual, and the competition mode is based on
Figure BDA0001639751930000075
Calculating;
updating the initial probability vector according to the condition that the value of each gene position in the winner (i) is ' 1 ' or ' 0
Figure BDA0001639751930000076
Each bit value of (a).
2.5 updating probability vector mode
Entropy and joint entropy were introduced to measure the diversity of each gene and the diversity of each generation.
Individuals in the population with the generation t
Figure BDA0001639751930000081
Consists of m genes, and is:
Figure BDA0001639751930000082
Figure BDA0001639751930000083
is 0 or 1(5)
Let the entropy of the kth (k ═ 1, 2.., m) gene of the t-th generation population be
Figure BDA00016397519300000813
Figure BDA0001639751930000084
When in use
Figure BDA0001639751930000085
When the temperature of the water is higher than the set temperature,
Figure BDA0001639751930000086
taking the maximum value
Figure BDA0001639751930000087
Let the joint entropy of the t generation population be Ht:
Figure BDA0001639751930000088
When in use
Figure BDA0001639751930000089
When H is presenttGet the maximum value
Figure BDA00016397519300000810
The probability vector PtEach item in (1) update
Figure BDA00016397519300000815
Comprises the following steps:
Figure BDA00016397519300000811
Figure BDA00016397519300000814
the probability vector PtComprises the following steps:
Figure BDA00016397519300000812
2.6 judgment
If the probability vector PtConverging, and ending; if the probability vector PtWithout convergence go to step 2.3.
The feasibility of the multi-target cooperative tracking method is proved by simulation experiments, the model is assumed to have 3 targets in a monitoring area of [0, 5000] mx [0, 5000] m, 9 available UGVs are arranged in the monitoring area, and a distribution diagram is shown in FIG. 2.
Object distance matrix Dm×n：
Figure BDA0001639751930000091
The obtained optimal target assignment matrix A9X3Comprises the following steps:
Figure BDA0001639751930000092
according to the improved compact genetic algorithm, the population size is 10, the maximum iteration number is 50, the algorithm is operated 100 times, the optimal solution can be obtained, and the sum J of the distances between UGV and the target is 6968.4.

Claims (2)

1. A multi-target cooperative tracking method for a multi-ground unmanned vehicle is characterized by comprising the following steps:
the first step is as follows: construction of mathematical models
The method comprises the steps that n targets are arranged, m UGVs are arranged, a command control center assigns the m UGVs to cooperatively track each target, each UGV is required to be responsible for one tracking task, each tracking task can be cooperatively completed by a plurality of UGVs, and each UGV is guaranteed to uniformly track each target;
let the distance between the ith UGV and the jth target be dijWherein i is 1,2, …, m; j is 1,2, …, n;
target assignment matrix Am×nThe element is aijWherein i is 1,2, …, m; j is 1,2, …, n; a isijA value of 0 or 1, aij1 denotes assigning the ith UGV to track the jth target, otherwise aij＝0；
The sum of the distances of the minimized UGV from the target is minJ:
Figure FDA0001639751920000011
target assignment matrix Am×nThe columns in (1) sum:
Figure FDA0001639751920000012
target assignment matrix Am×nRow summation in (2):
Figure FDA0001639751920000013
target assignment matrix Am×nThe overall summation in (1):
Figure FDA0001639751920000014
formula (1) represents that the optimal assignment scheme is solved to minimize the distance sum, namely, the total benefit is optimal;
equation (2) indicates that each UGV can track only one target;
formula (3) shows that the command center uniformly assigns UGVs to track each target, each platform tracks at least one target, wherein [ ] shows rounding operation;
formula (4) is represented by dijComposed matrix Dm×n＝(dij)m×nAssigning a target distance matrix of the problem for multi-UGV, multi-target tracking;
the second step is that: computing tracking models using improved algorithms
2.1 determining population size n and Gene number m
Corresponding to the mathematical model in the first step, wherein the population scale n is the number of tracking targets, and the gene number m is the UGV number;
2.2 initializing probability vectors
A population is represented by a probability vector, the value of each element of the probability vector representing the probability that the chromosome of the population takes a "1" or a "0" at each locus, the value of each element of the initial probability vector being 0.5, i.e. the value of each element of the initial probability vector is 0.5
Figure FDA0001639751920000021
2.3 Generation of two individuals
From the object distance matrix Dm×n＝(dij)m×nGenerating corresponding initial assignment matrix
Figure FDA0001639751920000022
Figure FDA0001639751920000023
The element in (A) isijWherein i is 1,2, …, m; j is 1,2, …, n;
at object distance matrix Dm×n＝(dij)m×nIn, if there is dijSatisfy dpqThen a ispq1, otherwise aij0; wherein d ispqIs a target distance matrix Dm×nThe minimum value of each row, p is more than or equal to 1 and less than or equal to m; q is more than or equal to 1 and less than or equal to n;
provision for
Figure FDA0001639751920000024
The rows of the matrix are mutually in a domain relationship, and different values of the positions of the switching domains are interleaved to obtain another individual A'm×n；
2.4 two individuals compete
In the two individuals generated
Figure FDA0001639751920000025
And A'm×nIn the method, a good individual is found out from the two individuals through competition, winner (i) is a winning individual, loser (i) is a failed individual, and the competition mode is based on
Figure FDA0001639751920000026
Calculating;
updating the initial probability vector according to the condition that the value of each gene position in the winner (i) is ' 1 ' or ' 0
Figure FDA0001639751920000031
Each bit value of (a);
2.5 updating probability vector mode
Introducing entropy and joint entropy to measure the diversity of each gene and the diversity of each generation;
2.6 judgment
If the probability vector PtConverging, and ending; if the probability vector PtWithout convergence go to step 2.3.
2. The multi-target cooperative tracking method for the multi-ground unmanned vehicle as claimed in claim 1, characterized by comprising the following steps: the 2.5 updating probability vector mode introduces entropy and joint entropy to measure the diversity of each gene and the diversity of each generation, and comprises the following specific steps:
individuals in the population with the generation t
Figure FDA00016397519200000315
Consists of m genes, wherein the genes consist of,comprises the following steps:
Figure FDA0001639751920000032
Figure FDA0001639751920000033
is 0 or 1(5)
Let the entropy of the kth (k ═ 1, 2.., m) gene of the t-th generation population be
Figure FDA0001639751920000034
Figure FDA0001639751920000035
When in use
Figure FDA0001639751920000036
When the temperature of the water is higher than the set temperature,
Figure FDA0001639751920000037
taking the maximum value
Figure FDA0001639751920000038
Let the joint entropy of the t generation population be Ht:
Figure FDA0001639751920000039
When in use
Figure FDA00016397519200000310
When H is presenttGet the maximum value
Figure FDA00016397519200000311
The probability vector PtEach item in (1) update
Figure FDA00016397519200000312
Comprises the following steps:
Figure FDA00016397519200000313
Figure FDA00016397519200000314
the probability vector PtComprises the following steps:
Figure FDA0001639751920000041
obtain a probability vector Pt。
CN201810375883.2A 2018-04-16 2018-04-16 Multi-target cooperative tracking method for multi-ground unmanned vehicle Active CN108334998B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810375883.2A CN108334998B (en) 2018-04-16 2018-04-16 Multi-target cooperative tracking method for multi-ground unmanned vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810375883.2A CN108334998B (en) 2018-04-16 2018-04-16 Multi-target cooperative tracking method for multi-ground unmanned vehicle

Publications (2)

Publication Number Publication Date
CN108334998A CN108334998A (en) 2018-07-27
CN108334998B true CN108334998B (en) 2021-08-20

Family

ID=62934445

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810375883.2A Active CN108334998B (en) 2018-04-16 2018-04-16 Multi-target cooperative tracking method for multi-ground unmanned vehicle

Country Status (1)

Country Link
CN (1) CN108334998B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111103887B (en) * 2020-01-14 2021-11-12 大连理工大学 Multi-sensor-based multi-mobile-robot scheduling system design method
CN111220998B (en) * 2020-02-26 2022-10-28 江苏大学 Multi-target cooperative tracking method based on vehicle-to-vehicle communication

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070220586A1 (en) * 2006-03-01 2007-09-20 Norman Salazar Computing resource assignment method and apparatus using genetic algorithms
CN102929285A (en) * 2012-11-16 2013-02-13 中国民用航空飞行学院 Multi-target distribution and flight path planning method for multiple rescue helicopters
CN106022601B (en) * 2016-05-18 2020-08-25 聊城大学 Multi-target resource allocation method
CN107292911B (en) * 2017-05-23 2021-03-30 南京邮电大学 Multi-target tracking method based on multi-model fusion and data association

Also Published As

Publication number Publication date
CN108334998A (en) 2018-07-27

Similar Documents

Publication Publication Date Title
CN108549402B (en) Unmanned aerial vehicle group task allocation method based on quantum crow group search mechanism
Shin et al. An autonomous aerial combat framework for two-on-two engagements based on basic fighter maneuvers
CN111240353B (en) Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree
CN109636699A (en) A kind of unsupervised intellectualized battle deduction system based on deeply study
CN107832885B (en) Ship formation fire power distribution method based on self-adaptive migration strategy BBO algorithm
CN108334998B (en) Multi-target cooperative tracking method for multi-ground unmanned vehicle
CN108985549A (en) Unmanned plane method for allocating tasks based on quantum dove group's mechanism
Duan et al. Optimal formation reconfiguration control of multiple UCAVs using improved particle swarm optimization
CN109541960B (en) System and method for aircraft digital battlefield confrontation
Duan et al. Multiple UCAVs cooperative air combat simulation platform based on PSO, ACO, and game theory
CN111160511A (en) Group intelligent method for consensus active learning
Zeng et al. Multi-objective cooperative salvo attack against group target
CN111061995B (en) Combat resource allocation method, first equipment and second equipment
CN113435598A (en) Knowledge-driven intelligent strategy deduction decision method
CN116700079A (en) Unmanned aerial vehicle countermeasure occupation maneuver control method based on AC-NFSP
CN113110517A (en) Multi-robot collaborative search method based on biological elicitation in unknown environment
CN112926825A (en) Multi-unmanned aerial vehicle task allocation method based on multi-target quantum shrimp swarm mechanism
CN116360503B (en) Unmanned plane game countermeasure strategy generation method and system and electronic equipment
CN108804741B (en) D-S evidence theory cannonball combined fire power distribution method under maximum efficiency condition
CN115903885B (en) Unmanned aerial vehicle flight control method of swarm Agent model based on task traction
CN116088586A (en) Method for planning on-line tasks in unmanned aerial vehicle combat process
Schubert et al. Towards combining a neocortex model with entorhinal grid cells for mobile robot localization
CN115617071A (en) Multi-unmanned-aerial-vehicle task planning method of quantum ounce mechanism
Han et al. Cooperative Multi-task Assignment of Unmanned Autonomous Helicopters Based on Hybrid Enhanced Learning ABC Algorithm
CN115457809A (en) Multi-agent reinforcement learning-based flight path planning method under opposite support scene

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