CN116339378A - Unmanned aerial vehicle collaborative air combat maneuver decision-making method - Google Patents
Unmanned aerial vehicle collaborative air combat maneuver decision-making method Download PDFInfo
- Publication number
- CN116339378A CN116339378A CN202310244436.4A CN202310244436A CN116339378A CN 116339378 A CN116339378 A CN 116339378A CN 202310244436 A CN202310244436 A CN 202310244436A CN 116339378 A CN116339378 A CN 116339378A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- red
- algorithm
- blue
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 82
- 230000008569 process Effects 0.000 claims abstract description 28
- 238000004088 simulation Methods 0.000 claims abstract description 12
- 238000012795 verification Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 43
- 239000003016 pheromone Substances 0.000 claims description 21
- 230000008901 benefit Effects 0.000 claims description 20
- 239000003795 chemical substances by application Substances 0.000 claims description 19
- 230000005855 radiation Effects 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000004083 survival effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 241000257303 Hymenoptera Species 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 230000002829 reductive effect Effects 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 4
- 238000011160 research Methods 0.000 description 11
- 230000015572 biosynthetic process Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- UBVSIAHUTXHQTD-UHFFFAOYSA-N 2-n-(4-bromophenyl)-1,3,5-triazine-2,4-diamine Chemical compound NC1=NC=NC(NC=2C=CC(Br)=CC=2)=N1 UBVSIAHUTXHQTD-UHFFFAOYSA-N 0.000 description 1
- 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
- SGHZXLIDFTYFHQ-UHFFFAOYSA-L Brilliant Blue Chemical compound [Na+].[Na+].C=1C=C(C(=C2C=CC(C=C2)=[N+](CC)CC=2C=C(C=CC=2)S([O-])(=O)=O)C=2C(=CC=CC=2)S([O-])(=O)=O)C=CC=1N(CC)CC1=CC=CC(S([O-])(=O)=O)=C1 SGHZXLIDFTYFHQ-UHFFFAOYSA-L 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- ONTQJDKFANPPKK-UHFFFAOYSA-L chembl3185981 Chemical compound [Na+].[Na+].CC1=CC(C)=C(S([O-])(=O)=O)C=C1N=NC1=CC(S([O-])(=O)=O)=C(C=CC=C2)C2=C1O ONTQJDKFANPPKK-UHFFFAOYSA-L 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000012732 erythrosine Nutrition 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention belongs to the field of unmanned combat systems, and particularly relates to a maneuvering decision-making method for a collaborative air combat by a manned-unmanned aerial vehicle, which comprises the following steps: step 1, establishing a manned-unmanned plane collaborative air combat modeling; step 2, establishing a maneuver decision algorithm; step 3, establishing a cooperative strategy of the unmanned aerial vehicle; and step 4, performing simulation verification on the simulation result. The dynamic grid is used for modeling the air combat process, so that planning space can be effectively controlled, and the problem that planning speed is reduced due to overlarge air combat field is avoided. Aiming at the defects that the ACO algorithm is slow in planning speed and easy to be trapped into local optimum, an ACO-Astar hybrid maneuver decision algorithm is provided, the algorithm can effectively accelerate the planning speed and improve the quality of solutions. The constructed manned/unmanned cooperative air combat platform can support multi-machine air combat simulation. The cooperative tactics of auxiliary decision making and electronic interference support are provided by the man-machine, so that the winning rate of the unmanned aerial vehicle air combat can be effectively improved.
Description
Technical Field
The invention belongs to the field of unmanned combat systems, and particularly relates to a maneuvering decision-making method for a collaborative air combat by a manned unmanned aerial vehicle.
Background
The current unmanned combat system is developed rapidly, the pedigree covers a plurality of fields such as land, sea, air, network electricity and the like, and the unmanned aerial vehicle is used for forming a cooperative combat system with mutual cooperation, complementary advantages and multiplied efficiency on an air combat field, so that the unmanned aerial vehicle becomes a hot spot for world competitive research. The man-unmanned plane cooperative combat is one of the latest combat models, wherein a typical in-study project is a 'loyalty plane' project, and the prototype of the plane is currently used for carrying out test flight verification. However, the current unmanned aerial vehicle has insufficient autonomous decision-making capability, and the unmanned aerial vehicle still needs to rely on the decision-making capability of people in the process of carrying out collaborative combat with an organic machine, especially in the field of air combat, and the decision-making function of people plays a key role in the effectiveness of combat marshalling. However, when a person controls the unmanned aerial vehicle, the person also needs to control the unmanned aerial vehicle, the workload is increased, the person can take the threat around the unmanned aerial vehicle into consideration, and once the unmanned aerial vehicle is knocked down by the opponent, the whole combat marshalling efficiency is seriously damaged. Therefore, an air combat decision-making technical architecture needs to be studied, the workload of people is reasonably distributed, and the combat effectiveness of the collaborative combat grouping of the people and the unmanned aerial vehicle is most likely to be exerted.
The current research on unmanned aerial vehicle air combat mainly considers a complete autonomous decision maneuvering method of the unmanned aerial vehicle, but the distance from actual combat application is larger, the research on cooperative combat between the unmanned aerial vehicle and the unmanned aerial vehicle is relatively lacking, the research on air combat maneuvering decision under the finite supervision decision of the unmanned aerial vehicle is relatively less, the research on cooperative technical architecture between the unmanned aerial vehicle and the unmanned aerial vehicle is not clear, and a larger technical gap exists for realizing the cooperative combat between the unmanned aerial vehicle and the unmanned aerial vehicle.
Disclosure of Invention
The embodiment of the invention aims to provide a maneuvering decision-making method for the unmanned aerial vehicle collaborative air combat, which aims to solve the problems that the current research on the unmanned aerial vehicle air combat mainly considers a completely autonomous decision-making maneuvering method for the unmanned aerial vehicle, but the distance between the unmanned aerial vehicle and the actual combat application is larger, the research on the collaborative combat between the unmanned aerial vehicle is relatively lacking, the maneuvering decision-making research on the air combat under the finite supervision decision of the unmanned aerial vehicle is relatively less, the research on the collaborative technical architecture between the unmanned aerial vehicle and the unmanned aerial vehicle is not clear, and a relatively large technical gap exists for realizing the collaborative combat between the unmanned aerial vehicle and the unmanned aerial vehicle.
The embodiment of the invention is realized in such a way that the manned-unmanned aerial vehicle collaborative air combat maneuver decision-making method comprises the following steps:
step 3, establishing a man-unmanned aerial vehicle cooperative strategy: establishing an unmanned aerial vehicle cooperative algorithm, and prescribing a man-machine maneuvering criterion and a winning or losing judgment criterion;
and step 4, performing simulation verification on the simulation result.
As a further scheme of the invention, the design of the unmanned aerial vehicle-unmanned aerial vehicle collaborative air combat tactic in the step 1 is carried out, wherein the unmanned aerial vehicle is always kept out of the effective attack range of the enemy plane, and the electronic interference equipment is assembled on the unmanned aerial vehicle.
As a further scheme of the present invention, the judgment is performed according to the situation in the step 1, and a dynamic grid environment model is established according to the judgment result, wherein the judgment of the situation is based on the speed, the distance, the relative angle and the height, and the calculation formula of the distance and the relative angle is as follows:
wherein: (x) r ,y r ) And (x) b ,y b ) The ground coordinate positions of the red and blue unmanned aerial vehicle are respectively; θ rb V is the opposite angle of the red square and the blue square r Is the heading vector of the red party; v rb Vector for red unmanned aerial vehicle to point to blue unmanned aerial vehicle;
according to different angles of the unmanned aerial vehicles, the situation is divided into an advantage situation and a threat situation, wherein the advantage situation is the degree of damage to enemy, and the calculation method comprises the following steps:
wherein: c (C) rij Is the advantage situation of the red square ith unmanned aerial vehicle on Lan Fangdi j unmanned aerial vehicles, d ij The distance between the red square ith unmanned plane and Lan Fangdi j unmanned planes is the distance;
Λ rij according to the number of the relative angular changes of the red and blue square, the calculation method comprises the following steps:
g is a number according to the distance change of the red and blue unmanned aerial vehicle, and the calculation method comprises the following steps:
wherein: θ rf Is one half of the radiation angle of the red square fire control radar, theta br For the opposite angle of the blue square, θ bf Is one half of the radiation angle of the blue-square fire control radar, theta bt Is one half of the rear corner of the blue square tail,
distance of action for fire control radar of red ith unmanned aerial vehicle；
The degree of possible damage to the red square formed by the blue square is judged by the distance and the angle, and the calculation method is expressed as follows:
wherein: t (T) rij The threat situation formed by the blue jth unmanned aerial vehicle to the red ith unmanned aerial vehicle is provided;
the Urij is a number according to the relative angular change of the red and blue square, and the calculation method comprises the following steps:
based on the calculated advantages and threats, an advantage and threat judgment matrix can be formed, which can be expressed as:
in the formulas (7) and (8), m is the number of red unmanned aerial vehicles, and n is the number of blue unmanned aerial vehicles;
if the red unmanned aerial vehicle i is knocked down in the air combat process, the ith row of the row in which the formula (7) is positioned becomes 0, and the ith column of the formula (8) becomes 0;
adding equation (7) and equation (8) can yield a comprehensive judgment matrix, which can be expressed as:
M r ＝C r +T r (9)；
modeling is carried out according to a dynamic grid environment, a dynamic self-adaptive grid planning space is designed, and if the clockwise is negative, a coordinate conversion formula is as follows:
in (x) g ,y g ) Is any grid coordinate; (x ', y') is the corresponding geodetic coordinates; θ g The angle formed by the grid coordinates and the geodetic coordinates is phi, and the unmanned aerial vehicle is in the grid coordinatesThe angle formed by the position vector of (c) and the X axis specifies a positive counter-clockwise rotation.
As a further aspect of the present invention, the establishing a maneuver decision algorithm described in step 2: the method comprises the steps of establishing a maneuvering control algorithm, wherein the maneuvering control algorithm is only designed for a control algorithm in the horizontal direction so as to meet the control requirement of horizontal maneuvering in the unmanned plane beyond-the-horizon air combat, and the maneuvering control algorithm can be expressed as follows:
in (x) i ,y i ) Is the position coordinate of the unmanned aerial vehicle i, v i For the speed of the unmanned aerial vehicle i,
is the heading of unmanned plane i, a i Acceleration, omega of unmanned plane i i Is the turning angular speed of the unmanned aerial vehicle i;
in addition, the speed, acceleration and turning angular speed of the unmanned plane are limited by performance, so that the following conditions should be satisfied:
where min and max each represent the maximum and minimum values of the corresponding variables.
As a further aspect of the present invention, the establishing an ACO-based path planning algorithm in step 2 includes:
establishing a basic formula of probability search of an intelligent agent:
in the method, in the process of the invention,
for the probability of agent k transitioning from grid point i to j at time t, τ j (t) is the pheromone concentration, eta of the grid point j j Heuristic factor, coefficient, for node jLambda can control the intensity of action of heuristic factors;
in order to accelerate the searching speed of the agent, heuristic factors are added into the ACO, and the distance visibility is utilized to guide the agent to move towards the target point, which can be expressed as:
wherein d j The Euclidean distance from the node j to the target point;
after all the agents complete one-time path optimizing, one-time pheromone updating is carried out on the path node, and the calculation formula is as follows:
wherein ρ is the volatilization rate of the node pheromone,
for the current optimal path node pheromone concentration variation, < >>
The pheromone left for the node passed by the kth agent in the path ranking in the iteration;
the pheromone added by ants with different ranks has different concentrations, and the calculation method comprises the following steps:
wherein F is * And F is a constant, L * And L k The lengths of the optimal path and the suboptimal path with rank k, respectively.
As a further scheme of the invention, the unmanned aerial vehicle cooperative algorithm is established in the step 3, and a man-machine maneuvering criterion and a winning or losing judgment criterion are specified;
each unmanned aerial vehicle selects the maximum or minimum value of the corresponding row according to the allocation strategy adopted by the man-machine, and the calculation method for selecting the target according to the dominance criterion is as follows:
in the method, in the process of the invention,
blue Fang Moren machine serial numbers selected for the ith unmanned aerial vehicle of the red square are the unmanned aerial vehicle serial numbers with the greatest advantage;
the calculation method for selecting the target according to the threat criterion comprises the following steps:
at this time
The serial number of the unmanned aerial vehicle with the greatest threat is obtained;
the method for calculating the flight target point of the man-machine based on the position points of the red and blue parties comprises the following steps:
wherein (xh, yh) is the target point position of the organic machine, (X) UAV ,Y UAV ) Mean clustering center for survival of red and blue squares, L e Is constant and is related to the electronic interference distance of the organic machine,
is vector v c The angle formed by the unit base coordinate vector of the geodetic coordinate X axis is positive anticlockwise;
v c the calculation method of (1) is as follows:
v c ＝(X R ,Y R )-(X UAV ,Y UAV )(21)；
wherein (X) R ,Y R ) The mean value clustering center of the red-square survival unmanned aerial vehicle;
the mean value clustering center calculating method comprises the following steps:
wherein (xk, yk) is the earth coordinates, sigma, of the kth unmanned aerial vehicle k Taking the value as 1 when the unmanned aerial vehicle k survives as a constant, otherwise taking the value as 0, and taking n as the total number of the unmanned aerial vehicles in the red and blue directions;
when the distance between the unmanned aerial vehicle and the target point is greater than LH, maneuvering to the target point based on an ACO-A star algorithm, and when the distance is less than or equal to LH, performing spiral flight to implement electronic interference.
As a further scheme of the present invention, the winning or losing judgment criterion in step 3, when the unmanned aerial vehicle uses the fire radar to irradiate the target machine, there is a certain probability that the enemy machine is locked and knocked down, and the hit probability calculation azimuth is assumed as follows:
in the method, in the process of the invention,
the hit probability of the attack of the red unmanned aerial vehicle i on the unmanned aerial vehicle j is determined; b and w are constants, delta r Diagonal and distance variations according to red Lan Fangxiang;
δ r the calculation method of (1) is as follows:
in [ theta ] emin ,θ emax ]For the radiation angle range of the man-machine electronic interference pod d e For the electronic interference distance d hj Is the distance theta between the unmanned aerial vehicle and the blue-side unmanned aerial vehicle j hbj The relative angle between the heading of the unmanned aerial vehicle and the blue-square unmanned aerial vehicle j;
when all unmanned aerial vehicles of a certain party are knocked down, the task is considered to fail;
because the single-time winner and the minus of the rounds cannot judge the performance of the algorithm, the quality of the maneuver decision algorithm is judged according to the multiple-time winner and minus ratio, and the calculation method comprises the following steps:
wherein B is r The ratio that wins for the red party,
the number of rounds winning for the red party is R is the total number of rounds.
The method for making a maneuver in cooperation with an air combat by using a man-unmanned aerial vehicle provided by the embodiment of the invention comprises the following steps of
The beneficial effects are that:
(1) The dynamic grid is used for modeling the air combat process, so that planning space can be effectively controlled, and the problem that planning speed is reduced due to overlarge air combat field is avoided.
(2) Aiming at the defects that the ACO algorithm is slow in planning speed and easy to be trapped into local optimum, an ACO-Astar hybrid maneuver decision algorithm is provided, the algorithm can effectively accelerate the planning speed and improve the quality of solutions.
(3) The constructed manned/unmanned cooperative air combat platform can support multi-machine air combat simulation. The cooperative tactics of auxiliary decision making and electronic interference support are provided by the man-machine, so that the winning rate of the unmanned aerial vehicle air combat can be effectively improved.
Drawings
FIG. 1 is a schematic representation of a manned-unmanned cooperative air combat tactical strategy;
FIG. 2 is the unmanned aerial vehicle angular relationship FIG. 1;
FIG. 3 is an unmanned aerial vehicle angular relationship FIG. 2;
FIG. 4 is a dynamic grid environment diagram;
FIG. 5 is a hybrid algorithm planning flowchart;
FIG. 6 is a diagram of a stand-alone countermeasure process;
FIG. 7 is a time-consuming comparison of algorithm planning;
fig. 8 is a diagram of a red and blue unmanned aerial vehicle countermeasure process;
FIG. 9 is a graph of red Fang Sheng rate;
FIG. 10 is a diagram of a process of a manned-unmanned cooperative air combat;
fig. 11 is a graph of the defeat rate of the person-to-person synergy.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
As shown in fig. 1, in an embodiment of the present invention, it includes:
1 manned-unmanned plane cooperative air combat modeling
The unmanned aerial vehicle and the unmanned aerial vehicle have more cooperative air combat patterns, and more excellent combat performance can be exerted through mutual supplement of weapon platforms. At this time, unmanned aerial vehicle is as main preparation air combat strength and the development combat of enemy machine, and the high value target that has the man-machine as combat marshalling is located the battle position rear, provides the strength support for unmanned aerial vehicle formation.
1.1 design of unmanned aerial vehicle and unmanned aerial vehicle in coordination with air combat tactics
Because the cooperative combat patterns of the unmanned aerial vehicle and the unmanned aerial vehicle are rich and various, and the cooperative methods and decision bases under different scenes have differences, the invention designs the cooperative combat tactics of the unmanned aerial vehicle and the unmanned aerial vehicle aiming at the air combat scene.
The man-machine is a decision core of formation fight, and once the decision support of the man-machine is lost, the fight capacity of the formation is seriously damaged, so that the man-machine is always kept out of the effective attack range of the enemy machine. Meanwhile, the unmanned aerial vehicle has better load capacity, can load electronic interference equipment with strong performance, provides accompanying electronic interference when controlling the unmanned aerial vehicle behind the array position, and reduces the fight efficiency of the enemy aircraft. The electronic interference effect of the man-machine is mainly reflected in the aspect of reducing the radar performance of enemy. When the enemy aircraft is disturbed, the ability of the fire radar to detect my is significantly reduced, and thus the probability of being able to successfully implement target locking and hit is significantly reduced.
Unmanned aerial vehicles are the main attack force for making air combat, and fire control radars are used for irradiating enemy planes through active maneuvering turns. However, the unmanned aerial vehicles of both the enemy parties also carry electronic interference devices, and are assumed to be forward interference devices, if the unmanned aerial vehicles and the enemy machines implement mutual locking and interference, the hit probabilities of both parties are reduced, and the attack strategy is not optimal. Therefore, the maneuver strategy of the drone should actively implement radar irradiation and fire weapon ammunition from the side or rear of the enemy plane. Meanwhile, radar irradiation of an enemy plane should be effectively avoided, and the enemy radar irradiation is avoided while the enemy attack is completed. For convenience of expression, the following takes the my unmanned aerial vehicle as a red party, the enemy unmanned aerial vehicle as a blue party and the man-machine as a red party formation leader. The strategy of the cooperative air combat tactic of the unmanned aerial vehicle is shown in fig. 1:
1.2 situation judgment method
The judgment of the unmanned aerial vehicle on the situation is the basis of maneuver decision and the basis of different tactical strategies adopted by the unmanned aerial vehicle. In the existing research literature, judgment of situations is mainly based on factors such as speed, distance, angle and altitude. However, the influence analysis and weight distribution of the altitude potential energy are not clear at present, particularly in the process of over-the-horizon air combat, the influence of speed and altitude factors is weakened, and the most critical factors are distance and angle, so that the calculation of the situation is mainly based on the distance and the relative angle. The distance and relative angle are calculated as:
wherein: (x) r ,y r ) And (x) b ,y b ) The ground coordinate positions of the red and blue unmanned aerial vehicle are respectively; θ rb V is the opposite angle of the red square and the blue square r Is the heading vector of the red party; v rb Vector for red unmanned aerial vehicle to point to blue unmanned aerial vehicle;
according to different angles of the unmanned aerial vehicles, the situation is divided into an advantage situation and a threat situation, wherein the advantage situation is the degree of damage to enemy, and the calculation method comprises the following steps:
wherein: c (C) rij Is the advantage situation of the red square ith unmanned aerial vehicle on Lan Fangdi j unmanned aerial vehicles, d ij The distance between the red square ith unmanned plane and Lan Fangdi j unmanned planes is the distance; Λ type rij According to the number of the relative angular changes of the red and blue square, the calculation method comprises the following steps:
g is a number according to the distance change of the red and blue unmanned aerial vehicle, and the calculation method comprises the following steps:
wherein: θ rf Is one half of the radiation angle of the red square fire control radar, theta br For the opposite angle of the blue square, θ bf Is one half of the radiation angle of the blue-square fire control radar, theta bt Is one half of the rear corner of the blue square tail,
the action distance of the fire control radar of the ith unmanned aerial vehicle is red;
the angular relationship is shown in fig. 3:
the threat situation is the degree of damage to the red party formed by the blue party, and the threat situation can be judged by the distance and the angle, and the calculation method is expressed as follows:
wherein: t (T) rij The threat situation formed by the blue jth unmanned aerial vehicle to the red ith unmanned aerial vehicle is provided;
the Urij is a number according to the relative angular change of the red and blue square, and the calculation method comprises the following steps:
based on the calculated advantages and threats, an advantage and threat judgment matrix can be formed, which can be expressed as:
in the formulas (7) and (8), m is the number of red unmanned aerial vehicles, and n is the number of blue unmanned aerial vehicles;
if the red unmanned aerial vehicle i is knocked down in the air combat process, the ith row of the row in which the formula (7) is positioned becomes 0, and the ith column of the formula (8) becomes 0;
adding equation (7) and equation (8) can yield a comprehensive judgment matrix, which can be expressed as:
M r ＝C r +T r (9)；
1.3 dynamic grid Environment modeling
The implementation of maneuver decision is based on a path planning algorithm, so that the planning speed is increased, the decision efficiency is improved, and the discretization processing is needed for the planning space. Spatial rasterization is the most common practice, but traditional grid planning methods all have static characteristics and are grid spaces with relatively fixed geodetic coordinates. If the unmanned aerial vehicle performs path planning in a static grid space, the planning time has a larger correlation with the resolution of the grid, and when the combat area is larger, the grid resolution has to be reduced to maintain the original planning rate. In this regard, the present invention contemplates a dynamically adaptive grid planning space, as shown in FIG. 4.
Theta in the figure g For the intersection angle of the grid coordinate and the geodetic coordinate, the coordinate conversion formula is given that clockwise is negative:
in (x) g ,y g ) Is any grid coordinate; (x ', y') is the corresponding geodetic coordinates; θ g For grid coordinates and ground sittingThe marked angle phi is an included angle formed by the position vector of the unmanned aerial vehicle in the grid coordinates and the X axis, and the anticlockwise rotation is regulated to be positive.
2 maneuver decision algorithm
2.1 maneuver control algorithm
The control algorithm of the fixed wing unmanned aerial vehicle is researched more mature, more control models with three degrees of freedom are applied, but because the control laws of the vertical method and the horizontal method have weak coupling characteristics, the control algorithm in the horizontal direction is only designed, so that the control requirement of horizontal maneuver in the beyond-sight air combat of the unmanned aerial vehicle is met. Can be expressed as:
in (x) i ,y i ) Is the position coordinate of the unmanned aerial vehicle i, v i For the speed of the unmanned aerial vehicle i,
is the heading of unmanned plane i, a i Acceleration, omega of unmanned plane i i Is the turning angular speed of the unmanned aerial vehicle i;
in addition, the speed, acceleration and turning angular speed of the unmanned plane are limited by performance, so that the following conditions should be satisfied:
where min and max each represent the maximum and minimum values of the corresponding variables.
According to the current common tactics of air countermeasure, the aircrafts usually keep cruising speed to fly before the unmanned plane enters the battlefield, and when the formation enters the battlefield, the formation needs to be actively changed to preempt the favorable situation. It may be assumed that the drone cruises at a minimum speed, accelerates at a maximum acceleration after entering the area of war, and maneuvers until a maximum speed is reached. And after the unmanned aerial vehicle leaves the battlefield, decelerating at the maximum deceleration until reaching the minimum speed cruising. The horizontal maneuvering modes of the unmanned aerial vehicle or the unmanned aerial vehicle are only 3, and the unmanned aerial vehicle or the unmanned aerial vehicle turns left, turns right or flies straight. When the next node of the survived route is left turning, the aircraft performs left turning mechanical turning, and the control instruction is not changed in a unit time interval until a new instruction is generated. The right turn or straight line instruction execution method is similar.
2.2 ACO-based Path planning Algorithm
The ant colony algorithm (Ant Colony Algorithm, ACO) is a typical intelligent bionic evolutionary algorithm, and can be quickly solved in a global range through the introduction of heuristic factors, so that the optimizing effect is good. The method uses the ant colony algorithm to construct the path planning algorithm, and has certain random search characteristics, so that certain uncertainty factors can be introduced for the air combat maneuver decision, and the maneuver principle is prevented from being broken due to too single maneuver principle. The basic formula of probability search of the intelligent agent is as follows:
in the method, in the process of the invention,
for the probability of agent k transitioning from grid point i to j at time t, τ j (t) is the pheromone concentration, eta of the grid point j j As the heuristic factor of the node j, the coefficient lambda can control the action intensity of the heuristic factor;
in order to accelerate the searching speed of the agent, heuristic factors are added into the ACO, and the distance visibility is utilized to guide the agent to move towards the target point, which can be expressed as:
wherein d j The Euclidean distance from the node j to the target point;
after all the agents complete one-time path optimizing, one-time pheromone updating is carried out on the path node, and the calculation formula is as follows:
wherein ρ is the volatilization rate of the node pheromone,
for the current optimal path node pheromone concentration variation, < >>
The pheromone left for the node passed by the kth agent in the path ranking in the iteration;
however, not all paths in the formula (15) leave pheromones, and the invention only releases the pheromones for the paths with K top ranks so as to accelerate the convergence of optimization. The pheromone added by ants with different ranks has different concentrations, and the calculation method comprises the following steps:
wherein F is * And F is a constant, L * And L k The lengths of the optimal path and the suboptimal path with rank k, respectively. After the pheromone is updated, the single iteration is finished, a new round of agent searching is started, and after the specified iteration times are completed, the recorded optimal path is the output path.
2.3ACO-Astar hybrid path planning algorithm
Research shows that the ant colony algorithm has the defects of low optimizing speed and easy sinking into local optimum, and more effective heuristic factors are required to be introduced during use so as to improve the planning performance of the ant colony algorithm. Therefore, the invention provides an ACO-Astar mixing algorithm to improve the planning capacity. The Astar algorithm is also a classical heuristic search algorithm. The algorithm combines the search strategies of the Dijkstra algorithm and the BFS algorithm, thereby realizing quick optimization. But the Astar algorithm only uses local search information in the search process, the utilization degree of global information is very low, and the planning optimization of each step is only based on the current information, so that an iteration process is omitted, the calculation speed is higher, and the planning result is a suboptimal solution.
The path planned by Astar is used as a heuristic factor, the iterative process of ACO is quickened in the form of a reference path, redundant road sections in the path planning process of the ACO algorithm are helped to be removed, and the planning efficiency of the ACO algorithm can be effectively improved. In addition, the ACO algorithm is a probabilistic search algorithm, has a certain probability to optimize the quality of the Astar planning path, and the uncertainty factor is added in the maneuver decision to be more suitable for the air combat situation, so that the ACO algorithm is not easy to be broken by the tactics of the opponent. The hybrid algorithm programming flow is shown in fig. 5:
3.1 unmanned plane cooperative algorithm
For the air combat of multiple unmanned aerial vehicles, a certain cooperative criterion is necessarily required to reasonably distribute the force and the fire. The assignment of the present invention to the target is performed by an organic decision based on equations (7) to (9). Each unmanned aerial vehicle selects the maximum or minimum value of the corresponding row according to the allocation strategy adopted by the man-machine, and the calculation method for selecting the target according to the dominance criterion is as follows:
in the method, in the process of the invention,
blue Fang Moren machine serial numbers selected for the ith unmanned aerial vehicle of the red square are the unmanned aerial vehicle serial numbers with the greatest advantage;
the calculation method for selecting the target according to the threat criterion comprises the following steps:
at this time
The serial number of the unmanned aerial vehicle with the greatest threat is obtained;
in addition, the target can be selected according to the comprehensive situation based on the formula (9), and the description is omitted here.
3.2 organic-mechanical maneuver guidelines
The task division of the unmanned aerial vehicle in formation mainly makes decisions on the fight mode of the unmanned aerial vehicle, including when to go out of the enemy, attack mode conversion, evacuation and the like. The man-machine is required to be positioned at the rear of the battlefield at any time to provide accompanying electronic interference for the unmanned aerial vehicle and play a role of a decision center. The unmanned plane tactics are adjusted timely due to the need of closely observing the air situation, so the flight control of the unmanned plane tactics is mainly completed by an autopilot. In order to fully exert the effect of electronic interference, the flying position of the man-machine needs to be continuously adjusted to implement the interference, the invention mainly calculates the flying target point of the man-machine based on the position points of both red and blue, and the calculation method comprises the following steps:
wherein (xh, yh) is the target point position of the organic machine, (X) UAV ,Y UAV ) Mean clustering center for survival of red and blue squares, L e Is constant and is related to the electronic interference distance of the organic machine,
is vector v c The angle formed by the unit base coordinate vector of the geodetic coordinate X axis is positive anticlockwise;
v c the calculation method of (1) is as follows:
v c ＝(X R ,Y R )-(X UAV ,Y UAV ) (21)；
wherein (X) R ,Y R ) The mean value clustering center of the red-square survival unmanned aerial vehicle;
the mean value clustering center calculating method comprises the following steps:
wherein (xk, yk) is the earth coordinates, sigma, of the kth unmanned aerial vehicle k Taking the value as 1 when the unmanned aerial vehicle k survives as a constant, otherwise taking the value as 0, and taking n as the total number of the unmanned aerial vehicles in the red and blue directions;
when the distance between the unmanned aerial vehicle and the target point is greater than LH, maneuvering to the target point based on an ACO-Astar algorithm, and when the distance is less than or equal to LH, performing spiral flight to implement electronic interference.
3.3 victory-defeat judgment criterion
When the unmanned aerial vehicle uses the fire control radar to implement and shine to the target machine, have certain probability locking enemy machine and hit it down, obviously the closer to enemy machine distance, the higher radar irradiation intensity can have higher hit probability, assumes that hit probability calculates the position and is:
in the method, in the process of the invention,
the hit probability of the attack of the red unmanned aerial vehicle i on the unmanned aerial vehicle j is determined; b and w are constants, delta r Diagonal and distance variations according to red Lan Fangxiang;
δ r the calculation method of (1) is as follows:
in [ theta ] emin ,θ emax ]For the radiation angle range of the man-machine electronic interference pod d e For the electronic interference distance d hj Is the distance theta between the unmanned aerial vehicle and the blue-side unmanned aerial vehicle j hbj The relative angle between the heading of the unmanned aerial vehicle and the blue-square unmanned aerial vehicle j;
when all unmanned aerial vehicles of a certain party are knocked down, the task is considered to fail;
because the man-machine is behind the array position, the situation that the man-machine participates in the battle is not considered. Because the single-time winner and the minus of the rounds cannot judge the performance of the algorithm, the quality of the maneuver decision algorithm is judged according to the multiple-time winner and minus ratio, and the calculation method comprises the following steps:
wherein B is r The ratio that wins for the red party,
the number of rounds winning for the red party is R is the total number of rounds.
4 simulation verification
Firstly, verifying the effectiveness of an algorithm, and examining the effectiveness of an ant colony algorithm in a one-to-one air combat countermeasure scene. The algorithm basic parameter settings are shown in table 1:
table 1: algorithm parameter setting
The red party uses ACO-A star algorithm to make maneuvering decision, the blue party uses ACO algorithm to make maneuvering decision, and the air combat countermeasure process is shown in figure 6:
the algorithm decision time consumption in the air combat process is shown in fig. 7:
the effectiveness of the improved algorithm can be verified through single-machine air combat countermeasure, then the effectiveness and tactical superiority of the manned-unmanned plane collaborative decision algorithm are verified through multi-machine countermeasure, and simulated countermeasure parameter settings are shown in table 2:
table 2: multi-machine countermeasure parameter setting
Looking first at the multi-machine countermeasure process without accompanying interference, the maneuver decisions of both red and blue are based on the ACO-A star algorithm, as shown in FIG. 8:
in the round of countermeasure, the unmanned aerial vehicle No. 2 and No. 3 of the red party are knocked down by the unmanned aerial vehicle No. Fang Jila of the blue party, and finally the red party wins. 20 red-blue challenge simulations were performed with a final win-loss ratio of:
at this time, the proportion of the winning or losing of the red and blue squares is equivalent. And then checking the air combat countermeasure process after the joining of the man-machine, as shown in fig. 10:
in the process of the partial air combat, the blue No. 3 machine is knocked down at the time of 47 xDeltat, the blue No. 2 machine is knocked down at the time of 53 xDeltat, the red No. 4 machine at the time of 57 xDeltat, the blue No. 1 machine at the time of 59 xDeltat, the red No. 3 machine at the time of 64 xDeltat, and the blue No. 4 machine at the time of 100 xDeltat. 20 air combat countermeasure simulations were performed to examine the improvement effect of the cooperative tactics on combat effectiveness, the effects being shown in fig. 11:
as can be seen from the comparison between fig. 9 and fig. 11, the man-unmanned aerial vehicle collaborative combat maneuver decision algorithm designed by the invention is effective, and can remarkably improve the combat efficiency of combat marshalling and the winning rate.
(1) The dynamic grid is used for modeling the air combat process, so that planning space can be effectively controlled, and the problem that planning speed is reduced due to overlarge air combat field is avoided.
(2) Aiming at the defects that the ACO algorithm is slow in planning speed and easy to be trapped into local optimum, an ACO-Astar hybrid maneuver decision algorithm is provided, the algorithm can effectively accelerate the planning speed and improve the quality of solutions.
(3) The constructed manned/unmanned cooperative air combat platform can support multi-machine air combat simulation. The cooperative tactics of auxiliary decision making and electronic interference support are provided by the man-machine, so that the winning rate of the unmanned aerial vehicle air combat can be effectively improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. The manned-unmanned aerial vehicle collaborative air combat maneuver decision-making method is characterized by comprising the following steps of:
step 1, establishing a manned-unmanned plane collaborative air combat modeling: designing a manned-unmanned plane cooperative air combat tactic, judging according to situations, and establishing a dynamic grid environment model according to judgment results;
step 2, establishing a maneuver decision algorithm: establishing A maneuvering control algorithm, and establishing an ACO-A star-based mixed path planning algorithm and an ACO-A star-based mixed path planning algorithm;
step 3, establishing a man-unmanned aerial vehicle cooperative strategy: establishing an unmanned aerial vehicle cooperative algorithm, and prescribing a man-machine maneuvering criterion and a winning or losing judgment criterion;
and step 4, performing simulation verification on the simulation result.
2. The manned-unmanned aerial vehicle collaborative air combat maneuver decision-making method of claim 1, wherein the manned-unmanned aerial vehicle collaborative air combat maneuver is designed as described in step 1, wherein the manned-unmanned aerial vehicle remains outside the effective range of attack of the enemy aircraft at all times, and wherein the manned-unmanned aerial vehicle is equipped with electronic interference equipment.
3. The manned unmanned aerial vehicle collaborative air combat maneuver decision-making method according to claim 2, wherein in step 1, the judgment is performed according to situation, and a dynamic grid environment model is established according to the judgment result, wherein the judgment of situation is based on speed, distance, relative angle and altitude, and the calculation formula of distance and relative angle is:
wherein: (x) r ,y r ) And (x) b ,y b ) The ground coordinate positions of the red and blue unmanned aerial vehicle are respectively; θ rb V is the opposite angle of the red square and the blue square r Is the heading vector of the red party; v rb Vector for red unmanned aerial vehicle to point to blue unmanned aerial vehicle;
according to different angles of the unmanned aerial vehicles, the situation is divided into an advantage situation and a threat situation, wherein the advantage situation is the degree of damage to enemy, and the calculation method comprises the following steps:
wherein: c (C) rij Is the advantage situation of the red square ith unmanned aerial vehicle on Lan Fangdi j unmanned aerial vehicles, d ij The distance between the red square ith unmanned plane and Lan Fangdi j unmanned planes is the distance;
Λ rij according to the number of the relative angular changes of the red and blue square, the calculation method comprises the following steps:
g is a number according to the distance change of the red and blue unmanned aerial vehicle, and the calculation method comprises the following steps:
wherein: θ rf Is one half of the radiation angle of the red square fire control radar, theta br For the opposite angle of the blue square, θ bf Is one half of the radiation angle of the blue-square fire control radar, theta bt Is one half of the rear corner of the blue square tail,
the action distance of the fire control radar of the ith unmanned aerial vehicle is red;
the degree of possible damage to the red square formed by the blue square is judged by the distance and the angle, and the calculation method is expressed as follows:
wherein: t (T) rij The threat situation formed by the blue jth unmanned aerial vehicle to the red ith unmanned aerial vehicle is provided;
the Urij is a number according to the relative angular change of the red and blue square, and the calculation method comprises the following steps:
based on the calculated advantages and threats, an advantage and threat judgment matrix can be formed, which can be expressed as:
in the formulas (7) and (8), m is the number of red unmanned aerial vehicles, and n is the number of blue unmanned aerial vehicles;
if the red unmanned aerial vehicle i is knocked down in the air combat process, the ith row of the row in which the formula (7) is positioned becomes 0, and the ith column of the formula (8) becomes 0;
adding equation (7) and equation (8) can yield a comprehensive judgment matrix, which can be expressed as:
M r ＝C r +T r (9)；
modeling is carried out according to a dynamic grid environment, a dynamic self-adaptive grid planning space is designed, and if the clockwise is negative, a coordinate conversion formula is as follows:
in (x) g ,y g ) Is any grid coordinate; (x ', y') is the corresponding geodetic coordinates; θ g The angle phi formed by the grid coordinates and the ground coordinates is the included angle formed by the position vector of the unmanned aerial vehicle in the grid coordinates and the X axis, and the anticlockwise rotation is regulated to be positive.
4. The manned unmanned aerial vehicle collaborative air combat maneuver decision-making method according to claim 1, wherein the maneuver decision-making algorithm is set up in step 2: the method comprises the steps of establishing a maneuvering control algorithm, wherein the maneuvering control algorithm is only designed for a control algorithm in the horizontal direction so as to meet the control requirement of horizontal maneuvering in the unmanned plane beyond-the-horizon air combat, and the maneuvering control algorithm can be expressed as follows:
in (x) i ,y i ) Is the position coordinate of the unmanned aerial vehicle i, v i For the speed of the unmanned aerial vehicle i,
is the heading of unmanned plane i, a i Acceleration, omega of unmanned plane i i Is the turning angular speed of the unmanned aerial vehicle i;
in addition, the speed, acceleration and turning angular speed of the unmanned plane are limited by performance, so that the following conditions should be satisfied:
where min and max each represent the maximum and minimum values of the corresponding variables.
5. The manned unmanned aerial vehicle collaborative air combat maneuver decision-making method of claim 1, wherein the establishing of the ACO-based path planning algorithm in step 2 comprises:
establishing a basic formula of probability search of an intelligent agent:
in the method, in the process of the invention,
for the probability of agent k transitioning from grid point i to j at time t, τ j (t) is the pheromone concentration, eta of the grid point j j As the heuristic factor of the node j, the coefficient lambda can control the action intensity of the heuristic factor;
in order to accelerate the searching speed of the agent, heuristic factors are added into the ACO, and the distance visibility is utilized to guide the agent to move towards the target point, which can be expressed as:
wherein d j The Euclidean distance from the node j to the target point;
after all the agents complete one-time path optimizing, one-time pheromone updating is carried out on the path node, and the calculation formula is as follows:
wherein ρ is the volatilization rate of the node pheromone,
for the current optimal path node pheromone concentration variation, < >>
The pheromone left for the node passed by the kth agent in the path ranking in the iteration;
the pheromone added by ants with different ranks has different concentrations, and the calculation method comprises the following steps:
wherein F is * And F is a constant, L * And L k The lengths of the optimal path and the suboptimal path with rank k, respectively.
6. The manned-unmanned aerial vehicle collaborative air combat maneuver decision-making method according to claim 1, wherein the unmanned aerial vehicle collaborative algorithm is established in step 3, and a manned maneuver criterion and a win/loss judgment criterion are specified;
each unmanned aerial vehicle selects the maximum or minimum value of the corresponding row according to the allocation strategy adopted by the man-machine, and the calculation method for selecting the target according to the dominance criterion is as follows:
in the method, in the process of the invention,
blue Fang Moren machine serial numbers selected for the ith unmanned aerial vehicle of the red square are the unmanned aerial vehicle serial numbers with the greatest advantage;
the calculation method for selecting the target according to the threat criterion comprises the following steps:
at this time
The serial number of the unmanned aerial vehicle with the greatest threat is obtained;
the method for calculating the flight target point of the man-machine based on the position points of the red and blue parties comprises the following steps:
wherein (xh, yh) is the target point position of the organic machine, (X) UAV ,Y UAV ) Mean clustering center for survival of red and blue squares, L e Is constant, is related to the electronic interference distance of the organic machine, and theta is vector v c The angle formed by the unit base coordinate vector of the geodetic coordinate X axis is positive anticlockwise;
v c the calculation method of (1) is as follows:
v c ＝(X R ,Y R )-(X UAV ,Y UAV )(21)；
wherein (X) R ,Y R ) The mean value clustering center of the red-square survival unmanned aerial vehicle;
the mean value clustering center calculating method comprises the following steps:
wherein (xk, yk) is the earth coordinates, sigma, of the kth unmanned aerial vehicle k Taking the value as 1 when the unmanned aerial vehicle k survives as a constant, otherwise taking the value as 0, and taking n as the total number of the unmanned aerial vehicles in the red and blue directions;
when the distance between the unmanned aerial vehicle and the target point is greater than LH, maneuvering to the target point based on an ACO-A star algorithm, and when the distance is less than or equal to LH, performing spiral flight to implement electronic interference.
7. The method for collaborative air combat maneuver decision-making according to claim 1, wherein the win-loss criterion in step 3 locks the enemy aircraft and knocks it down with a probability when the drone uses the fire radar to illuminate the target aircraft, assuming the hit probability calculation orientation is:
in the method, in the process of the invention,
the hit probability of the attack of the red unmanned aerial vehicle i on the unmanned aerial vehicle j is determined; b and w are constants, delta r Diagonal and distance variations according to red Lan Fangxiang;
δ r the calculation method of (1) is as follows:
in [ theta ] emin ,θ emax ]For the radiation angle range of the man-machine electronic interference pod d e For the electronic interference distance d hj Is the distance theta between the unmanned aerial vehicle and the blue-side unmanned aerial vehicle j hbj The relative angle between the heading of the unmanned aerial vehicle and the blue-square unmanned aerial vehicle j;
when all unmanned aerial vehicles of a certain party are knocked down, the task is considered to fail;
because the single-time winner and the minus of the rounds cannot judge the performance of the algorithm, the quality of the maneuver decision algorithm is judged according to the multiple-time winner and minus ratio, and the calculation method comprises the following steps:
wherein B is r The ratio that wins for the red party,
the number of rounds winning for the red party is R is the total number of rounds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244436.4A CN116339378A (en) | 2023-03-14 | 2023-03-14 | Unmanned aerial vehicle collaborative air combat maneuver decision-making method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244436.4A CN116339378A (en) | 2023-03-14 | 2023-03-14 | Unmanned aerial vehicle collaborative air combat maneuver decision-making method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116339378A true CN116339378A (en) | 2023-06-27 |
Family
ID=86894206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310244436.4A Pending CN116339378A (en) | 2023-03-14 | 2023-03-14 | Unmanned aerial vehicle collaborative air combat maneuver decision-making method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116339378A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117348392A (en) * | 2023-09-27 | 2024-01-05 | 四川大学 | Multi-machine short-distance air combat maneuver decision distributed optimization method |
-
2023
- 2023-03-14 CN CN202310244436.4A patent/CN116339378A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117348392A (en) * | 2023-09-27 | 2024-01-05 | 四川大学 | Multi-machine short-distance air combat maneuver decision distributed optimization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111880563B (en) | Multi-unmanned aerial vehicle task decision method based on MADDPG | |
| CN110031004B (en) | Static and dynamic path planning method for unmanned aerial vehicle based on digital map | |
| CN113791634B (en) | Multi-agent reinforcement learning-based multi-machine air combat decision method | |
| CN112783209B (en) | Unmanned aerial vehicle cluster confrontation control method based on pigeon intelligent competition learning | |
| CN111240353A (en) | Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree | |
| Wang et al. | Improving maneuver strategy in air combat by alternate freeze games with a deep reinforcement learning algorithm | |
| CN112666981B (en) | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group | |
| CN103413186A (en) | Cooperative multi-aircraft target distribution method based on hybrid optimization algorithm | |
| CN116339378A (en) | Unmanned aerial vehicle collaborative air combat maneuver decision-making method | |
| CN112327927B (en) | Multi-angle strike track planning method for formation unmanned aerial vehicles based on grid planning algorithm | |
| CN115903865A (en) | Aircraft near-distance air combat maneuver decision implementation method | |
| CN113052289A (en) | Unmanned ship cluster striking position selection method based on game theory | |
| CN112733251A (en) | Multi-unmanned aerial vehicle collaborative track planning method | |
| Xiang et al. | Research on UAV swarm confrontation task based on MADDPG algorithm | |
| Kang et al. | Beyond-visual-range tactical game strategy for multiple uavs | |
| CN117035435A (en) | Multi-unmanned aerial vehicle task allocation and track planning optimization method in dynamic environment | |
| CN116661496B (en) | Multi-patrol-missile collaborative track planning method based on intelligent algorithm | |
| CN117850471A (en) | Multi-agent collaborative track planning method considering radar threat in three-dimensional environment and planning system thereof | |
| CN108445755A (en) | Electronic jammers spatial domain based on refined Hook Jeeves algorighm delineates method | |
| CN116520884A (en) | Unmanned plane cluster countermeasure strategy optimization method based on hierarchical reinforcement learning | |
| Liu et al. | Firepower distribution method of anti-ship missile based on coupled path planning | |
| Zhao et al. | Shuffled frog leaping algorithm with non-dominated sorting for dynamic weapon-target assignment | |
| CN114167899A (en) | Unmanned aerial vehicle swarm cooperative countermeasure decision-making method and system | |
| Wei et al. | UCAVs online collaborative path planning method based on dynamic task allocation | |
| Guopeng et al. | Research on Path planning of Three-Dimensional UAV Based on Levy Flight Strategy and Improved Particle Swarm Optimization Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |