CN114779823A - Unmanned aerial vehicle cooperative capture control method under saturation attack task - Google Patents
Unmanned aerial vehicle cooperative capture control method under saturation attack task Download PDFInfo
- Publication number
- CN114779823A CN114779823A CN202210585638.0A CN202210585638A CN114779823A CN 114779823 A CN114779823 A CN 114779823A CN 202210585638 A CN202210585638 A CN 202210585638A CN 114779823 A CN114779823 A CN 114779823A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- target
- representing
- attack
- 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 31
- 230000007123 defense Effects 0.000 claims abstract description 24
- 229920006395 saturated elastomer Polymers 0.000 claims abstract description 13
- 230000035515 penetration Effects 0.000 claims description 12
- 238000013461 design Methods 0.000 claims description 10
- 230000009194 climbing Effects 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001926 trapping method Methods 0.000 description 1
- 238000012795 verification 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
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
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 discloses an unmanned aerial vehicle cooperative capture control method under a saturation attack task, which comprises the steps of building a target defense system model under a saturation attack task scene, and designing the cluster defense probability of unmanned aerial vehicles to ensure that at least one unmanned aerial vehicle completes an attack task; based on the situation that the target is moved and the target speed is unknown, the distributed cooperative capture controller of the unmanned aerial vehicle under the saturated attack task is designed, so that the unmanned aerial vehicle cluster can accurately estimate the target speed, prevent collision and accurately surround. When receiving the attack instruction, the targets are simultaneously attacked by the shortest path. The invention provides a saturation attack control method based on an unmanned aerial vehicle cluster, and a distributed cooperative capture controller is designed. And special instruction information is generated according to different states of each unmanned aerial vehicle, so that the enclosure can be better completed. Meanwhile, the controller has good universality and expandability. In the aspect of control effect, the cooperative trapping controller has better convergence and anti-interference performance, and ensures that each unmanned aerial vehicle can complete tasks quickly and accurately.
Description
Technical Field
The invention relates to the technical field of multi-agent control, in particular to an unmanned aerial vehicle cooperative capture control method under a saturation attack task.
Background
Along with the improvement of the autonomous ability of the unmanned aerial vehicle, the unmanned aerial vehicle is widely applied to various tasks. They have the advantages of low cost, high efficiency, good reliability and the like. However, a single unmanned aerial vehicle has limitations, and some complex tasks need multiple unmanned aerial vehicles to be completed in a cooperative manner, so that the success rate and the efficiency of the tasks can be ensured. From this, two concepts, a multi-drone system and a drone cluster, are studied by a wide range of scholars. How to control multiple unmanned aerial vehicles to cooperatively complete a task becomes a research topic nowadays.
The task is then materialized, for example, a saturation attack task for a cluster of drones. First, a saturation attack task is a tactical strategy for a group of low-cost unmanned aerial vehicles to penetrate through a target and effectively attack a high-value target. The high density of drone clusters can put the target's air defense system into an overload state, thereby enforcing the attack. However, the target defense system is complex and even diversified, and how to complete the saturation attack task by using the minimum unmanned aerial vehicle becomes the key point of research. Secondly, in the aspect of control, how to design the controller to effectively trap the moving target is also a difficult problem. The state information of the unmanned aerial vehicles is time-varying, if the information is delayed or the instruction is inaccurate, the capture is difficult to complete, and meanwhile, the collision among the unmanned aerial vehicles can be caused; second, the target is mobile, but the speed is unknown to my drone. If not accurate estimation, it is difficult to accomplish the enclosure, causes the unmanned aerial vehicle track the target that can not be fine easily, reduces the success rate of task. Therefore, if a corresponding control target and a cooperative capture controller are designed without aiming at a saturation attack task, the unmanned aerial vehicle is difficult to estimate the target speed in a task mode, and capture is difficult to form.
In conclusion, in the prior art, research on saturation attack task strategies and control is less, and a targeted distributed controller is lacked. The enclosure strategy in the formation mode needs more information, the control complexity is increased, and the stability and the rapidity of the multi-unmanned aerial vehicle system are difficult to ensure.
Disclosure of Invention
The invention provides a cooperative trapping control method based on an unmanned aerial vehicle cluster saturation attack task, so that an unmanned aerial vehicle cluster can effectively estimate a target speed, and meanwhile collision is prevented to finish cooperative trapping. And when the unmanned aerial vehicle receives the attack instruction, initiating attack at the shortest distance.
Based on the above invention, the following technical scheme is adopted:
an unmanned aerial vehicle cooperative capture control method under a saturation attack task comprises the following steps:
1) the method comprises the steps that a target defense system model is built under a saturated attack task scene, wherein the target defense system model comprises an early warning system, an air defense missile and an electronic interference module, and unmanned aerial vehicle cluster defense penetration probability is designed to ensure that at least one unmanned aerial vehicle completes an attack task;
2) based on the moving target and the unknown target speed, aiming at an unmanned aerial vehicle model containing an autopilot, designing an unmanned aerial vehicle capture control target and a distributed cooperative capture controller under a saturated attack task, driving the unmanned aerial vehicle by an instruction converter, realizing the accurate estimation of the target speed, the prevention of collision and the accurate surrounding of an unmanned aerial vehicle cluster, and finally finishing the cooperative capture of the target; when receiving the attack instruction, the targets are simultaneously attacked by the shortest path.
Further, the cooperative trapping control method based on the saturation attack task can be described as follows:
(1) at least one unmanned aerial vehicle breaks through a target defense system to complete a saturation attack task;
(2) the target is captured by the unmanned aerial vehicle;
(3) no collision exists between the unmanned aerial vehicles;
(4) the unmanned aerial vehicle can accurately estimate the speed of the target.
Further, the design of the unmanned aerial vehicle cluster defense burst probability in step 1) is as follows:
according to the saturated attack task scene, at least one unmanned aerial vehicle is required to complete the penetration, so the minimum number of the unmanned aerial vehicles sent out is designed as follows:
wherein n represents the number of target missiles; pfRepresenting an average probability of service for the air weapons; p isLRepresenting the detection probability of the early warning system; qaAnd QeRespectively representing the penetration probability of the air defense weapons and the electronic interference; n is a radical ofmRepresenting the number of drones that completed the task with the least success; n represents the number of drones dispatched.
Further, the model of the unmanned aerial vehicle containing the autopilot in the step 2) is expressed as
In the formula, xi(t),yi(t),hi(t) is the centroid position of the unmanned aerial vehicle i at the moment t; wherein Vi(t),θi(t) respectively representing the speed, the course angle and the climbing angle of the unmanned aerial vehicle i at the moment t; vci(t),θci(t) indicating the corresponding speed command, heading angle command and climbing angle command; tau.V,τθRespectively, representing the time constant of each channel.
Further, the unmanned aerial vehicle capture control target under the design saturated attack task in the step 2) is as follows:
the distributed collaborative fence controller is represented as:
in the formula, pi,pj,ptargetRespectively representing the position of the unmanned aerial vehicle i, the position of the unmanned aerial vehicle j and the position of the target; u. ofi=[uxi,uyi,uhi]TRepresenting acceleration signals of the unmanned aerial vehicle on a forward channel, a transverse channel and a height channel respectively; r represents any point on the surrounding ring formed by the unmanned aerial vehicle; d represents the distance between the object and the surrounding circle, if and only if ptargetDetermining that the target is captured when epsilon co (p); n represents the number of unmanned aerial vehicles; d is a radical ofijRepresents the distance between drone i and drone j; dsRepresenting a safe distance between the unmanned aerial vehicles, wherein the distance between the unmanned aerial vehicles cannot be smaller than the safe distance; vi(t),Vtarget(t) respectively representing the actual speed of the unmanned aerial vehicle i, the estimated speed of the unmanned aerial vehicle i on the target and the actual speed of the target; lambdaiα, β, γ, and K represent weight coefficients; ciA set of neighbor drones representing drone i; f. ofiAnd (4) representing an obstacle avoidance function of the unmanned aerial vehicle i.
Further, the controller in step 2) is composed of an attack term, an anti-collision term and an adaptive estimation term.
Further, step 2) the instruction converter is represented as:
in the formula ui=[uxi,uyi,uhi]TRepresenting acceleration commands of the unmanned aerial vehicle on a forward channel, a transverse channel and a height channel respectively; tau isV,τθRespectively, representing the time constant of each channel.
According to the designed saturation attack cooperative trapping control method and the trapping controller, the cooperative trapping of the minimum unmanned aerial vehicle can be realized, and meanwhile, the speed of the moving target can be estimated. Guarantee during the flight that no collision takes place between unmanned aerial vehicle.
The invention has the beneficial effects that:
compared with other enclosure methods, the unmanned aerial vehicle collaborative enclosure control method does not need to design a formation in advance. And (4) finishing the enclosure task according to the minimum safety distance between the unmanned aerial vehicles. Due to the real-time performance and complexity of the tasks, the method designed by the invention is difficult to predict by enemies, so that the success rate of the tasks is increased. Meanwhile, the controller has good expandability, can ensure that the large-scale unmanned aerial vehicle finishes the enclosure and can realize the enclosure by needing less state quantities (the position, the speed and the target position of the unmanned aerial vehicle). And the traditional formation controller can influence the formation quality and the task success rate because the number of the unmanned aerial vehicles is increased to cause the problems of calculation complexity and the accuracy of formation information.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of a distributed collaborative fencing controller system architecture;
FIG. 2 is a diagram of the probability of a cluster break-in defense of an unmanned aerial vehicle in an embodiment of the present invention;
fig. 3 is a three-dimensional unmanned aerial vehicle cluster flight curve diagram in the embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the technical solutions of the present invention, the present invention will be further described in detail with reference to the following detailed description.
The embodiment of the invention provides an unmanned aerial vehicle cooperative trapping control method under a saturation attack task, which mainly comprises a target defense system model (an early warning system, an air defense missile system and an electronic interference system) and a trapping process. The design structure diagram of the distributed cooperative trapping controller is shown in fig. 1. The unmanned aerial vehicle receives the task instruction, the position information of the target and the state information of other unmanned aerial vehicles within the communication radius at first, and then the controller outputs a corresponding control instruction to achieve the purpose of cooperatively trapping the target. The control command of each unmanned aerial vehicle comprises a speed command, a heading angle command and a climbing angle command.
The method specifically comprises the following steps:
firstly, according to a target defense system model, calculating the penetration probability of an unmanned aerial vehicle cluster, wherein the probability can be expressed as:
wherein n represents the number of target missiles; pfRepresenting an average probability of service for the air weapons; p isLRepresenting the detection probability of the early warning system; qa,QeRespectively representing the penetration probability of the air defense weapons and the electronic interference; n represents the number of drones dispatched.
And requiring at least one unmanned aerial vehicle to complete the penetration according to the saturated attack task scene. Meanwhile, the number of the dispatched unmanned aerial vehicles is larger than that of the least unmanned aerial vehicles, and the task can be successfully completed. Therefore, the minimum number of unmanned aerial vehicles dispatched is designed as follows:
in the formula, NmRepresenting the number of drones that completed the task with the least success; n represents the number of drones dispatched.
And then, dispatching a corresponding number of unmanned aerial vehicles according to the analysis, and designing a distributed cooperative trapping controller to perform cooperative trapping on the target. The nonlinear model feedback linearization of a fixed-wing unmanned aerial vehicle of a certain model is carried out, and an automatic pilot is added, so that the final unmanned aerial vehicle model containing the automatic pilot can be expressed as follows:
in the formula, xi(t),yi(t),hi(t) is the centroid position of the unmanned aerial vehicle i at the moment t; wherein Vi(t),θi(t) respectively representing the speed, the course angle and the climbing angle of the unmanned aerial vehicle i at the moment t; vci(t),θci(t) indicating the corresponding speed command, heading angle command and climbing angle command; tau isV,τθRespectively, representing the time constant of each channel.
Further, based on the situation that the moving target is not known and the target speed is unknown, aiming at an unmanned aerial vehicle model containing an automatic pilot, designing an unmanned aerial vehicle capture control target under a saturation attack task, wherein the unmanned aerial vehicle capture control target under the saturation attack task is as follows:
in the formula, ptargetRepresenting the position of the target; lambdaiRepresenting a weight coefficient; r represents any point on the surrounding ring formed by the unmanned aerial vehicle; d represents the distance between the target and the surrounding circle, if and only if ptargetDetermining that the target is captured when the epsilon is co (p); n represents the number of unmanned aerial vehicles; dijRepresents the distance between drone i and drone j; d is a radical ofsBetween unmanned aerial vehiclesThe distance between the unmanned planes cannot be smaller than the safety distance; vi(t),Vtarget(t) represents an actual speed of drone i, an estimated speed of drone i to the target, and an actual speed of the target, respectively.
Further, according to the proposed cooperative trapping control method, under a saturation attack task mode, the distributed cooperative trapping controller of the unmanned aerial vehicle cluster controls the unmanned aerial vehicles to perform cooperative trapping on the target, and meanwhile, collision among the unmanned aerial vehicles is avoided. The distributed collaborative capture controller is represented as:
in the formula, pi,pjRespectively representing the position of the unmanned plane i and the position of the unmanned plane j; u. ofi=[uxi,uyi,uhi]TRepresenting acceleration signals of the unmanned aerial vehicle on three channels of a forward channel, a transverse channel and a height channel respectively; α, β, γ, and K represent weight coefficients; ciA set of neighbor drones representing drone i; f. ofiAnd (4) representing an obstacle avoidance function of the unmanned aerial vehicle i. The controller uiThe method is composed of an attack item, an anti-collision item and an adaptive estimation item.
The distributed cooperative capture controller designed according to the above formula can obtain an actual control input instruction required by the unmanned aerial vehicle model through instruction conversion. The instruction converter can be represented as:
according to the distributed cooperative trapping controller, when the time tends to be infinite, the unmanned aerial vehicle can trap the target. Meanwhile, the speed of the unmanned aerial vehicle is equal to the speed of the target, and the estimated speed of the unmanned aerial vehicle to the target is equal to the speed of the target. And the distance between the unmanned aerial vehicles is always greater than the safety distance. Therefore, the unmanned aerial vehicle cluster completes the instruction of cooperative trapping. When the attack instruction is received, the unmanned plane can attack the target in the shortest distance, and therefore the saturated attack task is completed.
The numerical simulation verification of the embodiment is that according to the target defense system, the number n of target missiles is 4, and the average service probability P of air defense weaponsf0.7, detection probability P of early warning systemL0.8, penetration probability of air weapon and electronic interference Qa=0.4,Qe0.6. The overall defense probability simulation graph is shown in fig. 2. Based on the penetration probability, four unmanned aerial vehicles are dispatched to complete the saturation attack cooperative trapping task. Assume that the target position is (100,100,100) m and the velocity is 30 m/s. The number N of drones is set to 4, the initial positions are (-30,30,90) m, (0,160,110) m, (-10,100,120) m, (10,80,80) m, and the initial speeds are 25m/s, 24m/s, 26m/s, and 25m/s, respectively. The three-dimensional flight path of the drone cluster is shown in figure 3.
Based on simulation results, the cooperative trapping control method under the unmanned aerial vehicle cluster saturation attack task can well ensure that the least unmanned aerial vehicles finish the task and reduce the loss of funds and materials. Meanwhile, according to the simulation position curve, the distributed cooperative trapping controller designed by the invention can well help the unmanned aerial vehicle to accurately estimate the speed of the target, so that the target is surrounded. In this process, also can not bump between the unmanned aerial vehicle. And finally, the actual speed of the unmanned aerial vehicle, the estimated speed of the target and the actual speed of the target tend to be consistent. In addition, the command converter can effectively convert the command of the controller into the speed command V required by the unmanned aerial vehiclecTrack angle commandAnd a climb angle command θcAnd the automatic pilot can ensure that the unmanned aerial vehicle has better tracking performance and ensures the stability of the system.
The invention has the beneficial effects that:
the invention designs a saturation attack control method based on an unmanned aerial vehicle cluster. Meanwhile, aiming at the characteristics of the unmanned aerial vehicle and the task characteristics, the distributed cooperative capture controller is designed, and the control algorithm has the characteristics of high convergence speed and interference resistance. The algorithm is a distributed algorithm, and is less influenced by the number of the unmanned aerial vehicles, so that the algorithm has good expansibility;
compared with other trapping methods, the cooperative trapping control method in the saturation attack task mode does not need to design the formation in advance. And (4) finishing the enclosure task according to the minimum safety distance between the unmanned aerial vehicles. Due to the real-time performance and complexity of the tasks, the method designed by the invention is difficult to predict by enemies, so that the success rate of the tasks is increased. Meanwhile, the controller has good expandability, can ensure that the large-scale unmanned aerial vehicle finishes enclosure and can be realized by less state quantity (the position, the speed and the target position of the unmanned aerial vehicle). The traditional formation controller can influence the formation quality and the task success rate due to the problems of calculation complexity and accuracy of formation information caused by the increase of the number of the unmanned aerial vehicles; the controller design not only is applicable in unmanned aerial vehicle, can use multiple removal agent simultaneously. The method has better adaptability to linear and nonlinear systems.
In order to better meet the actual requirement, the invention builds a coupled unmanned aerial vehicle airplane model, also has an accurate instruction converter, and considers the constraints of the unmanned aerial vehicle, such as speed limit, course angle limit, climbing angle limit and the like, so as to simulate a real saturated attack task scene based on an unmanned aerial vehicle cluster.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. An unmanned aerial vehicle cooperative capture control method under a saturation attack task is characterized by comprising the following steps:
1) the method comprises the steps that a target defense system model is built under a saturated attack task scene, wherein the target defense system model comprises an early warning system, an air defense missile and an electronic interference module, and unmanned aerial vehicle cluster defense penetration probability is designed to ensure that at least one unmanned aerial vehicle completes an attack task;
2) based on the moving target and the unknown target speed, aiming at an unmanned aerial vehicle model containing an autopilot, designing an unmanned aerial vehicle capture control target and a distributed cooperative capture controller under a saturated attack task, driving the unmanned aerial vehicle by an instruction converter, realizing the accurate estimation of the target speed, the prevention of collision and the accurate surrounding of an unmanned aerial vehicle cluster, and finally finishing the cooperative capture of the target; when receiving the attack instruction, the targets are simultaneously attacked by the shortest path.
2. The unmanned aerial vehicle cooperative capture control method under the saturation attack task according to claim 1, wherein the design unmanned aerial vehicle cluster penetration probability in step 1) is:
according to the saturated attack task scene, at least one unmanned aerial vehicle is required to complete the penetration, so the minimum number of the unmanned aerial vehicles sent out is designed as follows:
wherein n represents the number of target missiles; pfRepresenting an average probability of service for the air weapons; p isLRepresenting the detection probability of the early warning system; qaAnd QeRespectively representing the penetration probability of air defense weapons and electronic interference; n is a radical ofmRepresenting the number of drones that completed the task with the least success; n represents the number of drones dispatched.
3. The unmanned aerial vehicle cooperative surrounding and catching control method under the saturated attack task according to claim 1, wherein the unmanned aerial vehicle model containing the automatic pilot in the step 2) is represented as
In the formula, xi(t),yi(t),hi(t) is the centroid position of the unmanned aerial vehicle i at time t; wherein Vi(t),θi(t) respectively representing the speed, the course angle and the climbing angle of the unmanned aerial vehicle i at the moment t; vci(t),θci(t) representing a corresponding speed command, heading angle command and climbing angle command; tau isV,τθRespectively, representing the time constant of each channel.
4. The unmanned aerial vehicle cooperative capture control method under the saturation attack task according to claim 1, wherein the unmanned aerial vehicle capture control target under the design saturation attack task in step 2) is:
the distributed collaborative fence controller is represented as:
in the formula, pi,pj,ptargetRespectively representing the position of the unmanned aerial vehicle i, the position of the unmanned aerial vehicle j and the position of a target; u. ui=[uxi,uyi,uhi]TRepresenting acceleration signals of the unmanned aerial vehicle on three channels of a forward channel, a transverse channel and a height channel respectively; r represents any point on the surrounding ring formed by the unmanned aerial vehicle; d represents the distance between the target and the surrounding circle, if and only if ptargetDetermining that the target is captured when the epsilon is co (p); n represents the number of unmanned aerial vehicles; d is a radical ofijRepresents the distance between drone i and drone j; dsRepresenting a safe distance between the unmanned aerial vehicles, wherein the distance between the unmanned aerial vehicles cannot be smaller than the safe distance; vi(t),Vtarget(t) respectively representing an actual speed of the drone i, an estimated speed of the drone i to the target, and an actual speed of the target; lambdaiα, β, γ, and K represent weight coefficients; ciA set of neighbor drones representing drone i; f. ofiAnd (4) representing an obstacle avoidance function of the unmanned aerial vehicle i.
5. The cooperative capture control method for the unmanned aerial vehicle under the saturated attack task according to claim 1, wherein the controller in the step 2) is composed of an attack item, an anti-collision item and an adaptive estimation item.
6. The unmanned aerial vehicle cooperative hunting control method according to claim 1, wherein the instruction converter in step 2) is represented as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210585638.0A CN114779823A (en) | 2022-05-26 | 2022-05-26 | Unmanned aerial vehicle cooperative capture control method under saturation attack task |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210585638.0A CN114779823A (en) | 2022-05-26 | 2022-05-26 | Unmanned aerial vehicle cooperative capture control method under saturation attack task |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114779823A true CN114779823A (en) | 2022-07-22 |
Family
ID=82408714
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210585638.0A Pending CN114779823A (en) | 2022-05-26 | 2022-05-26 | Unmanned aerial vehicle cooperative capture control method under saturation attack task |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114779823A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116068889A (en) * | 2022-12-29 | 2023-05-05 | 中国人民解放军陆军工程大学 | Saturated attack method and device for patrol projectile and storage medium |
CN116893690A (en) * | 2023-07-25 | 2023-10-17 | 西安爱生技术集团有限公司 | Unmanned aerial vehicle evasion attack input data calculation method based on reinforcement learning |
-
2022
- 2022-05-26 CN CN202210585638.0A patent/CN114779823A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116068889A (en) * | 2022-12-29 | 2023-05-05 | 中国人民解放军陆军工程大学 | Saturated attack method and device for patrol projectile and storage medium |
CN116068889B (en) * | 2022-12-29 | 2023-08-15 | 中国人民解放军陆军工程大学 | Saturated attack method and device for patrol projectile and storage medium |
CN116893690A (en) * | 2023-07-25 | 2023-10-17 | 西安爱生技术集团有限公司 | Unmanned aerial vehicle evasion attack input data calculation method based on reinforcement learning |
CN116893690B (en) * | 2023-07-25 | 2024-08-16 | 西安爱生技术集团有限公司 | Unmanned aerial vehicle evasion attack input data calculation method based on reinforcement learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111880563B (en) | Multi-unmanned aerial vehicle task decision method based on MADDPG | |
CN112880688B (en) | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm | |
CN113791634B (en) | Multi-agent reinforcement learning-based multi-machine air combat decision method | |
CN114779823A (en) | Unmanned aerial vehicle cooperative capture control method under saturation attack task | |
CN111026152B (en) | Unmanned aerial vehicle navigation decoy device and method based on flight destination prediction | |
CN114330115B (en) | Neural network air combat maneuver decision-making method based on particle swarm search | |
CN110412874B (en) | Multi-missile cooperative guidance law design method for maneuvering target and time delay communication | |
CN111897316A (en) | Multi-aircraft autonomous decision-making method under scene fast-changing condition | |
CN113139331A (en) | Air-to-air missile situation perception and decision method based on Bayesian network | |
CN105204512A (en) | Six-degree-of-freedom unmanned combat aerial vehicle short-range dogfight method based on simplified model machine game | |
Li et al. | Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm | |
CN114492805A (en) | Air combat maneuver decision design method based on fuzzy reasoning | |
CN110673488A (en) | Double DQN unmanned aerial vehicle concealed access method based on priority random sampling strategy | |
CN112198892A (en) | Multi-unmanned aerial vehicle intelligent cooperative penetration countermeasure method | |
CN114063644B (en) | Unmanned fighter plane air combat autonomous decision-making method based on pigeon flock reverse countermeasure learning | |
CN115903865A (en) | Aircraft near-distance air combat maneuver decision implementation method | |
CN114740497A (en) | Unmanned aerial vehicle deception method based on UKF multi-source fusion detection | |
Wang et al. | An optimal guidance strategy for moving-target interception by a multirotor unmanned aerial vehicle swarm | |
CN113741186B (en) | Double-aircraft air combat decision-making method based on near-end strategy optimization | |
CN112817329B (en) | Unmanned aerial vehicle tracking striking method, server and device | |
CN116661496B (en) | Multi-patrol-missile collaborative track planning method based on intelligent algorithm | |
Karelahti et al. | Game optimal support time of a medium range air-to-air missile | |
CN115202387B (en) | Fixed wing unmanned aerial vehicle obstacle avoidance control method based on bird-like phototaxis | |
CN116774714A (en) | Multi-constraint collaborative guidance method based on event triggering mechanism | |
CN112379599B (en) | Three-dimensional cooperative guidance method for air maneuvering target |
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 |