CN117077428A - Construction method of firepower planning objective function aiming at battlefield multidimensional requirements - Google Patents
Construction method of firepower planning objective function aiming at battlefield multidimensional requirements Download PDFInfo
- Publication number
- CN117077428A CN117077428A CN202311110119.XA CN202311110119A CN117077428A CN 117077428 A CN117077428 A CN 117077428A CN 202311110119 A CN202311110119 A CN 202311110119A CN 117077428 A CN117077428 A CN 117077428A
- Authority
- CN
- China
- Prior art keywords
- target
- considered
- battlefield
- objective function
- weapon
- 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
- 238000010276 construction Methods 0.000 title claims description 8
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000006378 damage Effects 0.000 claims description 15
- 230000002068 genetic effect Effects 0.000 claims description 12
- 238000002922 simulated annealing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 5
- 230000004927 fusion Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
Abstract
According to the method for constructing the firepower planning objective function aiming at the battlefield multidimensional requirement, five different objective functions are refined according to the battlefield requirement, a global objective function is obtained through fusion generalization processing of the five objective functions, and the global objective function is optimally solved to complete firepower planning, so that the battlefield multidimensional requirement can be more accurately simulated, and when a weapon system executes an autonomous striking task, an optimal striking strategy can be planned according to the different objective functions; the method can more accurately simulate the whole process of fire striking by embodying the aiming unit in the objective function.
Description
Technical Field
The invention belongs to the technical field of autonomous firepower planning of weapon systems, and particularly relates to a construction method of firepower planning objective functions aiming at battlefield multidimensional requirements.
Background
The fire autonomous planning of the multi-weapon system is a process of automatically distributing a certain type and quantity of fire units and aiming units according to factors such as the fight intention, the battlefield situation, the fire attributes of both enemy parties, the self resource condition and the like, and autonomously deciding to attack enemy targets. In battlefield command of unmanned equipment, fire autonomous planning is a key factor in determining the effect of combat. The fire autonomous planning of the multi-weapon system is a typical NP optimization problem, and for the solution thought of the problem, a mathematical model is constructed by using empirical knowledge or simulation data and solved, and the model generally has no analytical solution, and only can obtain an approximate numerical solution through an optimization algorithm. At present, most research achievements at home and abroad are constructed by constructing an objective function to express a mathematical model, and the damage probability of an objective is maximally used as the basis of autonomous programming of firepower to construct the objective function, but the method cannot refine more battlefield requirements and cannot flexibly cope with random situation strain of the battlefield. In addition, the conventional objective function constructed according to the probability of damage only shows the fire unit, but does not show the aiming unit, which does not conform to the actual weapon working principle, because the working of the aiming unit (such as a periscope and a sighting telescope) is the front stage of fire striking and is matched with the fire unit, therefore, the aiming unit needs to be incorporated into fire planning.
For fire planning, besides objective functions meeting battlefield requirements, an optimization algorithm is needed to carry out optimization solution on the objective functions, wherein the solution is a final solution of fire distribution, and many researches on the optimization algorithm are carried out at present, such as heuristic genetic algorithm, particle swarm algorithm, ant colony genetic algorithm, simulated annealing genetic algorithm and the like.
Disclosure of Invention
First, the technical problem to be solved
The invention provides a construction method of a fire planning objective function aiming at battlefield multidimensional requirements, aiming units are added on the basis of considering only fire units in the past to perfect the actual combat process of a ground fire system, meanwhile, different local objective functions are constructed according to various hitting principles, and all the local objective functions are fused into a global objective function, so that the technical problems of how to perfect and refine the objective functions capable of simulating the fire planning of a multi-weapon system are solved, and the optimal fire planning scheme conforming to the global objective function is found by utilizing the existing intelligent optimization algorithm.
(II) technical scheme
In order to solve the technical problems, the invention provides a construction method of a firepower planning objective function aiming at battlefield multidimensional requirements, which comprises the following steps:
s1, constructing a local objective function
Define i as weapon number; j is the target number; k is the aiming sensor number; h j；i ∈[0,1]Probability of hitting target j for weapon i; d (D) j；i ∈[0,1]Probability of damaging target j for weapon i; v (V) j E (0, 100) is the value of target j; t (T) i,j E (0, 100) is the threat level of the target j to the weapon i; s is S k = {0,1} is whether the kth sighting sensor is available, 0 is unavailable, 1 is available; wnum is the number of weapons; the Onum is the number of targets, and 2/3 targets are defined to be eliminated, so that the battlefield can be controlled to finish battle; on is the number of aiming sensors;
according to the requirements of a fire planning scene, on the premise of ensuring the damage of a target, the following five local objective functions are respectively constructed:
(1) Target value maximum function f 1
f 1 ＝∑V j (1-∏(1-H j；i *D j；i *S k ))i∈[0,Wnum],j∈[0,Onum],k∈[0,Pnum]
(2) Shortest function f of combat time 2
(3) Resource consumption minimum function f 3
(4) Maximum target damage number function f 4
f 4 ＝Onum*∏(1-∏(1-H j；i *D j；i *S k ))i∈[0,Wnum],j∈[0,Onum],k∈[0,Pnum]
(5) Target threat maximum function f 5
S2, constructing a global objective function
According to battlefield requirements, the global objective function f is constructed by jointly combining and generalizing five local objective functions 0 ：
i∈[0,Wnum],j∈[0,Onum]Or (b)
Wherein a is a control parameter of whether to consider the target value, the value range is {0,1},0 is not considered, and 1 is considered; b is a control parameter whether the target threat degree is considered, the value range is {0,1},0 is not considered, and 1 is considered; c is a control parameter whether the weapon quantity is considered, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 1 In order to consider whether one or more of target value, target threat degree, combat time and resource consumption are taken as control parameters of battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 2 In order to consider whether the target damage quantity is taken as a control parameter of battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered;
s3, optimally solving the global objective function to finish fire planning
And (3) carrying out optimal solution on the global objective function, sequentially solving weapon units and aiming units corresponding to all targets, and solving a plurality of groups of combinations of X (i, j, k) which are used as fire planning, wherein X (i, j, k) represents that a weapon i is matched with an aiming device j to strike the target k.
Further, in step S3, the solution is performed by using a heuristic genetic algorithm, an ant colony genetic algorithm or a simulated annealing genetic algorithm.
(III) beneficial effects
According to the method for constructing the firepower planning objective function aiming at the battlefield multidimensional requirement, five different objective functions are refined according to the battlefield requirement, a global objective function is obtained through fusion generalization processing of the five objective functions, and the global objective function is optimally solved to complete firepower planning, so that the battlefield multidimensional requirement can be more accurately simulated, and when a weapon system executes an autonomous striking task, an optimal striking strategy can be planned according to the different objective functions; the method can more accurately simulate the whole process of fire striking by embodying the aiming unit in the objective function.
Drawings
FIG. 1 is a flow chart of a construction method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a fire plan according to an embodiment of the present invention.
Detailed Description
To make the objects, contents and advantages of the present invention more apparent, the following detailed description of the present invention will be given with reference to the accompanying drawings and examples.
The embodiment provides a construction method of a fire planning objective function aiming at battlefield multidimensional requirements, and the flow is shown in fig. 1, and specifically comprises the following steps:
s1, constructing a local objective function
Define i as weapon number; j is the purposeNumbering; k is the aiming sensor number; h j；i ∈[0,1]Probability of hitting target j for weapon i; d (D) j；i ∈[0,1]Probability of damaging target j for weapon i; v (V) j E (0, 100) is the value of target j; t (T) i,j E (0, 100) is the threat level of the target j to the weapon i; s is S k = {0,1} is whether the kth sighting sensor is available, 0 is unavailable, 1 is available; wnum is the number of weapons; the Onum is the number of targets, and 2/3 targets are defined to be eliminated, so that the battlefield can be controlled to finish battle; on is the number of aiming sensors;
according to the requirements of a fire planning scene, on the premise of ensuring the damage of a target, the following five local objective functions are respectively constructed:
(1) Target value maximum function f 1
Target value maximum function f 1 The essence of (1) is that a hit strategy with the maximum total value of the damaged targets is found, the value V reflects the magnitude of the decision action of the battlefield situation, and the large value of a certain target means that the decision action of the target on the battlefield situation is large, for example, the value of a command target is larger than that of a logistics guarantee target. The quantification of the target value is generally derived from the past combat experience, the value is generally an integer, and the interval is [1,100 ]]Reference may be made to table 1.
TABLE 1 value and threat level of target field trend
The probability D of damage to the same target by different weapons in the hit condition exists, and meanwhile, different hit rates H exist when the weapons hit the target due to different internal and external conditions, so that the actual probability of damage to the target is represented by H.
Through analysis of the principle of fire striking, in the whole fire striking process, except the participation of the fire unit,the aiming unit is also required to be matched, and the fire striking task cannot be completed if the aiming unit is not available. Therefore, the targeting unit S needs to be screened while selecting the weapon preferentially, and the local objective function is expressed by h×d×s. The basic requirement of fire battlefield is that the target is destroyed, then the actual probability of destruction of the ith weapon striking the jth target is 1-pi (1-H j；i *D j；i ) Consider an aiming unit S k When the actual probability is 1-pi (1-H j；i *D j；i *S k )。
(2) Shortest function f of combat time 2
Shortest function f of combat time 2 The essence of this is that two-thirds of the total number of damaged objects can be used to determine the battlefield trend based on analysis of the past battlefield situation, thus definingShortest function f of combat time 2 Maximum function f with target value 1 Compared with the method, the striking strategy with the maximum total value of the damaged target is not changed, and the scope of the striking target is only reduced.
(3) Resource consumption minimum function f 3
Resource consumption minimum function f 3 The hit strategy with the maximum total value of the middle damaged target is the same as the maximum function f of the target value 1 And the shortest time of fight f 2 Except that the number of weapon resources Wnum is limited, the essence of this objective function is to achieve the maximum target total value of impact using the minimum number of weapons.
(4) Maximum target damage number function f 4
Resource consumption minimum function f 4 The essence of (a) is to ensure that each round of striking can destroy the maximum number of targets, different from the maximum function f of target value 1 Shortest function f of combat time 2 And resource consumption minimum function f 3 The value amounts are not distinguished between the targets, and all targets are equivalent. Therefore, the actual probability that all targets are destroyed simultaneously in each round of striking is multiplied by the total number of targets to obtain the number of destroyed targets, and the number is guaranteed to be the maximum value.
(5) Target threat maximum function f 5
Target threat maximum f 5 The essence of (a) is that the target combination with the greatest threat degree to weapons is preferentially hit, and for a multi-weapon battlefield, the threat to different weapons is different due to different internal and external properties of the same target, and the method is utilizedRepresenting the average threat degree of a certain target j to all weapons, and multiplying the average threat degree by the actual damage probability to obtain the maximum function f of the target threat 5 . This function is related to the target value maximum function f 1 The only difference is that the target threat level T is substituted for the target value V. For quantification of threat degrees, since threat degrees of the same target to different weapons are different, threat degrees to different weapons are quantified by floating up and down with the threat degrees in table 1 as a reference.
S2, constructing a global objective function
According to battlefield requirements, a global objective function is constructed by jointly combining and generalizing five local objective functions to express the battlefield requirements of complex situations.
Global objective function f 0 The method comprises the following steps:
i∈[0,Wnum],j∈[0,Onum]or (b)
Wherein a is a control parameter of whether to consider the target value, the value range is {0,1},0 is not considered, and 1 is considered; b is a control parameter whether the target threat degree is considered, the value range is {0,1},0 is not considered, and 1 is considered; c is a control parameter whether the weapon quantity is considered, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 1 In order to consider whether one or more of target value, target threat degree, combat time and resource consumption are taken as control parameters of battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 2 To consider whether the target number of lesions is the control parameter for battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered.
By selecting the control parameters, as shown in table 2, a combination of multiple local objective functions is obtained to realize multiple combat demands.
TABLE 2 conversion of global objective function to local objective function control parameter values
For example, 1: to achieve the battle requirement with minimum resource consumption and maximum target damage, the control parameters should be:
a＝1，b＝0，c＝1，λ 1 ＝1，λ 2 ＝1，j∈[0,Onum]
global objective function f 0 The method comprises the following steps:
for example 2: to achieve the battle requirement with the shortest battle time and the greatest target threat, the control parameters should be:
a＝1，b＝1，c＝0，λ 1 ＝1，λ 2 ＝0，
global objective function f 0 The method comprises the following steps:
for example 3: of course, many times, since the battlefield situation is unknown and the battle striking requirement cannot be determined, all striking modes should be satisfied, and at this time, the control parameters should be:
a＝1，b＝1，c＝1，λ 1 ＝1，λ 2 ＝1，
global objective function f 0 The method comprises the following steps:
s3, optimally solving the global objective function to finish fire planning
The fire planning of the multi-weapon system is essentially to carry out optimal solution by utilizing global objective functions of different battlefield requirements, and finally aims to sequentially calculate weapon units and aiming units corresponding to all targets by utilizing optimal solution methods such as heuristic genetic algorithm, ant colony genetic algorithm, simulated annealing genetic algorithm and the like, and calculate a plurality of groups of X (i, j, k) combinations as fire planning, wherein X (i, j, k) represents that weapon i is matched with aiming device j to strike target k.
As shown in fig. 2, X (3, 1, 4) represents the weapon 3 being deployed with the sight 1 to strike the target 4.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (2)
1. A method of constructing a fire planning objective function for battlefield multidimensional requirements, the method comprising the steps of:
s1, constructing a local objective function
Define i as weapon number; j is the target number; k is the aiming sensor number; h j；i ∈[0,1]Probability of hitting target j for weapon i; d (D) j；i ∈[0,1]Probability of damaging target j for weapon i; v (V) j E (0, 100) is the value of target j; t (T) i,j E (0, 100) is the threat level of the target j to the weapon i; s is S k = {0,1} is whether the kth sighting sensor is available, 0 is unavailable, 1 is available; wnum is the number of weapons; the Onum is the number of targets, and 2/3 targets are defined to be eliminated, so that the battlefield can be controlled to finish battle; on is the number of aiming sensors;
according to the requirements of a fire planning scene, on the premise of ensuring the damage of a target, the following five local objective functions are respectively constructed:
(1) Target value maximum function f 1
f 1 ＝∑V j (1-Π(1-H j；i *D j；i *S k ))i∈[0,Wnum],j∈[0,Onum],k∈[0,Pnum]
(2) Shortest function f of combat time 2
(3) Resource consumption minimum function f 3
(4) Maximum target damage number function f 4
f 4 ＝Onum*Π(1-Π(1-H j；i *D j；i *S k ))i∈[0,Wnum],j∈[0,Onum],k∈[0,Pnum]
(5) Target threat maximum function f 5
S2, constructing a global objective function
According to battlefield requirements, the global objective function f is constructed by jointly combining and generalizing five local objective functions 0 ：
i∈[0,Wnum],j∈[0,Onum]Or (b)
Wherein a is a control parameter of whether to consider the target value, the value range is {0,1},0 is not considered, and 1 is considered; b is a control parameter whether the target threat degree is considered, the value range is {0,1},0 is not considered, and 1 is considered; c is a control parameter whether the weapon quantity is considered, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 1 In order to consider whether one or more of target value, target threat degree, combat time and resource consumption are taken as control parameters of battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered; lambda (lambda) 2 In order to consider whether the target damage quantity is taken as a control parameter of battlefield requirements, the value range is {0,1},0 is not considered, and 1 is considered;
s3, optimally solving the global objective function to finish fire planning
And (3) carrying out optimal solution on the global objective function, sequentially solving weapon units and aiming units corresponding to all targets, and solving a plurality of groups of combinations of X (i, j, k) which are used as fire planning, wherein X (i, j, k) represents that a weapon i is matched with an aiming device j to strike the target k.
2. The construction method according to claim 1, wherein in step S3, the solution is performed using a heuristic genetic algorithm, an ant colony genetic algorithm or a simulated annealing genetic algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311110119.XA CN117077428A (en) | 2023-08-31 | 2023-08-31 | Construction method of firepower planning objective function aiming at battlefield multidimensional requirements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311110119.XA CN117077428A (en) | 2023-08-31 | 2023-08-31 | Construction method of firepower planning objective function aiming at battlefield multidimensional requirements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117077428A true CN117077428A (en) | 2023-11-17 |
Family
ID=88702159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311110119.XA Pending CN117077428A (en) | 2023-08-31 | 2023-08-31 | Construction method of firepower planning objective function aiming at battlefield multidimensional requirements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077428A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117809217A (en) * | 2023-12-26 | 2024-04-02 | 浙江大学 | Method and system for scouting and beating based on real-time single-stage target recognition |
-
2023
- 2023-08-31 CN CN202311110119.XA patent/CN117077428A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117809217A (en) * | 2023-12-26 | 2024-04-02 | 浙江大学 | Method and system for scouting and beating based on real-time single-stage target recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105302153B (en) | The planing method for the task of beating is examined in the collaboration of isomery multiple no-manned plane | |
| CN107886184B (en) | Multi-type air defense weapon mixed-programming fire group target distribution optimization method | |
| CN110083971B (en) | Self-explosion unmanned aerial vehicle cluster combat force distribution method based on combat deduction | |
| CN105844068B (en) | A kind of Q learning attack target assignment methods of Simulation-Oriented | |
| CN106779210B (en) | Algorithm of Firepower Allocation based on ant group algorithm | |
| CN107063255A (en) | A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm | |
| CN109460056A (en) | Unmanned plane cluster fight game decision-making method based on quantum krill group's mechanism of Evolution | |
| CN117077428A (en) | Construction method of firepower planning objective function aiming at battlefield multidimensional requirements | |
| CN113485456B (en) | Unmanned aerial vehicle group distributed online self-adaptive task planning method | |
| CN112364972B (en) | Unmanned combat vehicle team firepower distribution method based on deep reinforcement learning | |
| CN104950673A (en) | Method for distributing targets cooperatively attacked by unmanned aerial vehicle group | |
| CN114397911B (en) | Unmanned aerial vehicle cluster countermeasure decision-making method based on multiple intelligent agents | |
| CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
| CN112131730A (en) | Freezing analysis method and device for group intelligent unmanned system | |
| CN113553777B (en) | Anti-unmanned aerial vehicle swarm air defense deployment method, device, equipment and medium | |
| Li et al. | Multi-uav air combat weapon-target assignment based on genetic algorithm and deep learning | |
| Zhang et al. | A novel heterogeneous sensor-weapon-target cooperative assignment for ground-to-air defense by efficient evolutionary approaches | |
| CN116090356B (en) | Heterogeneous warhead multi-objective task planning method based on task reliability constraint | |
| CN110163502A (en) | A kind of more bullet collaboration multistage target assignment methods | |
| CN116151492B (en) | Auxiliary decision analysis system of combined combat system | |
| Cheng et al. | Weapon-target assignment of ballistic missiles based on Q-learning and genetic algorithm | |
| Song et al. | Multi-uav cooperative multi-target allocation method based on differential evolutionary algorithm | |
| Zhao et al. | Shuffled frog leaping algorithm with non-dominated sorting for dynamic weapon-target assignment | |
| CN112396288B (en) | Equipment system fire striking capability assessment method, device, equipment and medium | |
| CN114897267A (en) | Fire power distribution method and system for many-to-many intelligent agent cooperative battlefield scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |