CN116820121A - Unmanned aerial vehicle group joint investigation strategy generation method and terminal - Google Patents
Unmanned aerial vehicle group joint investigation strategy generation method and terminal Download PDFInfo
- Publication number
- CN116820121A CN116820121A CN202310544444.0A CN202310544444A CN116820121A CN 116820121 A CN116820121 A CN 116820121A CN 202310544444 A CN202310544444 A CN 202310544444A CN 116820121 A CN116820121 A CN 116820121A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- vehicle group
- information entropy
- probability
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000011159 matrix material Substances 0.000 claims abstract description 63
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 230000008447 perception Effects 0.000 claims description 35
- 238000012614 Monte-Carlo sampling Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005086 pumping Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002688 persistence Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method and a terminal for generating a joint investigation strategy of an unmanned aerial vehicle group, wherein the method comprises the following steps: performing grid division on a map of the region to be detected, and constructing probability information sets of all grids; calculating a probability matrix formed by unmanned aerial vehicle group detection according to an information entropy theory; calculating a weight matrix of the regional map grid according to a history heuristic algorithm; calculating to obtain corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix; selecting a plurality of positions with weighted information entropy meeting preset conditions for sensing, and unfolding and detecting the plurality of positions with detection priority by adjusting a controllable number of unmanned aerial vehicles; wherein the number of the plurality of locations is adapted to the current size of the unmanned aerial vehicle group. The invention can make reasonable investigation decisions meeting global optimum, so that unmanned aerial vehicle group collaborative investigation is more autonomous, flexible, accurate and efficient, and the efficiency of multi-unmanned aerial vehicle collaborative execution task is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a terminal for generating a joint investigation strategy of an unmanned aerial vehicle group.
Background
The unmanned aerial vehicle is an unmanned or remote-controlled aircraft, has the characteristics of low cost, low detectability, long endurance and the like, and is widely applied to the fields of the Internet of things and the like, for example, the unmanned aerial vehicle can be used as a base station for communication with ground or air wireless equipment, and can be used as a relay node for realizing signal relay and amplification, so that the coverage range of a wireless network is extended; in addition, the drone may provide energy support for ground or air wireless devices as a mobile power source. In recent years, unmanned aerial vehicles play an important role in reconnaissance, striking, interference and the like, and become an indispensable force in modern war. Development and use of unmanned aerial vehicles are being increased in various countries, and in particular, the fields of invisible unmanned aerial vehicles, attack unmanned aerial vehicles, group unmanned aerial vehicles and the like are being increased.
As the field Jing Jingpen of use of unmanned aerial vehicles increases, the cooperative investigation of unmanned aerial vehicle groups has attracted research interests of many scholars. The unmanned aerial vehicle group reconnaissance is a technology for performing target reconnaissance and data collection by the cooperative work of a system consisting of a plurality of unmanned aerial vehicles. Compared with single unmanned aerial vehicle reconnaissance, unmanned aerial vehicle crowd reconnaissance can improve reconnaissance efficiency and accuracy to can adapt to more complicated environment and task demand. However, because the number of unmanned aerial vehicle groups and the onboard energy of the unmanned aerial vehicle groups are limited, the investigation region range is often relatively large, so that how to formulate a reasonable and effective unmanned aerial vehicle investigation strategy is very important.
At present, unmanned aerial vehicle swarm reconnaissance has become a hotspot and leading edge field of research. The following are some prior art related to the present invention:
1. the cooperative control technology of multiple unmanned aerial vehicles comprises the following steps: the technology realizes task completion through cooperative combat among unmanned aerial vehicles. The unmanned aerial vehicles can cooperate with each other to complete the required tasks. For example, the multi-unmanned aerial vehicle collaborative flight method can be used for multi-unmanned aerial vehicle target tracking, track optimization, collaborative management, collaborative flight and task allocation, so that the multi-unmanned aerial vehicle collaborative flight has autonomy, flexibility and safety, and the efficiency of the multi-unmanned aerial vehicle collaborative execution of tasks is improved.
2. An autonomous unmanned aerial vehicle decision making technique: according to the intelligent unmanned aerial vehicle decision analysis technology, intelligent decision analysis is carried out on the unmanned aerial vehicle, so that the unmanned aerial vehicle can independently complete tasks and can autonomously process emergency situations. For example, a communication-decision-planning-control autonomous decision framework of unmanned aerial vehicle cluster multitasking is established, a centralized, fully distributed and mixed decision pattern is established according to a communication topological structure, on the basis, an inductive task reasoning decision model and a rational task reasoning decision model are respectively established, a solution framework of the model and a key technology solution way are determined, and the unmanned aerial vehicle cluster task decision has better guiding significance for planning and implementation of collaborative combat.
3. Multi-sensor fusion technique: the technology obtains scene information through a plurality of sensors, and then fuses the information, so that the cognition and decision capability of scenes are improved. For example, the unmanned aerial vehicle group combat collaborative navigation algorithm based on multi-sensor fusion can effectively track the enemy unmanned aerial vehicle group in the unmanned aerial vehicle group combat, and has high reliability and stability.
4. Artificial intelligence technology: the technology realizes the intelligent control of the unmanned aerial vehicle by learning and training data. For example, unmanned aerial vehicle cooperative multi-task allocation based on an ant colony algorithm can effectively solve the problem of unmanned aerial vehicle cooperative multi-task allocation. Unmanned aerial vehicle collaborative search based on a group intelligent algorithm constructs a multi-target and multi-constraint unmanned aerial vehicle cluster task allocation model based on a multi-travel business Model (MTSP). The feasibility and stability of the designed algorithm for solving the unmanned aerial vehicle collaborative search task allocation problem are verified by comparing experimental simulation with an original optimizing algorithm.
The technology is a mature technology in the unmanned aerial vehicle group reconnaissance, and can complement and cooperate with each other to more efficiently and accurately complete tasks. However, there are some drawbacks, such as lack of comprehensive knowledge of the environment when the unmanned aerial vehicle group performs investigation in the environment with incomplete information, and failure to grasp the real-time deployment situation of the enemy, so that reasonable investigation decisions meeting global optimization cannot be made, and no targeted method is available to evaluate and measure the incomplete information degree of the target environment and the corresponding investigation strategy generation method.
Accordingly, there is a need in the art for improvement.
Disclosure of Invention
The invention aims to solve the technical problems that aiming at the defects of the prior art, the invention provides a generation method and a terminal of a joint investigation strategy of an unmanned aerial vehicle group, so as to solve the technical problems that the traditional unmanned aerial vehicle group investigation technology cannot make reasonable investigation decisions meeting global optimum under the environment of incomplete information.
The technical scheme adopted for solving the technical problems is as follows:
in a first aspect, the present invention provides a method for generating a joint investigation policy of an unmanned aerial vehicle group, including:
performing grid division on a map of the region to be detected, and constructing probability information sets of all grids;
calculating a probability matrix formed by unmanned aerial vehicle group detection according to an information entropy theory;
calculating a weight matrix of the regional map grid according to a history heuristic algorithm;
calculating to obtain a corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix;
selecting a plurality of positions with weighted information entropy meeting preset conditions for sensing, and unfolding and detecting the plurality of positions with detection priority by adjusting a controllable number of unmanned aerial vehicles; wherein the number of the plurality of locations is adapted to the current size of the unmanned aerial vehicle group.
In one implementation, the meshing of the map of the area to be reconnaissad includes:
dividing the region to be detected into a group of grids with the same size to obtain divided grids;
the number of the divided grids is adapted to the number of the current unmanned aerial vehicles of the unmanned aerial vehicle group, and the size of the divided grids is adapted to the reconnaissance range of each unmanned aerial vehicle in the unmanned aerial vehicle group.
In one implementation manner, the calculating according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix to obtain the corresponding weighted information entropy includes:
each unmanned aerial vehicle corresponds to one reconnaissance grid, and all reconnaissance grids corresponding to the unmanned aerial vehicle group form a perception combination;
and extracting the perception combination according to the history heuristic algorithm and the Monte Carlo sampling algorithm.
In one implementation, the extracting the perceptual combination according to the history heuristic and a monte carlo sampling algorithm includes:
recording the extracted times and the perception result of the perception position in the perception combination when the perception combination is extracted each time;
setting the probability of all the sensing grids being pumped to be inversely proportional to the historical pumping times;
the information entropy value of the mesh that is not extracted is set as the information entropy value that continues to be stored historically.
In one implementation, the probability matrix is expressed in the form of:
wherein p is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid probability.
In one implementation, the weight matrix is expressed in the form of:
wherein w is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid weight.
In one implementation, the weighted information entropy is calculated by an information entropy formula:
p i is the probability of enemy occurrence within each grid.
In one implementation, the selecting the multiple positions with weighted information entropy meeting the preset condition to sense, and deploying the detection on the multiple positions with the detection priority by the unmanned aerial vehicle with the controlled number of the call sets includes:
judging whether the currently calculated weighted information entropy value is the minimum weighted information entropy or not according to the weighted information entropy value after probability normalization of the residual detection grid in the probability matrix;
if yes, recording the current perception combination;
if not, calculating the next perception combination;
selecting a perception combination with the minimum weighted information entropy value as a target area, and calculating the distances from all unmanned aerial vehicles to the target area;
and optimizing and invoking a controllable number of unmanned aerial vehicles according to the principle that the sum of the distances from all unmanned aerial vehicles to the destination is minimum, and unfolding and inspecting a plurality of positions with the inspection priority.
In a second aspect, the present invention provides a computer terminal comprising: the system comprises a processor and a memory, wherein the memory stores an unmanned aerial vehicle group joint investigation strategy generation program, and the unmanned aerial vehicle group joint investigation strategy generation program is used for realizing the operation of the unmanned aerial vehicle group joint investigation strategy generation method according to the first aspect when being executed by the processor.
In a third aspect, the present invention provides a computer readable storage medium storing a human-machine group joint investigation policy generation program for implementing the operations of the human-machine group joint investigation policy generation method according to the first aspect when the human-machine group joint investigation policy generation program is executed by a processor.
The technical scheme adopted by the invention has the following effects:
the invention provides an unmanned aerial vehicle group joint reconnaissance method oriented to a non-complete information area and based on weighted information entropy combined history heuristic tree search. Firstly, according to the reconnaissance range of the unmanned aerial vehicle in a specific problem, carrying out grid division on an area map to be reconnaissance, and constructing probability information sets of all grids based on historical data and a prediction method. Then, calculating a probability matrix formed by unmanned aerial vehicle group detection based on an information entropy theory, and calculating a weight matrix of the regional map grid based on a history heuristic algorithm; and calculating weighted information entropy by multiplying the information entropy corresponding to the probability matrix by the weight matrix, and finally selecting a plurality of positions with the smallest weighted information entropy and the most stable weighted information entropy for perception, wherein the number of perceived positions can be automatically adapted to the current scale of the unmanned aerial vehicle group, the unmanned aerial vehicle with the controllable number is regulated, and the plurality of positions with the detection priority are expanded and detected. The invention enables the unmanned aerial vehicle group collaborative reconnaissance to have autonomy, flexibility, accuracy and high efficiency, and improves the efficiency of the multi-unmanned aerial vehicle collaborative execution task.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for generating a joint investigation policy of a group of unmanned aerial vehicles in an implementation of the invention.
Fig. 2 is a diagram of an information set of meshing of areas to be scouted in one implementation of the invention.
FIG. 3 is an urban scene snapshot in one implementation of the invention.
FIG. 4 is a plot of mesh size partitioning according to one implementation of the invention.
Fig. 5 is a diagram of group communication of a drone in one implementation of the invention.
FIG. 6 is a diagram of an example probability matrix in one implementation of the invention.
FIG. 7 is a diagram of an example weight matrix in one implementation of the invention.
Fig. 8 is a scout grid map for which 3 drones are responsible in one implementation of the present invention.
Fig. 9 is a schematic diagram of the scout grid probability set 0 of fig. 8.
FIG. 10 is a schematic diagram of a target area map in one implementation of the invention.
Fig. 11 is a graph of probability matrix and weight matrix updates in fig. 10.
Fig. 12 is a functional schematic of a terminal in one implementation of the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear and clear, the present invention will be further described in detail below with reference to the accompanying drawings and examples. 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.
Exemplary method
In the technology which is mature in the unmanned aerial vehicle crowd reconnaissance, the unmanned aerial vehicle crowd reconnaissance can complement and cooperate with each other, and the task can be completed more efficiently and accurately. However, there are some drawbacks, such as lack of comprehensive knowledge of the environment when the unmanned aerial vehicle group performs investigation in the environment with incomplete information, and failure to grasp the real-time deployment situation of the enemy, so that reasonable investigation decisions meeting global optimization cannot be made, and no targeted method is available to evaluate and measure the incomplete information degree of the target environment and the corresponding investigation strategy generation method.
Aiming at the technical problems, the embodiment of the invention provides the generation method of the unmanned aerial vehicle group joint investigation strategy, which can enable the unmanned aerial vehicle group investigation technology to make reasonable investigation decisions meeting global optimum under the environment of incomplete information, thereby enabling the unmanned aerial vehicle group collaborative investigation to have autonomy, flexibility, accuracy and high efficiency and improving the efficiency of the multi-unmanned aerial vehicle collaborative execution task.
As shown in fig. 1, an embodiment of the present invention provides a method for generating a joint investigation policy of an unmanned aerial vehicle group, including the following steps:
step S100, meshing the map of the region to be detected, and constructing probability information sets of all meshes.
In this embodiment, the method for generating the joint investigation policy of the unmanned aerial vehicle group is applied to a terminal, where the terminal includes but is not limited to: and a computer, a mobile terminal and the like.
The embodiment discloses an unmanned aerial vehicle group joint reconnaissance method for a non-complete information area based on weighted information entropy and history heuristic tree search. The method combines the information entropy theory with the unmanned aerial vehicle group detection strategy, and specifically comprises the following steps:
firstly, according to the unmanned plane reconnaissance range in a specific reconnaissance problem, carrying out grid division on an area map to be reconnaissance, and constructing a probability information set of all grids based on historical data and a prediction method.
And secondly, calculating a probability matrix formed by unmanned aerial vehicle group detection based on an information entropy theory.
Then, a weight matrix of the regional map grid is calculated based on a historical heuristic, wherein the weight matrix describes other factors affecting the current detection effect, such as connectivity of the unmanned aerial vehicle group, distance from other units of the my, and the like. The product of the information entropy corresponding to the probability matrix and the weight matrix is the weighted information entropy.
And finally, selecting a plurality of positions with the minimum weighted information entropy (namely the most stable) to sense, wherein the number of the sensed positions can be automatically adapted to the current scale of the unmanned aerial vehicle group, and expanding and detecting the plurality of positions with the detection priority by modulating the controllable number of unmanned aerial vehicles.
The invention enables the unmanned aerial vehicle group collaborative reconnaissance to have autonomy, flexibility, accuracy and high efficiency, and improves the efficiency of the multi-unmanned aerial vehicle collaborative execution task.
Specifically, in one implementation manner of the present embodiment, step S100 includes the following steps:
step S101, dividing the region to be detected into a group of grids with the same size, and obtaining divided grids; the number of the divided grids is adapted to the number of the current unmanned aerial vehicles of the unmanned aerial vehicle group, and the size of the divided grids is adapted to the reconnaissance range of each unmanned aerial vehicle in the unmanned aerial vehicle group.
In this embodiment, when facing an incomplete information environment, the my unmanned aerial vehicle cannot obtain all environment information, where the unknown information in the incomplete information environment includes: the number of enemy unmanned aerial vehicles, the positions of the enemy unmanned aerial vehicles and the like, so that an unmanned aerial vehicle group is required to detect the environment; in the embodiment, the weighted information entropy is combined with the historical heuristic tree to search the unmanned aerial vehicle group for joint reconnaissance, wherein the information entropy is used for assisting in describing the incompleteness degree of the information of the current environment and is used as one of quantization characteristics of effectiveness of the unmanned aerial vehicle group reconnaissance strategy.
In one implementation manner of this embodiment, the area to be detected needs to be divided into a group of grids with the same size, so as to obtain the divided grids; as shown in fig. 2, fig. 2 gives a simple example that the area as a scout object can be divided into 4 grid areas, wherein each grid area contains two possible cases, namely, two possible cases where a scout object is present and no scout object is present. Only when the unmanned aerial vehicle reaches a certain grid area, the real situation of the unmanned aerial vehicle can be ascertained. In this case there are 16 different possibilities, which 16 possibilities are indistinguishable and can be regarded as one information set, as shown with reference to fig. 2. The information set contains a large number of possible states that cannot be determined. In the invention, the aim of unmanned aerial vehicle group investigation is to obtain more unknown incomplete information as much as possible.
For the 16 different possibilities mentioned above, in case the area is not scouted, a set of probability information for all grids can be constructed based on historical data and prediction methods, for example: according to historical data of unmanned aerial vehicle group reconnaissance, scene data similar to the current scene is searched, and prediction is carried out by using a similar available reconnaissance method (strategy), so that probability information sets of all grids are constructed.
As shown in fig. 1, in an implementation manner of the embodiment of the present invention, the method for generating the joint investigation policy of the unmanned aerial vehicle group further includes the following steps:
step S200, calculating a probability matrix formed by unmanned aerial vehicle group detection according to an information entropy theory;
step S300, calculating a weight matrix of the regional map grid according to a historical heuristic algorithm;
step S400, calculating to obtain corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix.
In this embodiment, the information entropy is used to assist in describing the incompleteness of the information of the current environment, and is used as one of the quantization features of the effectiveness of the unmanned aerial vehicle group detection strategy.
The concept of entropy derives from thermophysics, a measure of the degree of disorder of the movement of disordered molecules. The theory of information entropy is proposed by the parent claude-ale Wu De shannon of the theory of information, and the uncertainty of the theory of information is measured according to the probability of occurrence of a plurality of symbols of an information source. The more ordered a system is, the lower the entropy of information is; whereas the more chaotic it is, the higher its information entropy is.
The specific idea of the information entropy theory is as follows: consider n uncertain events, each with probability of p1, p2, …, pn, respectively. These events constitute a sample space U. The uncertainty of this sample space is denoted by H (U). It is known from the conventional principle that uncertainty of a sample space is maximum when occurrence probabilities of all events in the sample space are equal; the uncertainty of the sample space is minimal when one event in the sample space is necessarily occurring and the other events are necessarily not occurring. Namely:
at the same time, when the probability of occurrence of all events in the sample space is equal, the larger the sample space size, the larger the uncertainty should be. If the uncertainty of the upwardly facing surface when throwing a coin should be smaller than the uncertainty of the upwardly facing surface when throwing a dice. Namely:
should be a monotonically increasing function (2) that increases with increasing n
In addition, if an uncertainty event is decomposed into several persistence events, the uncertainty of the original event should be equal to the weighted sum of the uncertainties of the decomposed persistence events, and it should also be ensured that the function is a continuous function for a fixed natural number n. Combining these basic principles, shannon gives a function that is simple enough and meets all the requirements, as follows:
the information entropy formula smartly expresses the uncertainty of the information by a determined function, has proved the rationality and superiority in long-time rivers, and leads the research and development of modern information theory.
According to the invention, the information entropy theory is combined with the unmanned aerial vehicle group detection strategy, namely, a plurality of positions with the minimum (i.e. the most stable) weighted information entropy of the detected real-time information set are selected for sensing.
Specifically, in one implementation manner of the present embodiment, step S400 includes the following steps:
step S401, each unmanned aerial vehicle corresponds to one reconnaissance grid, and all reconnaissance grids corresponding to the unmanned aerial vehicle group are combined into a perception combination;
and step S402, extracting the perception combination according to the history heuristic algorithm and the Monte Carlo sampling algorithm.
In one implementation manner of this embodiment, step S402 includes the following steps:
step S402a, when the sensing combination is extracted each time, the extracted times and the sensing result of the sensing position in the sensing combination are recorded;
step S402b, the probability that all the sensing grids are pumped is set to be inversely proportional to the historical pumping times;
step S402c, the information entropy value of the grid that is not extracted is set as the information entropy value stored in the continuation history.
In this embodiment, when the unmanned aerial vehicle group performs reconnaissance, the incomplete information scene serving as the detection area is first abstracted into gridding data, as shown in fig. 3, the grid division of the current scene is represented in a matrix form, and the size of each grid is divided according to the reconnaissance range of the unmanned aerial vehicle, so as to obtain a divided grid.
As shown in fig. 4, the detection range of the unmanned aerial vehicle is an area in a circle, a square area in the area is selected as a grid, the detection range of one unmanned aerial vehicle can completely cover one grid, and a= { a1, a2, an } is adopted to represent a series of perceived positions, and each position corresponds to one grid. Taking i= { h1, h2,..hn } as an example of fig. 2, all real-time situations that may occur for the current target area, i= { (none ), (none, there)..there is (there is ) }, totaling the possible states in 16. Let pi denote the probability of occurrence of a scout object for a certain mesh of hi and wi denote the weight of a certain mesh of hi.
One unmanned aerial vehicle can only detect one grid at a certain moment, the positions of a plurality of sensing grids corresponding to the unmanned aerial vehicle group form a sensing combination, when the order of magnitude of the sensing combination is larger, all the sensing combinations cannot be directly traversed, and the sensing combination is extracted based on a history heuristic algorithm and Monte Carlo sampling. And when the sensing combination is extracted, recording the extracted times and the sensing results of the sensing positions in the sensing combination, wherein when the sensing combination is extracted next time, the probability of all sensing grids being extracted is inversely proportional to the historical extraction times, namely, the more the times that a certain sensing position is extracted, the smaller the probability of being extracted backwards. The non-extracted grids continue the historically stored entropy values of the information.
pi is related to the occurrence times of the enemy unmanned aerial vehicle in the grid, the more the enemy occurrence times are, the larger pi is, and the probabilities of all grids form a probability matrix. The probability matrix is related to the historically time nodes of the entire scout area because the probability of the occurrence of a scout object at each grid at different times is different. The probability matrix is expressed as follows:
wherein p is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid probability.
The weighting matrix is used to describe other influencing factors of a specific problem in the unmanned aerial vehicle group investigation process. In practice, it relates to the effects of connectivity, coordination with ground synchronization assistance units, terrain, weather, electromagnetic environment, etc. For example, to ensure that information detected by the unmanned aerial vehicle can be timely transmitted back to the command system, it is necessary to ensure that the unmanned aerial vehicle groups form a network capable of communicating with each other. This requires that the drone cannot be too far from other drones. wi and the connectivity of the present area to the my drone group, distance to other units of the my, etc., and the weight matrix is related to the historic time nodes of the entire scout area, since different time drone groups are at different distances from other units of the my. Taking the connectivity of the unmanned aerial vehicle group as an example, the unmanned aerial vehicle group can communicate with each other in a certain range to share the information obtained by each other, as shown in fig. 5, assuming that there are 3 unmanned aerial vehicles currently, two perception combinations a and B can be selected, the red circle represents the unmanned aerial vehicle, the blue circle represents the communication range of the unmanned aerial vehicle, it can be seen that the unmanned aerial vehicle group in the perception combination a cannot communicate, and the unmanned aerial vehicle group in the perception combination B can communicate, so that the grid weights of several grids in the perception combination B can be higher. The expression form of the weight matrix is as follows:
wherein w is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid weight.
In summary, the weighted entropy of each situation can be calculated by the entropy formula:
p i is the probability of enemy occurrence within each grid.
In this embodiment, when facing an incomplete information environment, due to lack of knowledge of environmental information and enemy information, and no efficient method for measuring the incomplete information degree of the target environment, a suitable unmanned aerial vehicle group detection strategy is often not generated. The embodiment of the invention creates a new key point by combining weighted information entropy and an unmanned aerial vehicle group reconnaissance strategy, and describing the incomplete information degree of the current environment by using the information entropy to acquire enemy information as much as possible. When a reconnaissance area is selected, a history heuristic algorithm is utilized to extract a perception position combination, and the perception position combination with the minimum weighted information entropy is selected for reconnaissance, so that the efficiency and the accuracy of the unmanned aerial vehicle group reconnaissance are greatly improved.
As shown in fig. 1, in an implementation manner of the embodiment of the present invention, the method for generating the joint investigation policy of the unmanned aerial vehicle group further includes the following steps:
and S500, selecting a plurality of positions with weighted information entropy meeting preset conditions for sensing, and unfolding and detecting the plurality of positions with detection priority by regulating a controllable number of unmanned aerial vehicles.
In this embodiment, the number of the plurality of locations is adapted to the current size of the unmanned aerial vehicle group.
Specifically, in one implementation manner of the present embodiment, step S500 includes the following steps:
step S501, judging whether the currently calculated weighted information entropy value is the minimum weighted information entropy or not according to the weighted information entropy value after probability normalization of the residual detection grid in the probability matrix;
step S502, if yes, recording the current perception combination;
step S503, if not, calculating the next perception combination;
step S504, selecting a perception combination with the minimum weighted information entropy value as a target area, and calculating the distances from all unmanned aerial vehicles to the target area;
in step S505, a controllable number of unmanned aerial vehicles are optimized and invoked to develop a investigation for a plurality of positions with investigation priority, based on the principle that the sum of the distances from all unmanned aerial vehicles to the destination is the smallest.
The following describes the generation method of the unmanned aerial vehicle group joint investigation strategy in the embodiment through an actual application scenario:
firstly, dividing a region to be detected into a group of grids with the same size, and mapping the divided grids into a probability matrix and a weight matrix, wherein the number of the detection grids can be automatically adapted to the current scale of the unmanned aerial vehicle group; the probability matrix and the weight matrix are shown in fig. 6 and fig. 7 respectively, the region to be scouted is divided into 16 grids, and the probability and the weight of each grid are different.
Then, each unmanned aerial vehicle corresponds to a reconnaissance grid, and the reconnaissance grids corresponding to all unmanned aerial vehicles form a perception combination. As shown in fig. 8, in this embodiment, there are 3 unmanned aerial vehicles, and the 3 detection grids responsible for the 3 unmanned aerial vehicles are the positions of circles, and these 3 detection grids form a sensing combination. Searching a perception combination by using a heuristic algorithm based on history, and setting the probability of a detection grid in the combination to zero; as shown in fig. 9, the probability of the 3 unmanned aerial vehicle responsible detection grid is set to 0.
Then, calculating a weighted information entropy value after probability normalization of the residual detection grid, comparing whether the weighted information entropy value is the minimum weighted information entropy, and if so, recording the current perception combination; if not, the next perceptual combination is calculated.
Then, after the calculation is completed, the perceptual combination with the smallest weighted information entropy value is selected as the target area, as shown in fig. 10.
And finally, calculating the distance from all the unmanned aerial vehicles to the target area, and nearby assigning unmanned aerial vehicles, wherein the sum of the distances from all the unmanned aerial vehicles to the destination is minimum.
After the drone scouts to the target area, the probability matrix and the weight matrix are updated, and the updated matrix is shown in fig. 11.
The invention uses the weighted information entropy to evaluate and measure the incomplete information degree of the target environment, generates a high-efficiency flexible unmanned aerial vehicle group detection strategy, realizes the detection, positioning and tracking of the moving object in the detection area, and greatly improves the efficiency of the unmanned aerial vehicle group to execute the detection task; the original unmanned aerial vehicle group reconnaissance technology is mainly aimed at reconnaissance of fixed targets, and is not applicable if the targets move. Therefore, the method records the historical moving track of the target in a probability matrix mode, thereby improving the searching precision and efficiency.
The following technical effects are achieved through the technical scheme:
the embodiment provides an unmanned aerial vehicle group joint reconnaissance method for a non-complete information area based on weighted information entropy combined with historical heuristic tree search, and the method combines an information entropy theory with an unmanned aerial vehicle group reconnaissance strategy. Firstly, according to the reconnaissance range of the unmanned aerial vehicle in a specific problem, carrying out grid division on an area map to be reconnaissance, and constructing probability information sets of all grids based on historical data and a prediction method. Then, calculating a probability matrix formed by unmanned aerial vehicle group detection based on an information entropy theory, and calculating a weight matrix of the regional map grid based on a history heuristic algorithm; and calculating weighted information entropy by multiplying the information entropy corresponding to the probability matrix by the weight matrix, and finally selecting a plurality of positions with the smallest weighted information entropy and the most stable weighted information entropy for perception, wherein the number of perceived positions can be automatically adapted to the current scale of the unmanned aerial vehicle group, the unmanned aerial vehicle with the controllable number is regulated, and the plurality of positions with the detection priority are expanded and detected. According to the embodiment, the unmanned aerial vehicle group collaborative reconnaissance is enabled to be more autonomous, flexible, accurate and efficient, and the efficiency of the multi-unmanned aerial vehicle collaborative execution task is improved.
Exemplary apparatus
Based on the above embodiment, the present invention further provides a computer terminal, including: the system comprises a processor, a memory, an interface, a display screen and a communication module which are connected through a system bus; wherein the processor is configured to provide computing and control capabilities; the memory includes a storage medium and an internal memory; the storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and computer programs in the storage medium; the interface is used for connecting external equipment, such as mobile terminals, computers and other equipment; the display screen is used for displaying corresponding information; the communication module is used for communicating with a cloud server or a mobile terminal.
The computer program is configured to implement the operations of a method for generating a joint investigation strategy of a group of unmanned aerial vehicles when executed by the processor.
It will be appreciated by those skilled in the art that the functional block diagram shown in FIG. 12 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer terminal to which the present inventive arrangements may be implemented, as a specific computer terminal may include more or fewer components than those shown, or may be combined with certain components or have a different arrangement of components.
In one embodiment, there is provided a computer terminal, including: the system comprises a processor and a memory, wherein the memory stores an unmanned aerial vehicle group joint investigation strategy generation program, and the unmanned aerial vehicle group joint investigation strategy generation program is used for realizing the operation of the unmanned aerial vehicle group joint investigation strategy generation method when being executed by the processor.
In one embodiment, a computer readable storage medium is provided, wherein the computer readable storage medium stores an unmanned aerial vehicle group joint investigation policy generation program, which when executed by the processor is configured to implement the operations of the unmanned aerial vehicle group joint investigation policy generation method as described above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program comprising instructions for the relevant hardware, the computer program being stored on a non-volatile storage medium, the computer program when executed comprising the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory.
In summary, the invention provides a method and a terminal for generating a joint investigation strategy of an unmanned aerial vehicle group, wherein the method comprises the following steps: performing grid division on a map of the region to be detected, and constructing probability information sets of all grids; calculating a probability matrix formed by unmanned aerial vehicle group detection according to an information entropy theory; calculating a weight matrix of the regional map grid according to a history heuristic algorithm; calculating to obtain corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix; selecting a plurality of positions with weighted information entropy meeting preset conditions for sensing, and unfolding and detecting the plurality of positions with detection priority by adjusting a controllable number of unmanned aerial vehicles; wherein the number of the plurality of locations is adapted to the current size of the unmanned aerial vehicle group. According to the invention, the unmanned aerial vehicle group reconnaissance technology can make reasonable reconnaissance decisions meeting global optimum in the environment of incomplete information, so that unmanned aerial vehicle group cooperative reconnaissance is more autonomous, flexible, accurate and efficient, and the efficiency of the cooperative execution of tasks by multiple unmanned aerial vehicles is improved.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (10)
1. The generation method of the unmanned aerial vehicle group joint investigation strategy is characterized by comprising the following steps of:
performing grid division on a map of the region to be detected, and constructing probability information sets of all grids;
calculating a probability matrix formed by unmanned aerial vehicle group detection according to an information entropy theory;
calculating a weight matrix of the regional map grid according to a history heuristic algorithm;
calculating to obtain a corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix;
selecting a plurality of positions with weighted information entropy meeting preset conditions for sensing, and unfolding and detecting the plurality of positions with detection priority by adjusting a controllable number of unmanned aerial vehicles; wherein the number of the plurality of locations is adapted to the current size of the unmanned aerial vehicle group.
2. The method for generating the joint investigation strategy of the unmanned aerial vehicle group according to claim 1, wherein the meshing of the map of the area to be investigated comprises:
dividing the region to be detected into a group of grids with the same size to obtain divided grids;
the number of the divided grids is adapted to the number of the current unmanned aerial vehicles of the unmanned aerial vehicle group, and the size of the divided grids is adapted to the reconnaissance range of each unmanned aerial vehicle in the unmanned aerial vehicle group.
3. The method for generating the joint investigation policy of the unmanned aerial vehicle group according to claim 1, wherein the calculating the corresponding weighted information entropy according to the product of the information entropy corresponding to the probability matrix and each weight in the weight matrix comprises:
each unmanned aerial vehicle corresponds to one reconnaissance grid, and all reconnaissance grids corresponding to the unmanned aerial vehicle group form a perception combination;
and extracting the perception combination according to the history heuristic algorithm and the Monte Carlo sampling algorithm.
4. The method for generating a joint scout strategy for an unmanned aerial vehicle cluster according to claim 3, wherein said extracting the perceptual combination according to the history heuristic algorithm and the monte carlo sampling algorithm comprises:
recording the extracted times and the perception result of the perception position in the perception combination when the perception combination is extracted each time;
setting the probability of all the sensing grids being pumped to be inversely proportional to the historical pumping times;
the information entropy value of the mesh that is not extracted is set as the information entropy value that continues to be stored historically.
5. The method for generating the joint investigation strategy of the unmanned aerial vehicle cluster according to claim 1, wherein the probability matrix is expressed in the form of:
wherein p is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid probability.
6. The method for generating the joint investigation strategy of the unmanned aerial vehicle group according to claim 1, wherein the weight matrix is expressed in the form of:
wherein w is ij I and j in (a) represent the number of rows and columns, respectively, of the current grid weight.
7. The method for generating the joint investigation strategy of the unmanned aerial vehicle group according to claim 1, wherein the weighted information entropy is calculated by an information entropy formula:
p i is the probability of enemy occurrence within each grid.
8. The method for generating the joint investigation strategy of the unmanned aerial vehicle group according to claim 1, wherein the selecting the plurality of positions where the weighted information entropy satisfies the preset condition is performed with perception, and the deploying the investigation for the plurality of positions with the investigation priority by the dispatching of the controllable number of unmanned aerial vehicles comprises:
judging whether the currently calculated weighted information entropy value is the minimum weighted information entropy or not according to the weighted information entropy value after probability normalization of the residual detection grid in the probability matrix;
if yes, recording the current perception combination;
if not, calculating the next perception combination;
selecting a perception combination with the minimum weighted information entropy value as a target area, and calculating the distances from all unmanned aerial vehicles to the target area;
and optimizing and invoking a controllable number of unmanned aerial vehicles according to the principle that the sum of the distances from all unmanned aerial vehicles to the destination is minimum, and unfolding and inspecting a plurality of positions with the inspection priority.
9. A computer terminal, comprising: the system comprises a processor and a memory, wherein the memory stores an unmanned aerial vehicle group joint investigation strategy generation program, and the unmanned aerial vehicle group joint investigation strategy generation program is used for realizing the operation of the unmanned aerial vehicle group joint investigation strategy generation method according to any one of claims 1-8 when being executed by the processor.
10. A computer readable storage medium, wherein the computer readable storage medium stores an unmanned aerial vehicle group joint investigation policy generation program, which when executed by a processor is configured to implement the operations of the unmanned aerial vehicle group joint investigation policy generation method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310544444.0A CN116820121A (en) | 2023-05-15 | 2023-05-15 | Unmanned aerial vehicle group joint investigation strategy generation method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310544444.0A CN116820121A (en) | 2023-05-15 | 2023-05-15 | Unmanned aerial vehicle group joint investigation strategy generation method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116820121A true CN116820121A (en) | 2023-09-29 |
Family
ID=88119355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310544444.0A Pending CN116820121A (en) | 2023-05-15 | 2023-05-15 | Unmanned aerial vehicle group joint investigation strategy generation method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116820121A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106959700A (en) * | 2017-03-21 | 2017-07-18 | 北京航空航天大学 | A kind of unmanned aerial vehicle group collaboration patrol tracing path planing method based on upper limit confidential interval algorithm |
| CN110262563A (en) * | 2018-05-23 | 2019-09-20 | 中国海洋大学 | Multiple no-manned plane collaboratively searching mesh calibration method waterborne |
| CN110502031A (en) * | 2019-08-02 | 2019-11-26 | 中国航空无线电电子研究所 | The isomery unmanned plane cluster of task based access control demand cooperates with optimal configuration method |
| CN111401168A (en) * | 2020-03-06 | 2020-07-10 | 上海神添实业有限公司 | Multi-layer radar feature extraction and selection method for unmanned aerial vehicle |
| CN111680934A (en) * | 2020-06-30 | 2020-09-18 | 西安电子科技大学 | Unmanned aerial vehicle task allocation method based on group entropy and Q learning |
| RU2020128891A (en) * | 2020-08-31 | 2021-02-08 | ||
| US20210124901A1 (en) * | 2019-10-28 | 2021-04-29 | The Chinese University Of Hong Kong | Systems and methods for place recognition based on 3d point cloud |
| CN113391644A (en) * | 2021-06-11 | 2021-09-14 | 中新国际联合研究院 | Unmanned aerial vehicle shooting distance semi-automatic optimization method based on image information entropy |
| CN114202010A (en) * | 2021-10-25 | 2022-03-18 | 北京仿真中心 | Information entropy-based complex system networked modeling method, device and medium |
| CN115840463A (en) * | 2022-11-23 | 2023-03-24 | 北京华如科技股份有限公司 | Data processing method and device for unmanned aerial vehicle cluster cooperative reconnaissance |
-
2023
- 2023-05-15 CN CN202310544444.0A patent/CN116820121A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106959700A (en) * | 2017-03-21 | 2017-07-18 | 北京航空航天大学 | A kind of unmanned aerial vehicle group collaboration patrol tracing path planing method based on upper limit confidential interval algorithm |
| CN110262563A (en) * | 2018-05-23 | 2019-09-20 | 中国海洋大学 | Multiple no-manned plane collaboratively searching mesh calibration method waterborne |
| CN110502031A (en) * | 2019-08-02 | 2019-11-26 | 中国航空无线电电子研究所 | The isomery unmanned plane cluster of task based access control demand cooperates with optimal configuration method |
| US20210124901A1 (en) * | 2019-10-28 | 2021-04-29 | The Chinese University Of Hong Kong | Systems and methods for place recognition based on 3d point cloud |
| CN111401168A (en) * | 2020-03-06 | 2020-07-10 | 上海神添实业有限公司 | Multi-layer radar feature extraction and selection method for unmanned aerial vehicle |
| CN111680934A (en) * | 2020-06-30 | 2020-09-18 | 西安电子科技大学 | Unmanned aerial vehicle task allocation method based on group entropy and Q learning |
| RU2020128891A (en) * | 2020-08-31 | 2021-02-08 | ||
| CN113391644A (en) * | 2021-06-11 | 2021-09-14 | 中新国际联合研究院 | Unmanned aerial vehicle shooting distance semi-automatic optimization method based on image information entropy |
| CN114202010A (en) * | 2021-10-25 | 2022-03-18 | 北京仿真中心 | Information entropy-based complex system networked modeling method, device and medium |
| CN115840463A (en) * | 2022-11-23 | 2023-03-24 | 北京华如科技股份有限公司 | Data processing method and device for unmanned aerial vehicle cluster cooperative reconnaissance |
Non-Patent Citations (3)
| Title |
|---|
| WANG, JINQUAN 等: "Double Unmanned Aerial Vehicle’s Path Planning for Scout via Cross-Entropy Method", 8TH ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, 1 January 2007 (2007-01-01), pages 632 - 635 * |
| 张加佳: "非完备信息机器博弈中风险及对手模型的研究", 信息科技辑, pages 29 - 33 * |
| 王文 等: "基于策略多样性熵指标的无人机群智系统激发-汇聚程度度量方法研究", 中国科学, 15 March 2023 (2023-03-15), pages 547 - 564 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Distributed trajectory optimization for multiple solar-powered UAVs target tracking in urban environment by Adaptive Grasshopper Optimization Algorithm | |
| Tang et al. | Dynamic reallocation model of multiple unmanned aerial vehicle tasks in emergent adjustment scenarios | |
| CN109711087B (en) | UUV dynamic threat situation assessment method | |
| Odonkor et al. | Distributed operation of collaborating unmanned aerial vehicles for time-sensitive oil spill mapping | |
| CN108897312A (en) | Lasting supervised path planing method of more unmanned vehicles to extensive environment | |
| Wang et al. | Virtual reality technology of multi uavearthquake disaster path optimization | |
| CN108196586A (en) | Unmanned aerial vehicle (UAV) control method, apparatus and storage medium | |
| Olofsson et al. | Multi-agent informed path planning using the probability hypothesis density | |
| CN116560406A (en) | Unmanned aerial vehicle cluster collaborative planning and autonomous scheduling method | |
| CN113495577B (en) | Unmanned aerial vehicle cluster sensor model correction method for digital twin simulation | |
| CN113536564B (en) | Unmanned bee colony autonomous collaborative assessment method and system based on virtual simulation | |
| Grasso et al. | A decision support system for optimal deployment of sonobuoy networks based on sea current forecasts and multi-objective evolutionary optimization | |
| Pannetier et al. | Wireless sensor network for tactical situation assessment | |
| CN116518979B (en) | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium | |
| Zu et al. | Research on UAV path planning method based on improved HPO algorithm in multi-task environment | |
| CN116820121A (en) | Unmanned aerial vehicle group joint investigation strategy generation method and terminal | |
| US20220107628A1 (en) | Systems and methods for distributed hierarchical control in multi-agent adversarial environments | |
| CN106996789B (en) | Multi-airborne radar cooperative detection airway planning method | |
| Mohammad et al. | Software Complex for Modelling Routing in Heterogeneous Model of Wireless Sensor Network | |
| Stodola et al. | Tactical and operational software library | |
| Zaier et al. | Vision-based UAV tracking using deep reinforcement learning with simulated data | |
| Vasunina et al. | Algorithm of UAV trajectory creation for data collecting from seismological sensors | |
| Bandari et al. | An optimal UAV height localization for maximum target coverage using improved deer hunting optimization algorithm | |
| Li et al. | A path planning for one UAV based on geometric algorithm | |
| Liang et al. | Optimization of spatiotemporal clustering for target tracking from multisensor data |
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 |