CN115494864B - Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm - Google Patents
Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm Download PDFInfo
- Publication number
- CN115494864B CN115494864B CN202211155444.3A CN202211155444A CN115494864B CN 115494864 B CN115494864 B CN 115494864B CN 202211155444 A CN202211155444 A CN 202211155444A CN 115494864 B CN115494864 B CN 115494864B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- task
- aerial vehicle
- target
- tasks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims abstract description 73
- 239000003016 pheromone Substances 0.000 claims abstract description 69
- 238000009826 distribution Methods 0.000 claims abstract description 19
- 238000012790 confirmation Methods 0.000 claims description 31
- 238000003825 pressing Methods 0.000 claims description 23
- 238000005457 optimization Methods 0.000 claims description 17
- 241000257303 Hymenoptera Species 0.000 claims description 16
- 230000001629 suppression Effects 0.000 claims description 16
- 230000008901 benefit Effects 0.000 claims description 12
- 230000007704 transition Effects 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000005728 strengthening Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 description 4
- 238000010200 validation analysis Methods 0.000 description 4
- 101150039208 KCNK3 gene Proteins 0.000 description 2
- 101150083764 KCNK9 gene Proteins 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009024 positive feedback mechanism Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a heterogeneous multi-unmanned aerial vehicle task allocation method based on an ant colony algorithm, which comprises the steps of classifying current candidate tasks, and determining candidate unmanned aerial vehicle sequences according to classification results and characteristics of different unmanned aerial vehicles; respectively selecting a next task and a undertaker of the next task according to the heuristic information and the pheromone concentration matrix, and if all candidate tasks of the current unmanned aerial vehicle do not meet constraint conditions, reselecting the unmanned aerial vehicle and calculating selection probability until the selection probability of each candidate task is not all zero; selecting one candidate task to complete one-time allocation, and updating a candidate task sequence and a candidate unmanned aerial vehicle sequence; repeatedly selecting unmanned aerial vehicles, calculating probability, and selecting tasks until all tasks are distributed; updating the pheromone concentration, repeating iteration until the preset iteration times are reached, and determining the optimal distribution scheme according to the optimal ant colony.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle control, in particular to a heterogeneous multi-unmanned aerial vehicle task allocation method based on an ant colony algorithm.
Background
Under the background that modern war has high complexity, unmanned aerial vehicle is flexible in realization by virtue of tactics, strong in continuous combat capability, low in platform cost and the like, and the unmanned aerial vehicle has become a key development object of a plurality of military countries. In the battlefield background, the task types and the task scale are large, the single unmanned aerial vehicle is difficult to meet the requirements, and the heterogeneous unmanned aerial vehicles are required to cooperate and cooperate with each other for the tasks. Thus, a good task allocation method is critical for multi-unmanned systems to exert their maximum utility.
In the related art, the deterministic method is mature. After the mission planning model is built, a breadth-first search or a depth-first search may be employed to list all feasible solutions within the feasible region to find the optimal price. In addition, integer programming can represent small-scale mission planning problems by establishing objective functions and constraints, depending on the intended purpose and goal. Among them, hungarian algorithm, simplex algorithm, branch-and-bound method, etc. are more common integer programming methods. However, the deterministic method is only suitable for solving a simple model, and as the number of unmanned aerial vehicles and tasks increases, the complexity of the algorithm greatly increases, the calculation time increases exponentially, the efficiency is low, and the fault tolerance is poor.
Compared with a deterministic method, a random method balances the solving precision and the solving time, can obtain an optimal solution or a suboptimal solution in a shorter time, has certain intelligence and parallelism, has the characteristics of easy realization, low complexity and the like, is suitable for treating large complex problems, and is widely applied in recent years. Particularly intelligent algorithms including particle swarm algorithms and genetic algorithms. However, as unmanned aerial vehicle technology matures, unmanned aerial vehicle types are increasingly being divided, and different types of unmanned aerial vehicles are designed to perform specific tasks. The traditional intelligent algorithm does not consider the isomerism among unmanned aerial vehicles or only considers the isomerism of basic attributes such as speed among unmanned aerial vehicles, and can not enable the isomerism unmanned aerial vehicles to correspond to the assigned tasks, and is not applicable to modern battlefields any more.
Disclosure of Invention
In view of the above, the invention provides a heterogeneous multi-unmanned aerial vehicle task allocation method based on an ant colony algorithm, which can solve the problem of heterogeneous multi-unmanned aerial vehicle task allocation under the background of complex time sequence requirements among various tasks. The time sequence requirement is met by means of maintaining the candidate task sequence, and the requirement corresponding to the executed task of the heterogeneous unmanned aerial vehicle is met by means of maintaining the candidate unmanned aerial vehicle sequence.
In order to achieve the above purpose, the technical scheme of the invention comprises the following steps:
Step 1: initializing ant colony according to the scale of the task, wherein one ant colony forms an allocation scheme together, one ant represents one unmanned aerial vehicle, and any ant in any ant colony has a respective pheromone concentration matrix; initializing unmanned aerial vehicle parameters at the same time; the unmanned aerial vehicle parameters include the speed of the unmanned aerial vehicle, the unmanned aerial vehicle type, unmanned aerial vehicle coordinates, the type of target, the coordinates of the target, and the type of task.
Step 2: aiming at a task to be executed of the heterogeneous multi-unmanned aerial vehicle system, constructing a candidate task sequence; and constructing a candidate unmanned aerial vehicle sequence according to the types of the current candidate tasks and the characteristics of the heterogeneous unmanned aerial vehicle for executing different types of tasks.
Step 3: and respectively selecting a next task and a undertaker of the next task according to the heuristic information and the pheromone concentration matrix. And if the current unmanned aerial vehicle cannot be matched with all the candidate tasks, deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence, and repeating the step 3 until the matching is completed.
Step 4: updating the candidate task sequence, updating the candidate unmanned aerial vehicle sequence, updating the position of the unmanned aerial vehicle, and repeatedly executing the selection and task allocation of the unmanned aerial vehicle in the steps 3 and 4 until all tasks are allocated to be completed, thereby obtaining an allocation matrix of the current iteration.
Step 5: and calculating an optimal target value of the current iteration time according to the distribution matrix of the current iteration time, and if the optimal target value of the current iteration time is better than the optimal target value of the optimal distribution matrix, updating the optimal distribution matrix by utilizing the distribution matrix of the current iteration time.
Updating the pheromone concentration matrix according to the optimal target value of the current iteration, repeatedly executing the steps 2-5 until the set iteration times are reached, obtaining a final optimal distribution matrix, and performing task distribution of the heterogeneous multi-unmanned aerial vehicle by using the final optimal distribution matrix.
Further, for a task to be executed by the heterogeneous multi-unmanned aerial vehicle system, a candidate task sequence is constructed, and the method specifically comprises the following steps: classifying tasks to be executed of the current heterogeneous multi-unmanned aerial vehicle system, considering a 3-task scene according to actual battlefield conditions, namely electromagnetic suppression, attack and confirmation, wherein the 3 tasks have strict time sequence relations, namely: the attack task to any target needs to be performed within the time range of electromagnetic suppression to the target, and the confirmation task to any target needs to be performed after the target is attacked. The candidate tasks can be classified into 7 types, namely only electromagnetic pressing tasks, only attack tasks, only confirmation tasks, only electromagnetic pressing and attack tasks, only electromagnetic pressing and confirmation tasks, only attack and confirmation tasks, and all three tasks. And sequencing the tasks to be executed according to the time sequence relation to obtain candidate task sequences.
Further, a candidate unmanned aerial vehicle sequence is constructed according to the type of the current candidate task and the characteristics of the heterogeneous unmanned aerial vehicle for executing different types of tasks, and specifically: the heterogeneous unmanned aerial vehicle comprises 4 different types of unmanned aerial vehicles, namely an electromagnetic pressing unmanned aerial vehicle, an attack unmanned aerial vehicle, a reconnaissance unmanned aerial vehicle and a helicopter; the electromagnetic suppression unmanned aerial vehicle only executes an electromagnetic suppression task, the attack unmanned aerial vehicle only executes an attack task, the reconnaissance unmanned aerial vehicle only executes a confirmation task, and the helicopter executes the attack task or the confirmation task. And constructing a reasonable candidate unmanned aerial vehicle sequence, and enabling the candidate unmanned aerial vehicle sequence to correspond to the candidate task.
Further, the size of the pheromone concentration matrix is N multiplied by N+1, N is the number of target points, the nth column represents the pheromone concentration of the unmanned aerial vehicle to each target at the nth target point, and the (n+1) th column represents the pheromone concentration of the unmanned aerial vehicle to each target at the initial position; the heuristic information is the distance between the current position of the unmanned aerial vehicle and the target position.
Further, in step 3, the next task and the assumption of the next task are selected according to the heuristic information and the pheromone concentration matrix, respectively. When the previous task is not an electromagnetic pressing task for any target, randomly selecting an unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence as a undertaker of the next task, acquiring the position of the current unmanned aerial vehicle, traversing all candidate tasks, calculating the transfer probability of the candidate tasks according to heuristic information and a pheromone concentration matrix, and selecting the next task in a roulette manner for all candidate tasks matched with the current unmanned aerial vehicle. When the previous task is an electromagnetic hold-down task for any target, the task to be executed at the moment is designated as an attack task for the target instead of selecting from candidate task sequences in a roulette manner. Traversing all candidate unmanned aerial vehicles, calculating the transfer probability of the candidate unmanned aerial vehicles according to heuristic information and a pheromone concentration matrix, and selecting a undertaker of a next task in a roulette manner for all candidate unmanned aerial vehicles matched with the current task; after the attack task is completed, the candidate task sequence is updated as usual.
Further, if the current unmanned aerial vehicle cannot be matched with all candidate tasks, deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence, specifically: the same unmanned aerial vehicle can only execute one task at the same target point; and recording the target point reached by each unmanned aerial vehicle, in the process of traversing the candidate tasks, setting the transition probability of selecting the candidate task to 0 if the current unmanned aerial vehicle has executed other tasks at the target point corresponding to the candidate task, and deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence and selecting a new unmanned aerial vehicle from the updated candidate unmanned aerial vehicle sequence as a undertaker of the next task when the transition probability of the unmanned aerial vehicle and all the candidate tasks is 0, namely that the current unmanned aerial vehicle and all the candidate tasks cannot be matched.
Further, updating the pheromone concentration matrix according to the optimized target value of the current iteration time, specifically: when updating, firstly volatilizing the pheromones, namely attenuating the pheromone concentration of all nodes in a certain proportion, and then strengthening the pheromone concentration of the nodes where ants walk, namely different target points where unmanned aerial vehicles arrive in a certain proportion.
Further, the optimization target value is a task total time or a benefit value; if the optimization target value is the total time of the task, the total time of the task is as follows: if the optimization target value is a benefit value, the benefit value is high.
The beneficial effects are that:
1. The invention provides a heterogeneous multi-unmanned aerial vehicle task allocation method based on an ant colony algorithm, which is used for solving the problem of heterogeneous multi-unmanned aerial vehicle task allocation under the background of complex time sequence requirements among various tasks. The time sequence requirement is met by means of maintaining the candidate task sequence, and the requirement corresponding to the executed task of the heterogeneous unmanned aerial vehicle is met by means of maintaining the candidate unmanned aerial vehicle sequence.
2. The heterogeneous multi-unmanned aerial vehicle task allocation method based on the ant colony algorithm has strong generalization and can be flexibly applied to various scenes. The best solution can be quickly approximated by fully utilizing heuristic information and a positive feedback mechanism.
Detailed Description
The invention will now be described in detail with reference to examples.
The invention provides a heterogeneous multi-unmanned aerial vehicle task allocation method based on an ant colony algorithm, which comprises the following steps:
according to the task scale, initializing ant colony, wherein one ant colony jointly forms an allocation scheme, one ant represents one unmanned aerial vehicle, in order to improve the searching efficiency and reduce the mutual interference among unmanned aerial vehicles, any ant in any ant colony has respective pheromone concentration matrixes, and the size of the matrixes is determined by the target number. And meanwhile, initializing parameters such as the speed of the unmanned aerial vehicle, the type of the unmanned aerial vehicle, the coordinates of the unmanned aerial vehicle, the type of the target, the coordinates of the target, the type of the task and the like.
And constructing a candidate unmanned aerial vehicle matrix according to the types of the current candidate tasks and the characteristics of the heterogeneous unmanned aerial vehicle for executing different types of tasks.
Randomly selecting an unmanned aerial vehicle from the candidate unmanned aerial vehicle matrix as a undertaker of a next task, acquiring the position of the current unmanned aerial vehicle, traversing all candidate tasks, calculating the selection probability of each candidate task according to heuristic information and pheromone concentration, and selecting the next task in a roulette manner. If the current unmanned aerial vehicle cannot be matched with all candidate tasks, deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence, and repeating the steps.
And updating the candidate task matrix, updating the position of the unmanned aerial vehicle, and judging whether all tasks are completed.
If not, repeatedly selecting the next task by adopting a roulette mode according to the heuristic information and the pheromone concentration.
Updating the pheromone concentration matrix according to the total time required for completing all tasks, and updating the optimal distribution matrix.
In one embodiment of the invention, a 3-task scenario is considered according to the actual battlefield situation, and the 3 tasks are electromagnetic suppression, attack and confirmation respectively.
The tasks have strict time sequence relation, the attack task to any target needs to be performed within the time range of electromagnetic pressing of the target, and the confirmation task to any target needs to be performed after the attack task to the target is completed.
The candidate tasks are classified into 7 types according to the task composition in the current candidate tasks, namely electromagnetic pressing only tasks, attack only tasks, confirmation only tasks, electromagnetic pressing and attack only tasks, electromagnetic pressing and confirmation only tasks, attack and confirmation only tasks, and three tasks.
In one embodiment of the invention, the candidate drone sequence is constructed according to the type of candidate task. There are 3 different types of unmanned aerial vehicles, electromagnetic compacting unmanned aerial vehicles, attack unmanned aerial vehicles, reconnaissance unmanned aerial vehicles and helicopters, respectively.
The electromagnetic suppression unmanned aerial vehicle can execute electromagnetic suppression tasks as far as possible, the attack unmanned aerial vehicle can only execute attack tasks, and the reconnaissance unmanned aerial vehicle can only execute confirmation tasks. The helicopter can perform both the attack task and the validation task.
Reasonable candidate unmanned aerial vehicle sequences need to be constructed to correspond to candidate tasks.
For example, when the candidate tasks only include electromagnetic pressing tasks, all electromagnetic pressing unmanned aerial vehicles form a candidate unmanned aerial vehicle sequence; when only the attack and confirmation tasks exist in the candidate tasks, all the attack unmanned aerial vehicles with the attack or confirmation capability and the reconnaissance unmanned aerial vehicle and the helicopter form a candidate unmanned aerial vehicle sequence.
In one embodiment of the invention, after the candidate drone sequence is determined, a frame is randomly selected from the sequence as the carrier for the next mission.
After the unmanned aerial vehicle is selected, traversing the candidate tasks, and calculating transition probability according to heuristic information and a pheromone concentration matrix, wherein the heuristic information is the distance between the current position and the target position of the unmanned aerial vehicle. In the traversal process, if the candidate task and the heterogeneous unmanned aerial vehicle cannot be matched, if an attack task is allocated to the electromagnetic suppression unmanned aerial vehicle, the state transition probability of the task is set to 0.
The same unmanned aerial vehicle can only execute one task at the same target point, and when traversing the candidate task, if the current unmanned aerial vehicle executes other tasks at the target point corresponding to the candidate task, the state transition probability of the task is set to 0.
After traversing all candidate tasks, selecting the next task by adopting a roulette mode according to the state transition probability of each task.
And updating the candidate task, such as deleting the task from the candidate task after completing the attack task to a certain target point, and adding the confirmation task to the target point into the candidate task sequence.
When the previous task is not an electromagnetic pressing task for any target, randomly selecting an unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence as a undertaker of the next task, acquiring the position of the current unmanned aerial vehicle, traversing all candidate tasks, calculating the transfer probability of the candidate tasks according to heuristic information and a pheromone concentration matrix, and selecting the next task in a roulette manner for all candidate tasks matched with the current unmanned aerial vehicle.
In one embodiment of the present invention, since the electromagnetic hold-down task for a target needs to be continued until the attack on the target is completed, in order to achieve maximum utilization of time and resources, the electromagnetic hold-down task and the attack task for the same target need to be arranged at the same time as much as possible. Therefore, when selecting a task, if the previous task is an electromagnetic pressing task for a certain target, the task to be executed at the moment is designated as an attack task for the target instead of selecting from a candidate task sequence in a roulette manner. Traversing all candidate unmanned aerial vehicles, calculating the transfer probability of the candidate unmanned aerial vehicles according to heuristic information and a pheromone concentration matrix, and selecting a undertaker of a next task in a roulette manner for all candidate unmanned aerial vehicles matched with the current task; after the attack task is completed, the candidate task sequence is updated as usual.
In one embodiment of the present invention, the task selection and the candidate task update are repeated until all tasks have been performed, thus obtaining a feasible solution. The feasible solution comprises the order of executing the tasks and the corresponding relation between the unmanned aerial vehicle and the tasks, so that the total time under the allocation scheme can be obtained.
In one embodiment of the invention, the pheromone concentration can be updated after a feasible solution is found.
Firstly, volatilizing pheromones, and attenuating the concentrations of all the pheromones according to a certain proportion.
Then, the concentration of the pheromone is enhanced, the ants can leave the pheromone in the passing path, and the shorter the path is, the stronger the concentration of the pheromone is left. In this example, the target point and the target point are communicated with each other and the initial point of the unmanned aerial vehicle form a graph, the unmanned aerial vehicle selects one side in the graph according to the assigned task and the current position, and the pheromone concentration of the selected side is enhanced.
When the optimization objective is that the total time is shortest, the pheromone concentration of the selected side is higher under the scheme with the shorter total time, and the probability that the scheme with the shorter total time is selected is higher under the action of positive feedback.
In one embodiment of the invention, in addition to minimizing task time, revenue maximization may also be used as an optimization objective for task allocation. In view of actual combat situations, different types of targets may have different strategic values, for example, the strategic value of a command center is higher than that of a common radar. In addition, the strategic value of the same type of target is also different, for example, radar at a junction location has a higher strategic value than other radars.
After electromagnetic suppression, attack and confirmation of a target are completed, the target can be considered to lose its strategic value completely, and the product of the strategic value and the effective working time of the target can be considered to be the total benefit provided by the target to the enemy, while the smaller the total benefit provided by the opposing enemy is, the larger the total benefit of the opposing me is. Therefore, when in war, the target with high strategic value can be preferentially obtained more benefits.
When the optimization goal is to minimize the total time, the intensity of the pheromone concentration boost is inversely proportional to the total time of the regimen when updating the pheromone concentration. Similarly, when the optimization target is the highest total profit, the original total time of the scheme is replaced by the total profit of the opposite enemy when the pheromone concentration is updated, and under the action of positive feedback, the probability that the scheme with the highest total profit is selected is higher.
The task allocation problem is modeled as a finite buffer flow shop scheduling problem. The model is commonly used for factory flow optimization and can be described as processing N workpieces on M machines, each workpiece requiring K machining passes. Under unmanned aerial vehicle task allocation problem, unmanned aerial vehicle represents as the machine, and the target that needs to be accomplished is the work piece, and the target needs the task that accomplishes be the processing number of times, and specific processing task can only be accomplished by specific machine.
Based on the problem that the M unmanned aerial vehicle performs K tasks to N targets, the following assumptions are provided:
1) Each target requires the drone to accomplish multiple tasks such as electromagnetic suppression, identification, attack, and validation. Can be changed into three tasks of electromagnetic suppression, attack and confirmation under certain simplified conditions;
2) Different unmanned aerial vehicles have the ability to perform different tasks (wherein a helicopter can perform both an attack and a validation task, an electromagnetic hold-down unmanned aerial vehicle only performs an electromagnetic hold-down task, an attack unmanned aerial vehicle only can perform an attack task, and a reconnaissance unmanned aerial vehicle only can perform a validation task).
3) The number of unmanned aerial vehicles is greater than or equal to the target number.
On the premise of meeting the related constraint conditions, the objective function of the problem is made to be the minimum maximum task completion time J. The constraint optimization model is defined in combination with a model of flow shop scheduling problem as follows
The specific meanings of the variables are shown in Table 1:
TABLE 1 significance of the variables
Equation (1) is an optimized objective function that minimizes the maximum task completion time under constraint (2) is satisfied. The value of J (|C N,M (·) |) is the maximum value in the cumulative time matrix C N,M. Specific definitions of variables and constraint sets Γ are described in the following section.
Time of flight cost matrix T ij
T ij is a matrix of N rows and N+M columns, wherein the rows represent targets in the task allocation problem, the first N columns are targets, and the last M columns are unmanned aerial vehicles. Element t ij represents the time of flight from node i to node j. The specific definition is as follows:
task accumulation time matrix C N,M
C N,M is a matrix of the time it takes for the drone to accumulate to complete the task. The rows of the matrix represent targets and the columns represent drones. Element c n,m is the current time when the mth unmanned aerial vehicle completes a task at the nth destination.
The current time c n,m when a certain task of the nth target is completed by the mth unmanned aerial vehicle is given by the following formula:
Cn,m＝max{Cn,Cm} (4)
Cn＝max{Cn,i|i＝1,2,…,M} (5)
Cm＝ti,j+max{Cj,m|j＝1,2,…,N},ti,j∈Tij (6)
C n is the maximum value in line n of C N,M, representing the maximum time required for the unmanned aerial vehicle to wait for completion of other tasks on the target before completing the target n current task; c m consists of two parts, wherein the former part is t i,j, the time required for the mth unmanned aerial vehicle to go to the nth target to execute a new task is required, and the latter part is the maximum value in the mth column of C N,M, which represents that the unmanned aerial vehicle can go to the target n to execute the new task after all tasks are required to be processed before the unmanned aerial vehicle finishes processing.
For matrix C N,M, the maximum of all its elements represents the time ultimately required to complete the entire assignment scheme.
Target value matrix V N
In addition to minimizing the maximum task execution time, an index of maximum combat benefit is also introduced herein. The index can obtain larger benefits by designing the target value matrix V N by considering different strategic values of different target points and performing preferential hit on the target with high strategic value.
Formula (7) is a target value matrix, and V i is the strategic value of the target i; c n is defined as formula (5), which is the maximum value in row n of the task accumulation time matrix C n,m, i.e., represents the target effective operating time. The product sum of the strategic value and the effective working time of the target is minimized by reasonable distribution. The overall optimization objective formula is expressed as:
target task sequence O NK
O NK is the order in which all targets in the assignment scheme are executed. Each element of the sequence is the number of objects and the task number is determined by the number of times the object appears. The kth occurrence of the ith object in O NK is represented by element O i-k, i.e., the kth task. Taking the case of one with only two targets and two tasks as shown in table 2, the 3 rd element O NK (3) is 1 and appears 2 nd in O NK, the corresponding operation is O 1-2, which indicates that the 2 nd task of the 1 st target is to be performed.
TABLE 2 task sequence definition
| ONK | ONK(1) | ONK(2) | ONK(3) | ONK(4) |
| Target object | 1 | 2 | 1 | 2 |
| Tasks | 01-1 | 02-1 | 01-2 | 02-2 |
Unmanned aerial vehicle allocation matrix pi K,N
And pi K,N is a matrix allocated to the unmanned aerial vehicle. The rows of the matrix correspond to the tasks that the targets need to perform and the columns correspond to the targets. The kth task, whose element pi k,n represents the nth target, is performed by unmanned pi k,n. Definition of pi K,N:
Constraint definition
According to the unmanned aerial vehicle assignment model defined above, the constraint can be divided according to strong constraint and weak constraint, and the specific division is shown in the following table:
TABLE 3 constraint definition
Constraint processing
In the above classification of constraints, weak constraints refer to constraint conditions that have been considered in the modeling process, which have been satisfied within the model. For example, for constraint Γ 1, the K rows of drone allocation matrix pi K,N meet the requirements that all tasks are performed; the relationship between the drone and the target mission is limited for constraint Γ 2,∏K,N.
For strong constraints, processing is performed by selecting a method that examines and adjusts the potential solutions within each iteration cycle and satisfies all constraints.
Pheromone concentration matrix P
The ant colony algorithm takes ants as a main body, takes pheromones as information transferred between iterations, and abstracts paths between foods into a graph. At the beginning, the concentration of pheromones on all paths is the same, after a period of time, ants on shorter paths have high round trip speed, the ants involved in the ants gradually increase, more pheromones are left, and the probability of selecting the paths by the ants is higher; and ants on a longer path are fewer, the round trip speed is low, and the concentration of pheromone is less and less in continuous volatilization. Under the effect of positive feedback, the ant colony gradually converges to the optimal path. In the task allocation problem, one ant colony represents one unmanned aerial vehicle group, and one ant is one unmanned aerial vehicle. The unmanned plane and the target are communicated with each other two by two to form an undirected graph, and the pheromone concentration of each side on the graph forms an pheromone concentration matrix P.
In order to prevent mutual interference between ants of the same ant colony, each ant has its independent pheromone concentration matrix P k,The concentration of pheromone representing the transfer of the kth ant from the node i to the node j, namely the concentration of pheromone of the path of the kth unmanned plane from the target i to the target j in the unmanned plane group, when i=n+1, represents the transfer of the unmanned plane from the initial point to other target points.
Ant colony coding design
For the assignment problem that M unmanned aerial vehicles go to N targets to execute K tasks, each ant colony group X i is designed to be composed of M ants, each ant X it represents a UAV, the element X it (N) in the vector is an integer, and the target to which the unmanned aerial vehicle t needs to go and the task which the unmanned aerial vehicle needs to go to correspondingly execute can be obtained after transformation, and the task is hereinafter referred to as a target-city. Specifically defined as formulas (10) and (11):
The constraint of equation (11) indicates that each group of ants accomplishes all tasks for all objectives. To simplify programming, for ease of comparison with other algorithms, equation (10) may be transformed to pi K,N, whose flow is shown in Table 4:
Table 4 pi K,N transform algorithm
For a specific process, reference may be made to the example given below, which describes X i and corresponding pi K,N for 3 target 4 unmanned aerial vehicles performing 2 tasks:
ant team X i example
| Xi | xi(1) | xi(2) |
| Xi1 | 4 | 5 |
| Xi2 | 1 | |
| Xi3 | 2 | |
| Xi4 | 3 | 6 |
Ant group X i corresponds to pi K,N
For the acquisition mode of the assigned time sequence O NK, the project adopts a sequence selection strategy following ant activity, and is recorded in O NK after the UAV and the task to be executed, namely the city, are selected.
| ONK | ONK(1) | ONK(2) | ONK(3) | ONK(4) | ONK(5) | ONK(6) |
| Target object | 1 | 1 | 2 | 2 | 2 | 1 |
| Tasks | 01-1 | 02-1 | 01-2 | 02-2 | 02-3 | 03-3 |
Assignment ant colony algorithm design
Classifying the current candidate tasks, constructing a candidate unmanned aerial vehicle sequence according to different classification results and the property that the heterogeneous unmanned aerial vehicle can only execute specific tasks, and randomly selecting one candidate unmanned aerial vehicle sequence as a undertaker of the next task. And traversing all candidate tasks to respectively calculate transition probabilities, and selecting the next task by adopting a roulette mode. For example, at the very beginning of the allocation, the set of electromagnetic throttle tasks for all targets constitutes a candidate task sequence, while all electromagnetic throttle drones constitutes a candidate drone sequence, since the electromagnetic throttle tasks must be executed first. While only confirmation tasks for certain tasks remain at the end of the allocation, all reconnaissance drones and helicopters with this capability constitute a candidate aircraft sequence.
When the ant selects the target to which the next step is carried out, the transfer probability is calculated according to the pheromone concentration and heuristic information, and the specific formula is as follows:
Wherein: i is the current target of the ant, j is the target to be accessed; the possibility in equation (12) represents that the drone can perform this type of task and no other tasks have been previously performed at this goal, thus ensuring that the heterogeneous drone does not select tasks that cannot be performed by itself, while satisfying the constraint that the same helicopter can only perform one task at the same goal. η ij in formula (13) is heuristic information, which is the reciprocal of the time t i,j taken to go to the next node j, i.e. ants tend to choose the node closest to themselves for state transition; c in the formula (14) is the initialized pheromone concentration, is an adaptive value, and τ ij (t) is the pheromone intensity from the point of time i to the point of j; allowed k is a candidate task sequence; alpha, beta are weighted values of pheromone and visibility.
After completing one assignment, the candidate task is updated, for example, after completing the attack task on the target 1, the task is deleted from the candidate task sequence, the confirmation task on the target is added, the candidate unmanned aerial vehicle sequence is updated along with the update of the candidate task, and the accumulated time matrix is updated. And repeating the assignment and the update until all tasks are executed, thereby obtaining an assignment scheme.
Updating pheromone concentration
Firstly, volatilizing pheromones, namely attenuating the pheromone concentration of all nodes in a certain proportion, and then strengthening the pheromone concentration of the nodes where ants walk, namely different target points where unmanned planes arrive, wherein the shorter the total time is, the more the pheromones are left by the ants, and the stronger the pheromone concentration is. In order to improve the search efficiency and reduce the interference between unmanned aerial vehicles, a separate pheromone matrix SP M is designed for each ant in the ant group, i.e. each unmanned aerial vehicle. The pheromone is also updated with iteration, and the update formula is as follows:
τij∈SPM (15)
Wherein: m is the number of ants, ρ is (0, 1), Δτ ij k is the pheromone evaporation rate, Δτ ij k is the pheromone left by the kth ant subgroup on paths i to j, and C k is the total path of the kth ant subgroup after the path is completed, which is the total time required by the allocation scheme in this example.
For the unmanned assignment problem, the specific flow of the whole algorithm is shown in table 5:
table 5 unmanned aerial vehicle assignment ant colony algorithm
The task allocation method of the heterogeneous multi-unmanned aerial vehicle based on the ant colony algorithm is further described through simulation experiments.
The method comprises the steps of setting a task area to be N=4, setting the total number of planes to be M=5, wherein the number of the electromagnetic pressing unmanned aerial vehicle is 2, the number of the attack unmanned aerial vehicle is 1, the number of the reconnaissance unmanned aerial vehicle is 1, the number of the tasks of the helicopter is 1, setting the number of the tasks to be K=3, and respectively setting the tasks to be electromagnetic pressing tasks, the number of the attack tasks and the number of the confirmation tasks. The unmanned aerial vehicle can only execute electromagnetic suppression tasks, the attack unmanned aerial vehicle can only execute attack tasks, the reconnaissance unmanned aerial vehicle can only execute confirmation tasks, the helicopter can execute both the attack tasks and the confirmation tasks, the attack tasks can be completed only when targets are subjected to electromagnetic suppression, and the confirmation tasks are to be executed after the attack tasks.
TABLE 6
| UAV | SP | Type | Vo |
| 1 | (9,10,50) | H | 1.0 |
| 2 | (18,10,50) | E | 1.5 |
| 3 | (27,10,50) | E | 1.5 |
| 4 | (36,10,50) | A | 1.5 |
| 5 | (45,10,50) | S | 1.5 |
TABLE 7
| Target | EP | Va |
| 1 | (10,1.4,140) | 1 |
| 2 | (20,3.6,140) | 2 |
| 3 | (30,7.7,140) | 3 |
| 4 | (40,11.4,140) | 4 |
In this example, specific parameters are shown in table 6, the starting position of the unmanned aerial vehicle/helicopter is SP, the Type is Type, H represents the helicopter, E represents the electromagnetic pressing unmanned aerial vehicle, a represents the attack unmanned aerial vehicle, S represents the reconnaissance unmanned aerial vehicle, the flying speed is V o, the coordinate position of the target is EP, and the target value is V a, which are continuously shown in table 2. In the simulation, the ant colony number is set as the iteration number, and the weight coefficient is set as
Simulation experiment one:
Setting the optimization target to be shortest in total time, and carrying out task allocation through the algorithm, wherein the allocation result is shown as follows
| ΠK,N | Target1 | Target2 | Target3 | Target4 |
| Task1 | 3 | 3 | 3 | 2 |
| Task2 | 4 | 4 | 4 | 4 |
| Task3 | 5 | 1 | 5 | 5 |
| ONK | ONK(1) | ONK(2) | ONK(3) | ONK(4) | ONK(5) | ONK(6) |
| Target object | 4 | 4 | 4 | 3 | 3 | 2 |
| Tasks | 04-1 | 04-2 | 04-3 | 03-1 | 03-2 | 02-1 |
| ONK | ONK(7) | ONK(8) | ONK(9) | ONK(10) | ONK(11) | ONK(12) |
| Target object | 2 | 1 | 1 | 3 | 2 | 1 |
| Tasks | 02-2 | 01-1 | 01-2 | 03-3 | 02-3 | 01-3 |
It can be seen that as ant populations are updated, the total time required is less and less, and the distribution results meet various constraints. The effectiveness of the algorithm was demonstrated.
Simulation experiment II:
setting the optimization target to be the highest in total income, and carrying out task allocation through the algorithm, wherein the allocation result is shown as follows
| ΠK,N | Target1 | Target2 | Target3 | Target4 |
| Task1 | 2 | 3 | 3 | 3 |
| Task2 | 4 | 4 | 4 | 4 |
| Task3 | 5 | 1 | 5 | 5 |
| ONK | ONK(1) | ONK(2) | ONK(3) | ONK(4) | ONK(5) | ONK(6) |
| Target object | 4 | 4 | 4 | 3 | 3 | 3 |
| Tasks | 04-1 | 04-2 | 04-3 | 03-1 | 03-2 | 03-3 |
| ONK | ONK(7) | ONK(8) | ONK(9) | ONK(10) | ONK(11) | ONK(12) |
| Target object | 2 | 2 | 1 | 1 | 2 | 1 |
| Tasks | 02-1 | 02-2 | 01-2 | 02-2 | 02-3 | 02-3 |
In summary, the above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. The heterogeneous multi-unmanned aerial vehicle task allocation method based on the ant colony algorithm is characterized by comprising the following steps of:
Step 1: initializing ant colony according to the scale of the task, wherein one ant colony forms an allocation scheme together, one ant represents one unmanned aerial vehicle, and any ant in any ant colony has a respective pheromone concentration matrix; initializing unmanned aerial vehicle parameters at the same time; the unmanned aerial vehicle parameters comprise unmanned aerial vehicle speed, unmanned aerial vehicle type, unmanned aerial vehicle coordinates, target type, target coordinates and task types;
Step 2: aiming at a task to be executed of a heterogeneous multi-unmanned aerial vehicle system, a candidate task sequence is constructed, and the method specifically comprises the following steps of: classifying tasks to be executed of the current heterogeneous multi-unmanned aerial vehicle system, considering a 3-task scene according to actual battlefield conditions, namely electromagnetic suppression, attack and confirmation, wherein the 3 tasks have strict time sequence relations, namely: the attack task of any target needs to be carried out within the time range of electromagnetic pressing of the target, and the confirmation task of any target needs to be carried out after the target is attacked; the candidate tasks can be divided into 7 types, namely only electromagnetic pressing tasks, only attack tasks, only confirmation tasks, only electromagnetic pressing and attack tasks, only electromagnetic pressing and confirmation tasks, only attack and confirmation tasks and three tasks; sequencing tasks to be executed according to the time sequence relation to obtain candidate task sequences;
Constructing a candidate unmanned aerial vehicle sequence according to the types of the current candidate tasks and the characteristics of the heterogeneous unmanned aerial vehicle for executing different types of tasks; the method comprises the following steps: the heterogeneous unmanned aerial vehicle comprises 4 unmanned aerial vehicles of different types, namely an electromagnetic pressing unmanned aerial vehicle, an attack unmanned aerial vehicle, a reconnaissance unmanned aerial vehicle and a helicopter; the electromagnetic suppression unmanned aerial vehicle only executes an electromagnetic suppression task, the attack unmanned aerial vehicle only executes an attack task, the reconnaissance unmanned aerial vehicle only executes a confirmation task, and the helicopter executes the attack task or the confirmation task; constructing a reasonable candidate unmanned aerial vehicle sequence, so that the candidate unmanned aerial vehicle sequence corresponds to a candidate task;
Step 3: the size of the pheromone concentration matrix is N multiplied by N+1, N is the number of target points, the nth column represents the pheromone concentration of the unmanned aerial vehicle to each target at the nth target point, and the (n+1) th column represents the pheromone concentration of the unmanned aerial vehicle to each target at the initial position; the heuristic information is the distance between the current position of the unmanned aerial vehicle and the target position;
Respectively selecting a next task and a undertaker of the next task according to heuristic information and a pheromone concentration matrix, wherein the steps are as follows: when the previous task is not an electromagnetic pressing task for any target, randomly selecting an unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence as a undertaker of a next task, acquiring the position of the current unmanned aerial vehicle, traversing all candidate tasks, calculating the transfer probability of the candidate tasks according to heuristic information and a pheromone concentration matrix, and selecting the next task in a roulette manner for all candidate tasks matched with the current unmanned aerial vehicle; when the previous task is an electromagnetic pressing task for any target, the task to be executed at the moment is designated as an attack task for the target instead of selecting from candidate task sequences in a roulette manner; traversing all candidate unmanned aerial vehicles, calculating the transfer probability of the candidate unmanned aerial vehicles according to heuristic information and a pheromone concentration matrix, and selecting a undertaker of a next task in a roulette manner for all candidate unmanned aerial vehicles matched with the current task; after the attack task is completed, updating the candidate task sequence as usual;
If the current unmanned aerial vehicle cannot be matched with all candidate tasks, deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence, and repeating the step 3 until the matching is completed; wherein: the same unmanned aerial vehicle can only execute one task at the same target point; recording the target point reached by each unmanned aerial vehicle, in the process of traversing the candidate tasks, setting the transition probability of selecting the candidate task to 0 if the current unmanned aerial vehicle has executed other tasks at the target point corresponding to the candidate task, deleting the unmanned aerial vehicle from the candidate unmanned aerial vehicle sequence when the transition probabilities of the unmanned aerial vehicle and all the candidate tasks are 0, namely that the current unmanned aerial vehicle and all the candidate tasks cannot be matched, and selecting a new unmanned aerial vehicle from the updated candidate unmanned aerial vehicle sequence as a undertaker of the next task;
Step 4: updating the candidate task sequence, updating the candidate unmanned aerial vehicle sequence, updating the position of the unmanned aerial vehicle, and repeatedly executing the selection and task allocation of the unmanned aerial vehicles in the steps 3 and 4 until all tasks are allocated to be completed, so as to obtain an allocation matrix of the current iteration time;
step 5: calculating an optimal target value of the current iteration time according to the distribution matrix of the current iteration time, and if the optimal target value of the current iteration time is better than the optimal target value of the optimal distribution matrix, updating the optimal distribution matrix by utilizing the distribution matrix of the current iteration time;
Updating the pheromone concentration matrix according to the optimal target value of the current iteration, repeatedly executing the steps 2-5 until the set iteration times are reached, obtaining a final optimal distribution matrix, and performing task distribution of the heterogeneous multi-unmanned aerial vehicle by using the final optimal distribution matrix;
wherein: based on the problem that M unmanned aerial vehicles execute K tasks to N targets, constraint conditions are as follows:
1) Each target requires the unmanned aerial vehicle to complete a plurality of tasks;
2) Different unmanned aerial vehicles have the ability to perform different tasks;
3) The number of unmanned aerial vehicles is greater than or equal to the target number;
On the premise of meeting the related constraint conditions, the objective function of the problem is to minimize the maximum task completion time J, and the constraint optimization model is defined by combining the model of the flow shop scheduling problem as follows
Where T ij＝{tij}(N+M)×N is a time cost matrix and T ij represents the task time required from node i to node j; c N,M＝{cn,m}N×M is a task accumulated time matrix, and C n,m is accumulated time of the mth unmanned aerial vehicle after the nth target is executed; o NK＝{cn,m}N×M is an accumulated time matrix; pi K,N＝{πk,n}K×N is a matrix allocated to the unmanned aerial vehicle, pi k,n represents that the unmanned aerial vehicle pi k,n goes to execute the kth task of the nth target; Γ is a constraint set;
Equation (1) is an optimized objective function that minimizes the maximum task completion time under the constraint condition (2) is satisfied; the value of J (|c N,M (·) |) is the maximum value in the cumulative time matrix C N,M;
the time-of-flight cost matrix T ij：Tij is a matrix of N rows n+m columns, where a row represents a target in the task allocation problem, the first N columns are targets, the last M columns are unmanned aerial vehicles, and element T ij represents a time-of-flight from node i to node j, which is specifically defined as follows:
Task cumulative time matrix C N,M: the rows of the matrix represent targets and the columns represent drones:
The current time C n,m when a certain task of the nth target is completed by the mth unmanned aerial vehicle is given by the following formula:
Cn,m＝max{Cn,Cm} (4)
Cn＝max{Cn，i|i＝1，2，...，M} (5)
Cm＝ti,j+max{Cj,m|j＝1,2,...,N},ti,j∈Tij (6)
C n is the maximum value in line n of C N,M, representing the maximum time required for the unmanned aerial vehicle to wait for completion of other tasks on the target before completing the target n current task; c m consists of two parts, wherein the former part is t i,j, the time required for the mth unmanned aerial vehicle to go to the nth target to execute a new task is needed, and the latter part is the maximum value in the mth column of C N,M, which represents that the unmanned aerial vehicle can go to the target n to execute the new task after all tasks are required to be processed before the unmanned aerial vehicle finishes processing the unmanned aerial vehicle; for matrix C N,M, the maximum of all its elements represents the time ultimately required to complete the entire assignment scheme;
target value matrix V N
Formula (7) is a target value matrix, and V i is the strategic value of the target i; c n is defined as formula (5), and is the maximum value in the nth row of the task accumulated time matrix C n,m, namely representing the effective working time of the target; the product sum of the strategic value and the effective working time of the target is minimized through reasonable distribution; the overall optimization objective formula is expressed as:
Unmanned aerial vehicle allocation matrix pi K,N: the rows of the matrix correspond to tasks to be executed by the targets, and the columns correspond to the targets; the kth task for which element pi k,n represents the nth target is performed by drone pi k,n, definition of pi K,N:
2. the ant colony algorithm-based heterogeneous multi-unmanned aerial vehicle task allocation method according to claim 1, wherein updating the pheromone concentration matrix according to the optimal target value of the current iteration time specifically comprises:
When updating, firstly volatilizing the pheromones, namely attenuating the pheromone concentration of all nodes in a certain proportion, and then strengthening the pheromone concentration of the nodes where ants walk, namely different target points where unmanned aerial vehicles arrive in a certain proportion.
3. The ant colony algorithm-based heterogeneous multi-unmanned aerial vehicle task allocation method according to claim 1, wherein the optimization target value is a task total time or a benefit value;
if the optimization target value is the total time of the task, the total time of the task is as follows:
if the optimization target value is a benefit value, the benefit value is high.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211155444.3A CN115494864B (en) | 2022-09-22 | 2022-09-22 | Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211155444.3A CN115494864B (en) | 2022-09-22 | 2022-09-22 | Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115494864A CN115494864A (en) | 2022-12-20 |
| CN115494864B true CN115494864B (en) | 2024-08-20 |
Family
ID=84469823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211155444.3A Active CN115494864B (en) | 2022-09-22 | 2022-09-22 | Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115494864B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689252B (en) * | 2022-12-28 | 2023-06-23 | 杭州中安电子有限公司 | Task allocation method and system based on self-adaptive ant colony algorithm |
| CN118092361A (en) * | 2024-04-17 | 2024-05-28 | 哈尔滨工业大学（威海） | Heterogeneous multi-robot task scheduling method and system for textile industry |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101136081A (en) * | 2007-09-13 | 2008-03-05 | 北京航空航天大学 | Unmanned operational aircraft multiple plains synergic tasks distributing method based on ant colony intelligent |
| CN105892480A (en) * | 2016-03-21 | 2016-08-24 | 南京航空航天大学 | Self-organizing method for cooperative scouting and hitting task of heterogeneous multi-unmanned-aerial-vehicle system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776612A (en) * | 2018-04-11 | 2018-11-09 | 深圳大学 | A kind of cloud computing method for allocating tasks, device, equipment and storage medium |
| CN111966050B (en) * | 2020-07-01 | 2023-04-25 | 北京工业大学 | AMMAS-GA nesting algorithm-based double-resource die job shop scheduling optimization method |
| CN112508369B (en) * | 2020-11-27 | 2023-05-16 | 北京工商大学 | Multi-unmanned aerial vehicle task allocation method based on improved ant colony algorithm |
-
2022
- 2022-09-22 CN CN202211155444.3A patent/CN115494864B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101136081A (en) * | 2007-09-13 | 2008-03-05 | 北京航空航天大学 | Unmanned operational aircraft multiple plains synergic tasks distributing method based on ant colony intelligent |
| CN105892480A (en) * | 2016-03-21 | 2016-08-24 | 南京航空航天大学 | Self-organizing method for cooperative scouting and hitting task of heterogeneous multi-unmanned-aerial-vehicle system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115494864A (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115494864B (en) | Heterogeneous multi-unmanned aerial vehicle task allocation method based on ant colony algorithm | |
| CN105302153B (en) | The planing method for the task of beating is examined in the collaboration of isomery multiple no-manned plane | |
| Xia et al. | Cooperative task assignment and track planning for multi-UAV attack mobile targets | |
| CN107045458A (en) | Unmanned plane cotasking distribution method based on multi-target quantum particle cluster algorithm | |
| CN114594794B (en) | Multi-machine collaborative task planning method considering subsystem execution capacity | |
| Ming et al. | Improved discrete mapping differential evolution for multi-unmanned aerial vehicles cooperative multi-targets assignment under unified model | |
| CN115755963B (en) | Unmanned aerial vehicle group collaborative mission planning method considering carrier delivery mode | |
| CN114020031A (en) | Improved pigeon swarm optimization-based unmanned aerial vehicle cluster collaborative dynamic target searching method | |
| CN112926825A (en) | Multi-unmanned aerial vehicle task allocation method based on multi-target quantum shrimp swarm mechanism | |
| CN112733251A (en) | Multi-unmanned aerial vehicle collaborative track planning method | |
| CN113608546A (en) | Quantum sea lion mechanism unmanned aerial vehicle group task allocation method | |
| CN115016537B (en) | Heterogeneous unmanned aerial vehicle configuration and task planning combined optimization method in SEAD scene | |
| CN115730700A (en) | Self-adaptive multi-target task planning method, system and equipment based on reference point | |
| CN115494873A (en) | Heterogeneous multi-unmanned aerial vehicle cooperative task allocation method based on Monte Carlo tree search architecture under time sequence constraint | |
| CN114879745A (en) | Multi-unmanned aerial vehicle collaborative task planning method based on preplanning and tabu search algorithm | |
| CN111797966A (en) | Multi-machine cooperative global target distribution method based on improved sheep swarm algorithm | |
| Tan et al. | Multi-UAV path planning based on IB-ABC with restricted planned arrival sequence | |
| CN116088586B (en) | Method for planning on-line tasks in unmanned aerial vehicle combat process | |
| Kong et al. | Multi-UAV simultaneous target assignment and path planning based on deep reinforcement learning in dynamic multiple obstacles environments | |
| Nian et al. | Large-scale UAV swarm confrontation based on hierarchical attention actor-critic algorithm | |
| Gaowei et al. | Using multi-layer coding genetic algorithm to solve time-critical task assignment of heterogeneous UAV teaming | |
| He et al. | An operation planning generation and optimization method for the new intelligent combat SoS | |
| Sastre et al. | Collision-free swarm take-off based on trajectory analysis and UAV grouping | |
| Ni et al. | An Improved Cooperative Control Method for Hybrid Unmanned Aerial‐Ground System in Multitasks | |
| CN115509256A (en) | Unmanned aerial vehicle cluster collaborative planning and autonomous scheduling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |