CN114326827A - Unmanned aerial vehicle cluster multi-task dynamic allocation method and system - Google Patents
Unmanned aerial vehicle cluster multi-task dynamic allocation method and system Download PDFInfo
- Publication number
- CN114326827A CN114326827A CN202210029987.4A CN202210029987A CN114326827A CN 114326827 A CN114326827 A CN 114326827A CN 202210029987 A CN202210029987 A CN 202210029987A CN 114326827 A CN114326827 A CN 114326827A
- Authority
- CN
- China
- Prior art keywords
- task
- unmanned aerial
- aerial vehicle
- ground station
- maximum
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000008859 change Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000008901 benefit Effects 0.000 claims description 65
- 230000002452 interceptive effect Effects 0.000 claims description 36
- 238000012163 sequencing technique Methods 0.000 claims description 20
- 230000003993 interaction Effects 0.000 claims description 14
- 239000000126 substance Substances 0.000 claims description 7
- 239000000446 fuel Substances 0.000 claims description 6
- 238000013461 design Methods 0.000 abstract description 3
- 238000005192 partition Methods 0.000 description 10
- 239000003795 chemical substances by application Substances 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000035899 viability Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method and a system for dynamically distributing multiple tasks of an unmanned aerial vehicle cluster, which utilize a design method of two-layer alliances, firstly, a ground station is used as a decision-making main body to carry out initial task distribution, then an unmanned aerial vehicle is used as the decision-making main body to carry out task redistribution, firstly, a ground station task distribution result is obtained and executed, when the task change or the alliance where the unmanned aerial vehicle is located is found, whether the current task can bring the maximum profit is judged, if the maximum profit cannot be brought, the alliance corresponding to the maximum profit is searched and added, meanwhile, the number of updating times is increased once every time the task is converted, and the accuracy of corresponding local information is judged by combining the number of updating times of each unmanned aerial vehicle, so that various emergency situations of the unmanned aerial vehicle in the task execution process can be fully considered, and the problem that the emergency situations cannot be considered in the prior art is effectively solved.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle cluster multi-task dynamic allocation method and system based on a double-layer alliance.
Background
With the continuous development of science and technology, Unmanned Aerial Vehicles (UAVs) are widely applied to various fields, such as environment detection, meteorological monitoring, scene rescue, pesticide spraying, topographic mapping, monitoring attack, and the like, due to the advantages of small size, strong viability and the like. In many complex scenarios, many dangerous tasks that the manpower can not accomplish can be accomplished by using unmanned aerial vehicles. The multi-tube launching device developed by the project can launch hundreds of small unmanned aerial vehicles from the ground, and can efficiently carry out tasks such as shielding, patrol or ground attack and the like together in a specified area. The 'attack swarm tactics' (OFFSET) project developed by the united states department of Defense Advanced Research Planning (DARPA) in 2016 assumes that in a complex and unknown urban environment, as many as 250 small-sized combat units cooperate to perform tasks such as search and threat clearing, and simultaneously realize man-machine cooperation combat, and the small-sized combat units consist of unmanned aerial vehicle systems (UAS) and/or unmanned ground vehicles (UGS). These projects also illustrate that multi-agent systems such as drone swarm can play a significant role in the military field, etc., and are also gaining increasing attention from various countries. The task allocation problem of the multi-agent system is an important problem in the current multi-agent research field.
At present, the unmanned aerial vehicle task allocation technology is explored and researched in various aspects at home and abroad, and a plurality of research achievements can well achieve the target in a static environment. However, as the number of unmanned aerial vehicles increases, the existing scheme has low efficiency and low convergence speed, and the uncertainty of different task targets and emergencies which may occur at any time are less considered.
Therefore, a technical solution with high task reallocation efficiency suitable for the situation of dynamic change of environment and task is needed in the art.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle cluster multi-task dynamic allocation method and system.
In order to achieve the purpose, the invention provides the following scheme:
a method for dynamically allocating unmanned aerial vehicle cluster multitasks, the method comprising the following steps:
acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes a task;
when the task change is detected or the alliance where the unmanned aerial vehicle is located is changed, judging whether the current task can bring the maximum benefit;
if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to an unmanned aerial vehicle benefit formula, adding an alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating times for one time, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction;
broadcasting interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
and updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the profit formula of the unmanned aerial vehicle, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times once, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
In some embodiments, when detecting that the task changes or the alliance in which the unmanned aerial vehicle is located changes, determining whether the current task can bring the maximum benefit includes:
when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit according to the unmanned aerial vehicle benefit formula; the unmanned aerial vehicle income formula is:
wherein the content of the first and second substances,
indicating the benefit of the drone i,
indicating the number of drones selecting task m,
is a relatively large random number, di,mRepresenting the distance of drone i from task m,
representing the fuel consumption of the drone per unit distance,
indicating the set of tasks, num, that drone i can selectmRepresenting the number of drones required for task m,
represents the profit of task m when
Less than nummBecause the number requirement of the unmanned aerial vehicles is not met, the alliance yield is zero; when in use
Num or moremSatisfy unmanned aerial vehicle quantity demand, will ally oneself with this momentThe allied revenue is set as the mission revenue.
In some embodiments, further comprising:
the ground station randomly sorts all the unmanned aerial vehicles to obtain a random sorting result;
the ground station selects an unmanned aerial vehicle in sequence according to the random sequencing result;
the ground station calculates the individual benefit of each task selected by the unmanned aerial vehicle by combining the number of the unmanned aerial vehicles required by each task in the initial task information;
the ground station distributes the task corresponding to the maximum individual income to the unmanned aerial vehicle and updates the task distribution result;
in the process of distributing tasks by the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit, if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched to;
and returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
In some embodiments, the task change or the change of the association where the unmanned aerial vehicle is located specifically includes: the task importance changes, newly added tasks appear, and a plurality of unmanned aerial vehicles in the alliance where the unmanned aerial vehicle is located fail.
The invention also provides an unmanned aerial vehicle cluster multitask dynamic allocation system, which comprises: an unmanned aerial vehicle;
the unmanned aerial vehicle is used for:
acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes a task;
when the task change is detected or the alliance where the unmanned aerial vehicle is located is changed, judging whether the current task can bring the maximum benefit;
if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to an unmanned aerial vehicle benefit formula, adding an alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating times for one time, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction;
broadcasting interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
and updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the profit formula of the unmanned aerial vehicle, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times once, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
In some embodiments, a ground station is also included;
the ground station is configured to:
randomly sequencing all unmanned aerial vehicles to obtain a random sequencing result;
selecting an unmanned aerial vehicle in sequence according to the random sequencing result;
calculating the individual profit of each task selected by the unmanned aerial vehicle according to the number of the unmanned aerial vehicles required by each task in the initial task information;
distributing the task corresponding to the maximum individual profit to the unmanned aerial vehicle, and updating a task distribution result; in the process of distributing tasks by the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit, if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched to;
and returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
In some embodiments, when detecting that the task changes or the alliance in which the unmanned aerial vehicle is located changes, determining whether the current task can bring the maximum benefit includes:
when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit according to the unmanned aerial vehicle benefit formula; the unmanned aerial vehicle income formula is:
wherein the content of the first and second substances,
indicating the benefit of the drone i,
indicating the number of drones selecting task m,
is a relatively large random number, di,mRepresenting the distance of drone i from task m,
representing the fuel consumption of the drone per unit distance,
indicating the set of tasks, num, that drone i can selectmRepresenting the number of drones required for task m,
represents the profit of task m when
Less than nummBecause the number requirement of the unmanned aerial vehicles is not met, the alliance yield is zero; when in use
Num or moremSatisfy unmanned aerial vehicle quantity demand, set up the alliance profit into the task profit this moment.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides an unmanned aerial vehicle cluster multi-task dynamic allocation method and system, which utilize a design method of two layers of alliances, firstly, a ground station is used as a decision-making main body to carry out task initial allocation, then an unmanned aerial vehicle is used as the decision-making main body to carry out task reallocation, firstly, a ground station task allocation result is obtained and executed, when the task change or the alliance where the unmanned aerial vehicle is located is found, whether the current task can bring the maximum profit is judged, if the maximum profit cannot be brought, the alliance corresponding to the maximum profit is searched and added, meanwhile, the number of updating times is increased once every time the task is converted, and the accuracy of corresponding local information is judged by combining the number of updating times of each unmanned aerial vehicle, so that various emergency situations of the unmanned aerial vehicle in the task execution process can be fully considered, and the problem that the emergency situations cannot be considered in the prior art is effectively solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic diagram of task allocation of an unmanned aerial vehicle cluster according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for dynamically allocating multiple tasks to an unmanned aerial vehicle cluster according to an embodiment of the present invention.
Fig. 3 is a flowchart of decision making of the unmanned aerial vehicle according to the first embodiment of the present invention.
Fig. 4 is a flowchart of a ground station decision making process according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a convergence rate of an initial task allocation method using a ground station as a decision-making subject according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a convergence rate of the task reallocation method using an unmanned aerial vehicle as a decision main body according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of an initial task allocation simulation using a ground station as a decision making subject according to an embodiment of the present invention.
Fig. 8 is a schematic diagram of simulation of initial task allocation to achieve nash stable partitioning according to an embodiment of the present invention.
Fig. 9 is a schematic view of simulation of the influence of the task increment on the unmanned aerial vehicle according to the first embodiment of the present invention.
Fig. 10 is a schematic diagram of task reallocation simulation using an unmanned aerial vehicle as a decision making subject according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide an unmanned aerial vehicle cluster multi-task dynamic allocation method and system.
The invention provides an unmanned aerial vehicle cluster multi-task dynamic allocation scheme based on a double-layer alliance, which combines two layers of ground station task allocation and unmanned aerial vehicle distributed redistribution, and establishes an unmanned aerial vehicle cluster task allocation problem model by utilizing a hedonic game; the initial task allocation of the ground station is completed by using a union formation algorithm, as shown in fig. 1(a), and the task reallocation is performed by using two stages of task selection and conflict resolution, as shown in fig. 1 (b). A virtual real-time verification platform is set up through the Unity3D, a scene that tasks are dynamically allocated after task changes (such as changes in task importance, newly added tasks and the like) and other emergencies (such as failure of an unmanned aerial vehicle and the like) are generated is simulated, the scheme integrity is good, the module replacement is easy, and the method is a set of system schemes with great value.
After the ground station completes initial allocation according to the known task information, the invention considers the emergency situation in the unmanned aerial vehicle task execution and adopts two stages of task selection and conflict resolution to realize the task reallocation. In the task selection stage, each unmanned aerial vehicle selects the most preferred task according to the current local information; in a conflict resolution stage, each unmanned aerial vehicle and adjacent machines exchange information, an optimal distribution scheme in a neighborhood is determined according to respective iteration times and time stamps, and conflicts are selected by autonomous resolution tasks. The method has the advantages of high convergence speed and good robustness.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The first embodiment is as follows:
as shown in fig. 2, this embodiment provides a method for dynamically allocating multiple tasks to an unmanned aerial vehicle cluster, where the method is implemented based on a hedonic game, and when a problem is solved by using the hedonic game, a hedonic game model needs to be established first, and then a coalition formation algorithm is designed.
The enjoyment game model can be used
Is shown in which
Representing participants and u representing federation revenue. Multitask dynamic partitioning for unmanned aerial vehicle clusterMatch problem, participant set
And federation revenue u is specifically defined as follows:
(1) participant collection
The V-rack drones performing the task are taken as participants, and therefore, the set of participants in the hedonic game can be represented as:
(2) alliance return u
Design alliance revenue by considering constraint conditions and task revenue
Number of drones, num, representing selection task mmRepresenting the number of drones required for task m,
representing the benefit of task m. When in use
Less than nummBecause the number requirement of the unmanned aerial vehicles is not met, the alliance yield is zero; when in use
Num or moremSatisfy unmanned aerial vehicle quantity demand, set up the alliance profit into the task profit this moment. Therefore, for the drone, the league revenue corresponding to each task can be expressed as:
wherein the content of the first and second substances,
representing a set of tasks, with a federation yield of 0 for empty tasks.
The league revenue is generally evenly distributed to the intra-league drones, and the present embodiment sets the i revenue of the drone as follows:
wherein the content of the first and second substances,
the unmanned aerial vehicle number is a larger random number and a randomly formulated constant, when the number requirement of the unmanned aerial vehicles is not met, the income of the unmanned aerial vehicles is larger than the income of selecting other tasks, so that the unmanned aerial vehicles cannot select other tasks, the number of the unmanned aerial vehicles required by the tasks can be reduced as soon as possible, and di,mRepresenting the distance of drone i from task m,
representing the fuel consumption of the drone per unit distance,
representing the set of tasks that drone i can select. In the hedonic game of the unmanned aerial vehicle cluster multi-task dynamic distribution system, each unmanned aerial vehicle aims at finding a task which enables the self income to be maximum.
In the method for dynamically allocating multiple tasks to a cluster of unmanned aerial vehicles provided in this embodiment, the steps specifically executed by each unmanned aerial vehicle include:
s1, acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; and the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes one task.
And S2, when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit.
S3, if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
s4, if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to the unmanned aerial vehicle benefit formula, adding the alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating frequency once, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction; local information in this embodiment refers to the task allocation result that this unmanned aerial vehicle can acquire, because of the restriction of communication distance, this unmanned aerial vehicle can only carry out information interaction with the unmanned aerial vehicle in the certain distance on every side, and colloquially says, local information refers to the current global task allocation result that unmanned aerial vehicle thinks.
S5, broadcasting the interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
s6, comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
s7, updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the unmanned aerial vehicle profit formula, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times for one time, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
Specifically, the drone flies to the respective mission area according to the mission assigned by the ground station. However, in the flight or task execution process, along with the change of time, the task importance may change, and an emergency such as a newly added task or an unmanned aerial vehicle failure may occur, while the ground station is usually far from the task area, and the update of the task information is not timely, under such a dynamic condition, the unmanned aerial vehicle i judges whether the current task can bring the maximum benefit according to formula (2), and if not, the distributed task reallocation needs to be completed.
In the layer of federation, each iterative process of task reallocation comprises two stages of task selection-conflict resolution. In the task selection stage, each unmanned aerial vehicle selects the most preferred task according to the current local information. The local information refers to a task allocation result considered by the unmanned aerial vehicle, and is obtained by unmanned aerial vehicle information interaction between adjacent unmanned aerial vehicles. And each unmanned aerial vehicle can only select tasks based on the existing local information due to the limitation of the communication range. However, the selection of other drones contained in the information is not accurate (because of the limited communication distance of the drones, the information of "tasks allocated by drones outside the communication range" that the drones store "may not be accurate, for example, because the drones i and the drone j cannot directly communicate because of too far distance, in a certain iteration, the drone j in the global task allocation result stored by the drone i is allocated to the task m, but the benefit of selecting the task n by the drone j is greater than that of the task m, then the drone j no longer selects the task m but selects the task n, and this information drone j can be transmitted to the drones within the communication range, but the drone i does not know the change in the current iteration, so the information of the drone i is not accurate, each drone stores the allocation results of all the tasks of all the drones, but the drone outside the communication range (supposing j) if the task is replaced, if the information is not transmitted yet, the task allocation result of the drone j in the task allocation result stored by the drone j is actually inaccurate), so that the result may not be the optimal result, and in order to solve the problem, a conflict resolution stage is introduced. And in the conflict resolution stage, each unmanned aerial vehicle and the adjacent machines exchange information. Take unmanned aerial vehicle i as an example, wherein mutual information includes: iteration number iterationiThe iteration times refer to the times of the unmanned aerial vehicle executing the task selection stage; random timestamp stamp for drone iiWherein the random time stamp is generated between 0-1; state of unmanned aerial vehicle iiAnd consists of 0 and 1, wherein 0 is in an unsatisfactory state, and 1 is in a satisfactory state. Determining the optimal distribution scheme in the neighborhood according to the iteration times and the time stamp (certain unmanned iteration)The higher the generation times and the timestamp are, the more comprehensive the information mastered by the user is, and the more credible the task allocation result), and the conflict resolution is completed.
As an alternative implementation, as shown in fig. 3, from the perspective of the entire unmanned aerial vehicle fleet, the specific task reallocation in this embodiment may be implemented by the following steps:
take unmanned aerial vehicle i as an example:
initializing piiEqual to the above ground station task decision resultiEqual to zero, stampiIs equal to zero; when the alliance where the unmanned aerial vehicle i is located changes or detects that the task changes, the unmanned aerial vehicle i is in an unsatisfied state, namely stateiIf not, the unmanned aerial vehicle i pi makes a decision on the current decision resultiSatisfaction, i.e. statei＝1；
If all the unmanned aerial vehicles are in a satisfactory state, the task redistribution algorithm is converged, and the algorithm is finished, otherwise, the unmanned aerial vehicle i executes the step three;
and a task selection stage:
a) judging whether the unmanned aerial vehicle i is in a satisfied state according to a formula (2);
b) when stateiWhen 1, it means that the unmanned aerial vehicle i pi allocates an allocation resultiIf satisfactory, executing step e);
c) when stateiWhen the value is 0, the unmanned aerial vehicle i transmits the distribution result iiiIs not satisfactory. At IIiThe task with the maximum profit is found, and the task is assumed to be m. If m is not equal to Πi(i)，Πi(i) Local information II expressed in unmanned aerial vehicle iiThe recorded task selected by the unmanned aerial vehicle i means that the unmanned aerial vehicle i can obtain higher unmanned aerial vehicle income when joining other alliances, and then leaves the current alliance
Joining a New alliance
And renew pii，iterationi＝iterationi+1, randomly generating a timestamp stampiRand (0, 1). If it ism*＝Πi(i) Mean unmanned aerial vehicleiThe current alliance
Is optimal, no alliance change is required;
d) because the unmanned aerial vehicle i selects the task which can bring the maximum profit, the unmanned aerial vehicle i becomes the satisfied state, namely the statei＝1；
e) Unmanned aerial vehicle i broadcasts message to all neighboring machinesi＝{iterationi,stampi,ΠiThe update times of unmanned aerial vehicle i are includediTimestamp stampiGlobal task allocation result pi stored by unmanned aerial vehicle iiAnd receiving message of all neighbork,
Wherein, neighbor isiAnd the adjacent plane of the unmanned plane i is determined by whether the communication is possible or not.
Fourthly, conflict resolution stage:
a) comparing all received messages by the unmanned aerial vehicle i, and selecting the message with the largest updating frequency, assuming that the message is from the adjacent machine k;
b) unmanned plane i contrast messageiAnd messagekWhen the operation is performedk>iterationiOr iterationk＝iterationi、stampk＞stampiIn time, it means local information pi of unmanned aerial vehicle kkGreater than piiMore effectively, unmanned aerial vehicle i changes self renewal number of times, timestamp, local information and state, carries out following operation: iterationi＝iterationk,stampi＝stampk,Πi＝Πk,statei＝0
Therein, IIkThe task of the drone i is not necessarily the one that maximizes the profit, and the state of the drone i becomes unsatisfactory. When the iteration is carried outk<iterationiOr iterationk＝iterationi、stampk≤stampiIn time, local information pi of unmanned aerial vehicle i is meantiMost efficient within the range of the neighboring drone, drone i does not need to perform any operations. Based on the steps, the unmanned aerial vehicle i completes conflict resolution in the range of the adjacent aircraft, and the task decision results are agreed. And returning to the step II.
When all the unmanned aerial vehicles are in a satisfactory state, the task reallocation algorithm converges.
In this embodiment, before each unmanned aerial vehicle acquires a task allocation result of a ground station and flies to a corresponding task area according to the task allocation result of the ground station, the ground station completes initial allocation by using an alliance formation algorithm according to known initial task information, and the specific steps are as follows:
and the ground station randomly sorts all the unmanned aerial vehicles to obtain a random sorting result.
And the ground station selects an unmanned aerial vehicle in sequence according to the random sequencing result.
The ground station calculates the individual benefit of each task selected by the drone using equation (2) in conjunction with the number of drones required for each task in the initial task information. Here the ground station stands at the holistic angle, distributes the task for every unmanned aerial vehicle one by one.
The ground station distributes the task corresponding to the maximum individual income to the unmanned aerial vehicle and updates the task distribution result; in the process of distributing tasks at the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit by using a formula (2), if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched. In addition, each unmanned aerial vehicle stands at the angle of the unmanned aerial vehicle, and whether the task allocated to the unmanned aerial vehicle is the largest or not is judged.
And returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
As an alternative implementation, in this embodiment, the ground station completes the initial assignment of the task according to the following steps. Firstly, randomly sequencing all unmanned aerial vehicles by a ground station, and setting each unmanned aerial vehicle task as null; then, the ground station iteratively performs the following steps: the ground station selects an unmanned aerial vehicle in sequence, the individual income of each task in the unmanned aerial vehicle selection initial task information is calculated according to the formula (2), a task which makes the unmanned aerial vehicle prefer (the individual income is the maximum) is selected, the task is distributed to the unmanned aerial vehicle, the task distribution result is updated, whether the task distribution result is a Nash stable partition is judged (when all unmanned aerial vehicles are satisfied with the partition of the unmanned aerial vehicle, the Nash stable partition is reached), the unmanned aerial vehicle which selects the same task can be regarded as a union, and the task distribution is that a group of unmanned aerial vehicles are divided into a plurality of unions, namely, the unmanned aerial vehicles are divided into a plurality of areas. If Nash stable subareas are reached, stopping iteration and outputting distribution results, otherwise, the ground station continuously selects an unmanned aerial vehicle according to the sequence generated by random sequencing, calculates the individual income of each task selected by the unmanned aerial vehicle according to the formula (2), selects a task which makes the unmanned aerial vehicle prefer (the individual income is maximum), distributes the task to the unmanned aerial vehicle, and updates the task distribution results.
Let Π denote the current task partition, take unmanned aerial vehicle i as an example, in order to form a stable partition, unmanned aerial vehicle i will continuously perform task switching, and change the task that needs to be performed by itself into the task with the largest profit. Judging whether the partition is a Nash stable partition or not, and meeting the requirement when the unmanned aerial vehicle i is preferred to the partition where the unmanned aerial vehicle is located currently
The allocation result is said to reach Nash stable partition, where ≧iIndicating a weak preference, Π (i) indicating the task selected by drone i,
the set of drones representing the selection task Π (i).
In this layer of federation, the ground station assigns an appropriate drone to each known task based on the known task information. The main flow is shown in fig. 4.
The embodiment is an unmanned aerial vehicle cluster multi-task dynamic allocation system based on a double-layer alliance. Firstly, the influence of constraints such as task requirements, task types and unmanned aerial vehicle capacity is comprehensively considered, and a problem model is established by taking the maximum benefit-loss ratio as a target. Secondly, designing an initial distribution method taking the ground station as a decision-making subject to complete a first layer of alliance; considering the situations of task change (such as change of task importance, newly added task and the like) and other emergencies (such as failure of the unmanned aerial vehicle and the like) of the unmanned aerial vehicle in the task execution process, a task reallocation method taking the unmanned aerial vehicle as a decision main body is designed to complete the second layer of alliance. And finally, a virtual real-time verification platform is set up, a simulation test is carried out on the dynamic task allocation process of the cluster unmanned aerial vehicle, and the effectiveness and the feasibility of the scheme are verified. The convergence rate of the initial task allocation method with the ground station as the decision subject is verified, and the statistical results of the convergence under different unmanned aerial vehicle scales and task scales are shown in fig. 5. The convergence speed and effectiveness of the task reallocation method using the unmanned aerial vehicle as the decision subject are verified, and the statistical result of the convergence under the change of the number of the unmanned aerial vehicles and the number of the tasks is shown in fig. 6.
In order to verify the effectiveness of the unmanned aerial vehicle cluster multi-task dynamic allocation scheme based on the double-layer game, a virtual real-time verification platform is set up in the embodiment, the simulation computer runs the task allocation method, and a real-time control instruction is given according to parameter information sent by the view computer and is transmitted back to the view computer. A vision computer is matched with a high-performance display card to run a vision software and database management module, wherein the vision demonstration software is developed based on a Unity3D game engine to construct a vivid three-dimensional visual virtual scene; and the database management module is developed based on MySQL and is used for storing and managing data such as a task allocation scheme and instructions in the task execution process of the unmanned aerial vehicle. The vision computer completes information updating of the unmanned aerial vehicle and the tasks according to the received control instruction, as shown in fig. 7-10, fig. 7 is initial task allocation with the ground station as a decision main body, fig. 8 is that the initial task allocation reaches nash stable partition, fig. 9 is that the unmanned aerial vehicle is influenced by task addition, and fig. 10 is task reallocation with the unmanned aerial vehicle as a decision main body.
The unmanned aerial vehicle cluster multi-task dynamic allocation system based on the double-layer alliance can effectively solve the problem of cooperative cooperation among all intelligent agents in a large-scale scene, improves the intelligence of the intelligent agents, and has great application value and very wide application prospect. Applications in the military field may include multi-agent cooperative reconnaissance combat, multi-agent cooperative radar interference, multi-agent cooperative regional patrol, and the like. And the method can also be used for emergency rescue in the fields of traffic detection, aerospace and the like. In a complex unmanned dynamic environment, tasks can be reasonably distributed according to the field environment and rescue resources, and the rescue robot multi-agent system is controlled to effectively complete the rescue tasks in the shortest time.
Example two:
this embodiment provides an unmanned aerial vehicle cluster multitask dynamic allocation system, and this system includes: an unmanned aerial vehicle;
the unmanned aerial vehicle is used for:
acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes a task;
when the task change is detected or the alliance where the unmanned aerial vehicle is located is changed, judging whether the current task can bring the maximum benefit;
if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to an unmanned aerial vehicle benefit formula, adding an alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating times for one time, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction;
broadcasting interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
and updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the profit formula of the unmanned aerial vehicle, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times once, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
The unmanned aerial vehicle cluster multitask dynamic distribution system also comprises a ground station;
the ground station is configured to:
randomly sequencing all unmanned aerial vehicles to obtain a random sequencing result;
selecting an unmanned aerial vehicle in sequence according to the random sequencing result;
calculating the individual benefit of each task selected by the unmanned aerial vehicle according to the number of the unmanned aerial vehicles required by each task in the initial task information;
distributing the task corresponding to the maximum individual profit to the unmanned aerial vehicle, and updating a task distribution result; in the process of distributing tasks by the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit, if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched to;
and returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
When detecting that the task changes or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit or not, and specifically comprising the following steps:
when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit according to the unmanned aerial vehicle benefit formula; the unmanned aerial vehicle income formula is:
wherein the content of the first and second substances,
representing the unmanned aerial vehicle i,
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. An unmanned aerial vehicle cluster multitask dynamic allocation method is characterized by comprising the following steps:
acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes a task;
when the task change is detected or the alliance where the unmanned aerial vehicle is located is changed, judging whether the current task can bring the maximum benefit;
if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to an unmanned aerial vehicle benefit formula, adding an alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating times for one time, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction;
broadcasting interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
and updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the profit formula of the unmanned aerial vehicle, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times once, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
2. The method according to claim 1, wherein when a task change is detected or a change occurs in an alliance in which the drone is located, determining whether a current task can bring a maximum benefit includes:
when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit according to the unmanned aerial vehicle benefit formula; the unmanned aerial vehicle income formula is:
wherein the content of the first and second substances,
indicating the benefit of the drone i,
indicating the number of drones selecting task m,
is a relatively large random number, di,mRepresenting the distance of drone i from task m,
representing the fuel consumption of the drone per unit distance,
indicating the set of tasks, num, that drone i can selectmRepresenting the number of drones required for task m,
represents the profit of task m when
Less than nummBecause the number requirement of the unmanned aerial vehicles is not met, the alliance yield is zero; when in use
Num or moremSatisfy unmanned aerial vehicle quantity demand, set up the alliance profit into the task profit this moment.
3. The method of claim 1, further comprising:
the ground station randomly sorts all the unmanned aerial vehicles to obtain a random sorting result;
the ground station selects an unmanned aerial vehicle in sequence according to the random sequencing result;
the ground station calculates the individual benefit of each task selected by the unmanned aerial vehicle by combining the number of the unmanned aerial vehicles required by each task in the initial task information;
the ground station distributes the task corresponding to the maximum individual income to the unmanned aerial vehicle and updates the task distribution result;
in the process of distributing tasks by the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit, if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched to;
and returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
4. The method according to claim 1, wherein the task change or the change of the alliance where the unmanned aerial vehicle is located specifically includes: the task importance changes, newly added tasks appear, and a plurality of unmanned aerial vehicles in the alliance where the unmanned aerial vehicle is located fail.
5. An unmanned aerial vehicle cluster multitask dynamic allocation system, characterized in that the system comprises: an unmanned aerial vehicle;
the unmanned aerial vehicle is used for:
acquiring a ground station task allocation result, and flying to a corresponding task area according to the ground station task allocation result; the ground station task allocation result is obtained by allocating the ground station according to the initial task information; the ground station task allocation result is that the unmanned aerial vehicle cluster is divided into a plurality of alliances, and each alliance executes a task;
when the task change is detected or the alliance where the unmanned aerial vehicle is located is changed, judging whether the current task can bring the maximum benefit;
if the current task can bring the maximum benefit, continuing to fly to the corresponding task area according to the task allocation result of the ground station;
if the current task cannot bring the maximum benefit, searching the task with the maximum benefit in the ground station task allocation result according to an unmanned aerial vehicle benefit formula, adding an alliance corresponding to the task with the maximum benefit, updating local information, increasing the updating times for one time, and generating a random timestamp; the local information refers to task allocation results of all unmanned aerial vehicles capable of performing information interaction;
broadcasting interactive information to surrounding unmanned aerial vehicles, and receiving the interactive information of the surrounding unmanned aerial vehicles; the interaction information comprises: updating times, random time stamps and local information;
comparing all received interactive information of surrounding unmanned aerial vehicles, and selecting the interactive information with the maximum updating times;
and updating the interactive information of the unmanned aerial vehicle by using the interactive information with the maximum updating times, and returning to the step of searching the task with the maximum profit in the ground station task allocation result according to the profit formula of the unmanned aerial vehicle, adding the alliance corresponding to the task with the maximum profit, updating the local information, increasing the updating times once, and generating a random timestamp until the unmanned aerial vehicle has the maximum updating times.
6. The unmanned aerial vehicle cluster multitask dynamic allocation system of claim 5, further comprising a ground station;
the ground station is configured to:
randomly sequencing all unmanned aerial vehicles to obtain a random sequencing result;
selecting an unmanned aerial vehicle in sequence according to the random sequencing result;
calculating the individual benefit of each task selected by the unmanned aerial vehicle according to the number of the unmanned aerial vehicles required by each task in the initial task information;
distributing the task corresponding to the maximum individual profit to the unmanned aerial vehicle, and updating a task distribution result; in the process of distributing tasks by the ground station, each unmanned aerial vehicle judges whether the task distributed to the unmanned aerial vehicle is the task with the maximum profit, if so, the task distributed to the unmanned aerial vehicle is received, and if not, the task with the maximum profit is switched to;
and returning to the step that the ground station selects one unmanned aerial vehicle in sequence according to the random sequencing result until all the unmanned aerial vehicles are distributed to the task corresponding to the maximum individual income, and obtaining a ground station task distribution result.
7. The system according to claim 5, wherein when detecting a change in the task or a change in the alliance where the drone is located, determining whether the current task can bring the maximum profit specifically comprises:
when the task change is detected or the alliance where the unmanned aerial vehicle is located changes, judging whether the current task can bring the maximum benefit according to the unmanned aerial vehicle benefit formula; the unmanned aerial vehicle income formula is:
wherein the content of the first and second substances,
indicating the benefit of the drone i,
indicating the number of drones selecting task m,
is a relatively large random number, di,mRepresenting the distance of drone i from task m,
representing the fuel consumption of the drone per unit distance,
indicating the set of tasks, num, that drone i can selectmRepresenting the number of drones required for task m,
represents the profit of task m when
Less than nummBecause the number requirement of the unmanned aerial vehicles is not met, the alliance yield is zero; when in use
Num or moremSatisfy unmanned aerial vehicle quantity demand, set up the alliance profit into the task profit this moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210029987.4A CN114326827B (en) | 2022-01-12 | 2022-01-12 | Unmanned aerial vehicle cluster multitasking dynamic allocation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210029987.4A CN114326827B (en) | 2022-01-12 | 2022-01-12 | Unmanned aerial vehicle cluster multitasking dynamic allocation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114326827A true CN114326827A (en) | 2022-04-12 |
| CN114326827B CN114326827B (en) | 2023-06-09 |
Family
ID=81026595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210029987.4A Active CN114326827B (en) | 2022-01-12 | 2022-01-12 | Unmanned aerial vehicle cluster multitasking dynamic allocation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114326827B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454125A (en) * | 2022-08-31 | 2022-12-09 | 北京瀚景锦河科技有限公司 | Unmanned aerial vehicle strike alliance building method based on iterative updating algorithm |
| CN116090342A (en) * | 2023-01-06 | 2023-05-09 | 天津大学 | Distributed task allocation method for large-scale unmanned aerial vehicle based on alliance forming game |
| CN117119534A (en) * | 2023-10-20 | 2023-11-24 | 南京邮电大学 | Unmanned aerial vehicle dynamic alliance-assisted unloading strategy and resource optimization method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106506657A (en) * | 2016-11-21 | 2017-03-15 | 黑龙江省科学院自动化研究所 | One kind distributes method of adjustment based on multiobject cloud computing virtual machine |
| CN110083173A (en) * | 2019-04-08 | 2019-08-02 | 合肥工业大学 | The optimization method of unmanned plane formation patrol task distribution |
| CN110308740A (en) * | 2019-06-28 | 2019-10-08 | 天津大学 | A kind of unmanned aerial vehicle group dynamic task allocation method towards mobile target tracking |
| CN111199360A (en) * | 2020-01-13 | 2020-05-26 | 西安电子科技大学 | Unmanned aerial vehicle task allocation planning method |
| CN111311049A (en) * | 2019-12-04 | 2020-06-19 | 南京理工大学 | Multi-agent task allocation method based on income maximization |
| US20200293374A1 (en) * | 2019-03-13 | 2020-09-17 | Tata Consultancy Services Limited | Method and system for privacy enabled task allocation |
| CN112910716A (en) * | 2021-03-08 | 2021-06-04 | 北方工业大学 | Mobile fog calculation loss joint optimization system and method based on distributed DNN |
| CN113009934A (en) * | 2021-03-24 | 2021-06-22 | 西北工业大学 | Multi-unmanned aerial vehicle task dynamic allocation method based on improved particle swarm optimization |
| EP3842890A1 (en) * | 2019-12-26 | 2021-06-30 | UVify Inc. | Unmanned aerial vehicle for fleet operation and fleet operation system |
| WO2021135336A1 (en) * | 2020-05-06 | 2021-07-08 | 农业农村部南京农业机械化研究所 | Cluster job task assignment method and device for plant-protection unmanned aerial vehicles |
| WO2021179550A1 (en) * | 2020-03-11 | 2021-09-16 | 五邑大学 | Task dispatch decision making method and system for unmanned aerial vehicle cluster |
| US20210294356A1 (en) * | 2020-03-19 | 2021-09-23 | Beihang University | Dynamic recovery method and system for uavs and storage medium |
-
2022
- 2022-01-12 CN CN202210029987.4A patent/CN114326827B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106506657A (en) * | 2016-11-21 | 2017-03-15 | 黑龙江省科学院自动化研究所 | One kind distributes method of adjustment based on multiobject cloud computing virtual machine |
| US20200293374A1 (en) * | 2019-03-13 | 2020-09-17 | Tata Consultancy Services Limited | Method and system for privacy enabled task allocation |
| CN110083173A (en) * | 2019-04-08 | 2019-08-02 | 合肥工业大学 | The optimization method of unmanned plane formation patrol task distribution |
| CN110308740A (en) * | 2019-06-28 | 2019-10-08 | 天津大学 | A kind of unmanned aerial vehicle group dynamic task allocation method towards mobile target tracking |
| CN111311049A (en) * | 2019-12-04 | 2020-06-19 | 南京理工大学 | Multi-agent task allocation method based on income maximization |
| EP3842890A1 (en) * | 2019-12-26 | 2021-06-30 | UVify Inc. | Unmanned aerial vehicle for fleet operation and fleet operation system |
| CN111199360A (en) * | 2020-01-13 | 2020-05-26 | 西安电子科技大学 | Unmanned aerial vehicle task allocation planning method |
| WO2021179550A1 (en) * | 2020-03-11 | 2021-09-16 | 五邑大学 | Task dispatch decision making method and system for unmanned aerial vehicle cluster |
| US20210294356A1 (en) * | 2020-03-19 | 2021-09-23 | Beihang University | Dynamic recovery method and system for uavs and storage medium |
| WO2021135336A1 (en) * | 2020-05-06 | 2021-07-08 | 农业农村部南京农业机械化研究所 | Cluster job task assignment method and device for plant-protection unmanned aerial vehicles |
| CN112910716A (en) * | 2021-03-08 | 2021-06-04 | 北方工业大学 | Mobile fog calculation loss joint optimization system and method based on distributed DNN |
| CN113009934A (en) * | 2021-03-24 | 2021-06-22 | 西北工业大学 | Multi-unmanned aerial vehicle task dynamic allocation method based on improved particle swarm optimization |
Non-Patent Citations (4)
| Title |
|---|
| AN ZHANG 等: "Dynamic Task Allocation for Formation Air-to-ground Attack", 《2013 SIXTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE》 * |
| NA XING 等: "A Game Theoretic Approach for Mobility Prediction Clustering in Unmanned Aerial Vehicle Networks", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 * |
| 林晨: "面向无人机集群任务分配的分布式算法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 王然然 等: "考虑协同航路规划的多无人机任务分配", 《航空学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454125A (en) * | 2022-08-31 | 2022-12-09 | 北京瀚景锦河科技有限公司 | Unmanned aerial vehicle strike alliance building method based on iterative updating algorithm |
| CN116090342A (en) * | 2023-01-06 | 2023-05-09 | 天津大学 | Distributed task allocation method for large-scale unmanned aerial vehicle based on alliance forming game |
| CN116090342B (en) * | 2023-01-06 | 2023-09-01 | 天津大学 | Distributed task allocation method for large-scale unmanned aerial vehicle based on alliance forming game |
| CN117119534A (en) * | 2023-10-20 | 2023-11-24 | 南京邮电大学 | Unmanned aerial vehicle dynamic alliance-assisted unloading strategy and resource optimization method |
| CN117119534B (en) * | 2023-10-20 | 2023-12-19 | 南京邮电大学 | Unmanned aerial vehicle dynamic alliance-assisted unloading strategy and resource optimization method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114326827B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114326827A (en) | Unmanned aerial vehicle cluster multi-task dynamic allocation method and system | |
| Dai et al. | Quality-aware UAV coverage and path planning in geometrically complex environments | |
| Li et al. | Trajectory planning for UAV based on improved ACO algorithm | |
| Tang et al. | Dynamic reallocation model of multiple unmanned aerial vehicle tasks in emergent adjustment scenarios | |
| Fu et al. | Swarm UAVs task and resource dynamic assignment algorithm based on task sequence mechanism | |
| CN108717572B (en) | Imaging task schedulability prediction method based on structured neural network | |
| CN111722643A (en) | Unmanned aerial vehicle cluster dynamic task allocation method imitating wolf colony cooperative hunting mechanism | |
| Peng et al. | Review of dynamic task allocation methods for UAV swarms oriented to ground targets | |
| Yao et al. | Task allocation strategies for cooperative task planning of multi-autonomous satellite constellation | |
| Huang et al. | A multi-robot coverage path planning algorithm for the environment with multiple land cover types | |
| CN114185362A (en) | Unmanned aerial vehicle cluster task dynamic allocation method based on suburb information entropy | |
| CN109597839B (en) | Data mining method based on avionic combat situation | |
| Sabo et al. | A formulation and heuristic approach to task allocation and routing of uavs under limited communication | |
| CN112327927B (en) | Multi-angle strike track planning method for formation unmanned aerial vehicles based on grid planning algorithm | |
| Sujit et al. | Self assessment-based decision making for multiagent cooperative search | |
| CN107622699A (en) | All the period of time spatial domain conflict probe and solution desorption method based on sequential | |
| Deng et al. | A two-phase coordinated planning approach for heterogeneous earth-observation resources to monitor area targets | |
| CN111580561A (en) | Unmanned aerial vehicle scheduling method and system based on particle swarm optimization and readable storage medium | |
| CN113485409A (en) | Unmanned aerial vehicle path planning and distribution method and system for geographic fairness | |
| CN108830449A (en) | It takes photo by plane unmanned plane choosing method and system | |
| Wu et al. | Integrate assignment of multiple heterogeneous unmanned aerial vehicles performing dynamic disaster inspection and validation task with Dubins path | |
| Xie et al. | Mathematical problems in engineering improved CNP‐Method‐Based local real‐time cooperative task allocation of heterogeneous multi‐UAV in communication‐constrained environment | |
| CN116088396B (en) | Unmanned cluster double-layer cooperative task control method and system | |
| Zu et al. | Research on UAV path planning method based on improved HPO algorithm in multi-task environment | |
| Yuksek et al. | Intelligent wargaming approach to increase course of action effectiveness in military operations |
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 |