A fast cooperative task allocation method adaptive to group dynamic change

Abstract

The application discloses a kind of quick cooperative task allocation methods suitable for group dynamic change, using dynamic decision center and each flight platform node distributed simultaneous calculation decision mode, by the optimal allocation of distributed node to decision center recommend, and the optimal allocation mode of decision center to all nodes, optimal allocation result coordination is realized, frequent allocation information interaction is avoided, and global allocation consistency convergence speed is increased;By using random selection flight platform and task target matching calculation, increase global optimization ability, each flight platform node distributed simultaneous calculation, increase matching optimization efficiency, limit each node optimization iteration number, ensure that approximate optimal decision result is quickly obtained, realize quick cooperative task allocation under the dynamic change of cluster.

Description

TECHNICAL FIELD

[0001] The application relates to a cluster cooperative task allocation method, in particular to a fast cooperative task allocation method suitable for dynamic changes of a group, and belongs to the technical field of cluster cooperative task decision. BACKGROUND

[0002] With the maturity of unmanned equipment technology and the rapid development of artificial intelligence technology, intelligent unmanned cluster cooperation to perform tasks has gradually become the norm, and multi-agent cooperative task allocation is the key to exerting the cooperative capability of the cluster. In aerial combat tasks, the group size and networking mode of the aircraft of both sides of the confrontation are various, and the number of clusters, the relative position in space, and the dynamic changes of inter-cluster communication state in the confrontation process. Therefore, it is necessary to solve the optimal task allocation strategy online in real time according to the real-time situation changes to improve the cooperative efficiency of the group.

[0003] At present, the cooperative task allocation method is divided into centralized allocation and distributed allocation according to the cooperative information processing mode. In the high dynamic environment of aerial combat, the distributed allocation method is more concerned due to its strong system robustness and the advantage of autonomous decision of each node. The patent (CN111489049A) of Beijing University of Technology proposes a multi-agent distributed task allocation method, which uses the idea of auction algorithm to allocate tasks under the condition of local communication of communication topology, and solves the problem of multi-agent distributed task allocation under the condition of local communication. The patent (CN117892933A) of the 28th Research Institute of China Electronics Technology Group proposes a multi-unmanned aerial vehicle real-time distributed task allocation and redistribution method, which solves the problems of unreasonable task allocation and redistribution and low running efficiency, and realizes real-time generation of multi-unmanned aerial vehicle multi-task pre-allocation and redistribution scheme. The patent (CN118377608A) of the University of Defense Science and Technology proposes a distributed task allocation method and system based on an auction algorithm, which fully utilizes the computing resources of each agent in the multi-agent system to improve the efficiency and speed of task allocation, and is suitable for large-scale, heterogeneous and dynamic agent systems. However, the existing distributed task allocation method is mainly improved based on the auction algorithm, and has the following problems:

[0004] (1) The complete distributed information interaction needs high inter-group communication quality as a guarantee. The task publisher and the bidder need to interact information multiple times to determine the final allocation scheme, which requires stable communication connection and high communication bandwidth between groups.

[0005] (2) The complete distributed information interaction is difficult to adapt to the high dynamic change environment of the group. In the high dynamic change environment of the number of cluster individuals, the number of targets, and the relative position of the two sides of the confrontation, the multi-round interaction of the complete distributed allocation needs to spend more time, and it is difficult to quickly reach a global consistent allocation, and the group coordination speed is insufficient. SUMMARY

[0006] The present application aims at overcoming the above-mentioned deficiencies of the prior art, and provides a fast cooperative task allocation method suitable for population dynamic change, which solves the problem of frequent information interaction required by the distributed allocation method; the present application further solves the problem of difficulty in quickly reaching global consistency caused by the dynamic change of cluster quantity and communication network.

[0007] To achieve the above-mentioned purpose, the present application provides a fast cooperative task allocation method suitable for population dynamic change, and the implementation steps are as follows:

[0008] Step 1: setting storage flight platform node state set {Sm} and task set {Tn} variables, initializing the sets as empty sets;

[0009] Step 2: obtaining the node state from the local, and receiving other node states from the cluster communication network, adding the node states participating in the task allocation into the node state set {Sm}, and the single node state at least includes the number, position, speed, execution task state and timestamp information of the flight platform;

[0010] Step 3: maintaining the task decision center node according to the data in the node state set {Sm}, which is used for optimal task allocation release;

[0011] Step 4: receiving all task states from the local and other nodes, and putting the tasks needing to participate in the allocation into the cluster task set {Tn}, and the single task information at least includes the number, position, type and timestamp information of the task target;

[0012] Step 5: calculating the optimal task allocation according to the node state set {Sm} and the cluster task set {Tn};

[0013] Step 6: if it is the first calculation, updating the historical optimal allocation with the calculated optimal task allocation; otherwise, judging whether the calculated optimal task allocation is better than the historical optimal allocation. If yes, turning to step 7; if no, turning to step 9;

[0014] Step 7: updating the historical optimal allocation with the calculated optimal task allocation;

[0015] Step 8: marking the allocation state as having local update;

[0016] Step 9: marking the allocation state as not having local update;

[0017] Step 10: reading data from the network port, and judging whether a new optimal allocation is received. If yes, turning to step 11; if no, turning to step 14;

[0018] Step 11: judge whether the received new optimal allocation is better than the local historical optimal allocation; if yes, go to step 12; if no, go to step 14;

[0019] Step 12: update the local historical optimal allocation with the received new optimal allocation;

[0020] Step 13: mark the allocation state as having external update;

[0021] Step 14: judge whether the current node is the task decision center; if yes, go to step 15; if no, go to step 18;

[0022] Step 15: judge whether the allocation state has update, i.e. whether there is local update or external update; if yes, go to step 16; if no, go to step 17;

[0023] Step 16: publish the historical optimal task allocation to all nodes;

[0024] Step 17: return to step 2;

[0025] Step 18: judge whether the allocation state has local update; if yes, go to step 19; if no, go to step 17;

[0026] Step 19: publish the historical optimal task allocation to the decision center node, and return to step 2.

[0027] Further, the step 3 of maintaining the task decision center node is implemented as follows:

[0028] Step 3.1: judge whether the current node number is the smallest in all nodes according to the data in the node state set {Sm}; if yes, go to step 3.2; if no, go to step 3.8;

[0029] Step 3.2: the current node calculates the maintained task decision center number;

[0030] Step 3.3: calculate the cluster center coordinates (X, Y) to obtain the average center position of all nodes, and the calculation method is as follows:

[0031]

[0032] Step 3.4: calculate the average center of all nodes and the relative distance of all nodes, and select the node closest to the distance as the decision center;

[0033] Step 3.5: judge whether to update the decision center number, compare the newly calculated decision center with the historically stored decision center, if consistent, go to step 3.6; if inconsistent, go to end calculation;

[0034] Step 3.6: publish the task decision center number to all nodes;

[0035] Step 3.7: update the local task decision center number, end the calculation;

[0036] Step 3.8: judge whether a new decision center number is received, if yes, go to step 3.9; if no, end the calculation;

[0037] Step 3.9: update the local task decision center number, end the calculation.

[0038] Further, the optimal task allocation calculation in step 5 is implemented as follows:

[0039] Step 5.1: judge whether there is a task to be allocated, if the task set {Tn} is not empty, there is a task to be allocated, go to step 5.2; otherwise, end the calculation;

[0040] Step 5.2: set the optimization number k to 0, and set the optimization limit number N, where N is determined by the product of the total number of flight platform nodes Nm and the total number of tasks Nt, and the maximum value of N should be limited according to the requirement of decision speed, so as to reduce the calculation time in the case of large number of clusters and tasks, when the task allocation calculation time is required to be within tens of milliseconds, the maximum value of N is set to within 100, and when the task allocation calculation time is allowed to be larger, the maximum value of N can be appropriately increased;

[0041] Step 5.3: judge whether the optimization number k is less than the optimization limit number N; if yes, go to step 5.4; otherwise, end the calculation;

[0042] Step 5.4: assign the node state set {Sm} to the new node state set {Smn};

[0043] Step 5.5: randomly select a node from the node state set {Smn} for task pairing, and remove the selected node from {Smn} and update {Smn};

[0044] Step 5.6: set the index number i of the task in the task set to 0;

[0045] Step 5.7: judge whether the index number i of the task reaches the total number of tasks; if yes, go to step 5.11; otherwise, go to step 5.8;

[0046] Step 5.8: match the task with index number i selected from the task set {Tn} with the node selected in step 5.5;

[0047] Step 5.9: judging whether the selected node matches the task; if yes, going to step 5.10; otherwise, going to step 5.16; the judging criterion of the matching success includes at least that the flight platform represented by the node can reach the location of the task and the flight platform has a greater maneuverability than the target when reaching the location;

[0048] Step 5.10: selecting the assignment relationship storage value distribution result set {A};

[0049] Step 5.11: judging whether the node state set {Smn} is an empty set; if yes, going to step 5.12; otherwise, going to step 5.4;

[0050] Step 5.12: calculating the generation value under the current assignment relationship;

[0051] Step 5.13: judging whether the calculated generation value is better than the historical optimal assignment generation value; if yes, going to step 5.14; otherwise, going to step 5.15;

[0052] Step 5.14: updating the historical optimal assignment with the current assignment relationship and updating the generation value;

[0053] Step 5.15: adding 1 to the value of the optimization number k and going to step 5.3;

[0054] Step 5.16: adding 1 to the index number i of the task and going to step 5.7. BRIEF DESCRIPTION OF DRAWINGS

[0055] Fig. 1 The flow chart of the task assignment in an embodiment of the present application.

[0056] Fig. 2 The flow chart of the step 3 of maintaining the task decision center point in an embodiment of the present application.

[0057] Fig. 3 The flow chart of the step 5 of the task assignment calculation in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The above description is made in connection with the accompanying drawings. Figs. 1-3The present invention is further described in detail with reference to the following embodiments. The advantages and features of the present invention will become clearer according to the following description. It should be noted that the drawings are in a very simplified form and are not in precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the drawings. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions for the implementation of the present invention, so they have no technical significance. Any modification of the structure, change in the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed in the present invention without affecting the efficacy and purpose that can be achieved by the present invention.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, unmanned cluster collaborative task allocation, article or field equipment that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, unmanned cluster collaborative task allocation, article or field equipment. In the absence of further restrictions, the elements defined by the statement "including one..." do not exclude the presence of other identical elements in the process, unmanned cluster collaborative control system, article or field equipment that includes the elements.

[0060] See also Fig. 1 As shown, this embodiment provides a method for rapid collaborative task allocation that adapts to group dynamic changes. The implementation steps are as follows:

[0061] Step 1: Set the variables for storing the flight platform node state set {Sm} and the task set {Tn}, and initialize the set to an empty set;

[0062] Step 2: Obtain the node status locally and receive the status of other nodes from the cluster communication network, and add the node status participating in the task allocation to the node status set {Sm}. The status of a single node includes at least the flight platform number, position, speed, task execution status, and timestamp information;

[0063] Step 3: Maintain the task decision center node based on the data in the node status set {Sm} for optimal task allocation and release;

[0064] Step 4: Receive all task states from local and other nodes, put the tasks that need to participate in allocation into cluster task set {Tn}, single task information at least includes task target number, location, type, timestamp information;

[0065] Step 5: Calculate optimal task allocation according to node state set {Sm} and cluster task set {Tn};

[0066] Step 6: If it is the first calculation, update the historical optimal allocation with the calculated optimal task allocation; otherwise, judge whether the calculated optimal task allocation is better than the historical optimal allocation. If yes, go to step 7; if no, go to step 9;

[0067] Step 7: Update the historical optimal allocation with the calculated optimal task allocation;

[0068] Step 8: Mark the allocation state as having local update;

[0069] Step 9: Mark the allocation state as not having local update;

[0070] Step 10: Read data from network port, judge whether a new optimal allocation is received; if yes, go to step 11; if no, go to step 14;

[0071] Step 11: Judge whether the received new optimal allocation is better than the local historical optimal allocation; if yes, go to step 12; if no, go to step 14;

[0072] Step 12: Update the local historical optimal allocation with the received new optimal allocation;

[0073] Step 13: Mark the allocation state as having external update;

[0074] Step 14: Judge whether the node is the task decision center; if yes, go to step 15; if no, go to step 18;

[0075] Step 15: Judge whether the allocation state has update, i.e. whether there is local update or external update; if yes, go to step 16; if no, go to step 17;

[0076] Step 16: Publish the historical optimal task allocation to all nodes;

[0077] Step 17: Return to step 2;

[0078] Step 18: Judge whether the allocation state has local update; if yes, go to step 19; if no, go to step 17;

[0079] Step 19: Publish the historical optimal task allocation to the decision center node, and return to step 2.

[0080] Further, please refer to Fig. 2 As shown in the figure, the embodiment provides a task allocation step 3 of maintaining a task decision center node, and the implementation steps are as follows:

[0081] Step 3.1: According to the data in the node state set {Sm}, it is judged whether the node number is the smallest in all nodes; if yes, go to step 3.2; if no, go to step 3.8;

[0082] Step 3.2: The node calculates the maintenance task decision center number;

[0083] Step 3.3: Calculate the cluster center coordinates (X, Y) to get the average center position of all nodes, and the calculation method is as follows:

[0084]

[0085] Step 3.4: Calculate the average center of all nodes and the relative distance of all nodes, and select the nearest node as the decision center;

[0086] Step 3.5: It is judged whether to update the decision center number, and the newly calculated decision center is compared with the historically stored decision center; if consistent, it is yes, go to step 3.6; if inconsistent, it is no, and the calculation is ended;

[0087] Step 3.6: Publish the task decision center number to all nodes;

[0088] Step 3.7: Update the local task decision center number, and end the calculation;

[0089] Step 3.8: It is judged whether a new decision center number is received; if yes, go to step 3.9; if no, end the calculation;

[0090] Step 3.9: Update the local task decision center number, and end the calculation.

[0091] Further, please refer to Fig. 3 As shown in the figure, the embodiment provides a task allocation step 5 of calculating the optimal task allocation, and the implementation steps are as follows:

[0092] Step 5.1: It is judged whether there is a task to be allocated; if the task set {Tn} is not empty, there is a task to be allocated, go to step 5.2; otherwise, end the calculation;

[0093] Step 5.2: Set the optimization number k as 0, and set the optimization limit number N, where N is determined by the product of the total number of flight platform nodes Nm and the total number of tasks Nt, and the maximum value of N should be limited according to the decision-making speed requirement, so as to reduce the calculation time in the case of large number of clusters and tasks. When the task allocation calculation time is required to be within tens of milliseconds, the maximum value of N is set to be within 100, and when the task allocation calculation time is allowed to be larger, the maximum value of N can be appropriately increased;

[0094] Step 5.3: Determine whether the optimization number k is less than the optimization limit number N; if yes, go to step 5.4; otherwise, end the calculation;

[0095] Step 5.4: Assign the node state set {Sm} to the new node state set {Smn};

[0096] Step 5.5: Randomly select a node from the node state set {Smn} for task pairing, and remove the selected node from {Smn} and update {Smn};

[0097] Step 5.6: Set the index number i of the task in the task set to 0;

[0098] Step 5.7: Determine whether the index number i of the task reaches the total number of tasks; if yes, go to step 5.11; otherwise, go to step 5.8;

[0099] Step 5.8: Select the task with index number i from the task set {Tn} and match it with the node selected in step 5.5;

[0100] Step 5.9: Determine whether the selected node and task match; if yes, go to step 5.10; otherwise, go to step 5.16; the matching success criterion at least includes that the flight platform represented by the node can reach the location of the task, and the flight platform maneuvering capability is greater than the target maneuvering capability when reaching;

[0101] Step 5.10: Select the assignment relationship storage value distribution result set {A};

[0102] Step 5.11: Determine whether the node state set {Smn} is empty; if yes, go to step 5.12; otherwise, go to step 5.4;

[0103] Step 5.12: Calculate the generation value under the current assignment relationship;

[0104] Step 5.13: Determine whether the calculated generation value is better than the historical optimal assignment generation value; if yes, go to step 5.14; otherwise, go to step 5.15;

[0105] Step 5.14: Update the historical optimal assignment with the current assignment relationship, and update the generation value;

[0106] Step 5.15: add 1 to the value of the optimization times k, and go to step 5.3;

[0107] Step 5.16: add 1 to the value of the index number i of the task, and go to step 5.7.

[0108] Compared with the prior art, the present application at least contains the following beneficial effects compared with the prior art:

[0109] (1) The present application adopts the mode of each flight platform node distributed simultaneous calculation of optimal allocation, node recommendation of optimal allocation to the decision center, and optimal allocation issued by the decision center to all nodes, realizes that each node only sends the calculation result to the outside in the case of calculating a better result than the global optimal allocation, avoids frequent allocation information interaction, reduces the communication demand, and at the same time increases the global allocation consistency convergence speed;

[0110] (2) The present application adopts the mode of dynamic maintenance of the decision center, realizes that the cluster has a unified and dynamically adjustable task decision center, can re-determine the decision center after the loss of the flight platform, avoids the failure of the cluster system after the loss of the fixed center, and improves the system robustness;

[0111] (3) The present application adopts random selection of flight platform and task target matching calculation at the flight platform node, increases the global optimization ability, and at the same time, due to the distributed simultaneous calculation of each flight platform node, greatly increases the matching optimization efficiency compared with single platform calculation.

[0112] (4) The present application utilizes the advantage of flight platform node distributed simultaneous calculation, limits the optimization iteration times of each node, can ensure that the approximate optimal decision result can be quickly obtained first, and thereafter gradually updates to the global optimum through the continuous optimization calculation and recommendation of each node.

[0113] Although the content of the present application has been described in detail through the above preferred embodiments, it should be recognized that the above description should not be considered as a limitation of the present application. After reading the above content, various modifications and substitutions of the present application will be obvious to those skilled in the art. Therefore, the protection scope of the present application should be defined by the appended claims.

Claims

1. A rapid collaborative task allocation method that adapts to group dynamic changes, characterized by: The steps are as follows: Step 1: Set the variables for storing the flight platform node state set {Sm} and the task set {Tn}, and initialize the set to an empty set; Step 2: Obtain the node status locally and receive the status of other nodes from the cluster communication network, and add the node status participating in task allocation to the node status set {Sm}; Step 3: Maintain the task decision center node based on the data in the node status set {Sm} for optimal task allocation and release; Step 4: Receive all task statuses from the local and other nodes, and place the tasks that need to be assigned into the cluster task set {Tn}. The information of a single task includes at least the number, location, type, and timestamp of the task target. Step 5: Calculate the optimal task allocation based on the node state set {Sm} and the cluster task set {Tn}; Step 6: If it is the first calculation, update the historical optimal allocation with the calculated optimal task allocation; otherwise, determine whether the calculated optimal task allocation is better than the historical optimal allocation; If yes, go to step 7; if no, go to step 9; Step 7: Update the historical optimal allocation with the calculated optimal task allocation; Step 8: Mark the allocation status as having local updates; Step 9: Mark the allocation status as no local update; Step 10: Read data from the network port to determine whether a new optimal allocation has been received; If yes, go to step 11; if no, go to step 14; Step 11: Determine whether the new optimal allocation received is better than the local historical optimal allocation; If yes, go to step 12; if no, go to step 14; Step 12: Update the local historical optimal allocation with the received new optimal allocation; Step 13: Mark the allocation status as having external update; Step 14: Determine whether this node is a task decision center; If yes, go to step 15; if no, go to step 18; Step 15: Determine whether the allocation status has been updated, that is, whether there is a local update or an external update; If yes, go to step 16; if no, go to step 17; Step 16: Publish the historical optimal task allocation to all nodes; Step 17: Return to step 2; Step 18: Determine whether the allocation status has been locally updated; If yes, go to step 19; if no, go to step 17; Step 19: Publish the historical optimal task allocation to the decision center node and return to step 2.

2. A rapid collaborative task allocation method that adapts to group dynamic changes according to claim 1, characterized in that: In step 2, the status of a single node includes at least the flight platform number, position, speed, mission execution status, and timestamp information.

3. A rapid collaborative task allocation method that adapts to group dynamic changes according to claim 2, characterized in that: The maintenance task decision center node in step 3 is implemented as follows: Step 3.1: Determine whether the node ID is the smallest among all nodes based on the data in the node status set {Sm}; If yes, go to step 3.2; if no, go to step 3.8; Step 3.2: This node calculates the maintenance task decision center number; Step 3.3: Calculate the cluster center coordinates (X, Y) to get the average center position of all nodes. The calculation method is as follows: Cluster center coordinates Node i coordinate (X, Y) / total number of nodes Nm; Step 3.4: Calculate the relative distance between the average center of all nodes and all nodes, and select the node with the closest distance as the decision center; Step 3.5: Determine whether to update the decision center number and compare the newly calculated decision center with the historically stored decision center; If they are consistent, then it is yes and go to step 3.6; if they are inconsistent, then it is no and the calculation ends; Step 3.6: Publish the task decision center number to all nodes; Step 3.7: Update the local task decision center number and end the calculation; Step 3.8: Determine whether a new decision center number has been received; If yes, go to step 3.9; if no, end the calculation; Step 3.9: Update the local mission decision center number and end the calculation.

4. A rapid collaborative task allocation method that adapts to group dynamic changes according to claim 3, characterized in that: The optimal task allocation calculation in step 5 is implemented as follows: Step 5.1: Determine whether there are tasks to be assigned. If the task set {Tn} is not empty, there are tasks to be assigned, and go to step 5.2; otherwise, end the calculation; Step 5.2: Set the optimization times k to 0 and the optimization limit times N, where N is determined by multiplying the total number of flight platform nodes Nm by the total number of tasks Nt. The maximum value of N should be limited based on the decision-making speed requirement to reduce the computation time when there are a large number of clusters and tasks. When the task allocation computation time is required to be within tens of milliseconds, the maximum value of N is set to within 100. When the task allocation computation time is required to be longer, the maximum value of N can be appropriately increased. Step 5.3: Determine whether the optimization times k is less than the optimization limit times N; if yes, go to step 5.4; otherwise, end the calculation; Step 5.4: Assign the node state set {Sm} to the new node state set {Smn}; Step 5.5: Randomly select a node from the node state set {Smn} for task pairing, remove the selected node from {Smn} and update {Smn}; Step 5.6: Set the index number i of the task in the task set to 0; Step 5.7: Determine whether the index number i of the task reaches the total number of tasks; If yes, go to step 5.11; otherwise, go to step 5.8; Step 5.8: Select the task with task index number i from the task set {Tn} and match it with the node selected in step 5.5; Step 5.9: Determine whether the selected node matches the mission. If so, proceed to step 5.

10. Otherwise, proceed to step 5.

16. The criteria for determining a successful match include at least the following: the flight platform represented by the node can reach the mission location, and the flight platform's maneuverability is greater than the target maneuverability upon arrival. Step 5.10: Select the allocation relationship storage value allocation result set {A}; Step 5.11: Determine whether the node state set {Smn} is an empty set; if so, go to step 5.12; otherwise, go to step 5.4; Step 5.12: Calculate the cost value under the current distribution relationship; Step 5.13: Determine whether the calculated cost value is better than the historical optimal allocation cost value; if so, go to step 5.14; otherwise, go to step 5.15; Step 5.14: Update the historical optimal allocation with the current allocation relationship and update the cost value; Step 5.15: Increase the optimization times k by 1 and go to step 5.3; Step 5.16: Increase the value of the task index number i by 1 and go to step 5.7.

Images