A Distributed Task Reconfiguration Method Based on Historical Information Backtracking

Abstract

The present invention provides a distributed task reconstruction method based on historical information backtracking, which relates to the field of distributed decision-making technology. The method includes: establishing a distributed multi-UAV collaborative task allocation model according to the constraint conditions of the information interaction architecture; generating a preliminary decision-making scheme, including two links of task construction and task negotiation; in the task negotiation link, designing an information backtracking mechanism for the failed UAV; constructing a task priority chain storage structure according to the information backtracking result; quantitatively analyzing the allocation model with random node failures, determining the UAV failure position, and performing task reconstruction. The present invention proposes a method capable of realizing dynamic reallocation after task allocation for the complex optimization problem of multi-UAV task allocation. Through the communication and cooperation between UAVs, the task allocation and reconstruction are jointly determined, further improving the flexibility and robustness.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed decision-making, and particularly to a distributed task reconstruction method based on historical information backtracking. Background Art

[0002] The concept of unmanned aerial vehicles (UAVs) can be traced back to the 19th century, when there were prototypes of unmanned aerial vehicles. In the late 20th century, with the rapid development of electronic technology and aviation technology, UAVs gradually became important tools in many fields.

[0003] Most early UAV systems were single UAVs. With the progress of technology, multi-UAV systems have been gradually developed and applied. Since the 1990s, systems using multiple UAVs to cooperate in operations have emerged in many fields.

[0004] With the application of multi-UAV systems in various fields, the technology of multi-UAV task allocation and reconstruction has become more important. Traditional centralized task allocation and reconstruction methods have problems of single-point failure and low efficiency. With the expansion of the scale and application scope of the agent system, the requirements for scalability and security will become more urgent. Summary of the Invention

[0005] The present invention provides a distributed task reconstruction method based on historical information backtracking to solve the defects of single-point failure and low efficiency in the prior art.

[0006] The present invention provides a distributed task reconstruction method based on historical information backtracking for dynamically reallocating after task allocation in a multi-UAV system, including:

[0007] S1. Establish a distributed multi-UAV cooperative task allocation model according to the constraint conditions of the information interaction architecture.

[0008] S2. Generate a preliminary decision-making plan, including a task construction link and a task negotiation link.

[0009] S3. In the task negotiation link, design an information backtracking mechanism for failed UAVs.

[0010] S4. Construct a task priority chain storage structure according to the information backtracking result.

[0011] S5. Conduct quantitative analysis on the allocation model with random node failures, determine the failure positions of UAVs, and perform task reconstruction.

[0012] According to the distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S1, it is set that there are n UAVs, and the upper limit of the target tasks that each UAV can complete is , and at the same time, For a target point, the formula of the distributed multi-UAV cooperative task allocation model is expressed as:

[0013]

[0014] The constraint conditions are set as:

[0015]

[0016]

[0017]

[0018] In the formula, represents the corresponding relationship mark between UAV and task point f. When task f is assigned to UAV , the corresponding relationship mark is , otherwise ; represents a -dimensional vector; represents the execution order of all tasks occupied by UAV i ; represents the revenue calculation function; represents the original revenue value.

[0019] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S2, in the task construction link, the task package of each UAV is constructed by adopting a greedy strategy, and the construction process includes:

[0020] Input the new task j, and solve the current revenue value after adding the new task j. The formula is expressed as:

[0021]

[0022] In the formula, represents the existing task path of UAV i, represents the total revenue value of UAV i when the task path is , represents adding task j at the nth position of the existing task path , represents finding the position n with the maximum revenue in the position , and the current revenue value is .

[0023] Compare the current revenue value with the original revenue value, and judge whether task j is added to the task package according to the comparison result. If , then use to replace , indicating that task j can be added to the task package. If , it means that task j cannot be added to the task package.

[0024] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S2, in the task negotiation session, by constructing a UAV task negotiation algorithm based on the market auction mechanism, the task construction conflicts between UAVs are resolved. The task negotiation session includes a predefined marking symbol and task negotiation.

[0025] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, the predefined marking symbols include:

[0026] Winner bid value list vector , vector represents the bid value of each task in the storage unit of UAV i. Among them, the bid value represents the task revenue value that UAV i needs to achieve to win the task.

[0027] Winner list vector , vector represents the ownership of each task in the storage unit of UAV i.

[0028] Timestamp marking vector , vector is used to mark the information update time of UAV i.

[0029] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, the process of task negotiation includes:

[0030] When , , information update is performed, that is, the information mark of task j in UAV i is replaced by the corresponding information mark of task j in UAV k.

[0031] When , 0, information reset is performed, that is, all the information about task j in UAV i is reset to the initial empty state.

[0032] When , , information non-operation is performed, that is, the information about task j in UAV i is retained.

[0033] In the formula, represents the bid value of the j-th task in the stored information of UAV i. represents the serial number value of the UAV to which the j-th task belongs in the stored information of UAV i.

[0034] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S3, the process of designing an information backtracking mechanism for a failed unmanned aerial vehicle includes:

[0035] S31. Given task T.

[0036] S32. Analyze the bidding processes of multiple iterations among each unmanned aerial vehicle, and let the unmanned aerial vehicles following the greedy optimization principle bid for task T independently, conduct the first iteration, compare the corresponding revenue value evaluations of the bids of the unmanned aerial vehicles following the greedy optimization principle, and determine the winner of the first round.

[0037] S33. Set an unmanned aerial vehicle that does not follow the greedy optimization principle to participate in the bidding, compare the revenue value of the current unmanned aerial vehicle with that of the winner in the previous round, conduct the current iteration, and determine the winner of the current iteration.

[0038] S34. Repeat step S33 until all unmanned aerial vehicles complete the bidding, and determine the execution right of task T.

[0039] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S4, the process of constructing a task priority chain storage structure includes:

[0040] Construct a chain storage logic based on priority.

[0041] Record each point in the chain node to the node of the previous priority.

[0042] Obtain the task T execution priority sorting chain.

[0043] According to a distributed task reconstruction method based on historical information backtracking provided by the present invention, in step S5, the process of quantitatively analyzing the allocation model with random node failures includes:

[0044] Set the initial network of the multi-unmanned aerial vehicle coordination task as , indicating a static connected initial network containing nodes.

[0045] Obtain the set of sub-networks generated when a certain node unmanned aerial vehicle R fails:

[0046]

[0047] If node R is directly connected to two or more other nodes, the number of sub-networks generated , and task reconstruction is required.

[0048] If there is an adjacent node in node R, the number of sub-networks generated , and task reconstruction is not required.

[0049] A distributed task reconstruction method based on historical information backtracking provided by the present invention. In step S5, the process of task reconstruction includes:

[0050] Obtain the position of the failed node.

[0051] Traverse all unmanned aerial vehicles (UAVs), and according to the priority chain storage structure, obtain the next-level UAVs of the failed node.

[0052] Reassign the task to the next-level UAVs and insert the task into the execution sequence.

[0053] A distributed task reconstruction method based on historical information backtracking provided by the present invention can timely and accurately detect the failure of UAV nodes by adopting the interaction threads between UAVs, and has real-time performance and high accuracy. It can quickly respond to the situation of UAV failure, thereby reducing the risk of task execution interruption and improving reliability and robustness. The advantage of real-time performance lies in that it can react immediately after the failure or fault of the UAV occurs without manual intervention, thus saving time and labor costs and enabling more efficient operation.

[0054] By adopting advanced algorithms and technologies, it can automatically determine the optimal task allocation scheme according to factors such as task requirements, UAV performance, and environmental conditions. Without manual intervention, it can quickly and accurately complete task allocation, improving efficiency and response speed.

[0055] Through the automatic task reallocation process, the robustness of the system is effectively improved. When a UAV fails, it can timely adjust the task allocation to avoid task interruption or delay, thereby ensuring continuous operation in the face of emergencies, which is crucial for ensuring the continuity and reliability of task execution. Through timely task reallocation, it can quickly adapt to different environmental and situation changes, reducing the risk of being affected by external interference or internal faults. Brief Description of the Drawings

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0057] Figure 1 It is a schematic flow chart of a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0058] Figure 2It is a schematic flowchart of generating a preliminary decision-making plan in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0059] Figure 3 It is a schematic diagram of node failure in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0060] Figure 4 It is a schematic diagram of the negotiation process of unmanned aerial vehicles in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0061] Figure 5 It is a flowchart of distributed collaborative search in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0062] Figure 6 It is a schematic diagram of search trajectory reconstruction in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention;

[0063] Figure 7 It is a schematic flowchart of the synchronization mechanism in a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention. Detailed implementation manners

[0064] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0065] The following Figures 1-7 describes a distributed task reconstruction method based on historical information backtracking of the present invention.

[0066] Figure 1 It is a schematic diagram of the steps of a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention.

[0067] As Figure 1 shown, a distributed task reconstruction method based on historical information backtracking provided by an embodiment of the present invention includes:

[0068] S1. Establish a distributed multi-unmanned aerial vehicle collaborative task allocation model according to the constraint conditions of the information interaction architecture.

[0069] In the collaborative decision-making of centralized multi-UAVs, the centralized terminal can obtain global information and solve for and output unified decision control instructions under a given objective constraint function. However, in a distributed multi-UAV system, due to the constraints of the information interaction architecture, it is necessary to solve for control instructions without task assignment conflicts through negotiation and iteration under a given objective constraint.

[0070] Suppose there are n UAVs, and each UAV can complete a maximum of target tasks. At the same time, given target points, at this time, the formula representation of the distributed multi-UAV collaborative task assignment model is:

[0071]

[0072] The constraint condition formula representation is:

[0073]

[0074]

[0075]

[0076] In the formula, represents the corresponding relationship mark between UAV and task point f. When task f is assigned to UAV , the corresponding relationship mark is , otherwise ; is a -dimensional vector, representing the marking situation of UAV i for tasks; represents the execution order of all tasks occupied by UAV i; represents the benefit calculation function; represents the original benefit value.

[0077] Among them, the benefit value is affected by all tasks occupied by UAV i and their execution order, and its calculation and solution satisfy the principle of diminishing marginal benefit.

[0078] In the distributed task negotiation and solution, the number of solution iterations is affected by the minimum value among the number of UAVs, the total number of tasks, and the upper limit of the number of tasks that a UAV can execute.

[0079] Suppose the iteration satisfies the condition, and the formula representation is:

[0080]

[0081] In the formula, Represents the minimum value among the number of UAVs, the total number of tasks, and the upper limit of tasks executed by UAVs.

[0082] S2. Generate a preliminary decision-making plan, including two links: task construction and task negotiation.

[0083] S211. In the task construction link, a greedy strategy is adopted to construct the task package for each UAV. The construction process includes:

[0084] Input the new task j, and solve the current revenue value after adding the new task j. The formula is expressed as:

[0085]

[0086] In the formula, represents the existing task path of UAV i, represents that UAV i is at the task path when the total revenue value, represents adding task j at the nth position of the existing task path , represents the position in which the position n with the maximum revenue is found, and the current revenue value is .

[0087] Compare the current revenue value with the original revenue value, and judge whether task j can be added to the task package according to the comparison result.

[0088] If , then use to replace , indicating that task j can be added to the task package; if , then it means that task j cannot be added to the task package.

[0089] S212. Construct a UAV task negotiation algorithm based on the market auction mechanism to resolve the task construction conflicts among UAVs.

[0090] Since UAVs are connected through a distributed topology network, there are time-sequence differences in the information transmission among UAVs. Therefore, information synchronization conditions are specified during the UAV task negotiation process. At the same time, some basic marking symbols are agreed upon in the UAV task negotiation link to simplify the comparison conditions and their operation descriptions for different negotiation situations.

[0091] The marking symbols include:

[0092] The list vector of winner bid values : The vector is a The vector, in which the bid values are marked, represents the bid values of each task in the storage unit of UAV i. Among them, the bid value is the numerical value calculated for the task revenue that UAV i needs to achieve to win the task. Represents the bid value of the j-th task in the stored information of UAV i.

[0093] Winner list vector : Vector Is a Vector, in which the serial numbers of the UAVs that win the corresponding tasks are marked, representing which UAV each task belongs to in the storage unit of UAV i, and its marking situation will change with the bid value vector Changes. Represents the serial number value of the UAV to which the j-th task belongs in the stored information of UAV i.

[0094] Timestamp marking vector : The timestamp is used to mark the information update time of UAV i, that is, the timestamp Is updated once.

[0095] After the specified UAV completes information interaction with the UAVs adjacent to it in the topological structure, according to the current information situation, the actions that the UAV can take are: information update, information reset, and information non-operation. The specific action contents are as follows:

[0096] Information update: , , that is, the information mark of task j in UAV i is replaced by the corresponding information mark of task j in UAV k.

[0097] Information reset: , , that is, all the information about task j in UAV i is reset to the initial empty state.

[0098] Information non-operation: , , that is, the information about task j in UAV i is retained.

[0099] Such as Figure 2 As shown, the relationship between task package construction and conflict resolution. After providing task information, the multi-UAV task decision-making will go through the repeated processes of task construction and task negotiation. When the output result of a specific iteration meets the termination condition, the task assignment is completed. At this time, the assignment result has reached consistency.

[0100] S3. In the task negotiation session, design an information backtracking mechanism for failed UAVs.

[0101] In order to prevent communication interruption between UAVs after a node fails, which may lead to information loss and mission conflicts, it is necessary to make the bidding process traceable, reconstruct the remaining tasks without conflicts, and ensure the optimization of benefits.

[0102] As Figure 4 shown, given task T, analyze the negotiation process of three iterations among UAVs to clarify the working process of the information traceback mechanism. In the first iteration, UAVs a, b, and c independently bid on task T respectively following the greedy optimization principle. The bids are evaluated by comparing the corresponding benefit values, and the result is . Therefore, UAV b becomes the winner of this round and enters the next iteration, temporarily retaining the ownership of task T. In this round, the winner of task T may change, and it can be determined by comparing the winner lists of the previous round and the current iteration :

[0103]

[0104] If the above formula holds, the UAV will record the priority as shown in the following formula:

[0105]

[0106] In the second iteration, UAV d joins the auction and submits a bid higher than that of UAV b, successfully obtaining task T.

[0107] In the third iteration, UAV d competes with UAV e, but its bid is still better, and finally obtains the right to execute task T.

[0108] Based on the above negotiation and construction process of task T by UAVs a, b, c, d, and e, it can be analyzed and summarized that the negotiation process of UAVs for tasks can generally be classified into two types of situations: The first situation is that, for example, UAV a and UAV c are defeated by UAV b in the same round. At this time, it is necessary to sort according to the bids of the two losing UAVs.

[0109] The second situation is that, for example, UAV b and UAV e are defeated by the same UAV in their respective iteration rounds. At this time, it is also necessary to further compare the two to distinguish the relative priorities.

[0110] S4. Construct a chained storage structure of task priorities according to the information traceback results.

[0111] Based on the above Figure 4In the UAV mission negotiation process analyzed herein, further, an information storage logic is constructed on the basis of the original negotiation structure of the UAVs. If global information storage is adopted and each UAV stores the priority ranking sequence of each task, then the size of its data matrix is , and its size will change rapidly with the changes in the number of tasks and UAVs, resulting in unnecessary storage consumption. Therefore, this section proposes a chained storage logic based on priority.

[0112] In the chained storage logic based on priority, each point in the chained node only needs to record the node of the previous priority and the corresponding one, which can greatly compress the storage space of information. For example, in the negotiation result shown in Figure 5, the execution priorities of task T from high to low are: . At this time, for UAV d, which is the UAV with the highest priority for task , only the corresponding task needs to be recorded as task t. For UAV e, since the priority of this UAV for task T is lower than that of UAV d, UAV e needs to record both UAV d of the previous priority and the corresponding task T. The same applies to the rest. Thus, a task T execution priority ranking chain composed of UAVs a, b, c, d, and e can be obtained.

[0113] S5. Quantitatively analyze the allocation model with random node failures, determine the UAV failure location, and perform task reconstruction.

[0114] Analyze the node failure type through the information synchronization mechanism between UAVs, accurately judge the node failure location, and complete task reconstruction.

[0115] In a distributed communication network, the number of consistent interactions and iterations of network information is positively correlated with the diameter D of the static connection network. At the same time, the smaller the communication network diameter D, the higher the required network density, which will lead to a higher communication load on the communication network nodes. However, as the scale of the communication network continues to expand, the communication bandwidth of the communication network nodes with too high density is far from sufficient. Therefore, usually, a fully connected network with such a high density is not adopted for multi-UAV networking. In a simplified static connected initial network, although the communication load of each node is reduced, when a certain node fails in the connected network, it may affect the connectivity of the network, thereby affecting the subsequent information flow process. In Figure 3It can be clearly seen that in the initial complete network, the information flow between node 3 and node 5 can be indirectly completed through node 2 and node 4. Similarly, the information flow between node 1 and node 6 can be indirectly completed through node 2. If there are random node failures in the allocation model, it can be specifically divided into two types of situations: First, the network can still maintain connectivity, that is, an information channel can still be established between any two valid nodes; Second, the network loses connectivity, that is, there are at least two nodes that cannot establish an effective information flow channel. In Figure 3 The failure of node 2 shown in

[0116] both belong to the second situation. In this case, the network cannot continue to perform effective information negotiation and interaction actions. In the distributed task allocation algorithm designed in step 1, if the second type of node failure occurs, it will cause the search trajectory planned by the UAV corresponding to this node to be unable to complete an effective traversal. At this time, it will directly lead to the failure of the search task. If the uncompleted search trajectory of the failed UAV cannot be decomposed consistently, it will lead to task conflicts among the remaining UAVs. Here, a quantitative analysis is carried out for the second situation. Assume that the above allocation model is denoted as represents a static connected initial network containing

[0117]

[0118] nodes. When a certain node UAV R fails, multiple sub-networks may be generated. The set of sub-networks is denoted as: Figure 3 From the above analysis of the situation in it can be seen that in the initial connected network, if node R is directly connected to two or more other nodes, then the failure of node R will cause the network to become disconnected. At this time, the number of sub-networks generated . If there is an adjacent node in node R, then the failure of node R will not affect the connectivity of the network. At this time, the number of sub-networks . When there are node failures, but the number of sub-networks generated , the multi-UAV system only needs to re-plan the remaining search paths. Therefore, the key problem solved by the present invention is when

[0119] As Figure 7 shown, in the response thread between UAVs, the UAVs adopt a time-interleaved response rhythm. Different time rhythms are adopted for interaction between two adjacent UAVs, which can effectively reduce information interaction resources while ensuring the reliability of the response between UAVs. When a UAV starts to pass through multiple time intervals at a certain moment If no signal is initiated, it is considered that the UAV R has failed, and then the initial UAV network is used to infer the sub-network set synchronously , and the sub-network set is synchronized among the remaining UAVs , and enter the task reconstruction mode.

[0120] Using the priority chain storage structure, the remaining UAVs responsible for reconfiguration will traverse whether the failed UAV is their previous priority UAV. If so, the task will be reallocated to the corresponding UAV, and by inserting the task into the execution sequence at the best position, it is ensured that the task reconfiguration will not affect the task execution efficiency of the UAV. Even when forming multiple unconnected sub-networks, this method can achieve conflict-free task reconfiguration of the failed node.

[0121] To verify the effectiveness of the proposed distributed task reconstruction method using historical information backtracking, a search trajectory reconstruction simulation verification is carried out in a multi-UAV cooperative search scenario. First, the map is rasterized and segmented, probability elements are integrated, and designated as task allocation blocks. Subsequently, a boundary gain function is established, with the path as an influencing factor. The reconstruction algorithm is integrated into the multi-UAV system to guide the collaborative search work, and finally efficient task reconstruction and search optimization are achieved. The overall process is as Figure 4 shown. As Figure 5 shown in the figure is the reconstruction result of the search path. It can be seen from the figure that when one of the UAVs fails, the proposed distributed task reconstruction method using historical information backtracking successfully reallocates the tasks originally assigned to the failed UAV. In addition, no conflicts are observed in the trajectory planning of the remaining UAVs. In addition, compared with the originally planned search trajectory, the new search path has undergone significant adjustments, and this adjustment is due to the UAVs re-planning the entire task package list when undertaking new search grids.

[0122] In summary, this embodiment provides a distributed task reconstruction method based on historical information backtracking, which adopts an interaction thread between UAVs, can detect the failure of UAV nodes in a timely and accurate manner, and has real-time performance and high accuracy. It can quickly respond to the situation of UAV failure, thereby reducing the risk of task execution interruption and improving reliability and robustness. The advantage of real-time performance lies in being able to react immediately after the UAV failure or fault occurs, without manual intervention, thus saving time and labor costs and being able to operate more efficiently.

[0123] By adopting advanced algorithms and technologies, it can automatically determine the best task allocation scheme according to factors such as task requirements, UAV performance, and environmental conditions. Without manual intervention, it can quickly and accurately complete task allocation, improving efficiency and response speed.

[0124] Through the automatic task reallocation process, the robustness of the system is effectively improved. When a drone fails, the task allocation can be adjusted in a timely manner to avoid task interruption or delay, thereby ensuring continuous operation in the face of emergencies, which is crucial for ensuring the continuity and reliability of task execution. Through timely task reallocation, it can quickly adapt to different environmental and situation changes, reducing the risk of being affected by external interference or internal failures.

[0125] Through the description of the above implementation manners, those skilled in the art can clearly understand that each implementation manner can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed task reconstruction method based on historical information backtracking, characterized in that Including: S1. Establish a distributed multi-UAV cooperative task allocation model according to the constraint conditions of the information interaction architecture; There are n drones set, and the upper limit of each drone to complete the target task is , and at the same time target points are given. Then the formula representation of the distributed multi-drone cooperative task allocation model is: The constraint conditions are set as: Wherein, represents the correspondence mark between the UAV and the mission point f. When the mission f is assigned to the UAV , the correspondence mark , otherwise ; represents a dimensional vector; represents the execution order of all missions occupied by the UAV i; represents the revenue calculation function; represents the original revenue value; S2. Generate a preliminary decision-making scheme, including a task construction link and a task negotiation link; In the task construction link, the task package of each UAV is constructed by adopting a greedy strategy. The construction process includes: Input a new task j, and solve the current benefit value after adding the new task j. The formula is expressed as: Wherein, represents the existing mission path of UAV i, represents the total revenue value of UAV i when the mission path is ; represents adding mission j at the nth position of the existing mission path ; represents finding the position n with the maximum revenue in the position , and the current revenue value is ; Compare the current revenue value with the original revenue value, and based on the comparison result, determine whether task j is added to the task package. If , then use to replace , indicating that task j is added to the task package; if , then it means that task j is not added to the task package; In the task negotiation link, a UAV task negotiation algorithm based on the market auction mechanism is constructed to resolve the task construction conflicts among UAVs. The task negotiation link includes a convention marker symbol and task negotiation; The process of performing the task negotiation includes: When , , information is updated, that is, the information mark regarding task j in UAV i is replaced by the corresponding information mark of task j in UAV k; When , is 0, information reset is performed, that is, all information about task j in UAV i is reset to the initial empty state; When , , no information operation is performed, that is, the information about mission j in UAV i is retained; wherein, represents the bid value of the j-th task in the storage information of UAV i; represents the serial number value of the UAV to which the j-th task belongs in the storage information of UAV i; S3. In the task negotiation link, design an information backtracking mechanism for failed UAVs; The process of designing an information backtracking mechanism for failed UAVs includes: S31. Given a task T; S32. Analyze the bidding processes of multiple iterations among each UAV, and the UAVs following the greedy optimization principle bid for the task T independently. Conduct the first iteration, compare the benefit value evaluations of the UAVs following the greedy optimization principle to judge the winner of the first round; S33. Set a UAV that does not follow the greedy optimization principle to participate in the bidding, compare the benefit value of the current UAV with that of the winner of the previous round, conduct the current iteration, and judge the winner of the current iteration; S34. Repeat step S33 until all UAVs complete the bidding and judge the execution right of the task T; S4. Construct a task priority chain storage structure according to the information backtracking result; S5. Conduct a quantitative analysis of the allocation model with random node failures, determine the UAV failure location, and execute task reconstruction; The process of conducting a quantitative analysis of the allocation model with random node failures includes: Set the initial network for multi-UAV coordinated tasks as , representing a static connected initial network containing nodes; Obtain the set of sub-networks generated when a certain node UAV R fails; If node R is directly connected to two or more other nodes, the number of sub-networks generated , task reconstruction is required; If there is an adjacent node in node R, the number of sub-networks generated , there is no need to perform task reconstruction; The process of task reconstruction includes: Obtain the failure node location; Traverse all UAVs, and according to the priority chain storage structure, obtain the next-level UAV of the failure node; Re-allocate the task to the next-level UAV and insert the task into the execution sequence.

2. The distributed task reconstruction method based on historical information backtracking according to claim 1, wherein The agreed marker symbols include: List vector of winner bid values , the vector represents the bid value of each task in the storage unit of UAV i; wherein, the bid value represents the task revenue value that UAV i needs to achieve to win the task. Winner list vector , the vector represents the attribution of each task in the storage unit of the drone i; Timestamp marking vector , the vector is used to mark the information update time of the drone i.

3. A distributed task reconstruction method based on historical information backtracking according to claim 1, characterized in that In step S4, the process of constructing a task priority chain storage structure includes: Construct a priority-based chain storage logic; Each point in the chain node records the node of the previous priority level; Obtain the task T execution priority sorting chain.

Images