Multi-unmanned aerial vehicle task fault-tolerant decision determination method and device, medium and product

Abstract

The invention discloses a multi-unmanned aerial vehicle task fault-tolerant decision determination method and device, a medium and a product, and relates to the field of multi-unmanned aerial vehicle task decision, and the method comprises the steps: obtaining the emergency endurance time of a fault unmanned aerial vehicle and a loss parameter caused by the fault unmanned aerial vehicle; judging whether the fault unmanned aerial vehicle is repaired or not according to the emergency endurance time, and obtaining a repair judgment result; determining a feasibility decision according to the repair judgment result; determining loss corresponding to the feasibility decision according to the loss parameter; determining a temporary decision according to the repair judgment result, the repair loss and the continued task loss; determining a final decision according to the feasibility decision, the loss corresponding to the temporary decision and the replacement loss; according to the method and the device, the completeness of the task can be ensured while the loss is minimized, and the influence visualization of resource reallocation is realized.

Description

Technical Field

[0001] This application relates to the field of multi-UAV mission decision-making, and in particular to a method, device, medium, and product for determining fault-tolerant decisions for multi-UAV missions. Background Technology

[0002] Currently, unmanned aerial vehicles (UAVs) are widely used in various fields such as logistics and transportation, disaster relief, agricultural plant protection, and military reconnaissance. During mission execution, UAVs may experience mission interruptions or failures due to hardware malfunctions (such as battery depletion or sensor failure), environmental interference (such as strong winds or electromagnetic interference), or human factors (such as operational errors). Existing technologies for handling UAV mission failures mainly fall into two categories: single-UAV dynamic threshold decision-making methods and mission reassignment methods in the event of UAV failures.

[0003] The single-drone dynamic threshold decision-making method sets dynamic thresholds based on the drone's real-time status to determine whether to abort or continue the task. For example, when a drone malfunctions, the system calculates the potential losses (such as task failure losses and repair costs) and time costs (such as waiting time) that might result from continuing the task, and selects the optimal decision. This can balance task reliability and cost to some extent. However, it only applies to single-drone scenarios and does not consider the mutual influence when multiple drones are cooperating in a task. The lack of a mandatory constraint that "the task must be completed" may lead to the premature abort of critical tasks (such as emergency rescue) due to cost calculations. The task redistribution method for drone malfunctions involves the system reassigning unfinished tasks to other available drones when a drone malfunctions, in order to improve the task completion rate. The task redistribution method primarily optimizes task completion time to ensure overall task efficiency. However, existing task redistribution methods not only fail to quantify losses (such as drone energy consumption and repair costs) but also fail to consider the impact of a malfunctioning drone on adjacent drones (such as a crash potentially blocking flight paths or damaging other drones). Furthermore, existing methods all assume that the receiving drone will definitely complete the task, but in reality, increased load may lead to new malfunctions, triggering a chain reaction.

[0004] It is evident that existing methods only optimize for single UAVs and do not consider the mutual influence when multiple UAVs are performing tasks collaboratively. This leads to a lack of collaborative decision-making among multiple UAVs. In a multi-UAV system, a single UAV failure may affect adjacent UAVs to varying degrees, but existing technologies do not provide a global optimization solution. Furthermore, existing methods do not adequately quantify losses during task decision-making. For example, they do not consider equipment losses due to UAV crashes and the additional costs of task reallocation, resulting in insufficient loss assessment.

[0005] Therefore, based on the above problems, there is an urgent need to provide a new fault-tolerant decision-making method for multi-UAV missions, which can dynamically quantify the losses, the impact of resource reallocation, and the time costs while ensuring mission completion, so as to minimize losses while ensuring mission completion, and at the same time visualize the impact of resource reallocation. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, medium, and product for determining fault-tolerant decisions for multi-UAV missions, which can dynamically quantify the impact of losses, resource reallocation, and time costs while ensuring mission completion, so as to minimize losses and ensure mission completion, and at the same time visualize the impact of resource reallocation.

[0007] To achieve the above objectives, this application provides the following solution:

[0008] Firstly, this application provides a method for determining fault-tolerant decisions for multi-UAV missions, which includes:

[0009] Obtain the emergency endurance time of the faulty drone and the loss parameters caused by the faulty drone; the emergency endurance time is determined by the warning time and inoperability time of the faulty drone; the loss parameters include: the loss caused by mission failure and drone failure, the total resource consumption of the faulty drone and adjacent drones, and the probability of complete failure of the faulty drone during the repair period and the remaining time of the mission.

[0010] Based on the emergency flight time, determine whether the malfunctioning drone should be repaired and obtain a repair decision result; the repair decision result includes: repair or no repair;

[0011] Based on the repair assessment, determine the feasibility decision; the feasibility decision includes: whether to continue the mission, whether to replace the adjacent drone, and whether to introduce a new drone;

[0012] Based on the loss parameters, determine the losses corresponding to the feasibility decision; the losses corresponding to the feasibility decision include: repair losses, mission continuation losses, replacement losses, and losses from introducing new drones;

[0013] Based on the repair assessment, repair losses, and losses from continuing the mission, a temporary decision is determined; the temporary decision is to repair or continue the mission.

[0014] The final decision is determined based on the losses and replacement losses corresponding to the feasibility decision, the provisional decision, and the replacement decision. The final decision includes: repair, continue the mission, replace the adjacent drone, or introduce a new drone.

[0015] Optionally, obtaining the emergency endurance time of the faulty drone specifically includes:

[0016] The emergency endurance time Y of the faulty drone is determined using the formula Y = ZX;

[0017] Where Z represents the inoperability time of the malfunctioning drone, and X represents the warning time of the malfunctioning drone.

[0018] Optionally, the step of determining whether the faulty drone needs repair based on the emergency flight time and obtaining a repair determination result specifically includes:

[0019] Use the formula ω(t) < Y to determine whether a faulty drone needs repair;

[0020] Where ω(t) is the time taken from the termination of the mission to the completion of repairs for the faulty UAV at time t, and Y is the emergency endurance time for the faulty UAV.

[0021] Optionally, determining the loss corresponding to the feasible decision based on the loss parameters specifically includes:

[0022] Using formula E r1 =C r +C s F Y (w(t)) and formula E r2 =C r +C s F Y (w(t))+γ||ΔR i 1. Determine the repair costs;

[0023] Using formula E c1 =(C r +C s )F Y (τ-t) and formula E c2 =(C r +C s )F Y (τ-t)+η∑||ΔR k ||1. Determine the loss of continuing the task;

[0024] Using formula E re1 =C re +C r (1-F Y (τ-t))+C s F Y (ω(t))+γ||ΔR j ||1 and formula E re2 =C re +C r (1-F Y (τ-t))+C s F Y (ω(t))+γ||ΔR i ||1. Determine the replacement loss;

[0025] Using the formula E new = C new Determine the loss of introducing a new UAV;

[0026] Using the formula τ - t < Y to determine the constraint condition for continuing the mission;

[0027] Using the formula T - τ > τ - t to determine the replacement constraint condition;

[0028] Using the formula T - τ < τ - Z to determine the constraint condition for introducing a new UAV;

[0029] Where, E r1 Is the repair loss when not affecting adjacent UAVs, E r2 Is the repair loss when affecting adjacent UAVs, E c1 Is the loss of continuing the mission when not affecting adjacent UAVs, E c2 Is the loss of continuing the mission when affecting adjacent UAVs, E re1 Is the replacement loss when not affecting adjacent UAVs, E re2 Is the replacement loss when affecting adjacent UAVs, E new Is the loss of introducing a new UAV, C new Is the cost generated by the new UAV replacing the old UAV to complete the mission, C r Is the loss caused by mission failure, C s Is the loss of the UAV having a non - repairable fault, F Y (w(t)) is the complete failure probability of the faulty UAV during the repair period, γ is the unit resource compensation cost coefficient, ||ΔR i ||1 is the total resource consumption of the faulty UAV, F Y (τ - t) is the complete failure probability of the faulty UAV within the remaining mission time, η is the penalty coefficient for the resource loss of adjacent UAVs, ∑||ΔR k ||1 is the total resource consumption of all adjacent UAVs, C re Is the loss caused by the replacement process, 1 - F Y (τ - t) is the mission success probability of the faulty UAV within the remaining time, ||ΔR j ||1 is the resource required to complete mission j, Y is the emergency endurance time of the faulty UAV, τ is the mission time of the faulty UAV, t is the mission time already consumed by the faulty UAV, T is the effective time available for the UAV in the mission, and Z is the inoperable time of the faulty UAV.

[0030] Optionally, determining the temporary decision according to the repair judgment result, repair loss and continuing mission loss specifically includes:

[0031] When the repair judgment result is not to repair, the temporary decision is to continue the mission;

[0032] When the repair assessment result is repair, compare the magnitude of the repair loss and the loss of continuing the task, and determine a temporary decision based on the comparison result.

[0033] Optionally, when the repair judgment result is repair, comparing the magnitude of the repair loss and the loss of continuing the task, and determining a temporary decision based on the comparison result, specifically includes:

[0034] When the repair loss is less than the loss from continuing the task, the temporary decision is to repair.

[0035] When the repair loss is greater than or equal to the loss of continuing the task, the temporary decision is to continue the task.

[0036] Optionally, determining the final decision based on the losses corresponding to feasible decisions, temporary decisions, and replacement losses specifically includes:

[0037] If the temporary decision is to continue the task under repair conditions, the magnitude of the loss from continuing the task and the loss from replacement should be compared. The comparison process includes:

[0038] When the loss from continuing the task is less than or equal to the replacement loss, a feasibility decision is made. The decision process includes: if the feasibility decision indicates that the task can continue, the final decision is to continue the task; if the feasibility decision indicates that the task cannot continue, the magnitudes of the repair loss and the replacement loss are compared; if the repair loss is less than or equal to the replacement loss, the final decision is to repair; if the repair loss is greater than the replacement loss, and the feasibility decision indicates that replacement is possible, the final decision is to replace; if the repair loss is greater than the replacement loss, and the feasibility decision indicates that replacement is not possible, the final decision is to repair.

[0039] When the loss from continuing the task outweighs the loss from replacement, a feasibility decision is made. The decision process includes: if the feasibility decision is that replacement is possible, the final decision is replacement; if the feasibility decision is that replacement is not possible and the task cannot continue, the final decision is repair; if the feasibility decision is that replacement is not possible but the task can continue, the final decision is to continue the task.

[0040] If the temporary decision is to repair under repair conditions, the comparison process includes: comparing the magnitude of repair losses and replacement losses.

[0041] When the repair loss is less than or equal to the replacement loss, the final decision is to repair; when the repair loss is greater than the replacement loss, a feasibility decision is assessed. The assessment process includes: if the feasibility decision indicates that replacement is possible, the final decision is to replace; if the feasibility decision indicates that replacement is not possible, the final decision is to repair.

[0042] If the temporary decision is to continue the task without repair, compare the magnitude of the loss from continuing the task with the loss from replacement. The comparison process includes:

[0043] When the loss from continuing the mission is less than or equal to the loss from replacement, a feasibility decision is made. The decision process includes: when the feasibility decision is that the mission can be continued, the final decision is to continue the mission; when the feasibility decision is that the mission cannot be continued but can be replaced, the final decision is to replace; when the feasibility decision is that the mission cannot be continued, cannot be replaced, and cannot be replaced by a new drone, the final decision is to replace; when the feasibility decision is that the mission cannot be continued, cannot be replaced, but can be replaced by a new drone, the final decision is to replace by a new drone.

[0044] When the loss from continuing the mission outweighs the loss from replacement, a feasibility decision is made. The decision process includes: if the feasibility decision is that replacement is possible, the final decision is to replace; if the feasibility decision is that replacement is not possible, but the mission can continue, the final decision is to continue the mission; if the feasibility decision is that replacement is not possible, the mission cannot continue, and a new drone cannot be introduced, the final decision is to replace; if the feasibility decision is that replacement is not possible, the mission cannot continue, but a new drone can be introduced, the final decision is to introduce a new drone.

[0045] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multi-UAV mission fault-tolerant decision determination method.

[0046] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the multi-UAV mission fault-tolerant decision determination method.

[0047] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the multi-UAV mission fault-tolerant decision determination method.

[0048] According to the specific embodiments provided in this application, this application has the following technical effects:

[0049] This application provides a method, device, medium, and product for determining fault-tolerant decisions for multi-UAV missions. By obtaining the emergency endurance time of a faulty UAV, it directly eliminates unrepairable situations, avoids invalid calculations, and reduces resource investment in unrepairable faulty UAVs. It calculates the loss corresponding to the feasibility decision using the loss parameters caused by the faulty UAV, quantifies the loss, and directly reflects the degree of impact of the faulty UAV on surrounding UAVs. Combined with feasibility decisions, it minimizes losses while ensuring mission completion and visualizes the impact of resource reallocation. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a multi-UAV mission fault-tolerant decision determination method in one embodiment of this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] In one exemplary embodiment, such as Figure 1 As shown, a fault-tolerant decision-making method for multi-UAV missions is provided, including the following S1-S6. Wherein:

[0055] S1: Obtain the emergency endurance time of the malfunctioning drone and the loss parameters caused by the malfunctioning drone.

[0056] Emergency endurance time is determined by the warning time and inoperability time of the malfunctioning drone, and is used to determine whether the malfunctioning drone can be repaired before the inoperability time arrives; specifically, the formula for calculating emergency endurance time Y is as follows:

[0057] Y = ZX;

[0058] Where Z represents the inoperability time of the malfunctioning drone, and X represents the warning time of the malfunctioning drone.

[0059] In this application, the warning time for the malfunctioning drone is X = 10h, the inoperability time of the malfunctioning drone is Z = 15h, and the emergency endurance time of the malfunctioning drone is Y = ZX = 5h.

[0060] The loss parameters caused by the faulty drone in this application include: the loss caused by mission failure and drone malfunction, the total resource consumption of the faulty drone and adjacent drones, and the probability of complete failure of the faulty drone during the repair period and the remaining time of the mission.

[0061] S2: Based on the emergency endurance time, determine whether the faulty drone should be repaired and obtain the repair judgment result; the repair judgment result includes: repair or not repair.

[0062] Specifically, repair involves suspending the mission and repairing the malfunctioning drone. If the malfunctioning drone malfunctions at time t, causing the mission to terminate, the emergency endurance time is used to determine whether the malfunctioning drone can be rescued at this moment. The determination formula is as follows:

[0063] ω(t)<Y;

[0064] Where ω(t) is the time taken from when the faulty UAV terminates its mission at time t to when the repair is completed.

[0065] If the time ω(t) from when the faulty drone terminates its mission to when the repair is completed is less than the emergency endurance time Y, the faulty drone can be rescued and the repair judgment result is repair; otherwise, it is not repaired.

[0066] By prioritizing the determination of whether a faulty drone should be repaired, the possibility of not repairing it is directly eliminated, thus avoiding unnecessary calculations and reducing resource investment in unrepairable drones (such as scheduling repair teams). This allows the focus to be placed on subsequent actionable options, clarify branch conditions, and ensure that subsequent steps only handle valid scenarios, laying the foundation for determining the final decision.

[0067] S3: Based on the repair assessment results, determine a feasible decision.

[0068] Specifically, feasibility decisions include: whether to continue the mission, whether to replace the adjacent drone, and whether to introduce a new drone. Continuing the mission means that the faulty drone continues to perform the mission despite the fault; replacing the adjacent drone means using an adjacent drone to replace the faulty drone, that is, the adjacent drone takes over the remaining mission of the faulty drone, which will be referred to as replacement below; introducing a new drone means introducing a new drone to take over the remaining mission of the faulty drone until the mission is completed.

[0069] The feasibility decision of this application is determined by constraints, including repair constraints, mission continuation constraints, replacement constraints, and the introduction of new UAVs.

[0070] S4: Determine the losses corresponding to the feasibility decision based on the loss parameters; the losses corresponding to the feasibility decision include: repair losses, mission continuation losses, replacement losses, and losses from introducing new drones.

[0071] A malfunctioning drone may affect neighboring drones, thus altering the losses incurred by the malfunctioning drone. For example, a malfunctioning drone may collide with a neighboring drone, damaging its load-bearing capacity. Therefore, when determining the losses corresponding to a feasible decision, calculations must be performed from both the perspectives of affecting neighboring drones and not affecting them.

[0072] S4 specifically includes:

[0073] S41: Determine repair losses and repair constraints.

[0074] Repair loss E r Includes: Repair losses E when they do not affect adjacent drones r1 Repair losses when affecting adjacent drones E r2 Repair loss E r The specific calculation process is as follows:

[0075] E r1 =C r +C s F Y (w(t));

[0076] E r2 =C r +C s F Y (w(t))+γ||ΔR i ||1;

[0077] Among them, C r C is responsible for the losses caused by the mission failure. s For losses due to unrepairable malfunctions of drones, F Y (w(t)) represents the complete failure probability of the faulty UAV during the repair period, γ represents the unit resource compensation cost coefficient, and ||ΔR i ||1 represents the total resource consumption of the faulty drone.

[0078] In this application, the calculation formula ω(t)<Y for determining whether a faulty UAV needs to be repaired is the repair constraint.

[0079] S42: Determine the continuation task loss and continuation task constraints.

[0080] Continued mission loss E c Includes: mission continuation loss E when it does not affect adjacent drones. c1 And the loss of mission continuity when affecting adjacent drones E c2 Continued mission loss E c The specific calculation process is as follows:

[0081] E c1 =(Cr +C s )F Y (τ-t);

[0082] E c2 =(C r +C s )F Y (τ-t)+η∑||ΔR k ||1;

[0083] Among them, F Y (τ-t) represents the complete failure probability of the faulty UAV within the remaining mission time, η is the penalty coefficient for resource loss of adjacent UAVs, and ∑||ΔR k ||1 represents the total resource consumption of all adjacent drones.

[0084] The formula for calculating the task continuation constraints is as follows:

[0085] τ-t <Y;

[0086] Where τ is the mission time of the malfunctioning drone, and t is the mission time already consumed by the malfunctioning drone.

[0087] The constraint for continuing the mission is that the remaining mission time of the faulty drone is less than the emergency endurance time, that is, the faulty drone must complete the remaining mission before the inoperable time expires.

[0088] S43: Determine the replacement loss and replacement constraints.

[0089] The replacement loss E in this application re Includes: replacement loss E when it does not affect adjacent drones re1 Replacement loss E when affecting adjacent drones re2 Replacement loss E re The specific calculation process is as follows:

[0090] E re1 =C re +C r (1-F Y (τ-t))+C s F Y (ω(t))+γ||ΔR j ||1;

[0091] E re2 =C re +C r (1-F Y (τ-t))+C s F Y (ω(t))+γ||ΔR i ||1;

[0092] Among them, C re For losses caused by the replacement process, 1-F Y (τ-t) represents the probability of the faulty drone successfully completing its mission within the remaining time, ||ΔR j ||1 represents the resources needed to complete task j.

[0093] The formula for calculating the replacement constraint is as follows:

[0094] T-τ>τ-t;

[0095] Where T represents the effective time available for the drone during the mission.

[0096] The replacement constraint is that the remaining time of the adjacent drone covers the remaining mission time of the faulty drone.

[0097] S44: Determine the losses and constraints of introducing new drones.

[0098] The calculation process for the loss of the new drone is as follows:

[0099] E new =C new ;

[0100] Among them, E new To introduce new drone losses, C new The cost of replacing old drones with new ones to complete tasks.

[0101] The loss from introducing a new drone is a constant, meaning the cost incurred when a new drone replaces a faulty one to complete the task. This loss cost stems from factors such as procurement, deployment, adjustment, and opportunity costs, and can be adaptively adjusted based on actual circumstances.

[0102] The calculation formula for the new UAV constraints is as follows:

[0103] T-τ<τ-Z.

[0104] The new constraint for drones is that the remaining time of adjacent drones cannot cover the remaining task time of the faulty drone, meaning that adjacent drones cannot complete the remaining task of the faulty drone.

[0105] If the mission cannot be completed without repairing the faulty drone, it is necessary to consider whether the remaining time of an adjacent drone covers the remaining mission time of the faulty drone when it reaches its inoperable time. If not, a new drone needs to be introduced to complete the remaining mission. Repair should be chosen when both the constraints of not repairing and replacement cannot be met, provided the drone is repairable.

[0106] When calculating repair losses and mission continuation losses, γ||ΔR is dynamically added based on the impact on adjacent UAVs.i ||1 and η∑||ΔR k ||1, When calculating the replacement loss, add γ||ΔR j ||1 or γ||ΔR i ||1, The above added value reflects the impact of the faulty UAV on adjacent UAVs and the occupation of mission resources for replacement. This application dynamically adjusts the loss, which can more accurately reflect the actual loss. It is suitable for complex mission environments (such as dense formations) and avoids a one-size-fits-all cost estimation. It quantifies the damage to adjacent UAVs through the resource loss item (L1 norm), clearly reflecting the impact of the faulty UAV on adjacent UAVs and supporting risk avoidance decision-making.

[0107] This application utilizes feasibility decision-making to reallocate mission resources. Mission resource reallocation refers to the resource depletion of adjacent drones after a malfunctioning drone impacts them. Therefore, mission resource reallocation is reflected in the costs of repair, mission continuation, and replacement following the impact of the malfunctioning drone. For example, repair losses increase the total resource depletion of the malfunctioning drone, mission continuation losses add to the total resource depletion of all adjacent drones, and replacement losses add the resources needed to complete the mission. The losses from the three decisions (repair, mission continuation, and replacement) in this application include two scenarios: losses when the malfunctioning drone does not affect adjacent drones, and losses when the malfunctioning drone does affect adjacent drones. Under the premise of satisfying constraints, the losses under the three decisions are comprehensively compared to determine the final decision. In other words, this application directly reflects the degree of impact of the malfunctioning drone on adjacent drones through changes in economic losses. Compared to traditional methods that only consider crash losses from single-drone repair (mission failure), this application is more practical and can prioritize mission completion and select the option with the least loss in scenarios where mission interruption is not possible.

[0108] S5: Based on the repair assessment results, repair losses, and losses from continuing the mission, determine a temporary decision; the temporary decision is to repair or continue the mission.

[0109] S51: When the repair decision is no repair, the temporary decision is to continue the task.

[0110] S52: When the repair judgment result is repair, compare the magnitude of the repair loss and the loss of continuing the task, and determine a temporary decision based on the comparison result. The purpose of the comparison is to select the more economical option with smaller loss between repair and continuing the task.

[0111] Specifically, when the repair loss is less than the loss from continuing the task, the temporary decision is to repair; when the repair loss is greater than or equal to the loss from continuing the task, the temporary decision is to continue the task. The specific representation of the temporary decision is as follows:

[0112]

[0113] S6: Determine the final decision based on the losses and replacement losses corresponding to the feasibility decision, the provisional decision, and the replacement decision; the final decision includes: repair, continue the mission, replace the adjacent drone, or introduce a new drone.

[0114] S6 specifically includes:

[0115] S61: If the temporary decision is to continue the task under repair conditions, compare the magnitude of the losses from continuing the task and the losses from replacement. The purpose of the comparison is to determine whether continuing the task is better than replacement. The comparison process includes:

[0116] When the loss from continuing the task is less than or equal to the loss from replacement, a feasibility decision is made. The decision process includes: if the feasibility decision indicates that the task can continue, the final decision is to continue the task; if the feasibility decision indicates that the task cannot continue, the magnitudes of the repair loss and the replacement loss are compared; if the repair loss is less than or equal to the replacement loss, the final decision is to repair; if the repair loss is greater than the replacement loss, and the feasibility decision indicates that replacement is possible, the final decision is to replace; if the repair loss is greater than the replacement loss, and the feasibility decision indicates that replacement is not possible, the final decision is to repair.

[0117] When the loss of continuing the task outweighs the loss of replacement, a feasibility decision is made. The decision process includes: if the feasibility decision is that replacement is possible, the final decision is replacement; if the feasibility decision is that replacement is not possible and the task cannot continue, the final decision is repair; if the feasibility decision is that replacement is not possible but the task can continue, the final decision is to continue the task.

[0118] Specifically, the process of comparing continuing the task under repair conditions with replacement in a temporary decision-making process can be represented as follows:

[0119]

[0120] S62: If the temporary decision is to repair under repair conditions, compare the magnitude of repair losses and replacement losses. The purpose of the comparison is to determine whether repair is better than replacement. The comparison process includes:

[0121] When the repair loss is less than or equal to the replacement loss, the final decision is to repair; when the repair loss is greater than the replacement loss, a feasibility decision is assessed. The assessment process includes: when the feasibility decision is that replacement is possible, the final decision is to replace; when the feasibility decision is that replacement is not possible, the final decision is to repair.

[0122] Specifically, the process of comparing repair and replacement under repair conditions for temporary decision-making can be represented as follows:

[0123]

[0124] S63: If the temporary decision is to continue the mission without repair, compare the magnitudes of the loss of continuing the mission and the replacement loss. The purpose of the comparison is to determine whether continuing the mission is more favorable than replacement. The comparison process includes:

[0125] When the loss of continuing the mission is less than or equal to the replacement loss, judge the feasibility decision; the judgment process includes: when the feasibility decision is to be able to continue the mission, the final decision is to continue the mission; when the feasibility decision is not to be able to continue the mission but can replace, the final decision is to replace; when the feasibility decision is not to be able to continue the mission, cannot replace, and cannot introduce a new UAV at the same time, the final decision is to replace; when the feasibility decision is not to be able to continue the mission, cannot replace, but can introduce a new UAV, the final decision is to introduce a new UAV.

[0126] When the loss of continuing the mission is greater than the replacement loss, judge the feasibility decision; the judgment process includes: when the feasibility decision is to be able to replace, the final decision is to replace; when the feasibility decision is not to be able to replace but can continue the mission, the final decision is to continue the mission; when the feasibility decision is not to be able to replace, cannot continue the mission, and cannot introduce a new UAV at the same time, the final decision is to replace; when the feasibility decision is not to be able to replace, cannot continue the mission, but can introduce a new UAV, the final decision is to introduce a new UAV.

[0127] Specifically, the comparison process of continuing the mission and replacement under the condition of non-repair in the temporary decision can be expressed as:

[0128]

[0129] When determining the final decision, it is necessary to first determine whether the constraint conditions are met, that is, to make a feasibility decision first. For example, the constraint condition τ - t < Z - t must be met to continue the mission, otherwise repair is forced to be selected. The constraint condition T - τ > τ - t must be met to replace, otherwise the temporary decision is retained. That is, before comparing the losses, the feasibility decision is verified first, and high-risk options (such as the crashed faulty UAV caused by continuing the mission) are forced to be excluded, avoiding decisions that are theoretically optimal but actually infeasible, using the constraint conditions to quickly prune and reducing invalid calculations (such as directly excluding the decision of continuing the mission that does not meet τ - t < Y).

[0130] By comparing the magnitudes of the repair loss, replacement loss, and the loss of continuing the mission, ensure that the plan with the lowest total cost is selected, directly reducing the mission loss. Within the feasible range, consider both direct costs (such as the loss C r caused by mission failure and the loss C s of the UAV having an irreparable fault) and indirect costs (such as the resource consumption of adjacent UAVs), avoiding local optimality. When both continuing the mission and replacement are infeasible, default repair (i.e., suspending the mission) is used as a fallback strategy to ensure that the mission does not completely fail.

[0131] In summary, there are four possible scenarios when a UAV malfunctions during mission execution: repair (continue mission after successful repair), continue mission (complete mission without repair, ignoring warning signals), replacement (use a neighboring UAV to replace the malfunctioning UAV and perform its remaining tasks), and introduction of a new UAV (introduce a new UAV to complete the remaining tasks of the malfunctioning UAV). Therefore, outputting a final decision is of practical significance. This application determines the final decision mainly through three major steps: first, determining a feasible decision based on the emergency endurance time of the malfunctioning UAV; second, determining a temporary decision based on the feasible decision and its corresponding losses; and finally, determining the final decision based on the temporary decision, the feasible decision, and its corresponding losses.

[0132] This application optimizes efficiency (prioritizing constraints), accuracy (dynamically quantifying losses), and robustness (constraints + fallback strategy) through a segmented, progressive decision-making process. This makes the application suitable for real-time fault recovery scenarios in UAV swarm missions. Each decision step incorporates constraints, meeting the high real-time requirements of UAV swarm missions and improving fault response speed. When a faulty UAV poses a high collision risk, replacement or repair is prioritized over mission continuation, reducing the total cost of repair, replacement, or mission interruption due to faults while increasing mission success rate. By using hierarchical screening, dynamic loss calculation, and constraint-based final decision determination, a balance between efficiency, safety, and economy is achieved.

[0133] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores fault-tolerant decision data for multi-UAV missions. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a fault-tolerant decision-making method for multi-UAV missions.

[0134] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0135] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0136] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0137] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0138] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0139] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0140] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for multi-UAV mission fault-tolerant decision determination, characterized in that, The multi-unmanned aerial vehicle task fault-tolerant decision determination method comprises the following steps: An emergency endurance time of the faulty unmanned aerial vehicle and a loss parameter caused by the faulty unmanned aerial vehicle are acquired; the emergency endurance time is determined by a warning time and an inoperable time of the faulty unmanned aerial vehicle; the loss parameter comprises a loss caused by a task failure and the unmanned aerial vehicle fault, a total resource consumption of the faulty unmanned aerial vehicle and adjacent unmanned aerial vehicles, and a complete failure probability of the faulty unmanned aerial vehicle during a repair period and a remaining task time; It is judged whether the faulty unmanned aerial vehicle is repaired according to the emergency endurance time, and a repair judgment result is obtained; the repair judgment result comprises repair and no repair; A feasibility decision is determined according to the repair judgment result; the feasibility decision comprises whether to continue the task, whether to replace the adjacent unmanned aerial vehicle, and whether to introduce a new unmanned aerial vehicle; A loss corresponding to the feasibility decision is determined according to the loss parameter; the loss corresponding to the feasibility decision comprises a repair loss, a continued task loss, a replacement loss, and a new unmanned aerial vehicle introduction loss; A temporary decision is determined according to the repair judgment result, the repair loss, and the continued task loss; the temporary decision is repair or continued task; A final decision is determined according to the feasibility decision, the loss corresponding to the temporary decision, and the replacement loss; the final decision comprises repair, continued task, replacement of the adjacent unmanned aerial vehicle, or introduction of the new unmanned aerial vehicle.

2. The multi-UAV mission fault-tolerant decision determination method according to claim 1, characterized in that, The emergency endurance time of the faulty unmanned aerial vehicle is acquired in detail as follows: The emergency endurance time Y of the faulty unmanned aerial vehicle is determined by using a formula Y = Z - X; Wherein, Z is the inoperable time of the faulty unmanned aerial vehicle, and X is the warning time of the faulty unmanned aerial vehicle.

3. The multi-UAV mission fault-tolerant decision determination method according to claim 1, characterized in that, The faulty unmanned aerial vehicle is judged whether to be repaired according to the emergency endurance time, and the repair judgment result is obtained in detail as follows: It is judged whether the faulty unmanned aerial vehicle is repaired by using a formula ω(t) < Y; Wherein, ω(t) is the time spent from the termination of the task of the faulty unmanned aerial vehicle at time t to the completion of the repair, and Y is the emergency endurance time of the faulty unmanned aerial vehicle.

4. The method of claim 1, wherein, The loss corresponding to the feasibility decision is determined according to the loss parameter in detail as follows: Using equation E r1 = C r + C s F Y (w(t)) and equation E r2 = C r + C s F Y (w(t)) + γ||AR i ||1 determines the repair loss; Using equation E c1 = (C r + C s ) F Y (τ - t) and equation E c2 = (C r + C s ) F Y (τ - t) + η∑||ΔR k ||1determine the continuation task loss; Using equation E re1 = C re + C r (1 - E Y (τ - t)) + C s E Y (ω(t)) + γ||ΔR j ||1 and equation E re2 = C re + C r (1 - F Y (τ - t)) + C s F Y (ω(t)) + γ||ΔR i ||1 determines the replacement loss; Using equation E new = C new Determining the loss of introducing a new drone; A continued task constraint condition is determined by using a formula τ - t < Y; A replacement constraint condition is determined by using a formula T - τ > τ - t; A new unmanned aerial vehicle introduction constraint condition is determined by using a formula T - τ < τ - Z. wherein, E r1 is the repair loss when the adjacent UAV is not affected, r2 is the repair loss when the adjacent UAV is affected, c1 is the continued mission loss when the adjacent UAV is not affected, c2 is the continued mission loss when the adjacent UAV is affected, re1 is the replacement loss when the adjacent UAV is not affected, re2 is the replacement loss when the adjacent UAV is affected, new is the loss of introducing a new UAV, C new is the cost of the new UAV replacing the old UAV to complete the mission, C r is the loss caused by the failure of the mission, C s is the loss of the UAV appearing unrepairable failure, F Y (w(t)) is the complete failure probability of the faulty UAV during repair, γ is the unit resource compensation cost coefficient, ∑||ΔR i ||1is the total resource consumption of the faulty UAV, F Y (τ-t) is the complete failure probability of the faulty UAV in the remaining mission time, η is the penalty coefficient of the resource loss of the adjacent UAV, ∑||ΔR k ||1is the total resource consumption of all adjacent UAVs, C re is the loss caused by the replacement process, 1-F Y (τ-t) is the task success probability of the faulty UAV in the remaining time, ||ΔR j ||1is the resource required to complete the task j, Y is the emergency endurance time of the faulty UAV, τ is the mission time of the faulty UAV, t is the task time consumed by the faulty UAV, T is the effective time available to the UAV in the mission, and Z is the inoperable time of the faulty UAV.

5. The method of claim 1, wherein, The temporary decision is determined according to the repair judgment result, the repair loss, and the continued task loss in detail as follows: When the repair judgment result is no repair, the temporary decision is continued task; When the repair judgment result is repair, the sizes of the repair loss and the continued task loss are compared, and the temporary decision is determined according to the comparison result.

6. The multi-UAV mission fault-tolerant decision determination method according to claim 5, characterized in that, The sizes of the repair loss and the continued task loss are compared when the repair judgment result is repair, and the temporary decision is determined according to the comparison result in detail as follows: When the repair loss is less than the continued task loss, the temporary decision is repair; When the repair loss is greater than or equal to the continued task loss, the temporary decision is continued task.

7. The method of claim 1, wherein, The final decision is determined according to the feasibility decision, the loss corresponding to the temporary decision, and the replacement loss in detail as follows: If the temporary decision is continued task under the condition of repair, the sizes of the continued task loss and the replacement loss are compared, and the comparison process comprises the following steps: When the continue task loss is less than or equal to the replacement loss, the feasibility decision is judged; the judging process comprises: when the feasibility decision is capable of continuing the task, the final decision is to continue the task; when the feasibility decision is incapable of continuing the task, the size of the repair loss and the replacement loss is compared; when the repair loss is less than or equal to the replacement loss, the final decision is to repair; when the repair loss is greater than the replacement loss and the feasibility decision is capable of replacement, the final decision is to replace; when the repair loss is greater than the replacement loss and the feasibility decision is incapable of replacement, the final decision is to repair; When the continue task loss is greater than the replacement loss, the feasibility decision is judged; the judging process comprises: when the feasibility decision is capable of replacement, the final decision is to replace; when the feasibility decision is incapable of replacement and incapable of continuing the task, the final decision is to repair; when the feasibility decision is incapable of replacement but capable of continuing the task, the final decision is to continue the task; If the temporary decision is repair under the repair condition, the size of the repair loss and the replacement loss is compared, and the comparison process comprises: When the repair loss is less than or equal to the replacement loss, the final decision is to repair; when the repair loss is greater than the replacement loss, the feasibility decision is judged; the judging process comprises: when the feasibility decision is capable of replacement, the final decision is to replace; when the feasibility decision is incapable of replacement, the final decision is to repair; If the temporary decision is to continue the task under the non-repair condition, the size of the continue task loss and the replacement loss is compared, and the comparison process comprises: When the continue task loss is less than or equal to the replacement loss, the feasibility decision is judged; the judging process comprises: when the feasibility decision is capable of continuing the task, the final decision is to continue the task; when the feasibility decision is incapable of continuing the task, the final decision is to replace; when the feasibility decision is incapable of continuing the task and incapable of replacement, the final decision is to replace; when the feasibility decision is incapable of continuing the task and incapable of replacement but capable of introducing a new unmanned aerial vehicle, the final decision is to introduce the new unmanned aerial vehicle; When the continue task loss is greater than the replacement loss, the feasibility decision is judged; the judging process comprises: when the feasibility decision is capable of replacement, the final decision is to replace; when the feasibility decision is incapable of replacement but capable of continuing the task, the final decision is to continue the task; when the feasibility decision is incapable of replacement and incapable of continuing the task, the final decision is to replace; when the feasibility decision is incapable of replacement and incapable of continuing the task but capable of introducing a new unmanned aerial vehicle, the final decision is to introduce the new unmanned aerial vehicle.

8. A computer device comprising: The memory, the processor and the computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to realize the multi-unmanned aerial vehicle task fault-tolerant decision determination method in any one of claims 1-7.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the multi-unmanned aerial vehicle task fault-tolerant decision determination method in any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the multi-unmanned aerial vehicle task fault-tolerant decision determination method in any one of claims 1-7.

Images